[GUI] Fixes and improvements for the GUI, including new image assets and updates to language files.

.gitignore

@@ -42,4 +42,3 @@ ehthumbs.db
 
 .vs/
 .idea/
-packages.lock.json

Directory.Build.props

@@ -9,7 +9,7 @@ SPDX-License-Identifier: GPL-2.0-or-later
     <ImplicitUsings>enable</ImplicitUsings>
     <Nullable>enable</Nullable>
     <GenerateDocumentationFile>true</GenerateDocumentationFile>
-    <SharpEmuVersion>0.0.2-beta.4</SharpEmuVersion>
+    <SharpEmuVersion>0.0.2-beta.3</SharpEmuVersion>
     <Version>$(SharpEmuVersion)</Version>
 
     <RepoRoot>$([MSBuild]::NormalizeDirectory('$(MSBuildThisFileDirectory)'))</RepoRoot>

REUSE.toml

@@ -8,8 +8,6 @@ path = [
     "**/packages.lock.json",
     "scripts/ps5_names.txt",
     "src/SharpEmu.GUI/Languages/**",
-    "src/SharpEmu.ShaderCompiler.Metal/Templates/**",
-    "tests/SharpEmu.ShaderCompiler.Metal.Tests/Goldens/**",
     "_logs/**",
     ".github/images/**",
     ".github/pull_request_template.md",

SharpEmu.slnx

@@ -14,13 +14,11 @@ SPDX-License-Identifier: GPL-2.0-or-later
     <Project Path="src/SharpEmu.Libs/SharpEmu.Libs.csproj" />
     <Project Path="src/SharpEmu.Logging/SharpEmu.Logging.csproj" />
     <Project Path="src/SharpEmu.ShaderCompiler/SharpEmu.ShaderCompiler.csproj" />
-    <Project Path="src/SharpEmu.ShaderCompiler.Metal/SharpEmu.ShaderCompiler.Metal.csproj" />
     <Project Path="src/SharpEmu.ShaderCompiler.Vulkan/SharpEmu.ShaderCompiler.Vulkan.csproj" />
     <Project Path="src/SharpEmu.SourceGenerators/SharpEmu.SourceGenerators.csproj" />
   </Folder>
   <Folder Name="/tests/">
     <Project Path="tests/SharpEmu.Libs.Tests/SharpEmu.Libs.Tests.csproj" />
-    <Project Path="tests/SharpEmu.ShaderCompiler.Metal.Tests/SharpEmu.ShaderCompiler.Metal.Tests.csproj" />
     <Project Path="tests/SharpEmu.SourceGenerators.Tests/SharpEmu.SourceGenerators.Tests.csproj" />
   </Folder>
 </Solution>

docs/aerolib-catalog.md

@@ -1,20 +0,0 @@
-<!--
-Copyright (C) 2026 SharpEmu Emulator Project
-SPDX-License-Identifier: GPL-2.0-or-later
--->
-
-# Aerolib Catalog
-
-```bash
-# NID to export name
-python scripts/aerolib_catalog.py lookup Zxa0VhQVTsk
-
-# Export name to NID
-python scripts/aerolib_catalog.py lookup sceKernelWaitSema
-
-# Search export names
-python scripts/aerolib_catalog.py search VideoOut --limit 20
-
-# Export all NID/name pairs to artifacts/aerolib.txt
-python scripts/aerolib_catalog.py export
-```

docs/bink2-bridge.md

@@ -14,9 +14,9 @@ available, presents its decoded BGRA frames at the normal guest-flip boundary.
 This preserves the game's own timing and lets the host Vulkan presenter display
 the movie without trying to execute the PS5-specific Bink GPU decode path.
 
-Without an adapter, Bink files remain visible to the guest and the game's
-statically linked decoder runs normally. Set SHARPEMU_BINK_MODE=skip only when
-explicitly testing a title whose cinematics are optional.
+Without an adapter, Bink movies are skipped by default: their open call returns
+not-found so games that mark cinematics as optional progress to their next
+state instead of waiting on an empty Bink GPU texture.
 
 Set SHARPEMU_BINK_MODE=dummy to retain the open and show a built-in,
 non-decoded placeholder frame. This requires no SDK, but is a visual diagnostic

global.json

@@ -1,6 +1,6 @@
 {
     "sdk": {
         "version": "10.0.103",
-        "rollForward": "latestFeature"
+        "rollForward": "disable"
     }
 }

scripts/aerolib_catalog.py

@@ -1,181 +0,0 @@
-#!/usr/bin/env python3
-
-# Copyright (C) 2026 SharpEmu Emulator Project
-# SPDX-License-Identifier: GPL-2.0-or-later
-
-from __future__ import annotations
-
-import argparse
-import base64
-import hashlib
-import re
-import sys
-from pathlib import Path
-
-
-NID_SUFFIX = bytes.fromhex("518d64a635ded8c1e6b039b1c3e55230")
-NID_PATTERN = re.compile(r"^[A-Za-z0-9+-]{11}$")
-DEFAULT_NAMES_FILE = Path(__file__).resolve().with_name("ps5_names.txt")
-DEFAULT_EXPORT_FILE = Path(__file__).resolve().parents[1] / "artifacts" / "aerolib.txt"
-
-
-def compute_nid(export_name: str) -> str:
-    digest = hashlib.sha1(export_name.encode("utf-8") + NID_SUFFIX).digest()
-    encoded = base64.b64encode(digest[:8][::-1]).decode("ascii")
-    return encoded.rstrip("=").replace("/", "-")
-
-
-def read_names(path: Path) -> list[str]:
-    try:
-        return [
-            line.strip()
-            for line in path.read_text(encoding="utf-8").splitlines()
-            if line.strip()
-        ]
-    except OSError as error:
-        raise SystemExit(f"Unable to read catalog '{path}': {error}") from error
-
-
-def write_pair(nid: str, export_name: str) -> None:
-    print(f"{nid}\t{export_name}")
-
-
-def lookup(args: argparse.Namespace) -> int:
-    value = args.value.strip()
-    if NID_PATTERN.fullmatch(value):
-        for export_name in read_names(args.names):
-            if compute_nid(export_name) == value:
-                write_pair(value, export_name)
-                return 0
-
-        print(f"NID not found in catalog: {value}", file=sys.stderr)
-        return 1
-
-    names = set(read_names(args.names))
-    write_pair(compute_nid(value), value)
-    if value not in names:
-        print("Warning: export name is not present in the catalog.", file=sys.stderr)
-    return 0
-
-
-def search(args: argparse.Namespace) -> int:
-    names = read_names(args.names)
-    if args.regex:
-        try:
-            pattern = re.compile(args.query, 0 if args.case_sensitive else re.IGNORECASE)
-        except re.error as error:
-            print(f"Invalid regular expression: {error}", file=sys.stderr)
-            return 2
-
-        matches = (name for name in names if pattern.search(name))
-    elif args.case_sensitive:
-        matches = (name for name in names if args.query in name)
-    else:
-        query = args.query.casefold()
-        matches = (name for name in names if query in name.casefold())
-
-    count = 0
-    for export_name in matches:
-        write_pair(compute_nid(export_name), export_name)
-        count += 1
-        if args.limit and count >= args.limit:
-            break
-
-    if count == 0:
-        print(f"No catalog names matched: {args.query}", file=sys.stderr)
-        return 1
-    return 0
-
-
-def export_catalog(args: argparse.Namespace) -> int:
-    pairs = [(compute_nid(name), name) for name in read_names(args.names)]
-    if args.sort == "nid":
-        pairs.sort(key=lambda pair: (pair[0], pair[1]))
-    elif args.sort == "name":
-        pairs.sort(key=lambda pair: pair[1])
-
-    args.output.parent.mkdir(parents=True, exist_ok=True)
-    try:
-        with args.output.open("w", encoding="utf-8", newline="\n") as output:
-            output.write("# NID\tExportName\n")
-            for nid, export_name in pairs:
-                output.write(f"{nid}\t{export_name}\n")
-    except OSError as error:
-        print(f"Unable to write catalog '{args.output}': {error}", file=sys.stderr)
-        return 1
-
-    print(f"Wrote {len(pairs)} entries to {args.output}")
-    return 0
-
-
-def create_parser() -> argparse.ArgumentParser:
-    parser = argparse.ArgumentParser(
-        description="Inspect the SharpEmu PS5 export-name/NID catalog.",
-        epilog=(
-            "Examples:\n"
-            "  python scripts/aerolib_catalog.py lookup Zxa0VhQVTsk\n"
-            "  python scripts/aerolib_catalog.py lookup sceKernelWaitSema\n"
-            "  python scripts/aerolib_catalog.py search VideoOut --limit 20\n"
-            "  python scripts/aerolib_catalog.py export"
-        ),
-        formatter_class=argparse.RawDescriptionHelpFormatter,
-    )
-    parser.add_argument(
-        "--names",
-        type=Path,
-        default=DEFAULT_NAMES_FILE,
-        help=f"source name list (default: {DEFAULT_NAMES_FILE})",
-    )
-
-    subparsers = parser.add_subparsers(dest="command", required=True)
-
-    lookup_parser = subparsers.add_parser(
-        "lookup", help="resolve a NID or calculate the NID for an export name"
-    )
-    lookup_parser.add_argument("value", help="11-character NID or exact export name")
-    lookup_parser.set_defaults(handler=lookup)
-
-    search_parser = subparsers.add_parser(
-        "search", help="find export names and print matching NID/name pairs"
-    )
-    search_parser.add_argument("query", help="name substring or regular expression")
-    search_parser.add_argument(
-        "--limit", type=int, default=50, help="maximum matches; 0 means unlimited"
-    )
-    search_parser.add_argument(
-        "--case-sensitive", action="store_true", help="match case exactly"
-    )
-    search_parser.add_argument(
-        "--regex", action="store_true", help="treat the query as a regular expression"
-    )
-    search_parser.set_defaults(handler=search)
-
-    export_parser = subparsers.add_parser(
-        "export", help="write every NID/name pair to a tab-separated text file"
-    )
-    export_parser.add_argument(
-        "output",
-        type=Path,
-        nargs="?",
-        default=DEFAULT_EXPORT_FILE,
-        help=f"output file (default: {DEFAULT_EXPORT_FILE})",
-    )
-    export_parser.add_argument(
-        "--sort",
-        choices=("source", "nid", "name"),
-        default="nid",
-        help="output ordering (default: nid)",
-    )
-    export_parser.set_defaults(handler=export_catalog)
-
-    return parser
-
-
-def main() -> int:
-    parser = create_parser()
-    args = parser.parse_args()
-    return args.handler(args)
-
-
-if __name__ == "__main__":
-    raise SystemExit(main())

src/SharpEmu.CLI/Program.cs

@@ -45,6 +45,11 @@ internal static partial class Program
     [STAThread]
     private static int Main(string[] args)
     {
+        // Avoid blocking full collections while guest and render threads are
+        // running, and establish the GC mode before the runtime reserves the
+        // fixed guest address-space window.
+        System.Runtime.GCSettings.LatencyMode = System.Runtime.GCLatencyMode.SustainedLowLatency;
+
         try
         {
             return Run(args);

src/SharpEmu.CLI/SharpEmu.CLI.csproj

@@ -49,6 +49,7 @@ SPDX-License-Identifier: GPL-2.0-or-later
     <GenerateDocumentationFile>false</GenerateDocumentationFile>
     <DebugType>none</DebugType>
     <DebugSymbols>false</DebugSymbols>
+    <RestorePackagesWithLockFile>true</RestorePackagesWithLockFile>
   </PropertyGroup>
 
   <PropertyGroup Condition="'$(RuntimeIdentifier)' == 'win-x64' Or '$(RuntimeIdentifier)' == ''">

src/SharpEmu.CLI/packages.lock.json

@@ -0,0 +1,596 @@
+{
+  "version": 2,
+  "dependencies": {
+    "net10.0": {
+      "Microsoft.NET.ILLink.Tasks": {
+        "type": "Direct",
+        "requested": "[10.0.3, )",
+        "resolved": "10.0.3",
+        "contentHash": "0B6nZyCHWXnvmlB559oduOspVdNOnpNXPjhpWVMovLPAsDVG7A4jJR9rzECf67JUzxP8/ee/wA8clwIzJcWNFA=="
+      },
+      "Avalonia.Angle.Windows.Natives": {
+        "type": "Transitive",
+        "resolved": "2.1.25547.20250602",
+        "contentHash": "ZL0VLc4s9rvNNFt19Pxm5UNAkmKNylugAwJPX9ulXZ6JWs/l6XZihPWWTyezaoNOVyEPU8YbURtW7XMAtqXH5A=="
+      },
+      "Avalonia.BuildServices": {
+        "type": "Transitive",
+        "resolved": "11.3.2",
+        "contentHash": "qHDToxto1e3hci5YqbG9n0Ty8mlp3zBUN5wT66wKqaDVzXyQ0do3EnRILd4Ke9jpvsktaPpgE0YjEk7hornryQ=="
+      },
+      "Avalonia.FreeDesktop": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "aUwv8BNruRUOaUfMu4U3uibIUS60/rSHgGOhd8zBkLkpxY3JFJvgRbeq5ZzHIyKXCuKi18PO00YHAgCarp3wdw==",
+        "dependencies": {
+          "Avalonia": "11.3.18",
+          "Tmds.DBus.Protocol": "0.21.3"
+        }
+      },
+      "Avalonia.Native": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "8g53DROFW6wVJAnTsE1Iu5bdZO5r0oqxbdbMQODs1QDYCK2IU/y/x/vQVKCYOvqxl4tXkzU9tExv8XqSGPWthQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "Avalonia.Remote.Protocol": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "vw+6ZfgTuu72dA9aVWn6u56t2nrBd5MoMU0wo/qI9XJAl/c0oYYphIvwLvJP1JorubQY4UE3d0ac8ULBhrGBiA=="
+      },
+      "Avalonia.Skia": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "/B4aXmNRNjG8I5U/a1xJI+bIi0XO6DDzS3mBrIKlVnJRY2CyZiUeESRQXLnIU77Z9TvqkUROs+D47s085YjFtA==",
+        "dependencies": {
+          "Avalonia": "11.3.18",
+          "HarfBuzzSharp": "8.3.1.1",
+          "HarfBuzzSharp.NativeAssets.Linux": "8.3.1.1",
+          "HarfBuzzSharp.NativeAssets.WebAssembly": "8.3.1.1",
+          "SkiaSharp": "2.88.9",
+          "SkiaSharp.NativeAssets.Linux": "2.88.9",
+          "SkiaSharp.NativeAssets.WebAssembly": "2.88.9"
+        }
+      },
+      "Avalonia.Win32": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "eioUHkM2PeLPETd1aEks3rvb9plbba6buIrNdrqCpwE/qgHKUjvRNBd5mUQfAbGgTLiAes524gB8uUMDhrsJVQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18",
+          "Avalonia.Angle.Windows.Natives": "2.1.25547.20250602"
+        }
+      },
+      "Avalonia.X11": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "m4Ki/G5Dovnq+6QzfS0iGbK8V77Q6oTjToMLOB0CxPCCrl3Oxywh6kIjuGJDPaN6kopMmjxlNShyQf+vPYL+JA==",
+        "dependencies": {
+          "Avalonia": "11.3.18",
+          "Avalonia.FreeDesktop": "11.3.18",
+          "Avalonia.Skia": "11.3.18"
+        }
+      },
+      "HarfBuzzSharp": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "tLZN66oe/uiRPTZfrCU4i8ScVGwqHNh5MHrXj0yVf4l7Mz0FhTGnQ71RGySROTmdognAs0JtluHkL41pIabWuQ==",
+        "dependencies": {
+          "HarfBuzzSharp.NativeAssets.Win32": "8.3.1.1",
+          "HarfBuzzSharp.NativeAssets.macOS": "8.3.1.1"
+        }
+      },
+      "HarfBuzzSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "3EZ1mpIiKWRLL5hUYA82ZHteeDIVaEA/Z0rA/wU6tjx6crcAkJnBPwDXZugBSfo8+J3EznvRJf49uMsqYfKrHg=="
+      },
+      "HarfBuzzSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "jbtCsgftcaFLCA13tVKo5iWdElJScrulLTKJre36O4YQTIlwDtPPqhRZNk+Y0vv4D1gxbscasGRucUDfS44ofQ=="
+      },
+      "HarfBuzzSharp.NativeAssets.WebAssembly": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "loJweK2u/mH/3C2zBa0ggJlITIszOkK64HLAZB7FUT670dTg965whLFYHDQo69NmC4+d9UN0icLC9VHidXaVCA=="
+      },
+      "HarfBuzzSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "UsJtQsfAJoFDZrXc4hCUfRPMqccfKZ0iumJ/upcUjz/cmsTgVFGNEL5yaJWmkqsuFYdMWbj/En5/kS4PFl9hBA=="
+      },
+      "MicroCom.Runtime": {
+        "type": "Transitive",
+        "resolved": "0.11.0",
+        "contentHash": "MEnrZ3UIiH40hjzMDsxrTyi8dtqB5ziv3iBeeU4bXsL/7NLSal9F1lZKpK+tfBRnUoDSdtcW3KufE4yhATOMCA=="
+      },
+      "Microsoft.DotNet.PlatformAbstractions": {
+        "type": "Transitive",
+        "resolved": "3.1.6",
+        "contentHash": "jek4XYaQ/PGUwDKKhwR8K47Uh1189PFzMeLqO83mXrXQVIpARZCcfuDedH50YDTepBkfijCZN5U/vZi++erxtg=="
+      },
+      "Microsoft.Extensions.DependencyModel": {
+        "type": "Transitive",
+        "resolved": "9.0.9",
+        "contentHash": "fNGvKct2De8ghm0Bpfq0iWthtzIWabgOTi+gJhNOPhNJIowXNEUE2eZNW/zNCzrHVA3PXg2yZ+3cWZndC2IqYA=="
+      },
+      "Silk.NET.Core": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "D7AT/nnwlB+4RZ84XY8QNGBZMJI5z9l4CSSETIJ1wCfRJzRt/341y3MRZ4HbnFz4r/IGaWOEZr86iE+0/65yyQ==",
+        "dependencies": {
+          "Microsoft.DotNet.PlatformAbstractions": "3.1.6",
+          "Microsoft.Extensions.DependencyModel": "9.0.9"
+        }
+      },
+      "Silk.NET.GLFW": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "UIs4sH57xlPUNHQ/1bt9rymPWlGy8IMDCNv86h0iM4TOA1CkIx0XM/n/tA4AReh1zQkNrvkxPEdZ3Blvy1dyXg==",
+        "dependencies": {
+          "Silk.NET.Core": "2.23.0",
+          "Ultz.Native.GLFW": "3.4.0"
+        }
+      },
+      "Silk.NET.Input.Common": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "QbJVV7kFBHEByayXCYdJtXXI9Sp4a+QAf0IdGV6uCWkFYcEmqBYW3aaNGvFOdSwTBDbHL5T/OtOCrGh4qYhk7A==",
+        "dependencies": {
+          "Silk.NET.Windowing.Common": "2.23.0"
+        }
+      },
+      "Silk.NET.Input.Glfw": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "KGHYqsv/IQRJtD6dloYh2tN4CkaM40vxM2kj0cGKBoCQiBDYHHhJiyDTyMPx0W7Fz5IgnhnG42ELmIAa0DH69A==",
+        "dependencies": {
+          "Silk.NET.Input.Common": "2.23.0",
+          "Silk.NET.Windowing.Glfw": "2.23.0"
+        }
+      },
+      "Silk.NET.Maths": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "r8PdIVzME8EH0qAgbmRPO87I4GfgR2j8TofT7EMuRJDf1QluoQwnVypDoFJjQ2ZBSRsGYk5unYxxogI05Ogsmw=="
+      },
+      "Silk.NET.Windowing.Common": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "ThStSinmY9KQI8DGiF5XEhkLJVnBcgRTBTzL9ijg1wMZAYuckz7ykrNw04fjRm2Gryh6tCNGbvz2XaY0efeFzg==",
+        "dependencies": {
+          "Silk.NET.Core": "2.23.0",
+          "Silk.NET.Maths": "2.23.0"
+        }
+      },
+      "Silk.NET.Windowing.Glfw": {
+        "type": "Transitive",
+        "resolved": "2.23.0",
+        "contentHash": "aYBudKmENmvLRn9p15HbdvlQTnnXskcDfTfbYwSb/4fr263rGLwYuDw/txUEc2jihHJiWCp5+75Y7z5wTJWl7g==",
+        "dependencies": {
+          "Silk.NET.GLFW": "2.23.0",
+          "Silk.NET.Windowing.Common": "2.23.0"
+        }
+      },
+      "SkiaSharp": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "3MD5VHjXXieSHCleRLuaTXmL2pD0mB7CcOB1x2kA1I4bhptf4e3R27iM93264ZYuAq6mkUyX5XbcxnZvMJYc1Q==",
+        "dependencies": {
+          "SkiaSharp.NativeAssets.Win32": "2.88.9",
+          "SkiaSharp.NativeAssets.macOS": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "cWSaJKVPWAaT/WIn9c8T5uT/l4ETwHxNJTkEOtNKjphNo8AW6TF9O32aRkxqw3l8GUdUo66Bu7EiqtFh/XG0Zg==",
+        "dependencies": {
+          "SkiaSharp": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "Nv5spmKc4505Ep7oUoJ5vp3KweFpeNqxpyGDWyeEPTX2uR6S6syXIm3gj75dM0YJz7NPvcix48mR5laqs8dPuA=="
+      },
+      "SkiaSharp.NativeAssets.WebAssembly": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "kt06RccBHSnAs2wDYdBSfsjIDbY3EpsOVqnlDgKdgvyuRA8ZFDaHRdWNx1VHjGgYzmnFCGiTJBnXFl5BqGwGnA=="
+      },
+      "SkiaSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "wb2kYgU7iy84nQLYZwMeJXixvK++GoIuECjU4ECaUKNuflyRlJKyiRhN1MAHswvlvzuvkrjRWlK0Za6+kYQK7w=="
+      },
+      "Ultz.Native.GLFW": {
+        "type": "Transitive",
+        "resolved": "3.4.0",
+        "contentHash": "Iy22JopynbOJ32vA0lBhFEzGi65GQJBuJHYBYRBpydrDpNoTiHnjIXfA65Gu+8qsOr/ZEoIF8r9aHCgAXuO6DA=="
+      },
+      "sharpemu.core": {
+        "type": "Project",
+        "dependencies": {
+          "Iced": "[1.21.0, )",
+          "SharpEmu.HLE": "[0.0.2-beta.3, )",
+          "SharpEmu.Libs": "[0.0.2-beta.3, )",
+          "SharpEmu.Logging": "[0.0.2-beta.3, )"
+        }
+      },
+      "sharpemu.debugger": {
+        "type": "Project",
+        "dependencies": {
+          "SharpEmu.Core": "[0.0.2-beta.3, )",
+          "SharpEmu.HLE": "[0.0.2-beta.3, )",
+          "SharpEmu.Logging": "[0.0.2-beta.3, )"
+        }
+      },
+      "sharpemu.gui": {
+        "type": "Project",
+        "dependencies": {
+          "Avalonia": "[11.3.18, )",
+          "Avalonia.Desktop": "[11.3.18, )",
+          "Avalonia.Fonts.Inter": "[11.3.18, )",
+          "Avalonia.Themes.Fluent": "[11.3.18, )",
+          "SharpEmu.Core": "[0.0.2-beta.3, )",
+          "SharpEmu.Libs": "[0.0.2-beta.3, )",
+          "SharpEmu.Logging": "[0.0.2-beta.3, )",
+          "Tmds.DBus.Protocol": "[0.21.3, )"
+        }
+      },
+      "sharpemu.hle": {
+        "type": "Project",
+        "dependencies": {
+          "SharpEmu.Logging": "[0.0.2-beta.3, )"
+        }
+      },
+      "sharpemu.libs": {
+        "type": "Project",
+        "dependencies": {
+          "SharpEmu.HLE": "[0.0.2-beta.3, )",
+          "SharpEmu.ShaderCompiler": "[0.0.2-beta.3, )",
+          "SharpEmu.ShaderCompiler.Vulkan": "[0.0.2-beta.3, )",
+          "Silk.NET.Input": "[2.23.0, )",
+          "Silk.NET.Vulkan": "[2.23.0, )",
+          "Silk.NET.Vulkan.Extensions.EXT": "[2.23.0, )",
+          "Silk.NET.Vulkan.Extensions.KHR": "[2.23.0, )",
+          "Silk.NET.Windowing": "[2.23.0, )"
+        }
+      },
+      "sharpemu.logging": {
+        "type": "Project"
+      },
+      "sharpemu.shadercompiler": {
+        "type": "Project",
+        "dependencies": {
+          "SharpEmu.HLE": "[0.0.2-beta.3, )"
+        }
+      },
+      "sharpemu.shadercompiler.vulkan": {
+        "type": "Project",
+        "dependencies": {
+          "SharpEmu.ShaderCompiler": "[0.0.2-beta.3, )"
+        }
+      },
+      "Avalonia": {
+        "type": "CentralTransitive",
+        "requested": "[11.3.18, )",
+        "resolved": "11.3.18",
+        "contentHash": "2C4UxhWUObWGgYKWic1x5BMMWGJP6SElb91WeOxs+X/iR26rtkqpxFFwwo50FXS9AyYnHfk8QKXDEfe7oT/kZA==",
+        "dependencies": {
+          "Avalonia.BuildServices": "11.3.2",
+          "Avalonia.Remote.Protocol": "11.3.18",
+          "MicroCom.Runtime": "0.11.0"
+        }
+      },
+      "Avalonia.Desktop": {
+        "type": "CentralTransitive",
+        "requested": "[11.3.18, )",
+        "resolved": "11.3.18",
+        "contentHash": "bilMPa5vYiis6fbNovb6esKytBnOCEGojBa1XFegLCRHCP6g6PvZwS0XF/YOAGkENRlHG8dI7lohOpQ9bIkq1g==",
+        "dependencies": {
+          "Avalonia": "11.3.18",
+          "Avalonia.Native": "11.3.18",
+          "Avalonia.Skia": "11.3.18",
+          "Avalonia.Win32": "11.3.18",
+          "Avalonia.X11": "11.3.18"
+        }
+      },
+      "Avalonia.Fonts.Inter": {
+        "type": "CentralTransitive",
+        "requested": "[11.3.18, )",
+        "resolved": "11.3.18",
+        "contentHash": "27u6hB3Y2Ue586yjfeVakberY73VNQXtuKwe/P927XG1QPlhsfmOyifLHDDpSHG85Zl1x/Xv9IZ3+tk9FnjcZQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "Avalonia.Themes.Fluent": {
+        "type": "CentralTransitive",
+        "requested": "[11.3.18, )",
+        "resolved": "11.3.18",
+        "contentHash": "+Q/TJoynD0zNuu5w2gD+xcTl7GNKJFxlPYAndRLs/mTDrNbbsvv/271WyIysbMPsXSjCyBDp7RCZzQkpD6x5Bg==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "Iced": {
+        "type": "CentralTransitive",
+        "requested": "[1.21.0, )",
+        "resolved": "1.21.0",
+        "contentHash": "dv5+81Q1TBQvVMSOOOmRcjJmvWcX3BZPZsIq31+RLc5cNft0IHAyNlkdb7ZarOWG913PyBoFDsDXoCIlKmLclg=="
+      },
+      "Silk.NET.Input": {
+        "type": "CentralTransitive",
+        "requested": "[2.23.0, )",
+        "resolved": "2.23.0",
+        "contentHash": "Xzl+tVwAp2eEd8blmGQjmJrsZPnp3PWG0KJjiAQHaY2Zr/ELVWeAROKXmZdCAvexzmte2JVGEy/dxnMycbxlpg==",
+        "dependencies": {
+          "Silk.NET.Input.Common": "2.23.0",
+          "Silk.NET.Input.Glfw": "2.23.0"
+        }
+      },
+      "Silk.NET.Vulkan": {
+        "type": "CentralTransitive",
+        "requested": "[2.23.0, )",
+        "resolved": "2.23.0",
+        "contentHash": "3/irtlSWXZ3eTi8N6nelI6L34NTB8ZJHpqVMNzZx2aX7Ek9YEQ34NoQW8/Tljrtmkg8KRhHW8hKTEzZaKV8PgA==",
+        "dependencies": {
+          "Silk.NET.Core": "2.23.0"
+        }
+      },
+      "Silk.NET.Vulkan.Extensions.EXT": {
+        "type": "CentralTransitive",
+        "requested": "[2.23.0, )",
+        "resolved": "2.23.0",
+        "contentHash": "+Oth189ksRiL6HvGCwIdnsYHawqrbO8y49u1H61z3wsfcHhQZeVDYe/wF5LD7fk3NcdgDvwFD3mLm1QWhdZySw==",
+        "dependencies": {
+          "Silk.NET.Core": "2.23.0",
+          "Silk.NET.Vulkan": "2.23.0"
+        }
+      },
+      "Silk.NET.Vulkan.Extensions.KHR": {
+        "type": "CentralTransitive",
+        "requested": "[2.23.0, )",
+        "resolved": "2.23.0",
+        "contentHash": "uRaf4j+SmH3DumjSSSUbFg33BnsGZUyXGj93O9NgGKZSJN3OTmNmQDxRew+/KiVLcgH6qzbto8aNGZ++j9GFWg==",
+        "dependencies": {
+          "Silk.NET.Core": "2.23.0",
+          "Silk.NET.Vulkan": "2.23.0"
+        }
+      },
+      "Silk.NET.Windowing": {
+        "type": "CentralTransitive",
+        "requested": "[2.23.0, )",
+        "resolved": "2.23.0",
+        "contentHash": "OPNPmt/lRyUKVYrFLQXVxyATqD3MKLc1iY1oKx1/2GppgmZxVZPwN12tekrQ4C7408kgB1L5JD1Wnirqqeb2kg==",
+        "dependencies": {
+          "Silk.NET.Windowing.Common": "2.23.0",
+          "Silk.NET.Windowing.Glfw": "2.23.0"
+        }
+      },
+      "Tmds.DBus.Protocol": {
+        "type": "CentralTransitive",
+        "requested": "[0.21.3, )",
+        "resolved": "0.21.3",
+        "contentHash": "hDwB8WsQoyALQKqIbwzS68UKdlnafDm4T/DkO/JrA/YIneP/rKv96SxYPVXeh3FP4i/SXfShrYftKLtciJAIlw=="
+      }
+    },
+    "net10.0/linux-x64": {
+      "Avalonia.Angle.Windows.Natives": {
+        "type": "Transitive",
+        "resolved": "2.1.25547.20250602",
+        "contentHash": "ZL0VLc4s9rvNNFt19Pxm5UNAkmKNylugAwJPX9ulXZ6JWs/l6XZihPWWTyezaoNOVyEPU8YbURtW7XMAtqXH5A=="
+      },
+      "Avalonia.Native": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "8g53DROFW6wVJAnTsE1Iu5bdZO5r0oqxbdbMQODs1QDYCK2IU/y/x/vQVKCYOvqxl4tXkzU9tExv8XqSGPWthQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "HarfBuzzSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "3EZ1mpIiKWRLL5hUYA82ZHteeDIVaEA/Z0rA/wU6tjx6crcAkJnBPwDXZugBSfo8+J3EznvRJf49uMsqYfKrHg=="
+      },
+      "HarfBuzzSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "jbtCsgftcaFLCA13tVKo5iWdElJScrulLTKJre36O4YQTIlwDtPPqhRZNk+Y0vv4D1gxbscasGRucUDfS44ofQ=="
+      },
+      "HarfBuzzSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "UsJtQsfAJoFDZrXc4hCUfRPMqccfKZ0iumJ/upcUjz/cmsTgVFGNEL5yaJWmkqsuFYdMWbj/En5/kS4PFl9hBA=="
+      },
+      "SkiaSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "cWSaJKVPWAaT/WIn9c8T5uT/l4ETwHxNJTkEOtNKjphNo8AW6TF9O32aRkxqw3l8GUdUo66Bu7EiqtFh/XG0Zg==",
+        "dependencies": {
+          "SkiaSharp": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "Nv5spmKc4505Ep7oUoJ5vp3KweFpeNqxpyGDWyeEPTX2uR6S6syXIm3gj75dM0YJz7NPvcix48mR5laqs8dPuA=="
+      },
+      "SkiaSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "wb2kYgU7iy84nQLYZwMeJXixvK++GoIuECjU4ECaUKNuflyRlJKyiRhN1MAHswvlvzuvkrjRWlK0Za6+kYQK7w=="
+      },
+      "Ultz.Native.GLFW": {
+        "type": "Transitive",
+        "resolved": "3.4.0",
+        "contentHash": "Iy22JopynbOJ32vA0lBhFEzGi65GQJBuJHYBYRBpydrDpNoTiHnjIXfA65Gu+8qsOr/ZEoIF8r9aHCgAXuO6DA=="
+      }
+    },
+    "net10.0/osx-arm64": {
+      "Avalonia.Angle.Windows.Natives": {
+        "type": "Transitive",
+        "resolved": "2.1.25547.20250602",
+        "contentHash": "ZL0VLc4s9rvNNFt19Pxm5UNAkmKNylugAwJPX9ulXZ6JWs/l6XZihPWWTyezaoNOVyEPU8YbURtW7XMAtqXH5A=="
+      },
+      "Avalonia.Native": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "8g53DROFW6wVJAnTsE1Iu5bdZO5r0oqxbdbMQODs1QDYCK2IU/y/x/vQVKCYOvqxl4tXkzU9tExv8XqSGPWthQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "HarfBuzzSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "3EZ1mpIiKWRLL5hUYA82ZHteeDIVaEA/Z0rA/wU6tjx6crcAkJnBPwDXZugBSfo8+J3EznvRJf49uMsqYfKrHg=="
+      },
+      "HarfBuzzSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "jbtCsgftcaFLCA13tVKo5iWdElJScrulLTKJre36O4YQTIlwDtPPqhRZNk+Y0vv4D1gxbscasGRucUDfS44ofQ=="
+      },
+      "HarfBuzzSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "UsJtQsfAJoFDZrXc4hCUfRPMqccfKZ0iumJ/upcUjz/cmsTgVFGNEL5yaJWmkqsuFYdMWbj/En5/kS4PFl9hBA=="
+      },
+      "SkiaSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "cWSaJKVPWAaT/WIn9c8T5uT/l4ETwHxNJTkEOtNKjphNo8AW6TF9O32aRkxqw3l8GUdUo66Bu7EiqtFh/XG0Zg==",
+        "dependencies": {
+          "SkiaSharp": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "Nv5spmKc4505Ep7oUoJ5vp3KweFpeNqxpyGDWyeEPTX2uR6S6syXIm3gj75dM0YJz7NPvcix48mR5laqs8dPuA=="
+      },
+      "SkiaSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "wb2kYgU7iy84nQLYZwMeJXixvK++GoIuECjU4ECaUKNuflyRlJKyiRhN1MAHswvlvzuvkrjRWlK0Za6+kYQK7w=="
+      },
+      "Ultz.Native.GLFW": {
+        "type": "Transitive",
+        "resolved": "3.4.0",
+        "contentHash": "Iy22JopynbOJ32vA0lBhFEzGi65GQJBuJHYBYRBpydrDpNoTiHnjIXfA65Gu+8qsOr/ZEoIF8r9aHCgAXuO6DA=="
+      }
+    },
+    "net10.0/osx-x64": {
+      "Avalonia.Angle.Windows.Natives": {
+        "type": "Transitive",
+        "resolved": "2.1.25547.20250602",
+        "contentHash": "ZL0VLc4s9rvNNFt19Pxm5UNAkmKNylugAwJPX9ulXZ6JWs/l6XZihPWWTyezaoNOVyEPU8YbURtW7XMAtqXH5A=="
+      },
+      "Avalonia.Native": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "8g53DROFW6wVJAnTsE1Iu5bdZO5r0oqxbdbMQODs1QDYCK2IU/y/x/vQVKCYOvqxl4tXkzU9tExv8XqSGPWthQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "HarfBuzzSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "3EZ1mpIiKWRLL5hUYA82ZHteeDIVaEA/Z0rA/wU6tjx6crcAkJnBPwDXZugBSfo8+J3EznvRJf49uMsqYfKrHg=="
+      },
+      "HarfBuzzSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "jbtCsgftcaFLCA13tVKo5iWdElJScrulLTKJre36O4YQTIlwDtPPqhRZNk+Y0vv4D1gxbscasGRucUDfS44ofQ=="
+      },
+      "HarfBuzzSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "UsJtQsfAJoFDZrXc4hCUfRPMqccfKZ0iumJ/upcUjz/cmsTgVFGNEL5yaJWmkqsuFYdMWbj/En5/kS4PFl9hBA=="
+      },
+      "SkiaSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "cWSaJKVPWAaT/WIn9c8T5uT/l4ETwHxNJTkEOtNKjphNo8AW6TF9O32aRkxqw3l8GUdUo66Bu7EiqtFh/XG0Zg==",
+        "dependencies": {
+          "SkiaSharp": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "Nv5spmKc4505Ep7oUoJ5vp3KweFpeNqxpyGDWyeEPTX2uR6S6syXIm3gj75dM0YJz7NPvcix48mR5laqs8dPuA=="
+      },
+      "SkiaSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "wb2kYgU7iy84nQLYZwMeJXixvK++GoIuECjU4ECaUKNuflyRlJKyiRhN1MAHswvlvzuvkrjRWlK0Za6+kYQK7w=="
+      },
+      "Ultz.Native.GLFW": {
+        "type": "Transitive",
+        "resolved": "3.4.0",
+        "contentHash": "Iy22JopynbOJ32vA0lBhFEzGi65GQJBuJHYBYRBpydrDpNoTiHnjIXfA65Gu+8qsOr/ZEoIF8r9aHCgAXuO6DA=="
+      }
+    },
+    "net10.0/win-x64": {
+      "Avalonia.Angle.Windows.Natives": {
+        "type": "Transitive",
+        "resolved": "2.1.25547.20250602",
+        "contentHash": "ZL0VLc4s9rvNNFt19Pxm5UNAkmKNylugAwJPX9ulXZ6JWs/l6XZihPWWTyezaoNOVyEPU8YbURtW7XMAtqXH5A=="
+      },
+      "Avalonia.Native": {
+        "type": "Transitive",
+        "resolved": "11.3.18",
+        "contentHash": "8g53DROFW6wVJAnTsE1Iu5bdZO5r0oqxbdbMQODs1QDYCK2IU/y/x/vQVKCYOvqxl4tXkzU9tExv8XqSGPWthQ==",
+        "dependencies": {
+          "Avalonia": "11.3.18"
+        }
+      },
+      "HarfBuzzSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "3EZ1mpIiKWRLL5hUYA82ZHteeDIVaEA/Z0rA/wU6tjx6crcAkJnBPwDXZugBSfo8+J3EznvRJf49uMsqYfKrHg=="
+      },
+      "HarfBuzzSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "jbtCsgftcaFLCA13tVKo5iWdElJScrulLTKJre36O4YQTIlwDtPPqhRZNk+Y0vv4D1gxbscasGRucUDfS44ofQ=="
+      },
+      "HarfBuzzSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "8.3.1.1",
+        "contentHash": "UsJtQsfAJoFDZrXc4hCUfRPMqccfKZ0iumJ/upcUjz/cmsTgVFGNEL5yaJWmkqsuFYdMWbj/En5/kS4PFl9hBA=="
+      },
+      "SkiaSharp.NativeAssets.Linux": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "cWSaJKVPWAaT/WIn9c8T5uT/l4ETwHxNJTkEOtNKjphNo8AW6TF9O32aRkxqw3l8GUdUo66Bu7EiqtFh/XG0Zg==",
+        "dependencies": {
+          "SkiaSharp": "2.88.9"
+        }
+      },
+      "SkiaSharp.NativeAssets.macOS": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "Nv5spmKc4505Ep7oUoJ5vp3KweFpeNqxpyGDWyeEPTX2uR6S6syXIm3gj75dM0YJz7NPvcix48mR5laqs8dPuA=="
+      },
+      "SkiaSharp.NativeAssets.Win32": {
+        "type": "Transitive",
+        "resolved": "2.88.9",
+        "contentHash": "wb2kYgU7iy84nQLYZwMeJXixvK++GoIuECjU4ECaUKNuflyRlJKyiRhN1MAHswvlvzuvkrjRWlK0Za6+kYQK7w=="
+      },
+      "Ultz.Native.GLFW": {
+        "type": "Transitive",
+        "resolved": "3.4.0",
+        "contentHash": "Iy22JopynbOJ32vA0lBhFEzGi65GQJBuJHYBYRBpydrDpNoTiHnjIXfA65Gu+8qsOr/ZEoIF8r9aHCgAXuO6DA=="
+      }
+    }
+  }
+}

src/SharpEmu.Core/Cpu/Emulation/Sha1InstructionEmulator.cs

@@ -1,81 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Numerics;
-
-namespace SharpEmu.Core.Cpu.Emulation;
-
-/// <summary>
-/// The four Intel SHA-extension operations used by SHA-1 code. This is the arithmetic half of
-/// the direct-execution SIGILL fallback used when an x86-64 guest runs under Rosetta 2, which
-/// does not expose Intel SHA instructions to translated processes.
-/// </summary>
-public static class Sha1InstructionEmulator
-{
-    public static Sha1Vector MessageSchedule1(Sha1Vector destination, Sha1Vector source) => new(
-        destination.Lane0 ^ source.Lane2,
-        destination.Lane1 ^ source.Lane3,
-        destination.Lane2 ^ destination.Lane0,
-        destination.Lane3 ^ destination.Lane1);
-
-    public static Sha1Vector MessageSchedule2(Sha1Vector destination, Sha1Vector source)
-    {
-        var lane3 = BitOperations.RotateLeft(destination.Lane3 ^ source.Lane2, 1);
-        return new Sha1Vector(
-            BitOperations.RotateLeft(destination.Lane0 ^ lane3, 1),
-            BitOperations.RotateLeft(destination.Lane1 ^ source.Lane0, 1),
-            BitOperations.RotateLeft(destination.Lane2 ^ source.Lane1, 1),
-            lane3);
-    }
-
-    public static Sha1Vector NextE(Sha1Vector destination, Sha1Vector source) => new(
-        source.Lane0,
-        source.Lane1,
-        source.Lane2,
-        unchecked(source.Lane3 + BitOperations.RotateLeft(destination.Lane3, 30)));
-
-    public static Sha1Vector FourRounds(Sha1Vector destination, Sha1Vector source, byte function)
-    {
-        uint a = destination.Lane3;
-        uint b = destination.Lane2;
-        uint c = destination.Lane1;
-        uint d = destination.Lane0;
-        uint e = 0;
-
-        uint constant = (function & 3) switch
-        {
-            0 => 0x5A82_7999u,
-            1 => 0x6ED9_EBA1u,
-            2 => 0x8F1B_BCDCu,
-            _ => 0xCA62_C1D6u,
-        };
-
-        for (var round = 0; round < 4; round++)
-        {
-            uint choose = (function & 3) switch
-            {
-                0 => (b & c) ^ (~b & d),
-                2 => (b & c) ^ (b & d) ^ (c & d),
-                _ => b ^ c ^ d,
-            };
-            uint word = round switch
-            {
-                0 => source.Lane3,
-                1 => source.Lane2,
-                2 => source.Lane1,
-                _ => source.Lane0,
-            };
-            uint next = unchecked(choose + BitOperations.RotateLeft(a, 5) + word + e + constant);
-            e = d;
-            d = c;
-            c = BitOperations.RotateLeft(b, 30);
-            b = a;
-            a = next;
-        }
-
-        return new Sha1Vector(d, c, b, a);
-    }
-}
-
-/// <summary>The four little-endian 32-bit lanes of an XMM register.</summary>
-public readonly record struct Sha1Vector(uint Lane0, uint Lane1, uint Lane2, uint Lane3);

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.Exceptions.cs

@@ -1113,12 +1113,7 @@ public sealed partial class DirectExecutionBackend
 		}
 	}
 
-	private unsafe static bool TryReadHostBytes(ulong address, byte[] buffer) =>
-		TryReadHostBytes(address, buffer.AsSpan());
-
-	// Span overload so signal-handler recovery paths can read into a stackalloc
-	// buffer instead of allocating managed arrays inside the handler.
-	private unsafe static bool TryReadHostBytes(ulong address, Span<byte> buffer)
+	private unsafe static bool TryReadHostBytes(ulong address, byte[] buffer)
 	{
 		if (address < 65536)
 		{
@@ -1142,7 +1137,7 @@ public sealed partial class DirectExecutionBackend
 
 		try
 		{
-			new ReadOnlySpan<byte>((void*)address, buffer.Length).CopyTo(buffer);
+			Marshal.Copy((nint)address, buffer, 0, buffer.Length);
 			return true;
 		}
 		catch

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.IllegalInstruction.cs

@@ -8,21 +8,21 @@ using SharpEmu.Core.Cpu.Emulation;
 
 namespace SharpEmu.Core.Cpu.Native;
 
-// Software fallback for unsupported guest CPU instructions.
+// Software fallback for the BMI1/BMI2/ABM general-purpose-register instructions.
 //
 // Guest code runs natively, so the guest and host share the same virtual address space and the
 // same registers (the OS delivers them in the CONTEXT record on a fault). When the host CPU lacks
 // one of these extensions it raises #UD instead of executing the opcode; without this the title
 // simply aborts. Here we decode the faulting instruction, evaluate it against the trapped register
 // and memory state, write the result back into the CONTEXT, step RIP past the instruction and ask
-// the OS to continue. BMI1/BMI2/ABM GPR operations and the Intel SHA-1 XMM operations are handled;
-// anything else falls through to the existing diagnostics unchanged.
+// the OS to continue. Only the register-only BMI/ABM forms are handled; anything else returns false
+// and falls through to the existing diagnostics unchanged, so this can never mis-handle an opcode it
+// does not fully model.
 public sealed partial class DirectExecutionBackend
 {
     // Windows x64 CONTEXT.EFlags lives just past the segment selectors. The GPR offsets it shares
     // with the rest of the backend are the CTX_* constants declared in DirectExecutionBackend.cs.
     private const int CTX_EFLAGS = 68;
-    private const int CTX_XMM0 = 0x1A0;
 
     // STATUS_ILLEGAL_INSTRUCTION (#UD surfaced by the Windows vectored handler).
     private const uint StatusIllegalInstruction = 0xC000001Du;
@@ -34,8 +34,6 @@ public sealed partial class DirectExecutionBackend
 
     private static int _bmiSoftwareFallbackAnnounced;
     private static long _bmiInstructionsEmulated;
-    private static int _sha1SoftwareFallbackAnnounced;
-    private static long _sha1InstructionsEmulated;
 
     private unsafe bool TryRecoverIllegalInstruction(void* contextRecord, ulong rip)
     {
@@ -44,11 +42,6 @@ public sealed partial class DirectExecutionBackend
             return false;
         }
 
-        if (TryRecoverSha1Instruction(contextRecord, rip, in instruction))
-        {
-            return true;
-        }
-
         if (instruction.Op0Kind != OpKind.Register ||
             !TryGetGprSlot(instruction.Op0Register, out var destOffset, out var size))
         {
@@ -79,139 +72,6 @@ public sealed partial class DirectExecutionBackend
         return true;
     }
 
-    private unsafe bool TryRecoverSha1Instruction(
-        void* contextRecord,
-        ulong rip,
-        in Instruction instruction)
-    {
-        if ((!OperatingSystem.IsWindows() && !_posixVectorContextAvailable) ||
-            instruction.Mnemonic is not (Mnemonic.Sha1msg1 or Mnemonic.Sha1msg2 or
-            Mnemonic.Sha1nexte or Mnemonic.Sha1rnds4) ||
-            instruction.Op0Kind != OpKind.Register ||
-            !TryGetXmmIndex(instruction.Op0Register, out var destinationIndex) ||
-            !TryReadSha1VectorOperand(contextRecord, in instruction, 1, out var source))
-        {
-            return false;
-        }
-
-        var destination = ReadXmm(contextRecord, destinationIndex);
-        Sha1Vector result;
-        switch (instruction.Mnemonic)
-        {
-            case Mnemonic.Sha1msg1:
-                result = Sha1InstructionEmulator.MessageSchedule1(destination, source);
-                break;
-            case Mnemonic.Sha1msg2:
-                result = Sha1InstructionEmulator.MessageSchedule2(destination, source);
-                break;
-            case Mnemonic.Sha1nexte:
-                result = Sha1InstructionEmulator.NextE(destination, source);
-                break;
-            case Mnemonic.Sha1rnds4:
-                if (instruction.Op2Kind != OpKind.Immediate8)
-                {
-                    return false;
-                }
-
-                result = Sha1InstructionEmulator.FourRounds(destination, source, instruction.Immediate8);
-                break;
-            default:
-                return false;
-        }
-
-        WriteXmm(contextRecord, destinationIndex, result);
-        WriteCtxU64(contextRecord, CTX_RIP, rip + (ulong)instruction.Length);
-
-        if (!_posixSignalWarmup)
-        {
-            Interlocked.Increment(ref _sha1InstructionsEmulated);
-            if (Interlocked.Exchange(ref _sha1SoftwareFallbackAnnounced, 1) == 0)
-            {
-                Console.Error.WriteLine(
-                    "[LOADER][INFO] Host lacks Intel SHA instructions used by the guest; " +
-                    "emulating SHA-1 instructions in software.");
-            }
-        }
-
-        return true;
-    }
-
-    private unsafe bool TryReadSha1VectorOperand(
-        void* contextRecord,
-        in Instruction instruction,
-        int operandIndex,
-        out Sha1Vector value)
-    {
-        switch (instruction.GetOpKind(operandIndex))
-        {
-            case OpKind.Register:
-                if (TryGetXmmIndex(instruction.GetOpRegister(operandIndex), out var sourceIndex))
-                {
-                    value = ReadXmm(contextRecord, sourceIndex);
-                    return true;
-                }
-                break;
-
-            case OpKind.Memory:
-                if (TryComputeMemoryAddress(contextRecord, in instruction, out var address))
-                {
-                    Span<byte> bytes = stackalloc byte[16];
-                    if (TryReadHostBytes(address, bytes))
-                    {
-                        value = new Sha1Vector(
-                            BinaryPrimitives.ReadUInt32LittleEndian(bytes.Slice(0, 4)),
-                            BinaryPrimitives.ReadUInt32LittleEndian(bytes.Slice(4, 4)),
-                            BinaryPrimitives.ReadUInt32LittleEndian(bytes.Slice(8, 4)),
-                            BinaryPrimitives.ReadUInt32LittleEndian(bytes.Slice(12, 4)));
-                        return true;
-                    }
-                }
-                break;
-        }
-
-        value = default;
-        return false;
-    }
-
-    private static unsafe Sha1Vector ReadXmm(void* contextRecord, int index)
-    {
-        uint* lanes = (uint*)((byte*)contextRecord + CTX_XMM0 + index * 16);
-        return new Sha1Vector(lanes[0], lanes[1], lanes[2], lanes[3]);
-    }
-
-    private static unsafe void WriteXmm(void* contextRecord, int index, Sha1Vector value)
-    {
-        uint* lanes = (uint*)((byte*)contextRecord + CTX_XMM0 + index * 16);
-        lanes[0] = value.Lane0;
-        lanes[1] = value.Lane1;
-        lanes[2] = value.Lane2;
-        lanes[3] = value.Lane3;
-    }
-
-    private static bool TryGetXmmIndex(Register register, out int index)
-    {
-        switch (register)
-        {
-            case Register.XMM0: index = 0; return true;
-            case Register.XMM1: index = 1; return true;
-            case Register.XMM2: index = 2; return true;
-            case Register.XMM3: index = 3; return true;
-            case Register.XMM4: index = 4; return true;
-            case Register.XMM5: index = 5; return true;
-            case Register.XMM6: index = 6; return true;
-            case Register.XMM7: index = 7; return true;
-            case Register.XMM8: index = 8; return true;
-            case Register.XMM9: index = 9; return true;
-            case Register.XMM10: index = 10; return true;
-            case Register.XMM11: index = 11; return true;
-            case Register.XMM12: index = 12; return true;
-            case Register.XMM13: index = 13; return true;
-            case Register.XMM14: index = 14; return true;
-            case Register.XMM15: index = 15; return true;
-            default: index = 0; return false;
-        }
-    }
-
     private unsafe bool TryEvaluate(
         void* contextRecord,
         in Instruction instruction,
@@ -334,37 +194,19 @@ public sealed partial class DirectExecutionBackend
         }
     }
 
-    // A managed allocation inside a signal handler is unsafe: the fault can
-    // interrupt the GC mid-operation, and re-entering the allocator corrupts
-    // the thread's allocation context (observed as a hard "Invalid Program" at
-    // the next managed alloc, amplified by tight SHA-1 recovery loops). These
-    // thread-static objects are created once per thread and reused so the
-    // recovery path never allocates on the hot path.
-    [ThreadStatic]
-    private static byte[]? _decodeBuffer;
-    [ThreadStatic]
-    private static ByteArrayCodeReader? _decodeReader;
-    [ThreadStatic]
-    private static Decoder? _decoder;
-
     private unsafe bool TryReadFaultingInstruction(ulong rip, out Instruction instruction)
     {
-        var buffer = _decodeBuffer ??= new byte[MaxInstructionBytes];
-        var reader = _decodeReader ??= new ByteArrayCodeReader(buffer);
-        var decoder = _decoder ??= Decoder.Create(64, reader);
-
         // Try the full instruction window first, then shrink so a fault near the end of a mapped
-        // page (where fewer than 15 bytes are readable) still decodes. The buffer is reused, so
-        // clear the tail past the readable window to keep decoding deterministic.
+        // page (where fewer than 15 bytes are readable) still decodes.
         foreach (var attempt in DecodeWindowSizes)
         {
-            if (!TryReadHostBytes(rip, buffer.AsSpan(0, attempt)))
+            var buffer = new byte[attempt];
+            if (!TryReadHostBytes(rip, buffer))
             {
                 continue;
             }
 
-            buffer.AsSpan(attempt).Clear();
-            reader.Position = 0;
+            var decoder = Decoder.Create(64, new ByteArrayCodeReader(buffer));
             decoder.IP = rip;
             decoder.Decode(out instruction);
             if (instruction.Code != Code.INVALID && instruction.Length > 0 && instruction.Length <= attempt)
@@ -404,8 +246,8 @@ public sealed partial class DirectExecutionBackend
                 }
 
                 var byteCount = size == GprOperandSize.Bits64 ? 8 : 4;
-                Span<byte> buffer = stackalloc byte[8];
-                if (!TryReadHostBytes(address, buffer[..byteCount]))
+                var buffer = new byte[byteCount];
+                if (!TryReadHostBytes(address, buffer))
                 {
                     return false;
                 }

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.Imports.cs

@@ -630,6 +630,27 @@ public sealed partial class DirectExecutionBackend
 					cpuContext[CpuRegister.Rax] = 18446744071562199298uL;
 				}
 			}
+			if (GuestThreadExecution.TryConsumeCurrentThreadBlock(
+					out var blockReason,
+					out var blockContinuation,
+					out var hasBlockContinuation,
+					out var blockWakeKey,
+					out var blockWaiter,
+					out var blockDeadlineTimestamp) &&
+				TryYieldGuestThreadToHostStub(argPackPtr, num, num7, importStubEntry.Nid, blockReason))
+			{
+				if (hasBlockContinuation)
+				{
+					RegisterBlockedGuestThreadContinuation(
+						GuestThreadExecution.CurrentGuestThreadHandle,
+						blockContinuation,
+						blockWakeKey,
+						blockWaiter,
+						blockDeadlineTimestamp);
+				}
+
+				cpuContext[CpuRegister.Rax] = 0uL;
+			}
 			if (flag || flag2 || flag3)
 			{
 				Console.Error.WriteLine($"[LOADER][TRACE] ImportRet#{num}: nid={importStubEntry.Nid} result={orbisGen2Result} rax=0x{cpuContext[CpuRegister.Rax]:X16}");
@@ -1324,13 +1345,35 @@ public sealed partial class DirectExecutionBackend
 			}
 		}
 
+		var consumedThreadBlock = GuestThreadExecution.TryConsumeCurrentThreadBlock(
+				out var blockReason,
+				out var blockContinuation,
+				out var hasBlockContinuation,
+				out var blockWakeKey,
+				out var blockWaiter,
+				out var blockDeadlineTimestamp);
+		if (consumedThreadBlock &&
+			TryYieldGuestThreadToHostStub(argPackPtr, dispatchIndex, returnRip, importStubEntry.Nid, blockReason))
+		{
+			if (hasBlockContinuation)
+			{
+				RegisterBlockedGuestThreadContinuation(
+					GuestThreadExecution.CurrentGuestThreadHandle,
+					blockContinuation,
+					blockWakeKey,
+					blockWaiter,
+					blockDeadlineTimestamp);
+			}
+
+			cpuContext[CpuRegister.Rax] = 0uL;
+		}
 		if (probeLeafReturn)
 		{
 			Console.Error.WriteLine(
 				$"[LOADER][TRACE] leaf-return-probe-exit nid={importStubEntry.Nid} " +
 				$"original=0x{returnRip:X16} final=0x{*(ulong*)(argPackPtr + 96):X16} " +
 				$"rsp=0x{leafStackPointer:X16} active_slot=0x{ActiveGuestReturnSlotAddress:X16} " +
-				$"yield={ActiveGuestThreadYieldRequested}");
+				$"block={consumedThreadBlock} yield={ActiveGuestThreadYieldRequested}");
 		}
 
 		result = cpuContext[CpuRegister.Rax];
@@ -1367,8 +1410,6 @@ public sealed partial class DirectExecutionBackend
 			"eE4Szl8sil8" or // sceKernelAprSubmitCommandBuffer
 			"qvMUCyyaCSI" or // sceKernelAprSubmitCommandBufferAndGetId
 			"Q2V+iqvjgC0" or // vsnprintf
-			"AV6ipCNa4Rw" or // strcasecmp
-			"viiwFMaNamA" or // strstr
 			"q1cHNfGycLI" or // scePadRead
 			"xk0AcarP3V4" or // scePadOpen
 			"yH17Q6NWtVg" or // sceUserServiceGetEvent
@@ -1395,9 +1436,6 @@ public sealed partial class DirectExecutionBackend
 		var expectedMutexTrylockBusy =
 			string.Equals(nid, "K-jXhbt2gn4", StringComparison.Ordinal) &&
 			result == OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
-		var expectedSemaphoreTrywaitAgain =
-			string.Equals(nid, "H2a+IN9TP0E", StringComparison.Ordinal) &&
-			result == OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN;
 		var expectedNetAcceptWouldBlock =
 			string.Equals(nid, "PIWqhn9oSxc", StringComparison.Ordinal) &&
 			resultValue == unchecked((int)0x80410123);
@@ -1411,7 +1449,6 @@ public sealed partial class DirectExecutionBackend
 			!expectedTimedWaitTimeout &&
 			!expectedEqueueTimeout &&
 			!expectedMutexTrylockBusy &&
-			!expectedSemaphoreTrywaitAgain &&
 			!expectedNetAcceptWouldBlock &&
 			!expectedUserServiceNoEvent &&
 			!expectedPrivacyInvalidParameter)
@@ -1534,8 +1571,6 @@ public sealed partial class DirectExecutionBackend
 			"WkkeywLJcgU" or // wcslen
 			"Ovb2dSJOAuE" or // strcmp
 			"aesyjrHVWy4" or // strncmp
-			"AV6ipCNa4Rw" or // strcasecmp
-			"viiwFMaNamA" or // strstr
 			"pNtJdE3x49E" or // wcscmp
 			"fV2xHER+bKE" or // wcscoll
 			"E8wCoUEbfzk" or // wcsncmp

src/SharpEmu.Core/Cpu/Native/DirectExecutionBackend.PosixSignals.cs

@@ -50,15 +50,6 @@ public sealed unsafe partial class DirectExecutionBackend
 	private const int LinuxUcontextGregsOffset = 40;
 	private const int LinuxGregsErrOffset = 19 * 8;
 
-	// XMM0 starts after the exception/thread states and the floating-point header on Darwin.
-	// Linux mcontext_t instead stores a pointer to an FXSAVE-compatible _libc_fpstate after
-	// gregs[23], where XMM0 begins at byte 160.
-	private const int DarwinMcontextFloatStateOffset = 16 + 21 * 8;
-	private const int DarwinFloatStateXmmOffset = 168;
-	private const int LinuxFpregsPointerOffset = 23 * 8;
-	private const int LinuxFxsaveXmmOffset = 160;
-	private const int XmmRegisterBlockSize = 16 * 16;
-
 	// Byte offsets of the general registers relative to GetPosixRegisterBase,
 	// ordered to match the contiguous Win64 CONTEXT block CTX_RAX..CTX_RIP
 	// (rax, rcx, rdx, rbx, rsp, rbp, rsi, rdi, r8..r15, rip). Verified
@@ -79,8 +70,6 @@ public sealed unsafe partial class DirectExecutionBackend
 
 	[ThreadStatic]
 	private static int _posixSignalHandlerDepth;
-	[ThreadStatic]
-	private static bool _posixVectorContextAvailable;
 
 	private void SetupPosixExceptionHandler()
 	{
@@ -132,10 +121,8 @@ public sealed unsafe partial class DirectExecutionBackend
 	{
 		byte* fakeUcontext = stackalloc byte[512];
 		new Span<byte>(fakeUcontext, 512).Clear();
-		// Large enough for the Darwin mcontext64 XMM block the handler now
-		// round-trips (exception+thread state + float state = 708 bytes).
-		byte* fakeMcontext = stackalloc byte[768];
-		new Span<byte>(fakeMcontext, 768).Clear();
+		byte* fakeMcontext = stackalloc byte[512];
+		new Span<byte>(fakeMcontext, 512).Clear();
 		if (OperatingSystem.IsMacOS())
 		{
 			*(byte**)(fakeUcontext + DarwinUcontextMcontextOffset) = fakeMcontext;
@@ -167,33 +154,6 @@ public sealed unsafe partial class DirectExecutionBackend
 			record.ExceptionInformation[1] = 0x70000;
 			_ = TryHandleLazyCommittedPage(&record, 0, 0);
 			ChainPreviousPosixAction(0, 0, 0);
-
-			// Rosetta can deliver the first unsupported SHA instruction before the
-			// runtime is in a safe state to JIT the recovery path. Decode and execute
-			// each supported form once now, while signal handlers are not installed.
-			byte[][] shaWarmupOpcodes =
-			{
-				new byte[] { 0x0F, 0x38, 0xC9, 0xC1 },       // sha1msg1 xmm0, xmm1
-				new byte[] { 0x0F, 0x38, 0xCA, 0xC1 },       // sha1msg2 xmm0, xmm1
-				new byte[] { 0x0F, 0x38, 0xC8, 0xC1 },       // sha1nexte xmm0, xmm1
-				new byte[] { 0x0F, 0x3A, 0xCC, 0xC1, 0x00 }, // sha1rnds4 xmm0, xmm1, 0
-			};
-			_posixVectorContextAvailable = true;
-			try
-			{
-				foreach (byte[] opcode in shaWarmupOpcodes)
-				{
-					fixed (byte* instructionBytes = opcode)
-					{
-						WriteCtxU64(contextRecord, CTX_RIP, (ulong)instructionBytes);
-						_ = TryRecoverIllegalInstruction(contextRecord, (ulong)instructionBytes);
-					}
-				}
-			}
-			finally
-			{
-				_posixVectorContextAvailable = false;
-			}
 		}
 		finally
 		{
@@ -291,15 +251,6 @@ public sealed unsafe partial class DirectExecutionBackend
 		{
 			WriteCtxU64(contextRecord, CTX_RAX + i * 8, *(ulong*)(registers + offsets[i]));
 		}
-		// Only bridge the XMM block for SIGILL, the sole signal whose recovery
-		// may emulate an XMM instruction (Intel SHA). Copying 256 bytes in and
-		// out of the mcontext on every SIGSEGV (the hot demand-paging path) is
-		// pure overhead and needless surface for corruption.
-		byte* xmmRegisters = signal == PosixSigIll ? GetPosixXmmBase(registers) : null;
-		if (xmmRegisters != null)
-		{
-			CopyXmmRegisterBlock(contextRecord + CTX_XMM0, xmmRegisters);
-		}
 
 		EXCEPTION_RECORD record = default;
 		record.ExceptionAddress = (void*)ReadCtxU64(contextRecord, CTX_RIP);
@@ -343,21 +294,13 @@ public sealed unsafe partial class DirectExecutionBackend
 		// every fault anyway, and recovering here avoids dumping the full
 		// VectoredHandler diagnostics for each recoverable trap.
 		int disposition = 0;
-		_posixVectorContextAvailable = xmmRegisters != null;
-		try
+		if (_posixRawRecoveryEnabled)
 		{
-			if (_posixRawRecoveryEnabled)
-			{
-				disposition = TryRecoverUnresolvedSentinel(&pointers);
-			}
-			if (disposition != -1 && !_posixSignalWarmup && _posixSignalBackend is { } backend)
-			{
-				disposition = backend.VectoredHandler(&pointers);
-			}
+			disposition = TryRecoverUnresolvedSentinel(&pointers);
 		}
-		finally
+		if (disposition != -1 && !_posixSignalWarmup && _posixSignalBackend is { } backend)
 		{
-			_posixVectorContextAvailable = false;
+			disposition = backend.VectoredHandler(&pointers);
 		}
 		if (traceSignal)
 		{
@@ -374,10 +317,6 @@ public sealed unsafe partial class DirectExecutionBackend
 		{
 			*(ulong*)(registers + offsets[i]) = ReadCtxU64(contextRecord, CTX_RAX + i * 8);
 		}
-		if (xmmRegisters != null)
-		{
-			CopyXmmRegisterBlock(xmmRegisters, contextRecord + CTX_XMM0);
-		}
 		return true;
 	}
 
@@ -396,25 +335,6 @@ public sealed unsafe partial class DirectExecutionBackend
 		return (byte*)ucontext + LinuxUcontextGregsOffset;
 	}
 
-	private static byte* GetPosixXmmBase(byte* registers)
-	{
-		if (OperatingSystem.IsMacOS())
-		{
-			return registers + DarwinMcontextFloatStateOffset + DarwinFloatStateXmmOffset;
-		}
-
-		byte* fpregs = *(byte**)(registers + LinuxFpregsPointerOffset);
-		return fpregs == null ? null : fpregs + LinuxFxsaveXmmOffset;
-	}
-
-	private static void CopyXmmRegisterBlock(byte* destination, byte* source)
-	{
-		for (var offset = 0; offset < XmmRegisterBlockSize; offset += sizeof(ulong))
-		{
-			*(ulong*)(destination + offset) = *(ulong*)(source + offset);
-		}
-	}
-
 	private static ulong GetPosixFaultAddress(nint siginfo, byte* registers)
 	{
 		ulong address = siginfo != 0 ? *(ulong*)((byte*)siginfo + PosixSigInfoAddressOffset) : 0;

src/SharpEmu.Core/Cpu/Native/JitStubs.cs

@@ -252,7 +252,7 @@ public static unsafe class JitStubs
         var pattern = TlsAccessPattern;
         var end = start + length - pattern.Length;
 
-        for (var ptr = start; ptr <= end; ptr++)
+        for (var ptr = start; ptr < end; ptr++)
         {
             if (MatchesPattern(ptr, pattern))
             {

src/SharpEmu.Core/Cpu/Native/Sse4aExtrqBlendPatch.cs

@@ -1,115 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System;
-
-namespace SharpEmu.Core.Cpu.Native;
-
-/// <summary>
-/// Recognizes Sony's AMD-only SSE4a EXTRQ+blend idiom and rewrites it into an
-/// equivalent SSE4.1 sequence. SharpEmu executes guest x86-64 natively, but
-/// Rosetta 2 and Intel hosts do not implement SSE4a, so the original opcode
-/// raises #UD -> SIGILL. The compiler emits the idiom against whichever XMM
-/// register it happens to allocate (Dead Cells uses xmm1, others xmm2), so the
-/// source register is read from the ModRM r/m field rather than hard-coded.
-///
-/// The match/encode logic is deliberately free of native page-patching so it
-/// can be unit-tested against handcrafted byte sequences.
-/// </summary>
-public static class Sse4aExtrqBlendPatch
-{
-    /// <summary>Length in bytes of both the matched idiom and its replacement.</summary>
-    public const int SequenceLength = 12;
-
-    /// <summary>
-    /// Matches the 12-byte idiom, extracting the destination register D and the
-    /// source (scratch) register N:
-    /// <code>
-    ///   EXTRQ    xmmN, 0x28, 0x00     ; 66 0F 78 /0 28 00      mask xmmN to low 40 bits
-    ///   VPBLENDD xmmD, xmmD, xmmN, 2  ; C4 E3 vvvv 02 /r 02    copy dword 1 into xmmD
-    /// </code>
-    /// N lives in the ModRM r/m field of both instructions; D (the blend
-    /// destination and src1) lives in the VPBLENDD ModRM reg field and VEX.vvvv.
-    /// Both are xmm0-xmm7 (the VEX byte1 0xE3 pins R/X/B, so no xmm8-15 extension).
-    /// The compiler allocates whichever registers it likes — Dead Cells builds use
-    /// D=xmm0 and D=xmm3, others differ — so both are read from the encoding.
-    /// </summary>
-    public static bool TryMatch(ReadOnlySpan<byte> source, out int destRegister, out int srcRegister)
-    {
-        destRegister = -1;
-        srcRegister = -1;
-        if (source.Length < SequenceLength)
-        {
-            return false;
-        }
-
-        // EXTRQ xmmN, 0x28, 0x00 : 66 0F 78, ModRM (mod=11 reg=000 rm=N), 28, 00.
-        if (source[0] != 0x66 || source[1] != 0x0F || source[2] != 0x78 ||
-            (source[3] & 0xF8) != 0xC0 || source[4] != 0x28 || source[5] != 0x00)
-        {
-            return false;
-        }
-
-        var n = source[3] & 0x07;
-
-        // VPBLENDD xmmD, xmmD, xmmN, 2 : C4 E3 <W=0 vvvv=~D L=0 pp=01> 02 ModRM 02.
-        // VEX.byte2 fixed bits (W, L, pp) must read 0b*0000*01; vvvv encodes ~D.
-        if (source[6] != 0xC4 || source[7] != 0xE3 || (source[8] & 0x87) != 0x01 ||
-            source[9] != 0x02 || source[11] != 0x02)
-        {
-            return false;
-        }
-
-        var d = (~(source[8] >> 3)) & 0x0F;
-        if (d > 7)
-        {
-            return false;
-        }
-
-        // ModRM: mod=11, reg=D (dest = src1), rm=N (src2 = the masked register).
-        if (source[10] != (0xC0 | (d << 3) | n))
-        {
-            return false;
-        }
-
-        destRegister = d;
-        srcRegister = n;
-        return true;
-    }
-
-    /// <summary>
-    /// Writes the SSE4.1 equivalent into <paramref name="destination"/>:
-    /// <code>
-    ///   PEXTRB eax, xmmN, 4  ; 66 0F 3A 14 /r 04   extract byte 4 (zero-extended)
-    ///   PINSRD xmmD, eax, 1  ; 66 0F 3A 22 /r 01   insert into xmmD dword lane 1
-    /// </code>
-    /// After EXTRQ masks xmmN to its low 40 bits, dword 1 is just byte 4
-    /// zero-extended, so the two-instruction extract/insert reproduces the exact
-    /// observable result the AMD idiom left in xmmD. eax is a caller-dead scratch
-    /// at every site the compiler emits this idiom.
-    /// </summary>
-    public static bool TryEncode(int destRegister, int srcRegister, Span<byte> destination)
-    {
-        if ((uint)destRegister > 7 || (uint)srcRegister > 7 || destination.Length < SequenceLength)
-        {
-            return false;
-        }
-
-        // PEXTRB eax, xmmN, 4 : ModRM (mod=11 reg=N rm=000 -> eax), imm8 = byte index 4.
-        destination[0] = 0x66;
-        destination[1] = 0x0F;
-        destination[2] = 0x3A;
-        destination[3] = 0x14;
-        destination[4] = (byte)(0xC0 | (srcRegister << 3));
-        destination[5] = 0x04;
-
-        // PINSRD xmmD, eax, 1 : ModRM (mod=11 reg=D -> xmmD, rm=000 -> eax), lane 1.
-        destination[6] = 0x66;
-        destination[7] = 0x0F;
-        destination[8] = 0x3A;
-        destination[9] = 0x22;
-        destination[10] = (byte)(0xC0 | (destRegister << 3));
-        destination[11] = 0x01;
-        return true;
-    }
-}

src/SharpEmu.Core/Memory/PhysicalVirtualMemory.cs

@@ -873,15 +873,6 @@ public sealed unsafe class PhysicalVirtualMemory : IVirtualMemory, IGuestMemoryA
 
     public bool TryWrite(ulong virtualAddress, ReadOnlySpan<byte> source)
     {
-        // A managed write into a page the guest-image write tracker has
-        // protected surfaces as a fatal AccessViolation — the runtime turns
-        // SIGSEGV in managed code into an exception before the resumable
-        // signal bridge can restore access (native guest stores recover
-        // there). Pre-visit the span so tracked pages are unprotected and
-        // their owners dirtied before the copy; guest addresses are
-        // host-identical, matching the tracker's fault addresses.
-        GuestImageWriteTracker.NotifyManagedWrite(virtualAddress, (ulong)source.Length);
-
         var requiresExclusiveAccess = false;
         _gate.EnterReadLock();
         try

src/SharpEmu.GUI/MainWindow.axaml.cs

@@ -92,11 +92,6 @@ public partial class MainWindow : Window
     // plain window color remains the fallback when the asset fails to load.
     private Bitmap? _defaultBackdrop;
 
-    // Whether the native loading/closing popup should be showing; it is a
-    // desktop-topmost popup, so it closes while the launcher is in the
-    // background or minimized and reopens from this flag on activation.
-    private bool _sessionLoadingActive;
-
     // Controller navigation state.
     private readonly DispatcherTimer _gamepadTimer;
     private HostGamepadButtons _previousPadButtons;
@@ -155,18 +150,8 @@ public partial class MainWindow : Window
         };
         _libraryBlurTimer.Tick += (_, _) => AdvanceLibraryBlur();
 
-        // Native popups float above every window on the desktop; they must
-        // follow the launcher into the background or a minimized state.
-        Activated += (_, _) =>
-        {
-            UpdateSessionBarVisibility();
-            SessionLoadingPopup.IsOpen = _sessionLoadingActive;
-        };
-        Deactivated += (_, _) =>
-        {
-            SessionBarPopup.IsOpen = false;
-            SessionLoadingPopup.IsOpen = false;
-        };
+        Activated += (_, _) => UpdateSessionBarVisibility();
+        Deactivated += (_, _) => SessionBarPopup.IsOpen = false;
 
         TitleBar.PointerPressed += OnTitleBarPointerPressed;
         GameList.SelectionChanged += (_, _) => UpdateSelectedGame();
@@ -429,15 +414,6 @@ public partial class MainWindow : Window
             return;
         }
 
-        if (_isRunning || _isStopping)
-        {
-            // The game renders inside the launcher window, so the launcher
-            // stays active while playing. The controller belongs to the game
-            // then: no navigation, and Circle/B must never stop the session.
-            _previousPadButtons = pad.Buttons;
-            return;
-        }
-
         var shoulderPressed = pad.Buttons & ~_previousPadButtons;
         if ((shoulderPressed & HostGamepadButtons.L1) != 0)
         {
@@ -487,6 +463,11 @@ public partial class MainWindow : Window
             LaunchSelected();
         }
 
+        if ((pressed & HostGamepadButtons.Circle) != 0)
+        {
+            StopEmulator();
+        }
+
         _previousPadButtons = pad.Buttons;
     }
 
@@ -1645,23 +1626,13 @@ public partial class MainWindow : Window
         base.OnPropertyChanged(change);
         if (change.Property == WindowStateProperty)
         {
-            // The XAML WindowState="Maximized" assignment raises this change
-            // during InitializeComponent, before named controls are wired up.
             if (WindowState == WindowState.Minimized)
             {
                 _sndPreview.Pause();
-                if (SessionLoadingPopup is { } popup)
-                {
-                    popup.IsOpen = false;
-                }
             }
             else
             {
                 _sndPreview.Resume();
-                if (SessionLoadingPopup is { } popup)
-                {
-                    popup.IsOpen = _sessionLoadingActive;
-                }
             }
         }
     }
@@ -2038,7 +2009,7 @@ public partial class MainWindow : Window
                 ContentToolbar.IsVisible = false;
                 ConsolePanel.IsVisible = false;
                 LaunchBar.IsVisible = false;
-                HideSessionLoading();
+                SessionLoadingPopup.IsOpen = false;
                 UpdateSessionBarVisibility();
             }
         });
@@ -2138,7 +2109,7 @@ public partial class MainWindow : Window
         GameView.IsVisible = false;
         GameView.IsHitTestVisible = true;
         SessionBarPopup.IsOpen = false;
-        HideSessionLoading();
+        SessionLoadingPopup.IsOpen = false;
         AnimateLibraryBlur(0, clearWhenComplete: true);
         MainContent.Margin = new Thickness(32, 24, 32, 20);
         ContentToolbar.IsVisible = true;
@@ -2222,14 +2193,7 @@ public partial class MainWindow : Window
     {
         SessionLoadingTitle.Text = title;
         SessionLoadingDetail.Text = detail;
-        _sessionLoadingActive = true;
-        SessionLoadingPopup.IsOpen = IsActive && WindowState != WindowState.Minimized;
-    }
-
-    private void HideSessionLoading()
-    {
-        _sessionLoadingActive = false;
-        SessionLoadingPopup.IsOpen = false;
+        SessionLoadingPopup.IsOpen = true;
     }
 
     private void ReturnToLibraryWhileStopping()

src/SharpEmu.HLE/GuestImageWriteTracker.cs

@@ -51,33 +51,9 @@ public static unsafe class GuestImageWriteTracker
     private static readonly object _gate = new();
     private static readonly Dictionary<ulong, TrackedRange> _rangesByAddress = new();
 
-    /// <summary>Immutable snapshot read lock-free from the signal handler and
-    /// the managed-write pre-visit; rebuilt on every mutation under the gate
-    /// (signal handlers must not take managed locks). Carrying the overall
-    /// bounds inside the same object keeps the hot-path intersection test
-    /// consistent with the array it guards.</summary>
-    private sealed class RangeSnapshot
-    {
-        public static readonly RangeSnapshot Empty = new([]);
-
-        public readonly TrackedRange[] Ranges;
-        public readonly ulong Start;
-        public readonly ulong End;
-
-        public RangeSnapshot(TrackedRange[] ranges)
-        {
-            Ranges = ranges;
-            Start = ulong.MaxValue;
-            End = 0;
-            foreach (var range in ranges)
-            {
-                Start = Math.Min(Start, range.Start);
-                End = Math.Max(End, range.End);
-            }
-        }
-    }
-
-    private static RangeSnapshot _rangeSnapshot = RangeSnapshot.Empty;
+    // Snapshot array read lock-free from the signal handler; rebuilt on every
+    // mutation under the gate. Signal handlers must not take managed locks.
+    private static TrackedRange[] _rangeSnapshot = [];
 
     private static readonly bool _enabled = !OperatingSystem.IsWindows() &&
         Environment.GetEnvironmentVariable("SHARPEMU_GUEST_IMAGE_CPU_SYNC") != "0";
@@ -290,17 +266,6 @@ public static unsafe class GuestImageWriteTracker
         var end = address > ulong.MaxValue - byteCount
             ? ulong.MaxValue
             : address + byteCount;
-
-        // Fast rejection for the hot path: this runs on every managed guest
-        // write, and almost none of them touch tracked texture pages. The
-        // bounds live inside the snapshot so they are always consistent with
-        // the ranges the per-page visit below would consult.
-        var snapshot = Volatile.Read(ref _rangeSnapshot);
-        if (snapshot.Ranges.Length == 0 || end <= snapshot.Start || address >= snapshot.End)
-        {
-            return;
-        }
-
         var candidate = address;
         while (candidate < end)
         {
@@ -346,7 +311,7 @@ public static unsafe class GuestImageWriteTracker
             return false;
         }
 
-        var ranges = Volatile.Read(ref _rangeSnapshot).Ranges;
+        var ranges = Volatile.Read(ref _rangeSnapshot);
         var writableStart = ulong.MaxValue;
         var writableEnd = 0UL;
         for (var index = 0; index < ranges.Length; index++)
@@ -493,7 +458,7 @@ public static unsafe class GuestImageWriteTracker
 
     private static void RebuildSnapshotLocked()
     {
-        Volatile.Write(ref _rangeSnapshot, new RangeSnapshot(_rangesByAddress.Values.ToArray()));
+        _rangeSnapshot = _rangesByAddress.Values.ToArray();
     }
 
     private static (ulong Start, ulong Length) PageAlign(ulong address, ulong byteCount)

src/SharpEmu.HLE/GuestThreadBlocking.cs

@@ -1,116 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-namespace SharpEmu.HLE;
-
-/// <summary>
-/// Support for HLE synchronization primitives that block the guest thread's
-/// host thread in place (inside the HLE call, on a host primitive) instead of
-/// capturing a continuation and re-scheduling through the cooperative wake-key
-/// machinery. In-place blocking makes block-and-wake atomic — the host
-/// primitive owns the race — which removes the lost-wakeup window the
-/// continuation path had between block registration and wake delivery.
-/// </summary>
-public static class GuestThreadBlocking
-{
-    /// <summary>
-    /// Upper bound on a single host wait while a guest thread is parked. Waits
-    /// are sliced so parked threads observe <see cref="ShutdownRequested"/>
-    /// promptly at teardown; a wake via Monitor.Pulse still lands immediately.
-    /// </summary>
-    public const int WaitSliceMilliseconds = 50;
-
-    private static volatile bool _shutdownRequested;
-
-    // Guest thread handle -> what it is parked on. Populated only while a
-    // thread is blocked (the slow path), read by the stall watchdog so
-    // in-place-blocked threads are not reported as opaque "Running" threads.
-    private static readonly System.Collections.Concurrent.ConcurrentDictionary<ulong, string> _blockDescriptions = new();
-
-    /// <summary>True once emulator teardown has begun; parked guest threads unwind.</summary>
-    public static bool ShutdownRequested => _shutdownRequested;
-
-    /// <summary>Called by the execution backend when guest execution is being torn down.</summary>
-    public static void RequestShutdown() => _shutdownRequested = true;
-
-    /// <summary>Records what the given guest thread is about to park on (diagnostics only).</summary>
-    public static void NoteBlocked(ulong guestThreadHandle, string description)
-    {
-        if (guestThreadHandle != 0)
-        {
-            _blockDescriptions[guestThreadHandle] = description;
-        }
-    }
-
-    /// <summary>Clears the parked-state note recorded by <see cref="NoteBlocked"/>.</summary>
-    public static void NoteUnblocked(ulong guestThreadHandle)
-    {
-        if (guestThreadHandle != 0)
-        {
-            _blockDescriptions.TryRemove(guestThreadHandle, out _);
-        }
-    }
-
-    /// <summary>What the thread is parked on, or null if it is not parked in place.</summary>
-    public static string? DescribeBlock(ulong guestThreadHandle) =>
-        _blockDescriptions.TryGetValue(guestThreadHandle, out var description) ? description : null;
-
-    /// <summary>All currently parked threads (diagnostics; covers the primary thread too).</summary>
-    public static KeyValuePair<ulong, string>[] SnapshotBlockDescriptions() => _blockDescriptions.ToArray();
-
-    // Interrupt delivery for threads parked in place. A thread blocked inside
-    // an HLE wait keeps its executor busy, so it never reaches the import-return
-    // safe point where queued guest exceptions (IL2CPP stop-the-world suspend)
-    // are delivered. When an exception is queued for such a thread, its handle
-    // is flagged here; each sliced wait loop calls Checkpoint, which — on the
-    // thread's OWN host thread, with the wait's gate released — runs the
-    // registered deliverer (the same safe-point delivery used at import
-    // boundaries), then the loop re-checks its predicate and re-parks. This is
-    // the SA_RESTART-style "signal on top of a blocking wait" a real kernel
-    // provides. Dormant unless an exception is actually pending (empty-check
-    // fast path), so it adds no cost to normal blocking.
-    private static readonly System.Collections.Concurrent.ConcurrentDictionary<ulong, byte> _interrupted = new();
-
-    /// <summary>Set by the backend: delivers any exception queued for the current guest thread, in place.</summary>
-    public static Action? DeliverInterruptForCurrentThread { get; set; }
-
-    /// <summary>Flags a parked guest thread to deliver a queued exception at its next wait checkpoint.</summary>
-    public static void RequestInterrupt(ulong guestThreadHandle)
-    {
-        if (guestThreadHandle != 0)
-        {
-            _interrupted[guestThreadHandle] = 0;
-        }
-    }
-
-    /// <summary>
-    /// Called from every sliced wait loop while it holds <paramref name="gate"/>. If an
-    /// exception is pending for the current guest thread, releases the gate, delivers it on
-    /// this host thread, then re-acquires the gate so the loop re-checks its predicate.
-    /// </summary>
-    public static void Checkpoint(ulong guestThreadHandle, object gate)
-    {
-        if (_interrupted.IsEmpty || guestThreadHandle == 0 || !_interrupted.TryRemove(guestThreadHandle, out _))
-        {
-            return;
-        }
-
-        var deliver = DeliverInterruptForCurrentThread;
-        if (deliver is null)
-        {
-            return;
-        }
-
-        // Never run guest code (the handler) while holding an HLE gate — the
-        // handler may re-enter this same primitive. Release across delivery.
-        Monitor.Exit(gate);
-        try
-        {
-            deliver();
-        }
-        finally
-        {
-            Monitor.Enter(gate);
-        }
-    }
-}

src/SharpEmu.HLE/GuestThreadExecution.cs

@@ -30,6 +30,13 @@ public readonly record struct GuestThreadSnapshot(
 /// false leaves it parked. Resume runs later on the woken thread outside that gate, and
 /// its return value becomes the guest's RAX for the resumed call.
 /// </summary>
+public interface IGuestThreadBlockWaiter
+{
+    int Resume();
+
+    bool TryWake();
+}
+
 public interface IGuestThreadScheduler
 {
     bool SupportsGuestContextTransfer { get; }
@@ -50,6 +57,10 @@ public interface IGuestThreadScheduler
         out ulong returnValue,
         out string? error);
 
+    void Pump(CpuContext callerContext, string reason);
+
+    int WakeBlockedThreads(string wakeKey, int maxCount = int.MaxValue);
+
     /// <summary>
     /// Applies a new guest scheduling priority to a live thread, mapping it
     /// onto the host thread if one is running. Returns false when the thread
@@ -141,12 +152,46 @@ public readonly record struct GuestCpuContinuation(
 
 public static class GuestThreadExecution
 {
+    private sealed class DelegateGuestThreadBlockWaiter : IGuestThreadBlockWaiter
+    {
+        private readonly Func<int> _resume;
+        private readonly Func<bool> _tryWake;
+
+        public DelegateGuestThreadBlockWaiter(Func<int> resume, Func<bool> tryWake)
+        {
+            _resume = resume;
+            _tryWake = tryWake;
+        }
+
+        public int Resume() => _resume();
+
+        public bool TryWake() => _tryWake();
+    }
+
     [ThreadStatic]
     private static ulong _currentGuestThreadHandle;
 
     [ThreadStatic]
     private static ulong _currentFiberAddress;
 
+    [ThreadStatic]
+    private static string? _pendingBlockReason;
+
+    [ThreadStatic]
+    private static bool _pendingBlockContinuationValid;
+
+    [ThreadStatic]
+    private static GuestCpuContinuation _pendingBlockContinuation;
+
+    [ThreadStatic]
+    private static string? _pendingBlockWakeKey;
+
+    [ThreadStatic]
+    private static IGuestThreadBlockWaiter? _pendingBlockWaiter;
+
+    [ThreadStatic]
+    private static long _pendingBlockDeadlineTimestamp;
+
     [ThreadStatic]
     private static bool _pendingEntryExit;
 
@@ -186,6 +231,12 @@ public static class GuestThreadExecution
     {
         var previous = _currentGuestThreadHandle;
         _currentGuestThreadHandle = threadHandle;
+        _pendingBlockReason = null;
+        _pendingBlockContinuationValid = false;
+        _pendingBlockContinuation = default;
+        _pendingBlockWakeKey = null;
+        _pendingBlockWaiter = null;
+        _pendingBlockDeadlineTimestamp = 0;
         _pendingEntryExit = false;
         _pendingEntryExitValue = 0;
         _pendingEntryExitReason = null;
@@ -201,6 +252,12 @@ public static class GuestThreadExecution
     public static void RestoreGuestThread(ulong previousThreadHandle)
     {
         _currentGuestThreadHandle = previousThreadHandle;
+        _pendingBlockReason = null;
+        _pendingBlockContinuationValid = false;
+        _pendingBlockContinuation = default;
+        _pendingBlockWakeKey = null;
+        _pendingBlockWaiter = null;
+        _pendingBlockDeadlineTimestamp = 0;
         _pendingEntryExit = false;
         _pendingEntryExitValue = 0;
         _pendingEntryExitReason = null;
@@ -224,6 +281,123 @@ public static class GuestThreadExecution
         _currentFiberAddress = previousFiberAddress;
     }
 
+    public static bool RequestCurrentThreadBlock(string reason) => RequestCurrentThreadBlock(null, reason);
+
+    public static bool RequestCurrentThreadBlock(
+        CpuContext? context,
+        string reason,
+        string? wakeKey = null,
+        IGuestThreadBlockWaiter? waiter = null,
+        long blockDeadlineTimestamp = 0)
+    {
+        if (!IsGuestThread)
+        {
+            return false;
+        }
+
+        _pendingBlockReason = string.IsNullOrWhiteSpace(reason) ? "guest_thread_blocked" : reason;
+        _pendingBlockWakeKey = string.IsNullOrWhiteSpace(wakeKey) ? _pendingBlockReason : wakeKey;
+        _pendingBlockWaiter = waiter;
+        _pendingBlockDeadlineTimestamp = blockDeadlineTimestamp;
+        if (context is not null && TryCaptureCurrentBlockContinuation(context, out var continuation))
+        {
+            _pendingBlockContinuation = continuation;
+            _pendingBlockContinuationValid = true;
+        }
+        else
+        {
+            _pendingBlockContinuation = default;
+            _pendingBlockContinuationValid = false;
+        }
+
+        return true;
+    }
+
+    // Compatibility bridge for exports that still describe blocked work as a
+    // resume/wake delegate pair. New hot paths should provide an
+    // IGuestThreadBlockWaiter directly to avoid allocating closures.
+    public static bool RequestCurrentThreadBlock(
+        CpuContext? context,
+        string reason,
+        string? wakeKey,
+        Func<int> resumeHandler,
+        Func<bool> wakeHandler,
+        long blockDeadlineTimestamp = 0) =>
+        RequestCurrentThreadBlock(
+            context,
+            reason,
+            wakeKey,
+            new DelegateGuestThreadBlockWaiter(resumeHandler, wakeHandler),
+            blockDeadlineTimestamp);
+
+    public static bool TryConsumeCurrentThreadBlock(out string reason)
+    {
+        return TryConsumeCurrentThreadBlock(out reason, out _, out _);
+    }
+
+    public static bool TryConsumeCurrentThreadBlock(
+        out string reason,
+        out GuestCpuContinuation continuation,
+        out bool hasContinuation)
+    {
+        return TryConsumeCurrentThreadBlock(
+            out reason,
+            out continuation,
+            out hasContinuation,
+            out _,
+            out _,
+            out _);
+    }
+
+    public static bool TryConsumeCurrentThreadBlock(
+        out string reason,
+        out GuestCpuContinuation continuation,
+        out bool hasContinuation,
+        out string wakeKey,
+        out IGuestThreadBlockWaiter? waiter)
+    {
+        return TryConsumeCurrentThreadBlock(
+            out reason,
+            out continuation,
+            out hasContinuation,
+            out wakeKey,
+            out waiter,
+            out _);
+    }
+
+    public static bool TryConsumeCurrentThreadBlock(
+        out string reason,
+        out GuestCpuContinuation continuation,
+        out bool hasContinuation,
+        out string wakeKey,
+        out IGuestThreadBlockWaiter? waiter,
+        out long blockDeadlineTimestamp)
+    {
+        reason = _pendingBlockReason ?? string.Empty;
+        if (string.IsNullOrEmpty(reason))
+        {
+            continuation = default;
+            hasContinuation = false;
+            wakeKey = string.Empty;
+            waiter = null;
+            blockDeadlineTimestamp = 0;
+            return false;
+        }
+
+        continuation = _pendingBlockContinuation;
+        hasContinuation = _pendingBlockContinuationValid;
+        wakeKey = _pendingBlockWakeKey ?? reason;
+        waiter = _pendingBlockWaiter;
+        blockDeadlineTimestamp = _pendingBlockDeadlineTimestamp;
+        _pendingBlockReason = null;
+        _pendingBlockContinuation = default;
+        _pendingBlockContinuationValid = false;
+        _pendingBlockWakeKey = null;
+        _pendingBlockWaiter = null;
+        _pendingBlockDeadlineTimestamp = 0;
+        return true;
+    }
+
     public static long ComputeDeadlineTimestamp(TimeSpan timeout)
     {
         if (timeout <= TimeSpan.Zero)
@@ -243,6 +417,45 @@ public static class GuestThreadExecution
         return now + Math.Max(1, ticks);
     }
 
+    private static bool TryCaptureCurrentBlockContinuation(CpuContext context, out GuestCpuContinuation continuation)
+    {
+        if (!TryGetCurrentImportCallFrame(out var frame) ||
+            frame.ReturnRip < 65536 ||
+            frame.ResumeRsp == 0 ||
+            frame.ReturnSlotAddress == 0)
+        {
+            continuation = default;
+            return false;
+        }
+
+        continuation = new GuestCpuContinuation(
+            frame.ReturnRip,
+            frame.ResumeRsp,
+            frame.ReturnSlotAddress,
+            context.Rflags,
+            context.FsBase,
+            context.GsBase,
+            0,
+            context[CpuRegister.Rcx],
+            context[CpuRegister.Rdx],
+            context[CpuRegister.Rbx],
+            context[CpuRegister.Rbp],
+            context[CpuRegister.Rsi],
+            context[CpuRegister.Rdi],
+            context[CpuRegister.R8],
+            context[CpuRegister.R9],
+            context[CpuRegister.R10],
+            context[CpuRegister.R11],
+            context[CpuRegister.R12],
+            context[CpuRegister.R13],
+            context[CpuRegister.R14],
+            context[CpuRegister.R15],
+            context.FpuControlWord,
+            context.Mxcsr,
+            RestoreFullFpuState: false);
+        return true;
+    }
+
     public static void RequestCurrentEntryExit(string reason, int status)
     {
         RequestCurrentEntryExit(reason, unchecked((ulong)(long)status));

src/SharpEmu.Libs/Agc/AgcExports.cs

@@ -14,12 +14,6 @@ namespace SharpEmu.Libs.Agc;
 
 public static partial class AgcExports
 {
-    // The backend is a process-fixed singleton, so its offset-alignment
-    // requirement is snapshot once: several per-draw paths (shader-key
-    // hashing, buffer-offset alignment) read it in loops.
-    private static readonly ulong _storageBufferOffsetAlignment =
-        GuestGpu.Current.GuestStorageBufferOffsetAlignment;
-
 #if DEBUG
     static AgcExports()
     {
@@ -568,8 +562,6 @@ public static partial class AgcExports
         public ulong WorkSequence { get; set; }
         public ulong SubmissionSequence { get; set; }
         public bool WaitMonitorRunning { get; set; }
-        public object WaitMonitorSignalGate { get; } = new();
-        public long WaitMonitorSignalVersion { get; set; }
     }
 
     private readonly record struct RegisteredAgcResource(
@@ -1775,58 +1767,6 @@ public static partial class AgcExports
         return ReturnPointer(ctx, commandAddress);
     }
 
-    // Single-register variant of the SET_SH_REG builders: the register rides
-    // in rsi as a packed struct (low 16 bits = register offset, high dword =
-    // byte offset of this dword within a multi-dword register write) and the
-    // value in edx. Emits the same 3-dword SET_SH_REG packet the plural
-    // sceAgcCbSetShRegistersDirect path produces per run. Hades calls this
-    // ~1k times per boot; leaving it unresolved corrupted its DCB stream.
-    [SysAbiExport(
-        Nid = "pFLArOT53+w",
-        ExportName = "sceAgcDcbSetShRegisterDirect",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAgc")]
-    public static int DcbSetShRegisterDirect(CpuContext ctx)
-    {
-        var commandBufferAddress = ctx[CpuRegister.Rdi];
-        var packedRegister = ctx[CpuRegister.Rsi];
-        var value = (uint)ctx[CpuRegister.Rdx];
-        if (commandBufferAddress == 0)
-        {
-            return ReturnPointer(ctx, 0);
-        }
-
-        var offset = (uint)(packedRegister & 0xFFFFu) + (uint)((packedRegister >> 32) >> 2);
-        if (!TryAllocateCommandDwords(ctx, commandBufferAddress, 3, out var commandAddress) ||
-            !TryWriteUInt32(ctx, commandAddress, Pm4(3, ItSetShReg, 0)) ||
-            !TryWriteUInt32(ctx, commandAddress + 4, offset & 0xFFFFu) ||
-            !TryWriteUInt32(ctx, commandAddress + 8, value))
-        {
-            return ReturnPointer(ctx, 0);
-        }
-
-        TraceAgc($"agc.dcb_set_sh_register_direct buf=0x{commandBufferAddress:X16} reg=0x{offset:X4} value=0x{value:X8}");
-        return ReturnPointer(ctx, commandAddress);
-    }
-
-    // Size probe for the wait-on-address writer below: same argument prefix
-    // minus the command buffer, returns the byte size the writer will emit so
-    // the game can reserve DCB space (7 dwords for a standard WAIT_REG_MEM,
-    // 6/9 for the 32/64-bit polled-NOP forms).
-    [SysAbiExport(
-        Nid = "43WJ08sSugE",
-        ExportName = "sceAgcDcbWaitOnAddressGetSize",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAgc")]
-    public static int DcbWaitOnAddressGetSize(CpuContext ctx)
-    {
-        var size = (uint)(ctx[CpuRegister.Rdi] & 0xFF);
-        var operation = (uint)(ctx[CpuRegister.Rdx] & 0xFF);
-        var packetDwords = operation is 2 or 3 ? 7u : size == 0 ? 6u : 9u;
-        ctx[CpuRegister.Rax] = packetDwords * sizeof(uint);
-        return (int)ctx[CpuRegister.Rax];
-    }
-
     [SysAbiExport(
         Nid = "VmW0Tdpy420",
         ExportName = "sceAgcDcbWaitRegMem",
@@ -2676,32 +2616,6 @@ public static partial class AgcExports
         return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
-    // Hands the game the driver-side context id its GPU event-queue packets
-    // reference. We key events purely on (equeue, ident, filter), so a single
-    // stable id satisfies the contract; the game only checks the call
-    // succeeded and threads the id back through later driver calls.
-    [SysAbiExport(
-        Nid = "Zw7uUVPulbw",
-        ExportName = "sceAgcDriverGetEqContextId",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAgcDriver")]
-    public static int DriverGetEqContextId(CpuContext ctx)
-    {
-        var contextIdAddress = ctx[CpuRegister.Rdi];
-        if (contextIdAddress == 0)
-        {
-            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        if (!TryWriteUInt32(ctx, contextIdAddress, 1))
-        {
-            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-        }
-
-        TraceAgc($"agc.driver_get_eq_context_id out=0x{contextIdAddress:X16} -> 1");
-        return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
-    }
-
     [SysAbiExport(
         Nid = "DL2RXaXOy88",
         ExportName = "sceAgcDriverDeleteEqEvent",
@@ -2752,7 +2666,7 @@ public static partial class AgcExports
             TraceAgc($"agc.driver_submit_dcb packet=0x{packetAddress:X16} addr=0x{commandAddress:X16} dwords={dwordCount}");
         }
 
-        GuestGpu.Current.AttachGuestMemory(ctx.Memory);
+        VulkanVideoPresenter.AttachGuestMemory(ctx.Memory);
         var gpuState = _submittedGpuStates.GetValue(ctx.Memory, static _ => new SubmittedGpuState());
         lock (gpuState.Gate)
         {
@@ -2804,7 +2718,7 @@ public static partial class AgcExports
                 $"addr=0x{commandAddress:X16} dwords={dwordCount}");
         }
 
-        GuestGpu.Current.AttachGuestMemory(ctx.Memory);
+        VulkanVideoPresenter.AttachGuestMemory(ctx.Memory);
         var gpuState = _submittedGpuStates.GetValue(ctx.Memory, static _ => new SubmittedGpuState());
         lock (gpuState.Gate)
         {
@@ -3032,7 +2946,7 @@ public static partial class AgcExports
         // guest-memory writes have finished. Put the notification on that same
         // logical graphics queue instead of approximating completion with a
         // timer, which can wake Unity while its upload data is still stale.
-        if (GuestGpu.Current.SubmitOrderedGuestAction(
+        if (VulkanVideoPresenter.SubmitOrderedGuestAction(
                 TriggerCompletionEvents,
                 $"agc submit completion {submissionId}") == 0)
         {
@@ -3056,11 +2970,11 @@ public static partial class AgcExports
             return false;
         }
 
-        using var guestQueueScope = GuestGpu.Current.EnterGuestQueue(
+        using var guestQueueScope = VulkanVideoPresenter.EnterGuestQueue(
             state.QueueName,
             state.ActiveSubmissionId);
         var windowByteCount = checked((int)(dwordCount * sizeof(uint)));
-        var rented = GuestDataPool.Shared.Rent(windowByteCount);
+        var rented = VulkanVideoPresenter.GuestDataPool.Rent(windowByteCount);
         try
         {
             if (ctx.Memory.TryRead(commandAddress, rented.AsSpan(0, windowByteCount)))
@@ -3082,7 +2996,7 @@ public static partial class AgcExports
         {
             _dcbWindowBuffer = null;
             _dcbWindowByteLength = 0;
-            GuestDataPool.Shared.Return(rented);
+            VulkanVideoPresenter.GuestDataPool.Return(rented);
         }
     }
 
@@ -3384,20 +3298,17 @@ public static partial class AgcExports
                     indexed: false);
             }
 
-            if (op is ItDispatchDirect or ItDispatchIndirect)
+            if ((op is ItDispatchDirect or ItDispatchIndirect) &&
+                TryReadComputeDispatch(
+                    ctx,
+                    state,
+                    currentAddress,
+                    length,
+                    op,
+                out var dispatch))
             {
-                if (TryReadComputeDispatch(
-                        ctx,
-                        state,
-                        currentAddress,
-                        length,
-                        op,
-                        out var dispatch,
-                        out _))
-                {
-                    state.FrameDispatchCount++;
-                    ObserveComputeDispatch(ctx, gpuState, state, dispatch);
-                }
+                state.FrameDispatchCount++;
+                ObserveComputeDispatch(ctx, gpuState, state, dispatch);
             }
 
             if (op == ItNop &&
@@ -3406,7 +3317,7 @@ public static partial class AgcExports
                 TryReadUInt32(ctx, currentAddress + 4, out var waitVideoOutHandle) &&
                 TryReadUInt32(ctx, currentAddress + 8, out var waitDisplayBufferIndex))
             {
-                var waitSequence = GuestGpu.Current.SubmitOrderedGuestFlipWait(
+                var waitSequence = VulkanVideoPresenter.SubmitOrderedGuestFlipWait(
                     unchecked((int)waitVideoOutHandle),
                     unchecked((int)waitDisplayBufferIndex));
                 TraceAgcShader(
@@ -3735,11 +3646,27 @@ public static partial class AgcExports
         void CompleteAndWake()
         {
             CompleteLabelProducer(producer);
-            lock (gpuState.WaitMonitorSignalGate)
+            if (GpuWaitRegistry.Count == 0)
             {
-                gpuState.WaitMonitorSignalVersion++;
-                Monitor.Pulse(gpuState.WaitMonitorSignalGate);
+                return;
             }
+
+            // Resuming a DCB can enqueue another compute dispatch and wait for
+            // it. Never do that reentrantly on the Vulkan render thread.
+            ThreadPool.UnsafeQueueUserWorkItem(
+                static state =>
+                {
+                    var (resumeContext, resumeGpuState) = state;
+                    lock (resumeGpuState.Gate)
+                    {
+                        DrainResumableDcbs(
+                            resumeContext,
+                            resumeGpuState,
+                            tracePackets: _traceAgc);
+                    }
+                },
+                (ctx, gpuState),
+                preferLocal: false);
         }
 
         void ApplyAndQueueCompletion()
@@ -3750,7 +3677,7 @@ public static partial class AgcExports
             // wake another queue before that mirror is visible. Queue a
             // second same-queue ordered action after all immediate follow-up
             // writes; it fences those writes before publishing the producer.
-            if (GuestGpu.Current.SubmitOrderedGuestAction(
+            if (VulkanVideoPresenter.SubmitOrderedGuestAction(
                     CompleteAndWake,
                     $"{debugName} completion") == 0)
             {
@@ -3758,7 +3685,7 @@ public static partial class AgcExports
             }
         }
 
-        if (GuestGpu.Current.SubmitOrderedGuestAction(
+        if (VulkanVideoPresenter.SubmitOrderedGuestAction(
                 ApplyAndQueueCompletion,
                 debugName) == 0)
         {
@@ -3968,11 +3895,11 @@ public static partial class AgcExports
                 TraceAgc(
                     $"agc.acquire_mem_applied queue={queueName} " +
                     $"submission={submissionId} packet=0x{packetAddress:X16} " +
-                    $"work_sequence={GuestGpu.Current.CurrentGuestWorkSequenceForDiagnostics}");
+                    $"work_sequence={VulkanVideoPresenter.CurrentGuestWorkSequenceForDiagnostics}");
             }
         }
 
-        var sequence = GuestGpu.Current.SubmitOrderedGuestAction(
+        var sequence = VulkanVideoPresenter.SubmitOrderedGuestAction(
             ApplyAcquire,
             debugName);
         if (sequence == 0)
@@ -4118,7 +4045,7 @@ public static partial class AgcExports
             return;
         }
 
-        foreach (var (address, width, height, byteCount) in GuestGpu.Current.GetGuestImageExtents())
+        foreach (var (address, width, height, byteCount) in VulkanVideoPresenter.GetGuestImageExtents())
         {
             if (scopeByteCount != ulong.MaxValue &&
                 !RangesOverlap(address, byteCount, scopeAddress, scopeByteCount))
@@ -4139,7 +4066,7 @@ public static partial class AgcExports
             var pixels = new byte[byteCount];
             if (ctx.Memory.TryRead(address, pixels))
             {
-                GuestGpu.Current.SubmitGuestImageWrite(address, pixels);
+                VulkanVideoPresenter.SubmitGuestImageWrite(address, pixels);
                 if (Interlocked.Increment(ref _guestImageSyncTraceCount) <= 64)
                 {
                     Console.Error.WriteLine(
@@ -4182,7 +4109,7 @@ public static partial class AgcExports
         ulong byteCount,
         uint? fillValue)
     {
-        var hasImage = GuestGpu.Current.TryGetGuestImageExtent(
+        var hasImage = VulkanVideoPresenter.TryGetGuestImageExtent(
             destinationAddress,
             out var width,
             out var height,
@@ -4206,14 +4133,14 @@ public static partial class AgcExports
 
         if (fillValue is { } fill)
         {
-            GuestGpu.Current.SubmitGuestImageFill(destinationAddress, fill);
+            VulkanVideoPresenter.SubmitGuestImageFill(destinationAddress, fill);
             return;
         }
 
         var pixels = new byte[imageBytes];
         if (ctx.Memory.TryRead(destinationAddress, pixels))
         {
-            GuestGpu.Current.SubmitGuestImageWrite(destinationAddress, pixels);
+            VulkanVideoPresenter.SubmitGuestImageWrite(destinationAddress, pixels);
         }
     }
 
@@ -4601,17 +4528,6 @@ public static partial class AgcExports
             ? fallbackMs
             : 0L) * System.Diagnostics.Stopwatch.Frequency / 1000L;
 
-    // How long a suspended GPU wait may sit before the deadlock breaker may
-    // release it using the last value a real producer wrote to its label. Long
-    // enough that legitimate GPU work (which completes within a frame) never
-    // trips it; short enough that a wedged cross-queue cycle unblocks quickly.
-    private static readonly long _gpuDeadlockBreakTicks =
-        (long.TryParse(
-             Environment.GetEnvironmentVariable("SHARPEMU_GPU_DEADLOCK_BREAK_MS"),
-             out var deadlockMs) && deadlockMs > 0
-            ? deadlockMs
-            : 500L) * System.Diagnostics.Stopwatch.Frequency / 1000L;
-
     // Reads the WAIT_REG_MEM watched address, reference, mask, and 3-bit compare
     // function for both the AGC NOP-encapsulated (RWaitMem32/64) and the standard
     // ItWaitRegMem packet layouts.
@@ -4676,85 +4592,6 @@ public static partial class AgcExports
     // Returns true when the DCB should suspend parsing at this wait (its
     // continuation was registered into GpuWaitRegistry); false to keep parsing
     // (already satisfied, unreadable, or legacy force-satisfy mode).
-    // How long an indirect dispatch may wait for its producing dispatch to write
-    // non-zero dimensions before we give up and drop it (matching the pre-existing
-    // reject behavior). The producer runs on the render thread within a frame or
-    // two; this only bounds the pathological/legitimately-empty case.
-    private const long IndirectDimsRetryBudgetMs = 150;
-
-    private static readonly object _indirectDimsGate = new();
-    // Keys (memory, packetAddress) whose retry deadline elapsed. Added by
-    // DrainResumableDcbs when it resumes an expired retry, consumed by the very
-    // next re-parse of that packet so it drops instead of re-suspending. Never
-    // persists across frames — a fresh submit of the same packet retries anew.
-    private static readonly HashSet<(object, ulong)> _indirectDimsExpired = new();
-
-    // Suspends an indirect-dispatch DCB until the guest buffer holding its
-    // thread-group dimensions becomes non-zero (written by a prior GPU dispatch),
-    // then re-parses the dispatch. Returns false — so the caller drops the work —
-    // when the dims already expired once (genuinely empty dispatch).
-    private static bool HandleSubmittedIndirectDimsWait(
-        CpuContext ctx,
-        SubmittedDcbState state,
-        ulong commandAddress,
-        ulong packetAddress,
-        uint offset,
-        uint dwordCount,
-        ulong dimsAddress,
-        bool tracePacket)
-    {
-        if (!_gpuWaitSuspendEnabled ||
-            dimsAddress == 0 ||
-            dimsAddress % sizeof(uint) != 0)
-        {
-            return false;
-        }
-
-        var key = (ctx.Memory, packetAddress);
-        lock (_indirectDimsGate)
-        {
-            // This is the re-parse right after the deadline elapsed: drop the
-            // dispatch instead of suspending again.
-            if (_indirectDimsExpired.Remove(key))
-            {
-                return false;
-            }
-        }
-
-        var waiter = new GpuWaitRegistry.WaitingDcb
-        {
-            CommandBufferAddress = commandAddress,
-            ResumeAddress = packetAddress, // re-parse this dispatch packet
-            ResumeOffset = offset,
-            TotalDwords = dwordCount,
-            WaitAddress = dimsAddress,
-            ReferenceValue = 0,
-            Mask = 0xFFFFFFFF,
-            CompareFunction = 4, // NOT_EQUAL: dims became available
-            Is64Bit = false,
-            IsStandard = false,
-            Memory = ctx.Memory,
-            QueueName = state.QueueName,
-            SubmissionId = state.ActiveSubmissionId,
-            RegisteredTicks = System.Diagnostics.Stopwatch.GetTimestamp(),
-            RetryDeadlineTicks = System.Diagnostics.Stopwatch.GetTimestamp() +
-                (IndirectDimsRetryBudgetMs * System.Diagnostics.Stopwatch.Frequency / 1000L),
-            State = state,
-        };
-
-        GpuWaitRegistry.Register(dimsAddress, waiter);
-        var gpuState = _submittedGpuStates.GetValue(ctx.Memory, static _ => new SubmittedGpuState());
-        EnsureGpuWaitMonitor(ctx, gpuState);
-        if (tracePacket)
-        {
-            TraceAgc(
-                $"agc.dispatch_indirect_wait dims=0x{dimsAddress:X16} " +
-                $"packet=0x{packetAddress:X16} queue={state.QueueName}");
-        }
-
-        return true;
-    }
-
     private static bool HandleSubmittedWaitRegMem(
         CpuContext ctx,
         SubmittedDcbState state,
@@ -4918,45 +4755,38 @@ public static partial class AgcExports
         SubmittedGpuState gpuState)
     {
         var delayMilliseconds = 1;
-        long observedSignal;
-        lock (gpuState.WaitMonitorSignalGate)
-        {
-            observedSignal = gpuState.WaitMonitorSignalVersion;
-        }
-
         while (true)
         {
-            int resumed;
-            int remaining;
+            var madeProgress = false;
             lock (gpuState.Gate)
             {
-                resumed = DrainResumableDcbs(ctx, gpuState, tracePackets: _traceAgc);
-                remaining = GpuWaitRegistry.CountForMemory(ctx.Memory);
-                if (_traceAgc && resumed != 0)
+                var before = GpuWaitRegistry.CountForMemory(ctx.Memory);
+                if (before == 0)
+                {
+                    gpuState.WaitMonitorRunning = false;
+                    return;
+                }
+
+                DrainResumableDcbs(ctx, gpuState, tracePackets: _traceAgc);
+                var after = GpuWaitRegistry.CountForMemory(ctx.Memory);
+                madeProgress = after < before;
+                if (madeProgress)
                 {
                     Console.Error.WriteLine(
-                        $"[LOADER][TRACE] agc.wait_monitor_resumed count={resumed} " +
-                        $"remaining={remaining}");
+                        $"[LOADER][TRACE] agc.wait_monitor_resumed count={before - after} " +
+                        $"remaining={after}");
                 }
-                if (remaining == 0)
+                if (after == 0)
                 {
                     gpuState.WaitMonitorRunning = false;
                     return;
                 }
             }
 
-            delayMilliseconds = resumed != 0
+            delayMilliseconds = madeProgress
                 ? 1
                 : Math.Min(delayMilliseconds * 2, 16);
-            lock (gpuState.WaitMonitorSignalGate)
-            {
-                if (gpuState.WaitMonitorSignalVersion == observedSignal)
-                {
-                    Monitor.Wait(gpuState.WaitMonitorSignalGate, delayMilliseconds);
-                }
-
-                observedSignal = gpuState.WaitMonitorSignalVersion;
-            }
+            Thread.Sleep(delayMilliseconds);
         }
     }
 
@@ -5010,17 +4840,16 @@ public static partial class AgcExports
     // guest memory (labels are advanced by ReleaseMem/WriteData/DmaData packets
     // or direct CPU writes) and resumes the ones now satisfied. A resumed DCB
     // can itself write labels that unblock others, so loop to a fixed point.
-    private static int DrainResumableDcbs(
+    private static void DrainResumableDcbs(
         CpuContext ctx,
         SubmittedGpuState gpuState,
         bool tracePackets)
     {
         if (!_gpuWaitSuspendEnabled)
         {
-            return 0;
+            return;
         }
 
-        var resumedCount = 0;
         for (var pass = 0; pass < 256; pass++)
         {
             var woken = GpuWaitRegistry.CollectSatisfied(ctx.Memory, (address, is64Bit) =>
@@ -5028,50 +4857,7 @@ public static partial class AgcExports
                     ? TryReadUInt64(ctx, address, out var value64) ? value64 : (ulong?)null
                     : TryReadUInt32(ctx, address, out var value32) ? value32 : (ulong?)null);
 
-            // Indirect-dispatch dimension retries whose deadline elapsed are
-            // resumed so they drop instead of stalling. Flag each so its immediate
-            // re-parse drops the dispatch rather than suspending again.
-            var expiredRetries = GpuWaitRegistry.CollectExpiredRetries(
-                ctx.Memory, System.Diagnostics.Stopwatch.GetTimestamp());
-            if (expiredRetries is not null)
-            {
-                lock (_indirectDimsGate)
-                {
-                    foreach (var retry in expiredRetries)
-                    {
-                        _indirectDimsExpired.Add((ctx.Memory, retry.ResumeAddress));
-                    }
-                }
-
-                foreach (var retry in expiredRetries)
-                {
-                    ResumeSuspendedDcb(ctx, gpuState, retry, tracePackets);
-                }
-            }
-
-            // Break cross-queue deadlocks: a waiter stuck past the deadline whose
-            // label a real producer already signalled (but guest memory has since
-            // been reset for reuse) is released using that produced value. Only
-            // fires for genuinely wedged waits, so fast-resolving ones on working
-            // titles are untouched.
-            var deadlockBroken = GpuWaitRegistry.CollectDeadlockBroken(
-                ctx.Memory, System.Diagnostics.Stopwatch.GetTimestamp(), _gpuDeadlockBreakTicks);
-            if (deadlockBroken is not null)
-            {
-                foreach (var waiter in deadlockBroken)
-                {
-                    if (tracePackets)
-                    {
-                        TraceAgc(
-                            $"agc.deadlock_break label=0x{waiter.WaitAddress:X16} " +
-                            $"queue={waiter.QueueName} submission={waiter.SubmissionId}");
-                    }
-
-                    ResumeSuspendedDcb(ctx, gpuState, waiter, tracePackets);
-                }
-            }
-
-            if (woken is null && expiredRetries is null && deadlockBroken is null)
+            if (woken is null)
             {
                 if (_gpuWaitStaleTicks > 0 &&
                     GpuWaitRegistry.CollectUnreportedStale(
@@ -5098,20 +4884,14 @@ public static partial class AgcExports
                     }
                 }
 
-                return resumedCount;
+                return;
             }
 
-            if (woken is not null)
+            foreach (var waiter in woken)
             {
-                foreach (var waiter in woken)
-                {
-                    ResumeSuspendedDcb(ctx, gpuState, waiter, tracePackets);
-                    resumedCount++;
-                }
+                ResumeSuspendedDcb(ctx, gpuState, waiter, tracePackets);
             }
         }
-
-        return resumedCount;
     }
 
     private static void ResumeSuspendedDcb(
@@ -5253,15 +5033,6 @@ public static partial class AgcExports
                     _ => false,
                 });
 
-                // Record + latch the written value so a same-frame label reset
-                // cannot lose the wakeup, and so the deadlock breaker can release
-                // a cross-queue waiter later (see ApplySubmittedReleaseMem).
-                if (wroteData && dataSelection is 1 or 2)
-                {
-                    GpuWaitRegistry.RecordProduced(
-                        ctx.Memory, destinationAddress, dataSelection == 1 ? dataLo : data);
-                }
-
                 if (tracePacket)
                 {
                     TraceAgc(
@@ -5327,16 +5098,6 @@ public static partial class AgcExports
                     _ => false,
                 };
 
-                // Latch waiters against the value we just wrote: the guest reuses
-                // these labels and can reset them to 0 before the wake pass reads
-                // memory, which otherwise loses the wakeup and stalls at a black
-                // screen (Astro Bot: graphics queue waiting on a compute EOP label).
-                if (wroteData && dataSelection is 1 or 2)
-                {
-                    GpuWaitRegistry.RecordProduced(
-                        ctx.Memory, destinationAddress, dataSelection == 1 ? dataLo : data);
-                }
-
                 if (tracePacket)
                 {
                     TraceAgc(
@@ -5637,7 +5398,7 @@ public static partial class AgcExports
                 state.KnownRenderTargets[resolveSource.Address] = resolveSource;
                 state.KnownRenderTargets[resolveDestination.Address] = resolveDestination;
                 ProvideRenderTargetInitialData(ctx, resolveSource);
-                if (GuestGpu.Current.TrySubmitGuestImageBlit(
+                if (VulkanVideoPresenter.TrySubmitGuestImageBlit(
                         resolveSource.Address,
                         resolveSource.Width,
                         resolveSource.Height,
@@ -5948,7 +5709,7 @@ public static partial class AgcExports
         var cacheKey = (
             exportShaderAddress,
             exportFingerprint,
-            _storageBufferOffsetAlignment);
+            VulkanVideoPresenter.GuestStorageBufferOffsetAlignment);
         _depthOnlyVertexShaderCache.TryGetValue(cacheKey, out var vertexShader);
 
         if (vertexShader is null)
@@ -5973,7 +5734,7 @@ public static partial class AgcExports
                         : guestGlobalBufferCount + 1,
                     requiredVertexOutputCount: 0,
                     storageBufferOffsetAlignment:
-                        _storageBufferOffsetAlignment))
+                        VulkanVideoPresenter.GuestStorageBufferOffsetAlignment))
             {
                 ReturnPooledEvaluationArrays(exportEvaluation);
                 return false;
@@ -5985,7 +5746,7 @@ public static partial class AgcExports
                 exportFingerprint,
                 vertexShader!,
                 exportState.Program);
-            GuestGpu.Current.CountShaderCompilation();
+            VulkanVideoPresenter.CountSpirvCompilation();
             _depthOnlyVertexShaderCache.TryAdd(cacheKey, vertexShader!);
         }
 
@@ -6271,7 +6032,7 @@ public static partial class AgcExports
             attributeCount,
             psInputEna,
             psInputAddr,
-            _storageBufferOffsetAlignment);
+            VulkanVideoPresenter.GuestStorageBufferOffsetAlignment);
 
         var guestGlobalBuffers =
             pixelEvaluation.GlobalMemoryBindings.Count +
@@ -6307,7 +6068,7 @@ public static partial class AgcExports
                     pixelInputEnable: psInputEna,
                     pixelInputAddress: psInputAddr,
                     storageBufferOffsetAlignment:
-                        _storageBufferOffsetAlignment) ||
+                        VulkanVideoPresenter.GuestStorageBufferOffsetAlignment) ||
                 !GuestGpu.Current.TryCompileVertexShader(
                     exportState,
                     exportEvaluation,
@@ -6319,7 +6080,7 @@ public static partial class AgcExports
                     scalarRegisterBufferIndex: _bakeScalars ? -1 : guestGlobalBuffers + 1,
                     requiredVertexOutputCount: (int)GetInterpolatedAttributeCount(pixelState),
                     storageBufferOffsetAlignment:
-                        _storageBufferOffsetAlignment))
+                        VulkanVideoPresenter.GuestStorageBufferOffsetAlignment))
             {
                 ReturnPooledEvaluationArrays(exportEvaluation);
                 ReturnPooledEvaluationArrays(pixelEvaluation);
@@ -6339,7 +6100,7 @@ public static partial class AgcExports
                 pixelStateFingerprint,
                 compiled.Pixel,
                 pixelState.Program);
-            GuestGpu.Current.CountShaderCompilation();
+            VulkanVideoPresenter.CountSpirvCompilation();
             _graphicsShaderCache.TryAdd(shaderKey, compiled);
         }
 
@@ -6617,7 +6378,7 @@ public static partial class AgcExports
         var bytesPerIndex = is32Bit ? sizeof(uint) : sizeof(ushort);
         var byteOffset = checked((ulong)state.DrawIndexOffset * (uint)bytesPerIndex);
         var byteCount = checked((int)(indexCount * (uint)bytesPerIndex));
-        var data = GuestDataPool.Shared.Rent(byteCount);
+        var data = VulkanVideoPresenter.GuestDataPool.Rent(byteCount);
         var span = data.AsSpan(0, byteCount);
         var address = state.IndexBufferAddress + byteOffset;
         if (ctx.Memory.TryRead(address, span) ||
@@ -6626,7 +6387,7 @@ public static partial class AgcExports
             return new GuestIndexBuffer(data, byteCount, is32Bit, Pooled: true);
         }
 
-        GuestDataPool.Shared.Return(data);
+        VulkanVideoPresenter.GuestDataPool.Return(data);
         return null;
     }
 
@@ -6653,7 +6414,7 @@ public static partial class AgcExports
         var byteOffset = checked((ulong)state.DrawIndexOffset * (uint)bytesPerIndex);
         var address = state.IndexBufferAddress + byteOffset;
         const int chunkBytes = 64 * 1024;
-        var scratch = GuestDataPool.Shared.Rent(chunkBytes);
+        var scratch = VulkanVideoPresenter.GuestDataPool.Rent(chunkBytes);
         var remaining = drawCount;
         var maxIndex = 0u;
         var sawIndex = false;
@@ -6695,7 +6456,7 @@ public static partial class AgcExports
         }
         finally
         {
-            GuestDataPool.Shared.Return(scratch);
+            VulkanVideoPresenter.GuestDataPool.Return(scratch);
         }
 
         var indexedRecords = sawIndex && maxIndex != uint.MaxValue
@@ -6819,7 +6580,7 @@ public static partial class AgcExports
         {
             hash = (hash ^ (
                 binding.BaseAddress &
-                (_storageBufferOffsetAlignment - 1))) * prime;
+                (VulkanVideoPresenter.GuestStorageBufferOffsetAlignment - 1))) * prime;
         }
 
         if (evaluation.ComputeSystemRegisters is { } computeSystemRegisters)
@@ -6909,8 +6670,7 @@ public static partial class AgcExports
             scissor,
             DecodeViewport(registers, target.Width, target.Height, scissor),
             DecodeRasterState(registers),
-            DecodeDepthState(registers),
-            DecodeBlendConstant(registers));
+            DecodeDepthState(registers));
     }
 
     private static GuestRenderState CreateRenderState(
@@ -6943,8 +6703,7 @@ public static partial class AgcExports
             scissor,
             DecodeViewport(registers, target.Width, target.Height, scissor),
             DecodeRasterState(registers),
-            DecodeDepthState(registers),
-            DecodeBlendConstant(registers));
+            DecodeDepthState(registers));
     }
 
     // DB_DEPTH_CONTROL (context register 0x200): Z_ENABLE bit1, Z_WRITE_ENABLE
@@ -7049,22 +6808,6 @@ public static partial class AgcExports
         return new GuestRasterState(cullFront, cullBack, frontFaceClockwise, wireframe);
     }
 
-    /// <summary>CB_BLEND_RED..ALPHA carry the constant blend color as raw
-    /// float bits; unwritten registers read as the reset value (0.0).</summary>
-    private static GuestBlendConstant DecodeBlendConstant(
-        IReadOnlyDictionary<uint, uint> registers)
-    {
-        registers.TryGetValue(CbBlendRed, out var red);
-        registers.TryGetValue(CbBlendGreen, out var green);
-        registers.TryGetValue(CbBlendBlue, out var blue);
-        registers.TryGetValue(CbBlendAlpha, out var alpha);
-        return new GuestBlendConstant(
-            BitConverter.Int32BitsToSingle(unchecked((int)red)),
-            BitConverter.Int32BitsToSingle(unchecked((int)green)),
-            BitConverter.Int32BitsToSingle(unchecked((int)blue)),
-            BitConverter.Int32BitsToSingle(unchecked((int)alpha)));
-    }
-
     private static GuestBlendState DecodeBlendState(
         IReadOnlyDictionary<uint, uint> registers,
         uint slot)
@@ -7577,7 +7320,7 @@ public static partial class AgcExports
         IReadOnlyList<uint> registers,
         IReadOnlyList<Gen5GlobalMemoryBinding> bindings)
     {
-        var bytes = GuestDataPool.Shared.Rent(
+        var bytes = VulkanVideoPresenter.GuestDataPool.Rent(
             GetRuntimeScalarBufferLength(bindings.Count));
         PackRuntimeScalarStateInto(bytes, registers, bindings);
         return bytes;
@@ -7603,7 +7346,7 @@ public static partial class AgcExports
         {
             var byteBias = checked((uint)(
                 bindings[index].BaseAddress &
-                (_storageBufferOffsetAlignment - 1)));
+                (VulkanVideoPresenter.GuestStorageBufferOffsetAlignment - 1)));
             BinaryPrimitives.WriteUInt32LittleEndian(
                 bytes.AsSpan(biasOffset + index * sizeof(uint), sizeof(uint)),
                 byteBias);
@@ -7646,7 +7389,7 @@ public static partial class AgcExports
         {
             if (binding.DataPooled && returned.Add(binding.Data))
             {
-                GuestDataPool.Shared.Return(binding.Data);
+                VulkanVideoPresenter.GuestDataPool.Return(binding.Data);
             }
         }
 
@@ -7656,7 +7399,7 @@ public static partial class AgcExports
             {
                 if (binding.DataPooled && returned.Add(binding.Data))
                 {
-                    GuestDataPool.Shared.Return(binding.Data);
+                    VulkanVideoPresenter.GuestDataPool.Return(binding.Data);
                 }
             }
         }
@@ -7682,7 +7425,7 @@ public static partial class AgcExports
             {
                 if (binding.DataPooled && returned.Add(binding.Data))
                 {
-                    GuestDataPool.Shared.Return(binding.Data);
+                    VulkanVideoPresenter.GuestDataPool.Return(binding.Data);
                 }
             }
         }
@@ -7693,7 +7436,7 @@ public static partial class AgcExports
             {
                 if (binding.DataPooled && returned.Add(binding.Data))
                 {
-                    GuestDataPool.Shared.Return(binding.Data);
+                    VulkanVideoPresenter.GuestDataPool.Return(binding.Data);
                 }
             }
         }
@@ -7701,7 +7444,7 @@ public static partial class AgcExports
         if (index && draw.IndexBuffer is { Pooled: true } indexBuffer &&
             returned.Add(indexBuffer.Data))
         {
-            GuestDataPool.Shared.Return(indexBuffer.Data);
+            VulkanVideoPresenter.GuestDataPool.Return(indexBuffer.Data);
         }
     }
 
@@ -7958,7 +7701,7 @@ public static partial class AgcExports
 
         if (!isStorage &&
             descriptor.Address != 0 &&
-            GuestGpu.Current.IsGpuGuestImageAvailable(
+            VulkanVideoPresenter.IsGuestImageAvailable(
                 descriptor.Address,
                 descriptor.Format,
                 descriptor.NumberType))
@@ -7987,7 +7730,7 @@ public static partial class AgcExports
         {
             var initialPixels = Array.Empty<byte>();
             var uploadKnown = descriptor.Address != 0 &&
-                GuestGpu.Current.IsGuestImageUploadKnown(
+                VulkanVideoPresenter.IsGuestImageUploadKnown(
                     descriptor.Address,
                     descriptor.Format,
                     descriptor.NumberType);
@@ -8068,8 +7811,8 @@ public static partial class AgcExports
         if (!_textureCopySkipDisabled &&
             descriptor.Address != 0 &&
             !SharpEmu.HLE.GuestImageWriteTracker.PeekDirty(descriptor.Address) &&
-            GuestGpu.Current.IsTextureContentCached(
-                new TextureContentIdentity(
+            VulkanVideoPresenter.IsTextureContentCached(
+                new VulkanVideoPresenter.TextureContentIdentity(
                     descriptor.Address,
                     descriptor.Width,
                     descriptor.Height,
@@ -8172,7 +7915,7 @@ public static partial class AgcExports
         CpuContext ctx,
         RenderTargetDescriptor target)
     {
-        if (!GuestGpu.Current.GuestImageWantsInitialData(target.Address))
+        if (!VulkanVideoPresenter.GuestImageWantsInitialData(target.Address))
         {
             return;
         }
@@ -8198,7 +7941,7 @@ public static partial class AgcExports
 
         if (nonZero)
         {
-            GuestGpu.Current.ProvideGuestImageInitialData(target.Address, initialData);
+            VulkanVideoPresenter.ProvideGuestImageInitialData(target.Address, initialData);
         }
     }
 
@@ -8495,14 +8238,9 @@ public static partial class AgcExports
         ulong packetAddress,
         uint packetLength,
         uint opcode,
-        out ComputeDispatch dispatch,
-        out ulong indirectDimsRetryAddress)
+        out ComputeDispatch dispatch)
     {
         dispatch = default;
-        // Non-zero only when this is an INDIRECT dispatch whose dimensions read as
-        // zero — meaning the producing GPU dispatch that computes them has not run
-        // yet. The caller suspends on this address instead of dropping the work.
-        indirectDimsRetryAddress = 0;
         ulong dimensionsAddress;
         uint initiator;
         string dispatchSource;
@@ -8551,17 +8289,6 @@ public static partial class AgcExports
 
         if (dispatchEndX == 0 || dispatchEndY == 0 || dispatchEndZ == 0)
         {
-            // Indirect dispatches read their dimensions from a guest buffer a
-            // prior GPU dispatch fills. Zero here means that producer has not run
-            // yet — signal the caller to suspend on the dims buffer and retry,
-            // rather than dropping the work (which black-screens GPU-driven games
-            // like Astro Bot). Direct dispatches carry dims inline, so a zero is
-            // genuinely malformed and still rejected.
-            if (opcode == ItDispatchIndirect)
-            {
-                indirectDimsRetryAddress = dimensionsAddress;
-            }
-
             return RejectComputeDispatch(
                 dimensionsAddress,
                 initiator,
@@ -8896,7 +8623,7 @@ public static partial class AgcExports
             // still queued, so the clear could erase newly constructed CPU
             // objects.  Waiting on the work sequence also retires preceding
             // Vulkan writes before the next evaluator snapshot is captured.
-            if (!GuestGpu.Current.WaitForGuestWork(semanticCopySequence))
+            if (!VulkanVideoPresenter.WaitForGuestWork(semanticCopySequence))
             {
                 computeError =
                     $"semantic-global-write-sync-timeout sequence={semanticCopySequence}";
@@ -8914,7 +8641,7 @@ public static partial class AgcExports
                 localSizeY,
                 localSizeZ,
                 dispatch.WaveLaneCount,
-                _storageBufferOffsetAlignment);
+                VulkanVideoPresenter.GuestStorageBufferOffsetAlignment);
             var guestGlobalBufferCount = evaluation.GlobalMemoryBindings.Count;
             var totalGlobalBufferCount = _bakeScalars
                 ? guestGlobalBufferCount
@@ -8936,7 +8663,7 @@ public static partial class AgcExports
                         : guestGlobalBufferCount,
                     waveLaneCount: dispatch.WaveLaneCount,
                     storageBufferOffsetAlignment:
-                        _storageBufferOffsetAlignment))
+                        VulkanVideoPresenter.GuestStorageBufferOffsetAlignment))
             {
                 DumpCompiledShader(
                     "cs",
@@ -8956,7 +8683,7 @@ public static partial class AgcExports
                     out _);
                 var globalMemoryBuffers =
                     CreateTranslatedComputeGlobalBuffers(evaluation);
-                GuestGpu.Current.SubmitComputeDispatch(
+                var workSequence = GuestGpu.Current.SubmitComputeDispatch(
                     shaderAddress,
                     computeShader,
                     textures,
@@ -8975,9 +8702,12 @@ public static partial class AgcExports
                     dispatch.ThreadCountX,
                     dispatch.ThreadCountY,
                     dispatch.ThreadCountZ);
-                // Vulkan queue order keeps dependent dispatches coherent. CPU visibility is
-                // published by explicit PM4 release/write actions instead of per dispatch.
                 gpuDispatch = true;
+                if (writesGlobalMemory &&
+                    !VulkanVideoPresenter.WaitForGuestWork(workSequence))
+                {
+                    computeError = $"global-write-sync-timeout sequence={workSequence}";
+                }
             }
         }
 
@@ -9168,7 +8898,7 @@ public static partial class AgcExports
         }
 
         var destinationAddress = destination.BaseAddress;
-        workSequence = GuestGpu.Current.SubmitOrderedGuestAction(
+        workSequence = VulkanVideoPresenter.SubmitOrderedGuestAction(
             () =>
             {
                 if (!ctx.Memory.TryWrite(destinationAddress, output))
@@ -9182,7 +8912,7 @@ public static partial class AgcExports
                 GuestImageWriteTracker.Track(
                     destinationAddress,
                     (ulong)output.Length,
-                    GuestGpu.Current.CurrentGuestWorkSequenceForDiagnostics,
+                    VulkanVideoPresenter.CurrentGuestWorkSequenceForDiagnostics,
                     "agc.masked-dword-copy");
             },
             $"masked_dword_copy dst=0x{destinationAddress:X16} bytes={output.Length}");
@@ -9871,7 +9601,7 @@ public static partial class AgcExports
                                  pixelInputEnable: psInputEna,
                                  pixelInputAddress: psInputAddr,
                                  storageBufferOffsetAlignment:
-                                     _storageBufferOffsetAlignment))
+                                     VulkanVideoPresenter.GuestStorageBufferOffsetAlignment))
                         {
                             TraceAgcShader(
                                 $"agc.shader_spirv ps=0x{pixelShaderAddress:X16} " +
@@ -11495,35 +11225,4 @@ public static partial class AgcExports
         TraceAgc($"agc.driver_unregister_resource handle={resourceHandle}");
         return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
     }
-
-    // Tessellation-factor ring and hull-shader off-chip buffers are guest-driver
-    // configuration for on-hardware tessellation memory. Our translator handles
-    // shader execution directly, so there is no guest-side ring to program: the
-    // guest driver only needs these to report success so init proceeds. Games
-    // (e.g. Unity titles) call them during GPU setup and stall if unresolved.
-    [SysAbiExport(
-        Nid = "XlNp7jzGiPo",
-        ExportName = "sceAgcDriverSetTFRing",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAgcDriver")]
-    public static int DriverSetTFRing(CpuContext ctx)
-    {
-        TraceAgc(
-            $"agc.driver_set_tf_ring ring=0x{ctx[CpuRegister.Rdi]:X16} " +
-            $"size=0x{(uint)ctx[CpuRegister.Rsi]:X8}");
-        return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
-    }
-
-    [SysAbiExport(
-        Nid = "MM4IZSEYytQ",
-        ExportName = "sceAgcDriverSetHsOffchipParam",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAgcDriver")]
-    public static int DriverSetHsOffchipParam(CpuContext ctx)
-    {
-        TraceAgc(
-            $"agc.driver_set_hs_offchip_param buffer=0x{ctx[CpuRegister.Rdi]:X16} " +
-            $"param=0x{(uint)ctx[CpuRegister.Rsi]:X8}");
-        return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
-    }
 }

src/SharpEmu.Libs/Agc/AgcShaderCompilerHooks.cs

@@ -3,7 +3,6 @@
 
 using System.Diagnostics.CodeAnalysis;
 using System.Runtime.CompilerServices;
-using SharpEmu.Libs.Gpu;
 using SharpEmu.Libs.Kernel;
 using SharpEmu.Libs.VideoOut;
 using SharpEmu.ShaderCompiler;
@@ -27,8 +26,8 @@ internal static class AgcShaderCompilerHooks
     internal static void Install()
     {
         Gen5ShaderScalarEvaluator.FallbackMemoryReader =
-            KernelMemoryCompatExports.TryReadShaderGuestMemory;
+            KernelMemoryCompatExports.TryReadTrackedLibcHeap;
         Gen5ShaderScalarEvaluator.GlobalMemoryPool =
-            GuestDataPool.Shared;
+            VulkanVideoPresenter.GuestDataPool;
     }
 }

src/SharpEmu.Libs/Agc/GpuWaitRegistry.cs

@@ -37,26 +37,10 @@ internal static class GpuWaitRegistry
         public long RegisteredTicks;
         public bool StaleReported;
         public object? State;
-        // Latched by LatchSatisfiedByValue when a producer wrote a value that
-        // satisfies this waiter. The label is frequently reused (reset to 0 for
-        // the next frame) immediately after the producing write, so re-reading
-        // guest memory at wake time can miss the transient satisfied window.
-        // Latching records satisfaction at the moment of the write instead.
-        public bool Latched;
-        // Non-zero for indirect-dispatch dimension retries: a bounded deadline
-        // (Stopwatch ticks) after which the waiter is resumed even if unsatisfied,
-        // so a legitimately empty indirect dispatch can never stall forever.
-        public long RetryDeadlineTicks;
     }
 
     private static readonly object _gate = new();
     private static readonly Dictionary<ulong, List<WaitingDcb>> _waiters = new();
-    // The last value each label producer wrote. Used only by the deadlock
-    // breaker: our serial submission parser cannot model two GPU queues running
-    // concurrently, so a label written -> reset -> re-waited across queues can
-    // cycle forever even though a real producer did signal it. Keyed by (memory,
-    // address) so distinct guest processes never alias.
-    private static readonly Dictionary<(object, ulong), ulong> _lastProduced = new();
 
     public static int Count
     {
@@ -130,14 +114,8 @@ internal static class GpuWaitRegistry
                         continue;
                     }
 
-                    var satisfied = list[i].Latched;
-                    if (!satisfied)
-                    {
-                        var value = readValue(address, list[i].Is64Bit);
-                        satisfied = value is not null && Compare(list[i], value.Value);
-                    }
-
-                    if (!satisfied)
+                    var value = readValue(address, list[i].Is64Bit);
+                    if (value is null || !Compare(list[i], value.Value))
                     {
                         continue;
                     }
@@ -258,162 +236,6 @@ internal static class GpuWaitRegistry
         return matches;
     }
 
-    /// <summary>
-    /// Records satisfaction for every waiter at <paramref name="address"/> whose
-    /// condition is met by <paramref name="value"/> — the value a producer just
-    /// wrote to that label. Called from the ordered producer side effect so a
-    /// same-frame label reset cannot lose the wakeup. The waiters stay registered
-    /// (latched) and are drained by the next CollectSatisfied. Returns true when
-    /// at least one waiter latched, so the caller can trigger a wake pass.
-    /// </summary>
-    public static bool LatchSatisfiedByValue(object memory, ulong address, ulong value)
-    {
-        var latchedAny = false;
-        lock (_gate)
-        {
-            if (!_waiters.TryGetValue(address, out var list))
-            {
-                return false;
-            }
-
-            for (var i = 0; i < list.Count; i++)
-            {
-                var waiter = list[i];
-                if (waiter.Latched ||
-                    !ReferenceEquals(waiter.Memory, memory) ||
-                    !Compare(waiter, value))
-                {
-                    continue;
-                }
-
-                waiter.Latched = true;
-                list[i] = waiter;
-                latchedAny = true;
-            }
-        }
-
-        return latchedAny;
-    }
-
-    /// <summary>
-    /// Removes and returns waiters carrying a <see cref="WaitingDcb.RetryDeadlineTicks"/>
-    /// that has elapsed. Used for indirect-dispatch dimension retries: the caller
-    /// resumes them so a genuinely empty dispatch (dims that never become non-zero)
-    /// is dropped after a bounded wait instead of stalling the queue forever.
-    /// </summary>
-    public static List<WaitingDcb>? CollectExpiredRetries(object memory, long nowTicks)
-    {
-        List<WaitingDcb>? expired = null;
-        lock (_gate)
-        {
-            List<ulong>? emptied = null;
-            foreach (var (address, list) in _waiters)
-            {
-                for (var i = list.Count - 1; i >= 0; i--)
-                {
-                    var waiter = list[i];
-                    if (waiter.RetryDeadlineTicks == 0 ||
-                        !ReferenceEquals(waiter.Memory, memory) ||
-                        nowTicks < waiter.RetryDeadlineTicks)
-                    {
-                        continue;
-                    }
-
-                    expired ??= new List<WaitingDcb>();
-                    expired.Add(waiter);
-                    list.RemoveAt(i);
-                }
-
-                if (list.Count == 0)
-                {
-                    emptied ??= new List<ulong>();
-                    emptied.Add(address);
-                }
-            }
-
-            if (emptied is not null)
-            {
-                foreach (var address in emptied)
-                {
-                    _waiters.Remove(address);
-                }
-            }
-        }
-
-        return expired;
-    }
-
-    /// <summary>Records the value a label producer wrote, for the deadlock
-    /// breaker. Also latches any already-waiting waiter it satisfies.</summary>
-    public static bool RecordProduced(object memory, ulong address, ulong value)
-    {
-        lock (_gate)
-        {
-            if (_lastProduced.Count >= 8192)
-            {
-                _lastProduced.Clear();
-            }
-
-            _lastProduced[(memory, address)] = value;
-        }
-
-        return LatchSatisfiedByValue(memory, address, value);
-    }
-
-    /// <summary>
-    /// Breaks cross-queue GPU deadlocks the serial parser cannot avoid: returns
-    /// (and removes) waiters that have been stuck longer than
-    /// <paramref name="minAgeTicks"/> and whose condition is satisfied by the
-    /// last value a real producer wrote to their label — even though guest
-    /// memory has since been reset. Never fabricates a value: a waiter is only
-    /// released when an actual producer signalled it at least once.
-    /// </summary>
-    public static List<WaitingDcb>? CollectDeadlockBroken(
-        object memory,
-        long nowTicks,
-        long minAgeTicks)
-    {
-        List<WaitingDcb>? broken = null;
-        lock (_gate)
-        {
-            List<ulong>? emptied = null;
-            foreach (var (address, list) in _waiters)
-            {
-                for (var i = list.Count - 1; i >= 0; i--)
-                {
-                    var waiter = list[i];
-                    if (!ReferenceEquals(waiter.Memory, memory) ||
-                        nowTicks - waiter.RegisteredTicks < minAgeTicks ||
-                        !_lastProduced.TryGetValue((memory, address), out var produced) ||
-                        !Compare(waiter, produced))
-                    {
-                        continue;
-                    }
-
-                    broken ??= new List<WaitingDcb>();
-                    broken.Add(waiter);
-                    list.RemoveAt(i);
-                }
-
-                if (list.Count == 0)
-                {
-                    emptied ??= new List<ulong>();
-                    emptied.Add(address);
-                }
-            }
-
-            if (emptied is not null)
-            {
-                foreach (var address in emptied)
-                {
-                    _waiters.Remove(address);
-                }
-            }
-        }
-
-        return broken;
-    }
-
     public static bool Compare(in WaitingDcb waiter, ulong value)
     {
         var masked = value & waiter.Mask;
@@ -438,7 +260,6 @@ internal static class GpuWaitRegistry
         lock (_gate)
         {
             _waiters.Clear();
-            _lastProduced.Clear();
         }
     }
 }

src/SharpEmu.Libs/Ampr/AmprExports.cs

@@ -6,7 +6,6 @@ using SharpEmu.Libs.Kernel;
 using System.Buffers;
 using System.Buffers.Binary;
 using System.Collections.Concurrent;
-using Microsoft.Win32.SafeHandles;
 
 namespace SharpEmu.Libs.Ampr;
 
@@ -44,17 +43,17 @@ public static class AmprExports
     {
         public CachedHostFile(string path)
         {
-            Handle = File.OpenHandle(
+            Stream = new FileStream(
                 path,
                 FileMode.Open,
                 FileAccess.Read,
                 FileShare.ReadWrite | FileShare.Delete,
+                bufferSize: 1024 * 1024,
                 FileOptions.RandomAccess);
-            Length = RandomAccess.GetLength(Handle);
         }
 
-        public SafeFileHandle Handle { get; }
-        public long Length { get; }
+        public object Gate { get; } = new();
+        public FileStream Stream { get; }
     }
 
     [SysAbiExport(
@@ -736,7 +735,13 @@ public static class AmprExports
                 return openResult;
             }
 
-            if (fileOffset >= (ulong)cachedFile.Length)
+            long fileLength;
+            lock (cachedFile.Gate)
+            {
+                fileLength = cachedFile.Stream.Length;
+            }
+
+            if (fileOffset >= (ulong)fileLength)
             {
                 return (int)OrbisGen2Result.ORBIS_GEN2_OK;
             }
@@ -755,10 +760,12 @@ public static class AmprExports
                 }
 
                 var request = (int)Math.Min((ulong)buffer.Length, size - bytesRead);
-                var read = RandomAccess.Read(
-                    cachedFile.Handle,
-                    buffer.AsSpan(0, request),
-                    unchecked((long)absoluteOffset));
+                int read;
+                lock (cachedFile.Gate)
+                {
+                    cachedFile.Stream.Position = unchecked((long)absoluteOffset);
+                    read = cachedFile.Stream.Read(buffer, 0, request);
+                }
 
                 if (read <= 0)
                 {

src/SharpEmu.Libs/AppContent/AppContentExports.cs

@@ -121,33 +121,6 @@ public static class AppContentExports
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
-    // Download data is not emulated as a real quota; report a comfortable
-    // fixed amount of free space so titles never take the "storage full" path.
-    [SysAbiExport(
-        Nid = "Gl6w5i0JokY",
-        ExportName = "sceAppContentDownloadDataGetAvailableSpaceKb",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceAppContent")]
-    public static int AppContentDownloadDataGetAvailableSpaceKb(CpuContext ctx)
-    {
-        const ulong availableSpaceKb = 1024UL * 1024UL; // 1 GiB
-        var availableSpaceAddress = ctx[CpuRegister.Rsi];
-        if (availableSpaceAddress == 0)
-        {
-            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT;
-        }
-
-        Span<byte> spaceBytes = stackalloc byte[sizeof(ulong)];
-        BinaryPrimitives.WriteUInt64LittleEndian(spaceBytes, availableSpaceKb);
-        if (!ctx.Memory.TryWrite(availableSpaceAddress, spaceBytes))
-        {
-            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
-        }
-
-        ctx[CpuRegister.Rax] = 0;
-        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
-    }
-
     private static bool TryReadUserDefinedParam(uint paramId, out int value)
     {
         value = 0;

src/SharpEmu.Libs/Audio/AudioOutExports.cs

@@ -14,12 +14,6 @@ public static class AudioOutExports
     private static readonly ConcurrentDictionary<int, PortState> Ports = new();
     private static int _nextPortHandle;
 
-    // Diagnostic: confirm sceAudioOutOutput is actually called and whether the
-    // guest submits real samples or silence. Gated so it costs nothing when off.
-    private static readonly bool _traceOutput = string.Equals(
-        Environment.GetEnvironmentVariable("SHARPEMU_LOG_AUDIO_OUT"), "1", StringComparison.Ordinal);
-    private static long _outputCount;
-
     private sealed class PortState : IDisposable
     {
         private readonly object _paceGate = new();
@@ -161,37 +155,6 @@ public static class AudioOutExports
         return ctx.SetReturn(0);
     }
 
-    [SysAbiExport(
-        Nid = "GrQ9s4IrNaQ",
-        ExportName = "sceAudioOutGetPortState",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceAudioOut")]
-    public static int AudioOutGetPortState(CpuContext ctx)
-    {
-        var handle = unchecked((int)ctx[CpuRegister.Rdi]);
-        var stateAddress = ctx[CpuRegister.Rsi];
-        if (stateAddress == 0 || !Ports.TryGetValue(handle, out var port))
-        {
-            return ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        // SceAudioOutPortState: report a connected primary output at full volume
-        // so pacing/mixing code sees a live port. We do no host rerouting, so
-        // rerouteCounter and flag stay zero.
-        Span<byte> state = stackalloc byte[16];
-        state.Clear();
-        System.Buffers.Binary.BinaryPrimitives.WriteUInt16LittleEndian(state, 1);
-        System.Buffers.Binary.BinaryPrimitives.WriteUInt16LittleEndian(
-            state[2..], (ushort)port.Channels);
-        state[7] = 127;
-        if (!ctx.Memory.TryWrite(stateAddress, state))
-        {
-            return ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-        }
-
-        return ctx.SetReturn(0);
-    }
-
     [SysAbiExport(
         Nid = "QOQtbeDqsT4",
         ExportName = "sceAudioOutOutput",
@@ -203,12 +166,7 @@ public static class AudioOutExports
         var sourceAddress = ctx[CpuRegister.Rsi];
         if (!Ports.TryGetValue(handle, out var port))
         {
-            // Host shutdown disposes the ports while guest audio threads are
-            // still draining their last buffers; report success so the guest
-            // winds down without a per-buffer error (and its WARN log flood).
-            return ctx.SetReturn(_shutdown
-                ? 0
-                : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
+            return ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
         }
 
         if (sourceAddress == 0)
@@ -225,17 +183,6 @@ public static class AudioOutExports
                 return ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
             }
 
-            if (_traceOutput)
-            {
-                var n = Interlocked.Increment(ref _outputCount);
-                if (n <= 8 || n % 200 == 0)
-                {
-                    var peak = PeakAmplitude(source, port.IsFloat, port.BytesPerSample);
-                    Console.Error.WriteLine(
-                        $"[LOADER][TRACE] audioout.output#{n} handle={handle} bytes={source.Length} ch={port.Channels} float={port.IsFloat} vol={port.Volume:F2} peak={peak:F4} backend={(port.Backend is null ? "none" : "coreaudio")}");
-                }
-            }
-
             if (port.Backend is null)
             {
                 port.PaceSilence();
@@ -319,40 +266,8 @@ public static class AudioOutExports
         return ctx.SetReturn(0);
     }
 
-    // Peak normalized amplitude [0,1] of an interleaved PCM buffer, used only by
-    // the SHARPEMU_LOG_AUDIO_OUT diagnostic to distinguish real audio from silence.
-    private static float PeakAmplitude(ReadOnlySpan<byte> source, bool isFloat, int bytesPerSample)
-    {
-        var peak = 0f;
-        if (isFloat && bytesPerSample == 4)
-        {
-            for (var i = 0; i + 4 <= source.Length; i += 4)
-            {
-                var v = Math.Abs(System.Buffers.Binary.BinaryPrimitives.ReadSingleLittleEndian(source.Slice(i, 4)));
-                if (v > peak)
-                {
-                    peak = v;
-                }
-            }
-        }
-        else if (bytesPerSample == 2)
-        {
-            for (var i = 0; i + 2 <= source.Length; i += 2)
-            {
-                var v = Math.Abs(System.Buffers.Binary.BinaryPrimitives.ReadInt16LittleEndian(source.Slice(i, 2)) / 32768f);
-                if (v > peak)
-                {
-                    peak = v;
-                }
-            }
-        }
-
-        return peak;
-    }
-
     public static void ShutdownAllPorts()
     {
-        Volatile.Write(ref _shutdown, true);
         foreach (var handle in Ports.Keys)
         {
             if (Ports.TryRemove(handle, out var port))
@@ -362,8 +277,6 @@ public static class AudioOutExports
         }
     }
 
-    private static bool _shutdown;
-
     private static bool TryGetFormat(
         int rawFormat,
         out int channels,

src/SharpEmu.Libs/Audio/AudioPropagationExports.cs

@@ -1,154 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.HLE;
-
-namespace SharpEmu.Libs.Audio;
-
-// PS5 acoustic-propagation (3D-audio ray/portal/room) module. We do not model
-// acoustic propagation; the geometry-driven reverb/occlusion it produces is a
-// quality feature, not a correctness gate. Games (e.g. Astro Bot) call it
-// during audio init and hard-assert if any entry point is missing:
-//   ASSERT ... sceAudioPropagationSystemQueryMemory failed : 0x80020002
-// The API is placement-style: QueryMemory reports a buffer size, the game
-// allocates it, and the "system"/objects live inside that caller-owned buffer,
-// so success-returning stubs let init proceed without us owning any state.
-public static class AudioPropagationExports
-{
-    private const int Ok = 0;
-
-    // QueryMemory reports the working-set size the caller must allocate before
-    // SystemCreate. rsi points at the out size/alignment; write a modest,
-    // aligned block so the caller's allocation succeeds.
-    [SysAbiExport(
-        Nid = "7xyAxrusLko",
-        ExportName = "sceAudioPropagationSystemQueryMemory",
-        Target = Generation.Gen5,
-        LibraryName = "libSceAudioPropagation")]
-    public static int SystemQueryMemory(CpuContext ctx)
-    {
-        var outAddress = ctx[CpuRegister.Rsi];
-        if (outAddress != 0)
-        {
-            // {size, alignment} — 1 MiB / 256 B covers the caller's allocation.
-            ctx.TryWriteUInt64(outAddress, 0x10_0000);
-            ctx.TryWriteUInt64(outAddress + sizeof(ulong), 0x100);
-        }
-
-        return ctx.SetReturn(Ok);
-    }
-
-    [SysAbiExport(Nid = "GrA9ke1QT+E", ExportName = "sceAudioPropagationSystemQueryInfo", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemQueryInfo(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "aNEqtSHdUSo", ExportName = "sceAudioPropagationSystemCreate", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemCreate(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "x5VPqg5iyAk", ExportName = "sceAudioPropagationSystemDestroy", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemDestroy(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "ile38Gl-p5M", ExportName = "sceAudioPropagationSystem", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int System(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "cMl3u+7QBBM", ExportName = "sceAudioPropagationSystemMemoryInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemMemoryInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "3B9IabLByyM", ExportName = "sceAudioPropagationSystemOptionInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemOptionInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "B2KI2AachWE", ExportName = "sceAudioPropagationSystemLock", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemLock(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "kIdb+iQUzCs", ExportName = "sceAudioPropagationSystemSetAttributes", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemSetAttributes(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "VlBT16890mA", ExportName = "sceAudioPropagationSystemSetRays", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemSetRays(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "ht-QXT3zGxo", ExportName = "sceAudioPropagationSystemGetRays", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemGetRays(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "CPLV6G-eXmk", ExportName = "sceAudioPropagationSystemRegisterMaterial", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemRegisterMaterial(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "XKCN4gpeYsM", ExportName = "sceAudioPropagationSystemUnregisterMaterial", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SystemUnregisterMaterial(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "8bI5h8req30", ExportName = "sceAudioPropagationRoomCreate", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int RoomCreate(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "S0JwP2AFTTE", ExportName = "sceAudioPropagationRoomDestroy", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int RoomDestroy(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "b-dYXrjSNZU", ExportName = "sceAudioPropagationPortalCreate", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int PortalCreate(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "ZQXE-xS6MTE", ExportName = "sceAudioPropagationPortalDestroy", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int PortalDestroy(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "WXMhENV2NcA", ExportName = "sceAudioPropagationPortalSetAttributes", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int PortalSetAttributes(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "i687TNRF+hw", ExportName = "sceAudioPropagationPortalSettingsInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int PortalSettingsInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "d84otraxt2s", ExportName = "sceAudioPropagationSourceCreate", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceCreate(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "wkseM3LWPuc", ExportName = "sceAudioPropagationSourceDestroy", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceDestroy(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "-wsUTr31yeg", ExportName = "sceAudioPropagationSourceSetAttributes", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceSetAttributes(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "PBcrVpEqUVY", ExportName = "sceAudioPropagationSourceCalculateAudioPaths", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceCalculateAudioPaths(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "eEeKqFeNI3o", ExportName = "sceAudioPropagationSourceGetAudioPath", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceGetAudioPath(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "G+QLTfyLMYk", ExportName = "sceAudioPropagationSourceGetAudioPathCount", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceGetAudioPathCount(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "aKJZx7wCma8", ExportName = "sceAudioPropagationSourceGetRays", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceGetRays(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "3aEY9tPXGKc", ExportName = "sceAudioPropagationSourceQueryInfo", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceQueryInfo(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "hhz9pITnC8k", ExportName = "sceAudioPropagationSourceRender", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceRender(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "SoKPzY1-3SU", ExportName = "sceAudioPropagationSourceRenderInfoInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceRenderInfoInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "tKSmk2JsMAA", ExportName = "sceAudioPropagationSourceSetAudioPath", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceSetAudioPath(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "5vzOS2pHMFc", ExportName = "sceAudioPropagationSourceSetAudioPaths", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceSetAudioPaths(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "MNmGapXrYRs", ExportName = "sceAudioPropagationSourceSetAudioPathsParamInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int SourceSetAudioPathsParamInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "i-0aUex3zCE", ExportName = "sceAudioPropagationAudioPathInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int AudioPathInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "JZIkSbmt2BE", ExportName = "sceAudioPropagationAudioPathPointInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int AudioPathPointInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "tL2AEPejVQE", ExportName = "sceAudioPropagationPathGetNumPoints", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int PathGetNumPoints(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "2BSFmuKtRss", ExportName = "sceAudioPropagationMaterialInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int MaterialInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "0r2+9UTg1BA", ExportName = "sceAudioPropagationRayInit", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int RayInit(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "BbOT4vBwAjs", ExportName = "sceAudioPropagationResetAttributes", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int ResetAttributes(CpuContext ctx) => ctx.SetReturn(Ok);
-
-    [SysAbiExport(Nid = "gCmQm6dvMxw", ExportName = "sceAudioPropagationReportApi", Target = Generation.Gen5, LibraryName = "libSceAudioPropagation")]
-    public static int ReportApi(CpuContext ctx) => ctx.SetReturn(Ok);
-}

src/SharpEmu.Libs/Bink/Bink2MovieBridge.cs

@@ -29,9 +29,10 @@ internal static class Bink2MovieBridge
     private static bool _availabilityReported;
 
     /// <summary>
-    /// Returns true only when movie skipping was explicitly requested. Without
-    /// a host adapter the guest must be allowed to run the Bink implementation
-    /// statically linked into its executable.
+    /// Returns true when the guest should receive a normal "file not found"
+    /// result for a Bink movie. This is the safe default without a decoder:
+    /// games that treat movies as optional fall through to their next state
+    /// rather than submitting an empty Bink GPU texture forever.
     /// </summary>
     internal static bool ShouldSkipGuestMovie(string hostPath) =>
         hostPath.EndsWith(".bk2", StringComparison.OrdinalIgnoreCase) &&
@@ -52,18 +53,12 @@ internal static class Bink2MovieBridge
                 return;
             }
 
-            var mode = ResolveMode();
-            if (mode == MovieMode.Dummy)
+            if (ResolveMode() == MovieMode.Dummy)
             {
                 AttachDummyMovieLocked(hostPath);
                 return;
             }
 
-            if (mode != MovieMode.Native)
-            {
-                return;
-            }
-
             var adapter = GetAdapterLocked();
             if (adapter is null)
             {
@@ -170,15 +165,16 @@ internal static class Bink2MovieBridge
             return MovieMode.Skip;
         }
 
-        // Prefer the optional host adapter when one is supplied. Otherwise let
-        // the game's statically linked Bink implementation consume the file.
+        // With no SDK adapter present, returning "not found" makes optional
+        // cinematics advance. Supplying either an explicit path or the normal
+        // side-by-side adapter enables native playback automatically.
         if (!string.IsNullOrWhiteSpace(Environment.GetEnvironmentVariable("SHARPEMU_BINK2_BRIDGE")) ||
             EnumerateAdapterCandidates().Any(File.Exists))
         {
             return MovieMode.Native;
         }
 
-        return MovieMode.Guest;
+        return MovieMode.Skip;
     }
 
     private static void AttachDummyMovieLocked(string hostPath)
@@ -339,7 +335,6 @@ internal static class Bink2MovieBridge
 
     private enum MovieMode
     {
-        Guest,
         Skip,
         Dummy,
         Native,

src/SharpEmu.Libs/Gpu/GuestDataPool.cs

@@ -1,140 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Buffers;
-using System.Numerics;
-
-namespace SharpEmu.Libs.Gpu;
-
-/// <summary>
-/// The pool backing AGC-to-presenter ownership transfers, shared by every backend
-/// (the AGC layer rents, the presenter returns, so both sides must use one pool).
-/// Guest draw snapshots churn through a small set of 128 KiB-16 MiB size classes
-/// thousands of times per second; the process-wide shared pool trims and
-/// repartitions those large arrays aggressively under GC load, causing hundreds of
-/// MiB/s of replacement byte[] allocations, so this pool is bounded and non-shared.
-/// </summary>
-internal static class GuestDataPool
-{
-    public static ArrayPool<byte> Shared { get; } = new BoundedByteArrayPool(
-        maxArrayLength: 16 * 1024 * 1024,
-        maxCachedBytes: 256UL * 1024 * 1024,
-        maxArraysPerBucket: 8);
-
-    public static void Trim() => ((BoundedByteArrayPool)Shared).Trim();
-
-    private sealed class BoundedByteArrayPool : ArrayPool<byte>
-    {
-        private readonly object _gate = new();
-        private readonly int _maxArrayLength;
-        private readonly ulong _maxCachedBytes;
-        private readonly int _maxArraysPerBucket;
-        private readonly Dictionary<int, Stack<byte[]>> _cachedByBucket = [];
-        private readonly HashSet<byte[]> _leases =
-            new(System.Collections.Generic.ReferenceEqualityComparer.Instance);
-        private ulong _cachedBytes;
-
-        public BoundedByteArrayPool(
-            int maxArrayLength,
-            ulong maxCachedBytes,
-            int maxArraysPerBucket)
-        {
-            ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArrayLength);
-            ArgumentOutOfRangeException.ThrowIfZero(maxCachedBytes);
-            ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArraysPerBucket);
-            _maxArrayLength = maxArrayLength;
-            _maxCachedBytes = maxCachedBytes;
-            _maxArraysPerBucket = maxArraysPerBucket;
-        }
-
-        public override byte[] Rent(int minimumLength)
-        {
-            ArgumentOutOfRangeException.ThrowIfNegative(minimumLength);
-            var length = GetAllocationLength(minimumLength);
-            byte[]? array = null;
-            lock (_gate)
-            {
-                if (length <= _maxArrayLength &&
-                    _cachedByBucket.TryGetValue(length, out var bucket) &&
-                    bucket.TryPop(out array))
-                {
-                    _cachedBytes -= (ulong)array.LongLength;
-                }
-
-                array ??= new byte[length];
-                _leases.Add(array);
-            }
-
-            return array;
-        }
-
-        public override void Return(byte[] array, bool clearArray = false)
-        {
-            ArgumentNullException.ThrowIfNull(array);
-            lock (_gate)
-            {
-                if (!_leases.Remove(array))
-                {
-                    return;
-                }
-            }
-
-            if (clearArray)
-            {
-                Array.Clear(array);
-            }
-
-            lock (_gate)
-            {
-                if (array.Length > _maxArrayLength ||
-                    !IsBucketLength(array.Length) ||
-                    (ulong)array.LongLength > _maxCachedBytes -
-                        Math.Min(_cachedBytes, _maxCachedBytes))
-                {
-                    return;
-                }
-
-                if (!_cachedByBucket.TryGetValue(array.Length, out var bucket))
-                {
-                    bucket = new Stack<byte[]>();
-                    _cachedByBucket.Add(array.Length, bucket);
-                }
-
-                if (bucket.Count >= _maxArraysPerBucket)
-                {
-                    return;
-                }
-
-                bucket.Push(array);
-                _cachedBytes += (ulong)array.LongLength;
-            }
-        }
-
-        public void Trim()
-        {
-            lock (_gate)
-            {
-                _cachedByBucket.Clear();
-                _cachedBytes = 0;
-            }
-        }
-
-        private int GetAllocationLength(int minimumLength)
-        {
-            if (minimumLength <= 16)
-            {
-                return 16;
-            }
-
-            if (minimumLength > _maxArrayLength)
-            {
-                return minimumLength;
-            }
-
-            return checked((int)BitOperations.RoundUpToPowerOf2((uint)minimumLength));
-        }
-
-        private static bool IsBucketLength(int length) =>
-            length >= 16 && (length & (length - 1)) == 0;
-    }
-}

src/SharpEmu.Libs/Gpu/GuestGpu.cs

@@ -1,7 +1,6 @@
 // Copyright (C) 2026 SharpEmu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-using SharpEmu.Libs.Gpu.Metal;
 using SharpEmu.Libs.Gpu.Vulkan;
 
 namespace SharpEmu.Libs.Gpu;
@@ -9,39 +8,11 @@ namespace SharpEmu.Libs.Gpu;
 /// <summary>
 /// Process-wide access point for the guest-GPU backend, mirroring HostPlatform for the
 /// host seam: static HLE export classes resolve the renderer through <see cref="Current"/>.
-/// Vulkan is the default everywhere; SHARPEMU_GPU_BACKEND=metal opts into the Metal
-/// backend (macOS only) while it is being brought up. macOS flips to Metal by default
-/// once the presenter reaches parity.
+/// Vulkan is the only backend today; Metal/DX12 slot in here.
 /// </summary>
 internal static class GuestGpu
 {
-    private static readonly Lazy<IGuestGpuBackend> Instance = new(Create);
+    private static readonly Lazy<IGuestGpuBackend> Instance = new(static () => new VulkanGuestGpuBackend());
 
     public static IGuestGpuBackend Current => Instance.Value;
-
-    private static IGuestGpuBackend Create()
-    {
-        var requested = Environment.GetEnvironmentVariable("SHARPEMU_GPU_BACKEND");
-        if (string.IsNullOrEmpty(requested) || requested.Equals("vulkan", StringComparison.OrdinalIgnoreCase))
-        {
-            return new VulkanGuestGpuBackend();
-        }
-
-        if (requested.Equals("metal", StringComparison.OrdinalIgnoreCase))
-        {
-            if (!OperatingSystem.IsMacOS())
-            {
-                Console.Error.WriteLine(
-                    "[LOADER][WARN] SHARPEMU_GPU_BACKEND=metal is only available on macOS; using Vulkan.");
-                return new VulkanGuestGpuBackend();
-            }
-
-            Console.Error.WriteLine("[LOADER][INFO] GPU backend: Metal (SHARPEMU_GPU_BACKEND).");
-            return new MetalGuestGpuBackend();
-        }
-
-        Console.Error.WriteLine(
-            $"[LOADER][WARN] Unknown SHARPEMU_GPU_BACKEND value '{requested}'; using Vulkan.");
-        return new VulkanGuestGpuBackend();
-    }
 }

src/SharpEmu.Libs/Gpu/GuestGpuTypes.cs

@@ -36,20 +36,6 @@ internal readonly record struct GuestSampler(
     uint Word2,
     uint Word3);
 
-/// <summary>Identity of a texture's content in a backend texture cache, keyed
-/// entirely on raw guest descriptor values; the AGC layer uses it to skip texel
-/// copies for content the backend already holds.</summary>
-internal readonly record struct TextureContentIdentity(
-    ulong Address,
-    uint Width,
-    uint Height,
-    uint Format,
-    uint NumberType,
-    uint DstSelect,
-    uint TileMode,
-    uint Pitch,
-    GuestSampler Sampler);
-
 internal sealed record GuestMemoryBuffer(
     ulong BaseAddress,
     byte[] Data,
@@ -136,22 +122,12 @@ internal readonly record struct GuestBlendState(
         WriteMask: 0xFu);
 }
 
-/// <summary>CB_BLEND_RED..ALPHA: the constant color referenced by the
-/// CONSTANT_COLOR / CONSTANT_ALPHA blend factors. One constant serves every
-/// render target of a draw; the hardware reset value is transparent black.</summary>
-internal readonly record struct GuestBlendConstant(
-    float Red,
-    float Green,
-    float Blue,
-    float Alpha);
-
 internal sealed record GuestRenderState(
     IReadOnlyList<GuestBlendState> Blends,
     GuestRect? Scissor,
     GuestViewport? Viewport,
     GuestRasterState Raster,
-    GuestDepthState Depth,
-    GuestBlendConstant BlendConstant = default)
+    GuestDepthState Depth)
 {
     public static GuestRenderState Default { get; } = new(
         [GuestBlendState.Default],

src/SharpEmu.Libs/Gpu/IGuestGpuBackend.cs

@@ -1,7 +1,6 @@
 // Copyright (C) 2026 SharpEmu Emulator Project
 // SPDX-License-Identifier: GPL-2.0-or-later
 
-using SharpEmu.HLE;
 using SharpEmu.ShaderCompiler;
 
 namespace SharpEmu.Libs.Gpu;
@@ -18,10 +17,6 @@ namespace SharpEmu.Libs.Gpu;
 /// </summary>
 internal interface IGuestGpuBackend
 {
-    /// <summary>Human-readable name of this backend ("Metal", "Vulkan"), shown in
-    /// the window title on macOS where either backend can run.</summary>
-    string BackendName { get; }
-
     /// <summary>Starts the presenter (window + device) once; safe to call repeatedly.</summary>
     void EnsureStarted(uint width, uint height);
 
@@ -193,70 +188,4 @@ internal interface IGuestGpuBackend
     /// the guest codes cross the seam and each backend maps them internally.
     /// </summary>
     bool TryGetRenderTargetOutputKind(uint dataFormat, uint numberType, out Gen5PixelOutputKind outputKind);
-
-    // Guest work ordering. AGC submissions execute on a single backend consumer in
-    // logical guest-queue order; sequences returned here are backend work tickets.
-    // A backend without a running presenter returns 0 from the Submit* methods and
-    // callers fall back to executing inline.
-
-    /// <summary>Scopes subsequent submissions on this thread to a named guest queue.</summary>
-    IDisposable EnterGuestQueue(string queueName, ulong submissionId);
-
-    /// <summary>Enqueues an action at its exact position in the current guest queue;
-    /// returns its work sequence, or 0 when nothing could be enqueued.</summary>
-    long SubmitOrderedGuestAction(Action action, string debugName);
-
-    /// <summary>Preserves sceAgcDcbWaitUntilSafeForRendering in queue order.</summary>
-    long SubmitOrderedGuestFlipWait(int videoOutHandle, int displayBufferIndex);
-
-    /// <summary>Blocks until the given work sequence completes; false on timeout,
-    /// close, or a non-positive sequence.</summary>
-    bool WaitForGuestWork(long workSequence, int timeoutMilliseconds = Timeout.Infinite);
-
-    /// <summary>Sequence currently executing on the guest-work consumer; diagnostics only.</summary>
-    long CurrentGuestWorkSequenceForDiagnostics { get; }
-
-    // Guest image lifecycle beyond presentation: CPU-visible seeding, writes, and
-    // extent queries the AGC layer uses to keep guest memory and backend images
-    // coherent. Addresses and formats are always raw guest values.
-
-    /// <summary>Whether the image exists on the backend or an already-queued upload
-    /// owns its initialization (a pending image may skip a duplicate upload but is
-    /// not yet a valid flip source).</summary>
-    bool IsGuestImageUploadKnown(ulong address, uint format, uint numberType);
-
-    /// <summary>True when the first draw into this address must seed the backend
-    /// image from guest memory (PS5 render targets alias guest memory, so
-    /// CPU-prefilled pixels are visible before the first draw).</summary>
-    bool GuestImageWantsInitialData(ulong address);
-
-    void ProvideGuestImageInitialData(ulong address, byte[] rgbaPixels);
-
-    void SubmitGuestImageFill(ulong address, uint fillValue);
-
-    void SubmitGuestImageWrite(ulong address, byte[] pixels);
-
-    bool TryGetGuestImageExtent(ulong address, out uint width, out uint height, out ulong byteCount);
-
-    IReadOnlyList<(ulong Address, uint Width, uint Height, ulong ByteCount)> GetGuestImageExtents();
-
-    /// <summary>Whether the backend's texture cache already holds this content; lets
-    /// the AGC layer skip copying texels out of guest memory on every draw.</summary>
-    bool IsTextureContentCached(in TextureContentIdentity identity);
-
-    /// <summary>Guest memory handle for backend self-healing (cache misses re-read
-    /// texels directly instead of showing a fallback pattern).</summary>
-    void AttachGuestMemory(ICpuMemory memory);
-
-    /// <summary>Alignment the AGC layer must apply to storage-buffer offsets before
-    /// they cross the seam.</summary>
-    ulong GuestStorageBufferOffsetAlignment { get; }
-
-    /// <summary>Counts a guest shader translation for the perf overlay.</summary>
-    void CountShaderCompilation();
-
-    (long Draws, double DrawMs, long Pipelines, long ShaderCompilations) ReadAndResetPerfCounters();
-
-    /// <summary>Asks a running presenter to close its window.</summary>
-    void RequestClose();
 }

src/SharpEmu.Libs/Gpu/Metal/MetalCompiledGuestShader.cs

@@ -1,28 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Text;
-using SharpEmu.ShaderCompiler.Metal;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-/// <summary>
-/// The Metal backend's compiled shader: MSL source plus the reflection data
-/// (<see cref="Gen5MslShader"/>) the presenter needs to create and bind pipeline
-/// states. The diagnostics payload is the source text — Metal has no portable
-/// binary form until an MTLBinaryArchive is introduced.
-/// </summary>
-internal sealed class MetalCompiledGuestShader(Gen5MslShader shader) : IGuestCompiledShader
-{
-    private byte[]? _payload;
-
-    public Gen5MslShader Shader { get; } = shader;
-
-    /// <summary>MTLLibrary handle cached by the presenter after the first
-    /// runtime compile; the render loop is its only reader and writer.</summary>
-    internal nint CachedLibrary;
-
-    public byte[] Payload => _payload ??= Encoding.UTF8.GetBytes(Shader.Source);
-
-    public string PayloadFileExtension => "msl";
-}

src/SharpEmu.Libs/Gpu/Metal/MetalGuestFormats.cs

@@ -1,270 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.ShaderCompiler;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-/// <summary>
-/// MTLPixelFormat raw values — only the formats the backend maps. Declared here
-/// rather than pulled from a binding package: the Metal backend talks to the OS
-/// exclusively through objc_msgSend, so ABI constants are owned locally.
-/// </summary>
-internal enum MtlPixelFormat : uint
-{
-    Invalid = 0,
-    R8Unorm = 10,
-    R8Snorm = 12,
-    R8Uint = 13,
-    R8Sint = 14,
-    R16Unorm = 20,
-    R16Snorm = 22,
-    R16Uint = 23,
-    R16Sint = 24,
-    R16Float = 25,
-    Rg8Unorm = 30,
-    Rg8Snorm = 32,
-    Rg8Uint = 33,
-    Rg8Sint = 34,
-    B5G6R5Unorm = 40,
-    R32Uint = 53,
-    R32Sint = 54,
-    R32Float = 55,
-    Rg16Unorm = 60,
-    Rg16Uint = 63,
-    Rg16Sint = 64,
-    Rg16Float = 65,
-    Rgba8Unorm = 70,
-    Rgba8UnormSrgb = 71,
-    Rgba8Uint = 73,
-    Rgba8Sint = 74,
-    Bgra8Unorm = 80,
-    Bgra8UnormSrgb = 81,
-    Rgb10A2Unorm = 90,
-    Rg11B10Float = 92,
-    Rgb9E5Float = 93,
-    Bgr10A2Unorm = 94,
-    Rg32Uint = 103,
-    Rg32Sint = 104,
-    Rg32Float = 105,
-    Rgba16Unorm = 110,
-    Rgba16Uint = 113,
-    Rgba16Sint = 114,
-    Rgba16Float = 115,
-    Rgba32Uint = 123,
-    Rgba32Sint = 124,
-    Rgba32Float = 125,
-    Bc1Rgba = 130,
-    Bc1RgbaSrgb = 131,
-    Bc2Rgba = 132,
-    Bc2RgbaSrgb = 133,
-    Bc3Rgba = 134,
-    Bc3RgbaSrgb = 135,
-    Bc4RUnorm = 140,
-    Bc4RSnorm = 141,
-    Bc5RgUnorm = 142,
-    Bc5RgSnorm = 143,
-    Bc6HRgbFloat = 150,
-    Bc6HRgbUfloat = 151,
-    Bc7RgbaUnorm = 152,
-    Bc7RgbaUnormSrgb = 153,
-    Depth32Float = 252,
-}
-
-/// <summary>A sampled-texture format: the Metal pixel format plus the byte
-/// layout the upload path needs. <see cref="BlockBytes"/> is nonzero for
-/// block-compressed formats (bytes per 4x4 block); otherwise
-/// <see cref="BytesPerPixel"/> applies.</summary>
-internal readonly record struct MetalTextureFormat(
-    MtlPixelFormat Format,
-    uint BytesPerPixel,
-    uint BlockBytes)
-{
-    public bool IsBlockCompressed => BlockBytes != 0;
-}
-
-internal readonly record struct MetalRenderTargetFormat(
-    MtlPixelFormat Format,
-    Gen5PixelOutputKind OutputKind)
-{
-    public static uint GetBytesPerPixel(MtlPixelFormat format) =>
-        format switch
-        {
-            MtlPixelFormat.R8Unorm or MtlPixelFormat.R8Uint => 1,
-            MtlPixelFormat.Rg8Unorm => 2,
-            MtlPixelFormat.Rg32Float => 8,
-            MtlPixelFormat.Rgba16Unorm or MtlPixelFormat.Rgba16Uint or
-                MtlPixelFormat.Rgba16Sint or MtlPixelFormat.Rgba16Float => 8,
-            MtlPixelFormat.Rgba32Float => 16,
-            _ => 4,
-        };
-}
-
-/// <summary>
-/// Guest texture-descriptor codes to Metal formats, mirroring the Vulkan
-/// backend's table case for case so both backends accept the same guest
-/// formats. Guest format 9 (2:10:10:10) maps to BGR10A2 — the bit layout that
-/// matches Vulkan's A2R10G10B10 pack.
-/// </summary>
-internal static class MetalGuestFormats
-{
-    /// <summary>Guest sampled-texture format to Metal, mirroring the Vulkan
-    /// backend's GetTextureFormat case for case (including its RGBA8 fallback
-    /// for unmapped codes, so unknown formats render something rather than
-    /// nothing). BC formats upload raw blocks — Mac-family GPUs decode them
-    /// natively.</summary>
-    public static MetalTextureFormat DecodeTextureFormat(uint dataFormat, uint numberType)
-    {
-        var format = (dataFormat, numberType) switch
-        {
-            (1, 0) => MtlPixelFormat.R8Unorm,
-            (1, 1) => MtlPixelFormat.R8Snorm,
-            (1, 4) => MtlPixelFormat.R8Uint,
-            (1, 5) => MtlPixelFormat.R8Sint,
-            (2, 0) => MtlPixelFormat.R16Unorm,
-            (2, 1) => MtlPixelFormat.R16Snorm,
-            (2, 4) => MtlPixelFormat.R16Uint,
-            (2, 5) => MtlPixelFormat.R16Sint,
-            (2, 7) => MtlPixelFormat.R16Float,
-            (3, 0) => MtlPixelFormat.Rg8Unorm,
-            (3, 1) => MtlPixelFormat.Rg8Snorm,
-            (3, 4) => MtlPixelFormat.Rg8Uint,
-            (3, 5) => MtlPixelFormat.Rg8Sint,
-            (4, 4) => MtlPixelFormat.R32Uint,
-            (4, 5) => MtlPixelFormat.R32Sint,
-            (4, 7) => MtlPixelFormat.R32Float,
-            (5, 0) => MtlPixelFormat.Rg16Unorm,
-            (5, 4) => MtlPixelFormat.Rg16Uint,
-            (5, 5) => MtlPixelFormat.Rg16Sint,
-            (5, 7) => MtlPixelFormat.Rg16Float,
-            (6, 7) or (7, 7) => MtlPixelFormat.Rg11B10Float,
-            (8, _) or (9, _) => MtlPixelFormat.Bgr10A2Unorm,
-            (10, 4) => MtlPixelFormat.Rgba8Uint,
-            (10, 5) => MtlPixelFormat.Rgba8Sint,
-            (10, 9) => MtlPixelFormat.Rgba8UnormSrgb,
-            (11, 4) => MtlPixelFormat.Rg32Uint,
-            (11, 5) => MtlPixelFormat.Rg32Sint,
-            (11, 7) => MtlPixelFormat.Rg32Float,
-            (12, 0) => MtlPixelFormat.Rgba16Unorm,
-            (12, 4) => MtlPixelFormat.Rgba16Uint,
-            (12, 5) => MtlPixelFormat.Rgba16Sint,
-            (12, 7) => MtlPixelFormat.Rgba16Float,
-            (13, 4) or (14, 4) => MtlPixelFormat.Rgba32Uint,
-            (13, 5) or (14, 5) => MtlPixelFormat.Rgba32Sint,
-            (13, _) or (14, _) => MtlPixelFormat.Rgba32Float,
-            (16, 0) => MtlPixelFormat.B5G6R5Unorm,
-            (34, 7) => MtlPixelFormat.Rgb9E5Float,
-            (169, _) => MtlPixelFormat.Bc1Rgba,
-            (170, _) => MtlPixelFormat.Bc1RgbaSrgb,
-            (171, _) => MtlPixelFormat.Bc2Rgba,
-            (172, _) => MtlPixelFormat.Bc2RgbaSrgb,
-            (173, _) => MtlPixelFormat.Bc3Rgba,
-            (174, _) => MtlPixelFormat.Bc3RgbaSrgb,
-            (175, 1) or (176, _) => MtlPixelFormat.Bc4RSnorm,
-            (175, _) => MtlPixelFormat.Bc4RUnorm,
-            (177, 1) or (178, _) => MtlPixelFormat.Bc5RgSnorm,
-            (177, _) => MtlPixelFormat.Bc5RgUnorm,
-            (179, _) => MtlPixelFormat.Bc6HRgbUfloat,
-            (180, _) => MtlPixelFormat.Bc6HRgbFloat,
-            (181, _) => MtlPixelFormat.Bc7RgbaUnorm,
-            (182, _) => MtlPixelFormat.Bc7RgbaUnormSrgb,
-            _ => MtlPixelFormat.Rgba8Unorm,
-        };
-
-        var blockBytes = format switch
-        {
-            MtlPixelFormat.Bc1Rgba or MtlPixelFormat.Bc1RgbaSrgb or
-                MtlPixelFormat.Bc4RUnorm or MtlPixelFormat.Bc4RSnorm => 8u,
-            MtlPixelFormat.Bc2Rgba or MtlPixelFormat.Bc2RgbaSrgb or
-                MtlPixelFormat.Bc3Rgba or MtlPixelFormat.Bc3RgbaSrgb or
-                MtlPixelFormat.Bc5RgUnorm or MtlPixelFormat.Bc5RgSnorm or
-                MtlPixelFormat.Bc6HRgbFloat or MtlPixelFormat.Bc6HRgbUfloat or
-                MtlPixelFormat.Bc7RgbaUnorm or MtlPixelFormat.Bc7RgbaUnormSrgb => 16u,
-            _ => 0u,
-        };
-
-        var bytesPerPixel = format switch
-        {
-            MtlPixelFormat.R8Unorm or MtlPixelFormat.R8Snorm or
-                MtlPixelFormat.R8Uint or MtlPixelFormat.R8Sint => 1u,
-            MtlPixelFormat.R16Unorm or MtlPixelFormat.R16Snorm or
-                MtlPixelFormat.R16Uint or MtlPixelFormat.R16Sint or
-                MtlPixelFormat.R16Float or MtlPixelFormat.Rg8Unorm or
-                MtlPixelFormat.Rg8Snorm or MtlPixelFormat.Rg8Uint or
-                MtlPixelFormat.Rg8Sint or MtlPixelFormat.B5G6R5Unorm => 2u,
-            MtlPixelFormat.Rg32Uint or MtlPixelFormat.Rg32Sint or
-                MtlPixelFormat.Rg32Float or MtlPixelFormat.Rgba16Unorm or
-                MtlPixelFormat.Rgba16Uint or MtlPixelFormat.Rgba16Sint or
-                MtlPixelFormat.Rgba16Float => 8u,
-            MtlPixelFormat.Rgba32Uint or MtlPixelFormat.Rgba32Sint or
-                MtlPixelFormat.Rgba32Float => 16u,
-            _ => 4u,
-        };
-
-        return new MetalTextureFormat(format, bytesPerPixel, blockBytes);
-    }
-
-    /// <summary>Source byte footprint of a sampled texture, block-aware —
-    /// the same math the AGC layer uses to size the texel copy it ships.</summary>
-    public static ulong GetTextureByteCount(in MetalTextureFormat format, uint width, uint height) =>
-        format.IsBlockCompressed
-            ? checked(((ulong)width + 3) / 4 * (((ulong)height + 3) / 4) * format.BlockBytes)
-            : checked((ulong)width * height * format.BytesPerPixel);
-
-    public static bool TryDecodeRenderTargetFormat(
-        uint dataFormat,
-        uint numberType,
-        out MetalRenderTargetFormat result)
-    {
-        var format = (dataFormat, numberType) switch
-        {
-            (4, 4) => MtlPixelFormat.R32Uint,
-            (4, 5) => MtlPixelFormat.R32Sint,
-            (4, 7) => MtlPixelFormat.R32Float,
-            (5, 4) => MtlPixelFormat.Rg16Uint,
-            (5, 5) => MtlPixelFormat.Rg16Sint,
-            (5, 7) => MtlPixelFormat.Rg16Float,
-            (6, 7) or (7, 7) => MtlPixelFormat.Rg11B10Float,
-            (9, _) => MtlPixelFormat.Bgr10A2Unorm,
-            (10, 4) => MtlPixelFormat.Rgba8Uint,
-            (10, 5) => MtlPixelFormat.Rgba8Sint,
-            (10, 9) => MtlPixelFormat.Rgba8UnormSrgb,
-            (10, _) => MtlPixelFormat.Rgba8Unorm,
-            (11, 7) => MtlPixelFormat.Rg32Float,
-            (12, 4) => MtlPixelFormat.Rgba16Uint,
-            (12, 5) => MtlPixelFormat.Rgba16Sint,
-            (12, 7) => MtlPixelFormat.Rgba16Float,
-            (13, 7) or (14, 7) => MtlPixelFormat.Rgba32Float,
-            (20, 0) => MtlPixelFormat.R32Uint,
-            (29, 0) or (4, 0) => MtlPixelFormat.R32Float,
-            (1, 0) or (36, 0) => MtlPixelFormat.R8Unorm,
-            (49, 0) => MtlPixelFormat.R8Uint,
-            (3, 0) => MtlPixelFormat.Rg8Unorm,
-            (5, 0) => MtlPixelFormat.Rg16Unorm,
-            (7, 0) => MtlPixelFormat.Rg11B10Float,
-            (12, 0) => MtlPixelFormat.Rgba16Unorm,
-            (13, 0) or (14, 0) => MtlPixelFormat.Rgba32Float,
-            (22, 0) or (71, 0) => MtlPixelFormat.Rgba16Float,
-            (56, 0) or (62, 0) or (64, 0) => MtlPixelFormat.Rgba8Unorm,
-            (75, 0) => MtlPixelFormat.Rg32Float,
-            _ => MtlPixelFormat.Invalid,
-        };
-
-        if (format == MtlPixelFormat.Invalid)
-        {
-            result = default;
-            return false;
-        }
-
-        var outputKind = format switch
-        {
-            MtlPixelFormat.R8Uint or MtlPixelFormat.R32Uint or MtlPixelFormat.Rg16Uint or
-                MtlPixelFormat.Rgba8Uint or MtlPixelFormat.Rgba16Uint => Gen5PixelOutputKind.Uint,
-            MtlPixelFormat.R32Sint or MtlPixelFormat.Rg16Sint or MtlPixelFormat.Rgba8Sint or
-                MtlPixelFormat.Rgba16Sint => Gen5PixelOutputKind.Sint,
-            _ => Gen5PixelOutputKind.Float,
-        };
-        result = new MetalRenderTargetFormat(format, outputKind);
-        return true;
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalGuestGpuBackend.cs

@@ -1,426 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.ShaderCompiler;
-using SharpEmu.ShaderCompiler.Metal;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-/// <summary>
-/// Metal backend for the guest-GPU seam: MSL codegen via
-/// SharpEmu.ShaderCompiler.Metal, rendering via the Metal presenter — the full
-/// surface (presentation, guest images, ordered flips, translated draws, and
-/// compute) with no Vulkan, MoltenVK, or windowing-library dependency.
-/// </summary>
-internal sealed class MetalGuestGpuBackend : IGuestGpuBackend
-{
-    public string BackendName => "Metal";
-
-    private static readonly IGuestCompiledShader DepthOnlyFragmentShader =
-        new MetalCompiledGuestShader(new Gen5MslShader(
-            MslFixedShaders.CreateDepthOnlyFragment(),
-            "depth_only_fs",
-            Gen5MslStage.Pixel,
-            [],
-            [],
-            AttributeCount: 0,
-            []));
-
-    public bool TryCompileVertexShader(
-        Gen5ShaderState state,
-        Gen5ShaderEvaluation evaluation,
-        out IGuestCompiledShader? shader,
-        out string error,
-        int globalBufferBase = 0,
-        int totalGlobalBufferCount = -1,
-        int imageBindingBase = 0,
-        int scalarRegisterBufferIndex = -1,
-        int requiredVertexOutputCount = 0,
-        ulong storageBufferOffsetAlignment = 1)
-    {
-        shader = null;
-        if (!Gen5MslTranslator.TryCompileVertexShader(
-                state,
-                evaluation,
-                out var compiled,
-                out error,
-                globalBufferBase,
-                totalGlobalBufferCount,
-                imageBindingBase,
-                scalarRegisterBufferIndex,
-                requiredVertexOutputCount,
-                storageBufferOffsetAlignment))
-        {
-            return false;
-        }
-
-        shader = new MetalCompiledGuestShader(compiled);
-        return true;
-    }
-
-    public bool TryCompilePixelShader(
-        Gen5ShaderState state,
-        Gen5ShaderEvaluation evaluation,
-        IReadOnlyList<Gen5PixelOutputBinding> outputs,
-        out IGuestCompiledShader? shader,
-        out string error,
-        int globalBufferBase = 0,
-        int totalGlobalBufferCount = -1,
-        int imageBindingBase = 0,
-        int scalarRegisterBufferIndex = -1,
-        uint pixelInputEnable = 0,
-        uint pixelInputAddress = 0,
-        ulong storageBufferOffsetAlignment = 1)
-    {
-        shader = null;
-        if (!Gen5MslTranslator.TryCompilePixelShader(
-                state,
-                evaluation,
-                outputs,
-                out var compiled,
-                out error,
-                globalBufferBase,
-                totalGlobalBufferCount,
-                imageBindingBase,
-                scalarRegisterBufferIndex,
-                pixelInputEnable,
-                pixelInputAddress,
-                storageBufferOffsetAlignment))
-        {
-            return false;
-        }
-
-        shader = new MetalCompiledGuestShader(compiled);
-        return true;
-    }
-
-    public bool TryCompileComputeShader(
-        Gen5ShaderState state,
-        Gen5ShaderEvaluation evaluation,
-        uint localSizeX,
-        uint localSizeY,
-        uint localSizeZ,
-        out IGuestCompiledShader? shader,
-        out string error,
-        int totalGlobalBufferCount = -1,
-        int initialScalarBufferIndex = -1,
-        uint waveLaneCount = 32,
-        ulong storageBufferOffsetAlignment = 1)
-    {
-        shader = null;
-        // Wave64 compute is emulated by the translator: cross-lane ops bridge
-        // the two 32-wide Apple simdgroups of a guest wave through threadgroup
-        // scratch, and wave-agnostic kernels run per-thread unchanged.
-        if (!Gen5MslTranslator.TryCompileComputeShader(
-                state,
-                evaluation,
-                localSizeX,
-                localSizeY,
-                localSizeZ,
-                out var compiled,
-                out error,
-                totalGlobalBufferCount,
-                initialScalarBufferIndex,
-                waveLaneCount,
-                storageBufferOffsetAlignment))
-        {
-            return false;
-        }
-
-        shader = new MetalCompiledGuestShader(compiled);
-        return true;
-    }
-
-    public IGuestCompiledShader GetDepthOnlyFragmentShader() =>
-        DepthOnlyFragmentShader;
-
-    public bool TryGetRenderTargetOutputKind(uint dataFormat, uint numberType, out Gen5PixelOutputKind outputKind)
-    {
-        if (MetalGuestFormats.TryDecodeRenderTargetFormat(dataFormat, numberType, out var format))
-        {
-            outputKind = format.OutputKind;
-            return true;
-        }
-
-        outputKind = default;
-        return false;
-    }
-
-    public void EnsureStarted(uint width, uint height) =>
-        MetalVideoPresenter.EnsureStarted(width, height);
-
-    public void HideSplashScreen() =>
-        MetalVideoPresenter.HideSplashScreen();
-
-    public void Submit(byte[] bgraFrame, uint width, uint height) =>
-        MetalVideoPresenter.Submit(bgraFrame, width, height);
-
-    public bool TrySubmitGuestImage(
-        ulong address,
-        uint width,
-        uint height,
-        uint pitchInPixel) =>
-        MetalVideoPresenter.TrySubmitGuestImage(address, width, height, pitchInPixel);
-
-    public bool TrySubmitOrderedGuestImageFlip(
-        int videoOutHandle,
-        int displayBufferIndex,
-        ulong address,
-        uint width,
-        uint height,
-        uint pitchInPixel) =>
-        MetalVideoPresenter.TrySubmitOrderedGuestImageFlip(
-            videoOutHandle,
-            displayBufferIndex,
-            address,
-            width,
-            height,
-            pitchInPixel);
-
-    public void RegisterKnownDisplayBuffer(ulong address, uint guestFormat) =>
-        MetalVideoPresenter.RegisterKnownDisplayBuffer(address, guestFormat);
-
-    public bool IsGpuGuestImageAvailable(ulong address, uint format, uint numberType) =>
-        MetalVideoPresenter.IsGuestImageAvailable(address, format, numberType);
-
-    public bool TrySubmitGuestImageBlit(
-        ulong sourceAddress,
-        uint sourceWidth,
-        uint sourceHeight,
-        uint sourceFormat,
-        uint sourceNumberType,
-        ulong destinationAddress,
-        uint destinationWidth,
-        uint destinationHeight,
-        uint destinationFormat,
-        uint destinationNumberType) =>
-        MetalVideoPresenter.TrySubmitGuestImageBlit(
-            sourceAddress,
-            sourceWidth,
-            sourceHeight,
-            sourceFormat,
-            sourceNumberType,
-            destinationAddress,
-            destinationWidth,
-            destinationHeight,
-            destinationFormat,
-            destinationNumberType);
-
-    public void SubmitGuestDraw(GuestDrawKind drawKind, uint width, uint height) =>
-        MetalVideoPresenter.SubmitGuestDraw(drawKind, width, height);
-
-    public void SubmitTranslatedDraw(
-        IGuestCompiledShader pixelShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint width,
-        uint height,
-        uint attributeCount,
-        IGuestCompiledShader? vertexShader = null,
-        uint vertexCount = 3,
-        uint instanceCount = 1,
-        uint primitiveType = 4,
-        GuestIndexBuffer? indexBuffer = null,
-        IReadOnlyList<GuestVertexBuffer>? vertexBuffers = null,
-        GuestRenderState? renderState = null) =>
-        MetalVideoPresenter.SubmitTranslatedDraw(
-            Msl(pixelShader),
-            textures,
-            globalMemoryBuffers,
-            width,
-            height,
-            attributeCount,
-            vertexShader is null ? null : Msl(vertexShader),
-            vertexCount,
-            instanceCount,
-            primitiveType,
-            indexBuffer,
-            vertexBuffers,
-            renderState);
-
-    public void SubmitDepthOnlyTranslatedDraw(
-        IGuestCompiledShader pixelShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint attributeCount,
-        GuestDepthTarget depthTarget,
-        IGuestCompiledShader? vertexShader = null,
-        uint vertexCount = 3,
-        uint instanceCount = 1,
-        uint primitiveType = 4,
-        GuestIndexBuffer? indexBuffer = null,
-        IReadOnlyList<GuestVertexBuffer>? vertexBuffers = null,
-        GuestRenderState? renderState = null,
-        ulong shaderAddress = 0) =>
-        MetalVideoPresenter.SubmitDepthOnlyTranslatedDraw(
-            Msl(pixelShader),
-            textures,
-            globalMemoryBuffers,
-            attributeCount,
-            depthTarget,
-            vertexShader is null ? null : Msl(vertexShader),
-            vertexCount,
-            instanceCount,
-            primitiveType,
-            indexBuffer,
-            vertexBuffers,
-            renderState,
-            shaderAddress);
-
-    public void SubmitOffscreenTranslatedDraw(
-        IGuestCompiledShader pixelShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint attributeCount,
-        IReadOnlyList<GuestRenderTarget> targets,
-        IGuestCompiledShader? vertexShader = null,
-        uint vertexCount = 3,
-        uint instanceCount = 1,
-        uint primitiveType = 4,
-        GuestIndexBuffer? indexBuffer = null,
-        IReadOnlyList<GuestVertexBuffer>? vertexBuffers = null,
-        GuestRenderState? renderState = null,
-        GuestDepthTarget? depthTarget = null,
-        ulong shaderAddress = 0) =>
-        MetalVideoPresenter.SubmitOffscreenTranslatedDraw(
-            Msl(pixelShader),
-            textures,
-            globalMemoryBuffers,
-            attributeCount,
-            targets,
-            vertexShader is null ? null : Msl(vertexShader),
-            vertexCount,
-            instanceCount,
-            primitiveType,
-            indexBuffer,
-            vertexBuffers,
-            renderState,
-            depthTarget,
-            shaderAddress);
-
-    public void SubmitStorageTranslatedDraw(
-        IGuestCompiledShader pixelShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint attributeCount,
-        uint width,
-        uint height,
-        ulong shaderAddress = 0) =>
-        MetalVideoPresenter.SubmitStorageTranslatedDraw(
-            Msl(pixelShader),
-            textures,
-            globalMemoryBuffers,
-            attributeCount,
-            width,
-            height,
-            shaderAddress);
-
-    private static MetalCompiledGuestShader Msl(IGuestCompiledShader shader) =>
-        shader as MetalCompiledGuestShader ??
-        throw new InvalidOperationException(
-            $"shader handle of type {shader.GetType().Name} was not compiled by the Metal backend");
-
-    public long SubmitComputeDispatch(
-        ulong shaderAddress,
-        IGuestCompiledShader computeShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint groupCountX,
-        uint groupCountY,
-        uint groupCountZ,
-        uint baseGroupX,
-        uint baseGroupY,
-        uint baseGroupZ,
-        uint localSizeX,
-        uint localSizeY,
-        uint localSizeZ,
-        bool isIndirect,
-        bool writesGlobalMemory,
-        uint threadCountX = uint.MaxValue,
-        uint threadCountY = uint.MaxValue,
-        uint threadCountZ = uint.MaxValue)
-    {
-        // The translated kernel bakes its threadgroup size; localSize and
-        // isIndirect are already folded in by the AGC layer before submission.
-        _ = localSizeX;
-        _ = localSizeY;
-        _ = localSizeZ;
-        _ = isIndirect;
-        return MetalVideoPresenter.SubmitComputeDispatch(
-            shaderAddress,
-            Msl(computeShader),
-            textures,
-            globalMemoryBuffers,
-            groupCountX,
-            groupCountY,
-            groupCountZ,
-            baseGroupX,
-            baseGroupY,
-            baseGroupZ,
-            writesGlobalMemory,
-            threadCountX,
-            threadCountY,
-            threadCountZ);
-    }
-
-    private long _perfShaderCompilations;
-
-    public IDisposable EnterGuestQueue(string queueName, ulong submissionId) =>
-        MetalVideoPresenter.EnterGuestQueue(queueName, submissionId);
-
-    public long SubmitOrderedGuestAction(Action action, string debugName) =>
-        MetalVideoPresenter.SubmitOrderedGuestAction(action, debugName);
-
-    public long SubmitOrderedGuestFlipWait(int videoOutHandle, int displayBufferIndex) =>
-        MetalVideoPresenter.SubmitOrderedGuestFlipWait(videoOutHandle, displayBufferIndex);
-
-    public bool WaitForGuestWork(long workSequence, int timeoutMilliseconds = Timeout.Infinite) =>
-        MetalVideoPresenter.WaitForGuestWork(workSequence, timeoutMilliseconds);
-
-    public long CurrentGuestWorkSequenceForDiagnostics =>
-        MetalVideoPresenter.CurrentGuestWorkSequenceForDiagnostics;
-
-    public bool IsGuestImageUploadKnown(ulong address, uint format, uint numberType) =>
-        MetalVideoPresenter.IsGuestImageUploadKnown(address, format, numberType);
-
-    public bool GuestImageWantsInitialData(ulong address) =>
-        MetalVideoPresenter.GuestImageWantsInitialData(address);
-
-    public void ProvideGuestImageInitialData(ulong address, byte[] rgbaPixels) =>
-        MetalVideoPresenter.ProvideGuestImageInitialData(address, rgbaPixels);
-
-    public void SubmitGuestImageFill(ulong address, uint fillValue) =>
-        MetalVideoPresenter.SubmitGuestImageFill(address, fillValue);
-
-    public void SubmitGuestImageWrite(ulong address, byte[] pixels) =>
-        MetalVideoPresenter.SubmitGuestImageWrite(address, pixels);
-
-    public bool TryGetGuestImageExtent(ulong address, out uint width, out uint height, out ulong byteCount) =>
-        MetalVideoPresenter.TryGetGuestImageExtent(address, out width, out height, out byteCount);
-
-    public IReadOnlyList<(ulong Address, uint Width, uint Height, ulong ByteCount)> GetGuestImageExtents() =>
-        MetalVideoPresenter.GetGuestImageExtents();
-
-    public bool IsTextureContentCached(in TextureContentIdentity identity) =>
-        MetalVideoPresenter.IsTextureContentCached(identity);
-
-    public void AttachGuestMemory(SharpEmu.HLE.ICpuMemory memory) =>
-        MetalVideoPresenter.AttachGuestMemory(memory);
-
-    // Over-alignment is always valid, and 256 covers every Metal buffer-offset
-    // requirement (Intel Macs need 256 for constant buffers; Apple GPUs less).
-    public ulong GuestStorageBufferOffsetAlignment => 256;
-
-    public void CountShaderCompilation() =>
-        Interlocked.Increment(ref _perfShaderCompilations);
-
-    public (long Draws, double DrawMs, long Pipelines, long ShaderCompilations) ReadAndResetPerfCounters()
-    {
-        var (draws, drawMs, pipelines) = MetalVideoPresenter.ReadAndResetDrawPerfCounters();
-        return (draws, drawMs, pipelines, Interlocked.Exchange(ref _perfShaderCompilations, 0));
-    }
-
-    public void RequestClose() =>
-        MetalVideoPresenter.RequestClose();
-
-}

src/SharpEmu.Libs/Gpu/Metal/MetalHostInput.cs

@@ -1,182 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.HLE.Host;
-using SharpEmu.HLE.Host.Posix;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-/// <summary>
-/// Keyboard state sampled from the Metal presenter's window, feeding the POSIX
-/// host input seam so pad emulation works like the Vulkan presenter's
-/// HostWindowInput. Key events arrive on the AppKit main thread as macOS
-/// virtual key codes; pad reads happen on guest threads, so state is guarded.
-/// Window gamepads are not surfaced by AppKit — controller support would go
-/// through GameController.framework and is out of scope here.
-/// </summary>
-internal static class MetalHostInput
-{
-    private static readonly object Gate = new();
-    private static readonly HashSet<ushort> Pressed = new();
-    private static volatile bool _connected;
-
-    /// <summary>Registers this window's keyboard as the host input source.</summary>
-    public static void Attach()
-    {
-        _connected = true;
-        PosixHostInput.SetSource(new MetalWindowInputSource());
-        Console.Error.WriteLine("[LOADER][INFO] Window keyboard input attached for pad emulation.");
-    }
-
-    // Debug automation: SHARPEMU_METAL_AUTOKEY="12:0x24,15:0x24" presses the
-    // macOS key code at each elapsed-seconds mark for a few frames, letting
-    // headless test runs navigate menus without a human at the keyboard.
-    private static readonly List<(double At, ushort Key, bool[] State)> _autoKeys = ParseAutoKeys();
-    private static readonly System.Diagnostics.Stopwatch _autoKeyClock =
-        System.Diagnostics.Stopwatch.StartNew();
-
-    private static List<(double, ushort, bool[])> ParseAutoKeys()
-    {
-        var keys = new List<(double, ushort, bool[])>();
-        var spec = Environment.GetEnvironmentVariable("SHARPEMU_METAL_AUTOKEY");
-        if (string.IsNullOrWhiteSpace(spec))
-        {
-            return keys;
-        }
-
-        foreach (var entry in spec.Split(',', StringSplitOptions.RemoveEmptyEntries))
-        {
-            var parts = entry.Split(':');
-            if (parts.Length == 2 &&
-                double.TryParse(parts[0], out var at) &&
-                TryParseKeyCode(parts[1], out var key))
-            {
-                keys.Add((at, key, new bool[2]));
-            }
-        }
-
-        return keys;
-    }
-
-    private static bool TryParseKeyCode(string text, out ushort key)
-    {
-        return text.StartsWith("0x", StringComparison.OrdinalIgnoreCase)
-            ? ushort.TryParse(text[2..], System.Globalization.NumberStyles.HexNumber, null, out key)
-            : ushort.TryParse(text, out key);
-    }
-
-    /// <summary>Called once per render frame; fires and releases scripted keys.</summary>
-    public static void PumpAutoKeys()
-    {
-        if (_autoKeys.Count == 0)
-        {
-            return;
-        }
-
-        var elapsed = _autoKeyClock.Elapsed.TotalSeconds;
-        foreach (var (at, key, state) in _autoKeys)
-        {
-            if (!state[0] && elapsed >= at)
-            {
-                state[0] = true;
-                KeyDown(key, isRepeat: false);
-                Console.Error.WriteLine($"[LOADER][INFO] Metal autokey press 0x{key:X} at {elapsed:F1}s");
-            }
-            else if (state[0] && !state[1] && elapsed >= at + 0.2)
-            {
-                state[1] = true;
-                KeyUp(key);
-            }
-        }
-    }
-
-    public static void KeyDown(ushort keyCode, bool isRepeat)
-    {
-        // kVK_F1: parity with the Vulkan window's perf-overlay toggle.
-        if (keyCode == 0x7A && !isRepeat)
-        {
-            VideoOut.PerfOverlay.Toggle();
-        }
-
-        lock (Gate)
-        {
-            Pressed.Add(keyCode);
-        }
-    }
-
-    public static void KeyUp(ushort keyCode)
-    {
-        lock (Gate)
-        {
-            Pressed.Remove(keyCode);
-        }
-    }
-
-    private static bool IsKeyCodeDown(ushort keyCode)
-    {
-        lock (Gate)
-        {
-            return Pressed.Contains(keyCode);
-        }
-    }
-
-    private sealed class MetalWindowInputSource : IPosixWindowInputSource
-    {
-        public bool HasKeyboardFocus => _connected;
-
-        public bool IsKeyDown(int virtualKey) =>
-            TryMapVirtualKey(virtualKey, out var keyCode) && IsKeyCodeDown(keyCode);
-
-        public int GetGamepadStates(Span<HostGamepadState> destination) => 0;
-
-        public string? DescribeConnectedGamepad() => null;
-    }
-
-    /// <summary>Windows virtual-key semantics (the seam's contract) to macOS
-    /// kVK virtual key codes, covering the keys pad emulation polls.</summary>
-    private static bool TryMapVirtualKey(int vk, out ushort keyCode)
-    {
-        keyCode = vk switch
-        {
-            0x08 => 0x33, // Backspace -> kVK_Delete
-            0x09 => 0x30, // Tab
-            0x0D => 0x24, // Enter -> kVK_Return
-            0x1B => 0x35, // Escape
-            0x20 => 0x31, // Space
-            0x25 => 0x7B, // Left
-            0x26 => 0x7E, // Up
-            0x27 => 0x7C, // Right
-            0x28 => 0x7D, // Down
-            // Letters: macOS ANSI key codes are layout-position based and
-            // non-contiguous, so map each polled letter explicitly.
-            0x41 => 0x00, // A
-            0x42 => 0x0B, // B
-            0x43 => 0x08, // C
-            0x44 => 0x02, // D
-            0x45 => 0x0E, // E
-            0x46 => 0x03, // F
-            0x47 => 0x05, // G
-            0x48 => 0x04, // H
-            0x49 => 0x22, // I
-            0x4A => 0x26, // J
-            0x4B => 0x28, // K
-            0x4C => 0x25, // L
-            0x4D => 0x2E, // M
-            0x4E => 0x2D, // N
-            0x4F => 0x1F, // O
-            0x50 => 0x23, // P
-            0x51 => 0x0C, // Q
-            0x52 => 0x0F, // R
-            0x53 => 0x01, // S
-            0x54 => 0x11, // T
-            0x55 => 0x20, // U
-            0x56 => 0x09, // V
-            0x57 => 0x0D, // W
-            0x58 => 0x07, // X
-            0x59 => 0x10, // Y
-            0x5A => 0x06, // Z
-            _ => ushort.MaxValue,
-        };
-        return keyCode != ushort.MaxValue;
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalNative.cs

@@ -1,430 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Runtime.InteropServices;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Core Graphics / Metal ABI structs passed by value through objc_msgSend. Struct
-// *returns* are deliberately never used: on x86-64 (this process runs under Rosetta
-// on Apple silicon) large struct returns switch to objc_msgSend_stret, and avoiding
-// them entirely keeps one calling convention everywhere.
-[StructLayout(LayoutKind.Sequential)]
-internal struct CGRect
-{
-    public double X;
-    public double Y;
-    public double Width;
-    public double Height;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct CGSize
-{
-    public double Width;
-    public double Height;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlClearColor
-{
-    public double Red;
-    public double Green;
-    public double Blue;
-    public double Alpha;
-}
-
-/// <summary>MTLTextureSwizzleChannels: one MTLTextureSwizzle byte per output
-/// channel (Zero=0, One=1, Red=2, Green=3, Blue=4, Alpha=5).</summary>
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlTextureSwizzleChannels
-{
-    public byte Red;
-    public byte Green;
-    public byte Blue;
-    public byte Alpha;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlRegion
-{
-    public nuint X;
-    public nuint Y;
-    public nuint Z;
-    public nuint Width;
-    public nuint Height;
-    public nuint Depth;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlSize
-{
-    public nuint Width;
-    public nuint Height;
-    public nuint Depth;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlOrigin
-{
-    public nuint X;
-    public nuint Y;
-    public nuint Z;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlScissorRect
-{
-    public nuint X;
-    public nuint Y;
-    public nuint Width;
-    public nuint Height;
-}
-
-[StructLayout(LayoutKind.Sequential)]
-internal struct MtlViewport
-{
-    public double OriginX;
-    public double OriginY;
-    public double Width;
-    public double Height;
-    public double ZNear;
-    public double ZFar;
-}
-
-/// <summary>
-/// Objective-C runtime access for the Metal presenter: AppKit, QuartzCore, and Metal
-/// through objc_msgSend, with one LibraryImport overload per distinct native
-/// signature. Dependency-free by design — this plus the OS frameworks is the entire
-/// Metal path, which is what keeps it NativeAOT-clean.
-/// </summary>
-internal static partial class MetalNative
-{
-    private const string CoreFoundation =
-        "/System/Library/Frameworks/CoreFoundation.framework/CoreFoundation";
-
-    [LibraryImport(CoreFoundation)]
-    public static partial nint CFRunLoopGetMain();
-
-    [LibraryImport(CoreFoundation)]
-    public static partial void CFRunLoopStop(nint runLoop);
-
-    private const string ObjCLibrary = "/usr/lib/libobjc.A.dylib";
-    private const string MetalFramework = "/System/Library/Frameworks/Metal.framework/Metal";
-    private const string AppKitFramework = "/System/Library/Frameworks/AppKit.framework/AppKit";
-    private const string QuartzCoreFramework = "/System/Library/Frameworks/QuartzCore.framework/QuartzCore";
-
-    private static bool _frameworksLoaded;
-
-    /// <summary>
-    /// Makes the AppKit and QuartzCore classes visible to objc_getClass; Metal is
-    /// pulled in by its own LibraryImport. Call once before any Class() lookup.
-    /// </summary>
-    public static void EnsureFrameworksLoaded()
-    {
-        if (_frameworksLoaded)
-        {
-            return;
-        }
-
-        NativeLibrary.Load(AppKitFramework);
-        NativeLibrary.Load(QuartzCoreFramework);
-        _frameworksLoaded = true;
-    }
-
-    [LibraryImport(MetalFramework)]
-    public static partial nint MTLCreateSystemDefaultDevice();
-
-    [LibraryImport(ObjCLibrary, StringMarshalling = StringMarshalling.Utf8)]
-    private static partial nint objc_getClass(string name);
-
-    [LibraryImport(ObjCLibrary, StringMarshalling = StringMarshalling.Utf8)]
-    private static partial nint sel_registerName(string name);
-
-    [LibraryImport(ObjCLibrary, StringMarshalling = StringMarshalling.Utf8)]
-    public static partial nint objc_allocateClassPair(nint superclass, string name, nuint extraBytes);
-
-    [LibraryImport(ObjCLibrary)]
-    public static partial void objc_registerClassPair(nint cls);
-
-    [LibraryImport(ObjCLibrary, StringMarshalling = StringMarshalling.Utf8)]
-    [return: MarshalAs(UnmanagedType.I1)]
-    public static partial bool class_addMethod(nint cls, nint name, nint imp, string types);
-
-    [LibraryImport(ObjCLibrary)]
-    public static partial nint objc_autoreleasePoolPush();
-
-    [LibraryImport(ObjCLibrary)]
-    public static partial void objc_autoreleasePoolPop(nint pool);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint Send(nint receiver, nint selector);
-
-    /// <summary>objc_msgSend for -gpuResourceID. MTLResourceID is a one-field
-    /// 8-byte struct, returned in a register on the x86-64 ABI, so it maps to a
-    /// ulong return — the value written into a Tier 2 argument buffer slot.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial ulong SendGpuResourceId(nint receiver, nint selector);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint Send(nint receiver, nint selector, nint argument);
-
-
-    /// <summary>objc_msgSend for a CGRect-returning selector (e.g. -bounds).
-    /// A 32-byte struct is returned via the x86-64 stret ABI — a hidden
-    /// pointer to caller storage passed ahead of self/_cmd — so this must not
-    /// be folded into the plain objc_msgSend overloads.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend_stret")]
-    public static partial void SendStretRect(out CGRect result, nint receiver, nint selector);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint Send(nint receiver, nint selector, nint argument, ref nint error);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint Send(nint receiver, nint selector, nint argument0, nint argument1, ref nint error);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendAtIndex(nint receiver, nint selector, nuint index);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    [return: MarshalAs(UnmanagedType.I1)]
-    public static partial bool SendBool(nint receiver, nint selector);
-
-    /// <summary>One-argument BOOL sends, e.g. respondsToSelector:.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    [return: MarshalAs(UnmanagedType.I1)]
-    public static partial bool SendBool(nint receiver, nint selector, nint argument);
-
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial double SendDouble(nint receiver, nint selector);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoid(nint receiver, nint selector);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoid(nint receiver, nint selector, nint argument);
-
-    /// <summary>Two-object-argument void sends, e.g. setObject:forKey:.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoid(nint receiver, nint selector, nint argument0, nint argument1);
-
-    /// <summary>performSelectorOnMainThread:withObject:waitUntilDone: — the SEL
-    /// to perform is itself an argument, followed by the object and the wait
-    /// flag.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidPerformSelector(
-        nint receiver,
-        nint selector,
-        nint performedSelector,
-        nint argument,
-        [MarshalAs(UnmanagedType.I1)] bool waitUntilDone);
-
-    /// <summary>setSwizzle: on MTLTextureDescriptor. Four one-byte
-    /// MTLTextureSwizzle values, passed packed like the framework expects.</summary>
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidSwizzle(
-        nint receiver,
-        nint selector,
-        MtlTextureSwizzleChannels channels);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidBool(nint receiver, nint selector, [MarshalAs(UnmanagedType.I1)] bool argument);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidDouble(nint receiver, nint selector, double argument);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidSize(nint receiver, nint selector, CGSize size);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidRect(nint receiver, nint selector, CGRect rect);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidClearColor(nint receiver, nint selector, MtlClearColor color);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidBlendColor(
-        nint receiver,
-        nint selector,
-        float red,
-        float green,
-        float blue,
-        float alpha);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidViewport(nint receiver, nint selector, MtlViewport viewport);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendSetAtIndex(nint receiver, nint selector, nint value, nuint index);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidCopyTexture(nint receiver, nint selector, nint source, nint destination);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendBuffer(nint receiver, nint selector, nint bytes, nuint length, nuint options);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendNewBuffer(nint receiver, nint selector, nuint length, nuint options);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendCopyTextureToBuffer(
-        nint receiver,
-        nint selector,
-        nint sourceTexture,
-        nuint sourceSlice,
-        nuint sourceLevel,
-        MtlOrigin sourceOrigin,
-        MtlSize sourceSize,
-        nint destinationBuffer,
-        nuint destinationOffset,
-        nuint destinationBytesPerRow,
-        nuint destinationBytesPerImage);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendCopyBufferToTexture(
-        nint receiver,
-        nint selector,
-        nint sourceBuffer,
-        nuint sourceOffset,
-        nuint sourceBytesPerRow,
-        nuint sourceBytesPerImage,
-        MtlSize sourceSize,
-        nint destinationTexture,
-        nuint destinationSlice,
-        nuint destinationLevel,
-        MtlOrigin destinationOrigin);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendDispatch(
-        nint receiver,
-        nint selector,
-        MtlSize threadgroups,
-        MtlSize threadsPerThreadgroup);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendSetBuffer(nint receiver, nint selector, nint buffer, nuint offset, nuint index);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendVoidScissor(nint receiver, nint selector, MtlScissorRect rect);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendDrawPrimitivesInstanced(
-        nint receiver,
-        nint selector,
-        nuint primitiveType,
-        nuint vertexStart,
-        nuint vertexCount,
-        nuint instanceCount);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendDrawIndexedPrimitives(
-        nint receiver,
-        nint selector,
-        nuint primitiveType,
-        nuint indexCount,
-        nuint indexType,
-        nint indexBuffer,
-        nuint indexBufferOffset,
-        nuint instanceCount);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendTimer(
-        nint receiver,
-        nint selector,
-        double interval,
-        nint target,
-        nint timerSelector,
-        nint userInfo,
-        [MarshalAs(UnmanagedType.I1)] bool repeats);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendInitFrame(nint receiver, nint selector, CGRect frame);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendInitWindow(
-        nint receiver,
-        nint selector,
-        CGRect contentRect,
-        nuint styleMask,
-        nuint backing,
-        [MarshalAs(UnmanagedType.I1)] bool defer);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendNextEvent(
-        nint receiver,
-        nint selector,
-        ulong eventMask,
-        nint untilDate,
-        nint inMode,
-        [MarshalAs(UnmanagedType.I1)] bool dequeue);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial nint SendTextureDescriptor(
-        nint receiver,
-        nint selector,
-        nuint pixelFormat,
-        nuint width,
-        nuint height,
-        [MarshalAs(UnmanagedType.I1)] bool mipmapped);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendReplaceRegion(
-        nint receiver,
-        nint selector,
-        MtlRegion region,
-        nuint mipmapLevel,
-        nint bytes,
-        nuint bytesPerRow);
-
-    [LibraryImport(ObjCLibrary, EntryPoint = "objc_msgSend")]
-    public static partial void SendDrawPrimitives(
-        nint receiver,
-        nint selector,
-        nuint primitiveType,
-        nuint vertexStart,
-        nuint vertexCount);
-
-    public static nint Class(string name) => objc_getClass(name);
-
-    public static nint Selector(string name) => sel_registerName(name);
-
-    /// <summary>Autoreleased NSString — only valid inside an autorelease pool
-    /// unless the caller retains it.</summary>
-    public static nint NsString(string value)
-    {
-        var utf8 = Marshal.StringToCoTaskMemUTF8(value);
-        try
-        {
-            return Send(Class("NSString"), Selector("stringWithUTF8String:"), utf8);
-        }
-        finally
-        {
-            Marshal.FreeCoTaskMem(utf8);
-        }
-    }
-
-    /// <summary>Reads an NSString's UTF-8 contents, or null if the handle is nil.</summary>
-    public static string? ReadNsString(nint nsString)
-    {
-        if (nsString == 0)
-        {
-            return null;
-        }
-
-        var utf8 = Send(nsString, Selector("UTF8String"));
-        return utf8 == 0 ? null : Marshal.PtrToStringUTF8(utf8);
-    }
-
-    public static string DescribeError(nint error)
-    {
-        if (error == 0)
-        {
-            return "unknown error";
-        }
-
-        var description = Send(error, Selector("localizedDescription"));
-        var utf8 = Send(description, Selector("UTF8String"));
-        return Marshal.PtrToStringUTF8(utf8) ?? "unknown error";
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalVideoPresenter.Batch.cs

@@ -1,50 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Guest draws and compute dispatches batch into one command buffer per drain
-// instead of one per work item, mirroring the Vulkan presenter's batched guest
-// commands: commit overhead dominated CPU time for scenes with dozens of draws
-// per frame. Ordering inside the batch is by encoder sequence (snapshot blits
-// for a draw's feedback reads are encoded before its render pass opens), and
-// everything that must observe batched work on the serial queue — flips, image
-// writes/blits, CPU-visible write-backs, the present pass — flushes first.
-internal static partial class MetalVideoPresenter
-{
-    private static nint _batchCommandBuffer;
-    private static bool _batchOpen;
-
-    /// <summary>Returns the open batch command buffer, opening one on first
-    /// use. Render thread only, like the drain it serves.</summary>
-    private static nint BeginBatchedGuestCommands(nint queue)
-    {
-        if (_batchOpen)
-        {
-            return _batchCommandBuffer;
-        }
-
-        _batchCommandBuffer = MetalNative.Send(queue, MetalNative.Selector("commandBuffer"));
-        _batchOpen = _batchCommandBuffer != 0;
-        return _batchCommandBuffer;
-    }
-
-    /// <summary>Commits the open batch (if any), tagging the upload pages and
-    /// snapshot resources it consumed. Returns the committed command buffer so
-    /// write-back sites can wait on it, or 0 when nothing was open.</summary>
-    private static nint FlushBatchedGuestCommands()
-    {
-        if (!_batchOpen)
-        {
-            return 0;
-        }
-
-        _batchOpen = false;
-        var commandBuffer = _batchCommandBuffer;
-        _batchCommandBuffer = 0;
-        MetalNative.SendVoid(commandBuffer, MetalNative.Selector("commit"));
-        TagUploadPages(commandBuffer);
-        TagSnapshotResources(commandBuffer);
-        return commandBuffer;
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalVideoPresenter.Compute.cs

@@ -1,424 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Guest compute dispatches: ordered guest work like draws, with two contracts to
-// honor. Storage images are shared live through the guest-image registry so a
-// dispatch's writes are visible to later draws, blits, and flips of the same
-// address; and CPU-visible buffer writes land back in guest memory before the
-// work item completes, which is the ordering point WaitForGuestWork promises.
-internal static partial class MetalVideoPresenter
-{
-    private static readonly bool _skipAllCompute =
-        Environment.GetEnvironmentVariable("SHARPEMU_SKIP_ALL_COMPUTE") == "1";
-    private static bool _tracedDispatchBase;
-
-    private sealed record ComputeGuestDispatch(
-        ulong ShaderAddress,
-        MetalCompiledGuestShader Shader,
-        GuestDrawTexture[] Textures,
-        GuestMemoryBuffer[] GlobalMemoryBuffers,
-        uint GroupCountX,
-        uint GroupCountY,
-        uint GroupCountZ,
-        uint BaseGroupX,
-        uint BaseGroupY,
-        uint BaseGroupZ,
-        uint ThreadCountX,
-        uint ThreadCountY,
-        uint ThreadCountZ);
-
-    private static readonly Dictionary<MetalCompiledGuestShader, nint> _computePipelineCache = new();
-
-    public static long SubmitComputeDispatch(
-        ulong shaderAddress,
-        MetalCompiledGuestShader computeShader,
-        IReadOnlyList<GuestDrawTexture> textures,
-        IReadOnlyList<GuestMemoryBuffer> globalMemoryBuffers,
-        uint groupCountX,
-        uint groupCountY,
-        uint groupCountZ,
-        uint baseGroupX,
-        uint baseGroupY,
-        uint baseGroupZ,
-        bool writesGlobalMemory,
-        uint threadCountX,
-        uint threadCountY,
-        uint threadCountZ)
-    {
-        var hasStorage = false;
-        foreach (var texture in textures)
-        {
-            hasStorage |= texture.IsStorage;
-        }
-
-        if (groupCountX == 0 ||
-            groupCountY == 0 ||
-            groupCountZ == 0 ||
-            (!hasStorage && !writesGlobalMemory))
-        {
-            return 0;
-        }
-
-        lock (_gate)
-        {
-            if (_closed || _thread is null)
-            {
-                return 0;
-            }
-
-            // Storage images a dispatch writes become flip sources and sampled
-            // inputs for later work, exactly like published render targets.
-            foreach (var texture in textures)
-            {
-                if (!texture.IsStorage || texture.Address == 0)
-                {
-                    continue;
-                }
-
-                var guestFormat = GetGuestTextureFormat(texture.Format, texture.NumberType);
-                if (guestFormat != 0)
-                {
-                    _availableGuestImages[texture.Address] = guestFormat;
-                }
-            }
-
-            var sequence = EnqueueGuestWorkLocked(
-                new ComputeGuestDispatch(
-                    shaderAddress,
-                    computeShader,
-                    ToArray(textures),
-                    ToArray(globalMemoryBuffers),
-                    groupCountX,
-                    groupCountY,
-                    groupCountZ,
-                    baseGroupX,
-                    baseGroupY,
-                    baseGroupZ,
-                    threadCountX,
-                    threadCountY,
-                    threadCountZ));
-            foreach (var texture in textures)
-            {
-                if (texture.IsStorage && texture.Address != 0)
-                {
-                    _guestImageWorkSequences[texture.Address] = sequence;
-                }
-            }
-
-            return sequence;
-        }
-    }
-
-    private static void ExecuteComputeDispatch(nint device, nint queue, ComputeGuestDispatch dispatch)
-    {
-        if (_skipAllCompute)
-        {
-            ReturnPooledComputeData(dispatch);
-            return;
-        }
-
-        VideoOut.PerfOverlay.RecordDraw();
-
-        if ((dispatch.BaseGroupX | dispatch.BaseGroupY | dispatch.BaseGroupZ) != 0 &&
-            !_tracedDispatchBase)
-        {
-            // Metal has no dispatch-base; the translated kernel derives its ids
-            // from the raw grid position, so a nonzero base computes offset-zero
-            // work until base support lands in the emitted kernel.
-            _tracedDispatchBase = true;
-            Console.Error.WriteLine(
-                "[LOADER][WARN] Metal compute dispatch with nonzero base group " +
-                $"({dispatch.BaseGroupX},{dispatch.BaseGroupY},{dispatch.BaseGroupZ}); " +
-                "executing without the base offset.");
-        }
-
-        if (!TryGetComputePipeline(device, dispatch.Shader, out var pipeline))
-        {
-            ReturnPooledComputeData(dispatch);
-            return;
-        }
-
-        var commandBuffer = BeginBatchedGuestCommands(queue);
-
-        // Pre-resolve textures before the compute encoder opens: snapshot
-        // blits for feedback reads encode into the batch and encoder order
-        // must place them ahead of this dispatch.
-        Span<nint> textureHandles = stackalloc nint[dispatch.Textures.Length];
-        Span<bool> textureOwned = stackalloc bool[dispatch.Textures.Length];
-        for (var index = 0; index < dispatch.Textures.Length; index++)
-        {
-            var descriptor = dispatch.Textures[index];
-            if (descriptor.IsStorage && descriptor.Address != 0)
-            {
-                textureHandles[index] = EnsureStorageImage(device, descriptor)?.Texture ?? 0;
-                textureOwned[index] = false;
-            }
-            else
-            {
-                textureHandles[index] = CreateDrawTexture(
-                    device, commandBuffer, descriptor, out var ownedTexture);
-                textureOwned[index] = ownedTexture;
-            }
-        }
-
-        var encoder = MetalNative.Send(commandBuffer, MetalNative.Selector("computeCommandEncoder"));
-        MetalNative.SendVoid(encoder, MetalNative.Selector("setComputePipelineState:"), pipeline);
-
-        var writeBackBuffers = new List<(nint Pointer, GuestMemoryBuffer Guest)>();
-        var selSetBuffer = MetalNative.Selector("setBuffer:offset:atIndex:");
-        var bufferCount = dispatch.GlobalMemoryBuffers.Length;
-        Span<uint> boundBytes = stackalloc uint[Math.Max(bufferCount, 1)];
-        for (var index = 0; index < bufferCount; index++)
-        {
-            var guest = dispatch.GlobalMemoryBuffers[index];
-            var pointer = UploadGlobalBuffer(
-                device, guest, out var buffer, out var offset, out boundBytes[index]);
-            MetalNative.SendSetBuffer(encoder, selSetBuffer, buffer, (nuint)offset, (nuint)index);
-            if (guest.Writable && guest.WriteBackToGuest)
-            {
-                writeBackBuffers.Add((pointer, guest));
-            }
-        }
-
-        // SharpEmuUniforms: the dispatch limit clamps the overshoot threads of the
-        // last threadgroup row, then each bound buffer's byte length follows
-        // (including the alignment-bias prefix the shader indexes past).
-        var shader = dispatch.Shader.Shader;
-        var uniforms = AllocateUpload(
-            device,
-            16 + (Math.Max(bufferCount, 1) * sizeof(uint)),
-            out var uniformsBuffer,
-            out var uniformsOffset);
-        WriteDispatchLimit(uniforms, 0, dispatch.ThreadCountX, dispatch.GroupCountX, shader.ThreadgroupSizeX);
-        WriteDispatchLimit(uniforms, 4, dispatch.ThreadCountY, dispatch.GroupCountY, shader.ThreadgroupSizeY);
-        WriteDispatchLimit(uniforms, 8, dispatch.ThreadCountZ, dispatch.GroupCountZ, shader.ThreadgroupSizeZ);
-        System.Buffers.Binary.BinaryPrimitives.WriteUInt32LittleEndian(uniforms[12..], 0);
-        for (var index = 0; index < bufferCount; index++)
-        {
-            System.Buffers.Binary.BinaryPrimitives.WriteUInt32LittleEndian(
-                uniforms[(16 + (index * sizeof(uint)))..],
-                boundBytes[index]);
-        }
-
-        // Bind at the stage's declared SharpEmuUniforms slot (see the draw path:
-        // stages compute their own index from globalBufferBase + total count).
-        var uniformsIndex = shader.UniformsBufferIndex;
-        MetalNative.SendSetBuffer(
-            encoder,
-            selSetBuffer,
-            uniformsBuffer,
-            (nuint)uniformsOffset,
-            (nuint)(uniformsIndex >= 0 ? uniformsIndex : bufferCount));
-
-        var selSetTexture = MetalNative.Selector("setTexture:atIndex:");
-        for (var index = 0; index < dispatch.Textures.Length; index++)
-        {
-            var texture = textureHandles[index];
-            if (texture != 0)
-            {
-                MetalNative.SendSetAtIndex(encoder, selSetTexture, texture, (nuint)index);
-                if (textureOwned[index])
-                {
-                    MetalNative.SendVoid(texture, MetalNative.Selector("release"));
-                }
-            }
-        }
-
-        // Samplers travel in an argument buffer bound at setBuffer (see the draw
-        // path), sidestepping Metal's 16-sampler-per-stage cap.
-        BindSamplerArgumentBuffer(device, encoder, selSetBuffer, dispatch.Shader, dispatch.Textures);
-
-        MetalNative.SendDispatch(
-            encoder,
-            MetalNative.Selector("dispatchThreadgroups:threadsPerThreadgroup:"),
-            new MtlSize
-            {
-                Width = dispatch.GroupCountX,
-                Height = dispatch.GroupCountY,
-                Depth = dispatch.GroupCountZ,
-            },
-            new MtlSize
-            {
-                Width = Math.Max(shader.ThreadgroupSizeX, 1),
-                Height = Math.Max(shader.ThreadgroupSizeY, 1),
-                Depth = Math.Max(shader.ThreadgroupSizeZ, 1),
-            });
-        MetalNative.SendVoid(encoder, MetalNative.Selector("endEncoding"));
-
-        // CPU-visible writes are ordering points (see the draw path): flush
-        // the batch and wait so the write-back lands before this work item
-        // completes. Pure-GPU dispatches stay in the open batch.
-        if (writeBackBuffers.Count > 0)
-        {
-            var committed = FlushBatchedGuestCommands();
-            MetalNative.SendVoid(committed, MetalNative.Selector("waitUntilCompleted"));
-            WriteBuffersBackToGuest(writeBackBuffers);
-        }
-
-        foreach (var descriptor in dispatch.Textures)
-        {
-            if (!descriptor.IsStorage || descriptor.Address == 0)
-            {
-                continue;
-            }
-
-            GuestImage? image;
-            lock (_gate)
-            {
-                _guestImages.TryGetValue(descriptor.Address, out image);
-            }
-
-            if (image is not null)
-            {
-                image.MarkContentChanged();
-            }
-        }
-
-        ReturnPooledComputeData(dispatch);
-    }
-
-    /// <summary>The live, shared storage image for a guest address: dispatches,
-    /// draws, blits, and flips of the same address all see one texture.</summary>
-    private static GuestImage? EnsureStorageImage(nint device, GuestDrawTexture descriptor)
-    {
-        lock (_gate)
-        {
-            if (_guestImages.TryGetValue(descriptor.Address, out var existing))
-            {
-                return existing;
-            }
-        }
-
-        if (descriptor.Width == 0 || descriptor.Height == 0 ||
-            descriptor.Width > 16384 || descriptor.Height > 16384)
-        {
-            return null;
-        }
-
-        var format = MetalGuestFormats.TryDecodeRenderTargetFormat(
-            descriptor.Format, descriptor.NumberType, out var decoded)
-            ? decoded.Format
-            : MtlPixelFormat.Rgba8Unorm;
-        var textureDescriptor = MetalNative.SendTextureDescriptor(
-            MetalNative.Class("MTLTextureDescriptor"),
-            MetalNative.Selector("texture2DDescriptorWithPixelFormat:width:height:mipmapped:"),
-            (nuint)format,
-            descriptor.Width,
-            descriptor.Height,
-            mipmapped: false);
-        MetalNative.Send(
-            textureDescriptor,
-            MetalNative.Selector("setUsage:"),
-            (nint)(UsageShaderRead | UsageShaderWrite | UsageRenderTarget));
-        var image = new GuestImage
-        {
-            Texture = MetalNative.Send(
-                device, MetalNative.Selector("newTextureWithDescriptor:"), textureDescriptor),
-            Width = descriptor.Width,
-            Height = descriptor.Height,
-            Format = format,
-        };
-        if (image.Texture == 0)
-        {
-            return null;
-        }
-
-        var bytesPerPixel = MetalRenderTargetFormat.GetBytesPerPixel(format);
-        // Snapshot copies arrive in the image's native texel layout; only
-        // 4-byte texels can be RGBA8 verbatim, wider ones carry native bytes.
-        if ((ulong)descriptor.RgbaPixels.Length >= (ulong)descriptor.Width * bytesPerPixel)
-        {
-            var pitch = descriptor.Pitch != 0
-                ? Math.Max(descriptor.Pitch, descriptor.Width)
-                : descriptor.Width;
-            ReplaceTextureContents(
-                image.Texture, descriptor.Width, descriptor.Height, descriptor.RgbaPixels, pitch, bytesPerPixel);
-            image.MarkContentChanged();
-        }
-
-        lock (_gate)
-        {
-            if (_guestImages.TryGetValue(descriptor.Address, out var raced))
-            {
-                MetalNative.SendVoid(image.Texture, MetalNative.Selector("release"));
-                return raced;
-            }
-
-            _guestImages[descriptor.Address] = image;
-            _guestImageExtents[descriptor.Address] =
-                (descriptor.Width, descriptor.Height, (ulong)descriptor.Width * descriptor.Height * bytesPerPixel);
-        }
-
-        return image;
-    }
-
-    private static bool TryGetComputePipeline(nint device, MetalCompiledGuestShader shader, out nint pipeline)
-    {
-        lock (_computePipelineCache)
-        {
-            if (_computePipelineCache.TryGetValue(shader, out pipeline))
-            {
-                return pipeline != 0;
-            }
-        }
-
-        var function = GetShaderFunction(device, shader);
-        if (function != 0)
-        {
-            nint error = 0;
-            pipeline = MetalNative.Send(
-                device,
-                MetalNative.Selector("newComputePipelineStateWithFunction:error:"),
-                function,
-                ref error);
-            if (pipeline == 0)
-            {
-                Console.Error.WriteLine(
-                    $"[LOADER][WARN] Metal compute pipeline creation failed: {MetalNative.DescribeError(error)}");
-            }
-            else
-            {
-                Interlocked.Increment(ref _perfPipelineCreations);
-            }
-        }
-        else
-        {
-            pipeline = 0;
-        }
-
-        lock (_computePipelineCache)
-        {
-            _computePipelineCache[shader] = pipeline;
-        }
-
-        return pipeline != 0;
-    }
-
-    private static void WriteDispatchLimit(
-        Span<byte> uniforms,
-        int offset,
-        uint threadCount,
-        uint groupCount,
-        uint threadgroupSize)
-    {
-        var limit = threadCount != uint.MaxValue
-            ? threadCount
-            : groupCount * Math.Max(threadgroupSize, 1);
-        System.Buffers.Binary.BinaryPrimitives.WriteUInt32LittleEndian(
-            uniforms[offset..],
-            limit);
-    }
-
-    private static void ReturnPooledComputeData(ComputeGuestDispatch dispatch)
-    {
-        foreach (var buffer in dispatch.GlobalMemoryBuffers)
-        {
-            if (buffer.Pooled)
-            {
-                GuestDataPool.Shared.Return(buffer.Data);
-            }
-        }
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalVideoPresenter.SnapshotPool.cs

@@ -1,180 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Feedback reads (draws sampling a live guest render target or depth image)
-// need a fresh ordered snapshot per draw. Creating and destroying an MTLTexture
-// — and for depth reads a private staging MTLBuffer — per draw is measurable
-// CPU and allocator churn at hundreds of feedback draws per second, so both
-// recycle through a pool with the same lifecycle as the upload arena pages:
-// acquired snapshots are tagged with the command buffer that samples them at
-// commit, and return to the free list once that command buffer completes (the
-// command queue is serial, so the earlier snapshot-blit command buffer is
-// necessarily complete by then too). Everything here runs on the render thread.
-internal static partial class MetalVideoPresenter
-{
-    private const int MaxFreeSnapshotResources = 16;
-
-    private sealed class PooledSnapshotResource
-    {
-        public nint Handle;
-        public bool IsBuffer;
-
-        /// <summary>Texture identity (unused for buffers).</summary>
-        public uint Format;
-        public uint Width;
-        public uint Height;
-        public nint Usage;
-
-        /// <summary>Buffer capacity in bytes (unused for textures).</summary>
-        public nuint Capacity;
-
-        /// <summary>Retained handle of the command buffer that samples this
-        /// snapshot; the resource is reusable once it completes.</summary>
-        public nint LastCommandBuffer;
-    }
-
-    private static readonly List<PooledSnapshotResource> _retiredSnapshotResources = [];
-    private static readonly List<PooledSnapshotResource> _pendingSnapshotResources = [];
-    private static readonly List<PooledSnapshotResource> _freeSnapshotResources = [];
-
-    /// <summary>Returns completed snapshot resources to the free list; called
-    /// once per render-loop drain, next to the upload-page recycler.</summary>
-    private static void RecycleCompletedSnapshotResources()
-    {
-        for (var index = _retiredSnapshotResources.Count - 1; index >= 0; index--)
-        {
-            var resource = _retiredSnapshotResources[index];
-            if (resource.LastCommandBuffer != 0)
-            {
-                // MTLCommandBufferStatus: Completed = 4, Error = 5.
-                var status = MetalNative.Send(
-                    resource.LastCommandBuffer, MetalNative.Selector("status"));
-                if (status < 4)
-                {
-                    continue;
-                }
-
-                MetalNative.SendVoid(resource.LastCommandBuffer, MetalNative.Selector("release"));
-                resource.LastCommandBuffer = 0;
-            }
-
-            _retiredSnapshotResources.RemoveAt(index);
-            if (_freeSnapshotResources.Count < MaxFreeSnapshotResources)
-            {
-                _freeSnapshotResources.Add(resource);
-            }
-            else
-            {
-                MetalNative.SendVoid(resource.Handle, MetalNative.Selector("release"));
-            }
-        }
-    }
-
-    /// <summary>Pops a pooled snapshot texture matching the exact identity, or
-    /// creates one. The returned handle is owned by the pool — callers must not
-    /// release it, and it must be tagged at the next commit.</summary>
-    private static nint AcquireSnapshotTexture(
-        nint device,
-        MtlPixelFormat format,
-        uint width,
-        uint height,
-        nint usage)
-    {
-        for (var index = 0; index < _freeSnapshotResources.Count; index++)
-        {
-            var candidate = _freeSnapshotResources[index];
-            if (!candidate.IsBuffer &&
-                candidate.Format == (uint)format &&
-                candidate.Width == width &&
-                candidate.Height == height &&
-                candidate.Usage == usage)
-            {
-                _freeSnapshotResources.RemoveAt(index);
-                _pendingSnapshotResources.Add(candidate);
-                return candidate.Handle;
-            }
-        }
-
-        var descriptor = MetalNative.SendTextureDescriptor(
-            MetalNative.Class("MTLTextureDescriptor"),
-            MetalNative.Selector("texture2DDescriptorWithPixelFormat:width:height:mipmapped:"),
-            (nuint)format,
-            width,
-            height,
-            mipmapped: false);
-        MetalNative.Send(descriptor, MetalNative.Selector("setUsage:"), usage);
-        var handle = MetalNative.Send(
-            device, MetalNative.Selector("newTextureWithDescriptor:"), descriptor);
-        if (handle == 0)
-        {
-            return 0;
-        }
-
-        _pendingSnapshotResources.Add(new PooledSnapshotResource
-        {
-            Handle = handle,
-            Format = (uint)format,
-            Width = width,
-            Height = height,
-            Usage = usage,
-        });
-        return handle;
-    }
-
-    /// <summary>Pops a pooled private-storage staging buffer of at least
-    /// <paramref name="minimumBytes"/>, or creates one. Pool-owned like
-    /// <see cref="AcquireSnapshotTexture"/>.</summary>
-    private static nint AcquireSnapshotBuffer(nint device, nuint minimumBytes)
-    {
-        for (var index = 0; index < _freeSnapshotResources.Count; index++)
-        {
-            var candidate = _freeSnapshotResources[index];
-            if (candidate.IsBuffer && candidate.Capacity >= minimumBytes)
-            {
-                _freeSnapshotResources.RemoveAt(index);
-                _pendingSnapshotResources.Add(candidate);
-                return candidate.Handle;
-            }
-        }
-
-        // MTLResourceStorageModePrivate = 32: staging never touches the CPU.
-        var handle = MetalNative.SendNewBuffer(
-            device, MetalNative.Selector("newBufferWithLength:options:"), minimumBytes, 32);
-        if (handle == 0)
-        {
-            return 0;
-        }
-
-        _pendingSnapshotResources.Add(new PooledSnapshotResource
-        {
-            Handle = handle,
-            IsBuffer = true,
-            Capacity = minimumBytes,
-        });
-        return handle;
-    }
-
-    /// <summary>Marks every snapshot resource acquired since the previous tag
-    /// as owing its lifetime to <paramref name="commandBuffer"/>. Called at the
-    /// same commit sites as <see cref="TagUploadPages"/>; a resource acquired
-    /// for a draw that never committed is tagged by the next commit, which is
-    /// conservative but safe.</summary>
-    private static void TagSnapshotResources(nint commandBuffer)
-    {
-        if (_pendingSnapshotResources.Count == 0)
-        {
-            return;
-        }
-
-        foreach (var resource in _pendingSnapshotResources)
-        {
-            resource.LastCommandBuffer = MetalNative.Send(
-                commandBuffer, MetalNative.Selector("retain"));
-            _retiredSnapshotResources.Add(resource);
-        }
-
-        _pendingSnapshotResources.Clear();
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalVideoPresenter.TextureCache.cs

@@ -1,179 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Collections.Concurrent;
-using SharpEmu.HLE;
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Draw textures decoded from guest memory are cached across draws keyed by
-// their full descriptor identity, mirroring the Vulkan presenter's texture
-// cache: once an identity is marked cached, the AGC submit thread skips the
-// guest-memory read/detile/copy entirely (shipping empty texels) and the
-// render thread serves the cached MTLTexture — for scenes that sample large
-// textures every draw, that per-draw copy dominated both allocation churn
-// and CPU time. GuestImageWriteTracker write-protects the source pages, so
-// a guest CPU write dirties the address and the entry is evicted at the next
-// drain; the following draw ships fresh texels and re-populates the cache.
-internal static partial class MetalVideoPresenter
-{
-    private const int MaxCachedDrawTextures = 2048;
-
-    /// <summary>Render-thread-only cache of decoded draw textures; each value
-    /// holds one retain. Committed command buffers retain the textures they
-    /// reference, so eviction releases immediately without a GPU drain.</summary>
-    private static readonly Dictionary<TextureContentIdentity, nint> _drawTextureCache = new();
-
-    /// <summary>Identities the AGC submit thread may skip texel copies for.
-    /// Read from the submit thread, written by the render thread.</summary>
-    private static readonly ConcurrentDictionary<TextureContentIdentity, byte> _cachedDrawTextureIdentities = new();
-
-    internal static bool IsTextureContentCached(in TextureContentIdentity identity) =>
-        _cachedDrawTextureIdentities.ContainsKey(identity);
-
-    /// <summary>Builds the same identity the AGC layer checks before skipping
-    /// a texel copy; the two must agree field-for-field or skips and cache
-    /// entries would never line up.</summary>
-    private static TextureContentIdentity GetDrawTextureIdentity(GuestDrawTexture texture) => new(
-        texture.Address,
-        texture.Width,
-        texture.Height,
-        texture.Format,
-        texture.NumberType,
-        texture.DstSelect,
-        texture.TileMode,
-        texture.Pitch,
-        texture.Sampler);
-
-    /// <summary>Caching requires the write tracker: without page protection a
-    /// guest CPU write would never evict the entry and draws would sample
-    /// stale texels forever. Storage textures are shader-writable on the GPU,
-    /// so their content identity is not stable either.</summary>
-    private static bool IsCacheableDrawTexture(GuestDrawTexture texture) =>
-        GuestImageWriteTracker.Enabled &&
-        texture.Address != 0 &&
-        !texture.IsStorage &&
-        !texture.IsFallback;
-
-    private static bool TryGetCachedDrawTexture(GuestDrawTexture texture, out nint handle) =>
-        _drawTextureCache.TryGetValue(GetDrawTextureIdentity(texture), out handle);
-
-    private static void CacheDrawTexture(GuestDrawTexture texture, nint handle)
-    {
-        var key = GetDrawTextureIdentity(texture);
-        if (_drawTextureCache.Remove(key, out var previous))
-        {
-            MetalNative.SendVoid(previous, MetalNative.Selector("release"));
-        }
-
-        _ = MetalNative.Send(handle, MetalNative.Selector("retain"));
-        _drawTextureCache[key] = handle;
-        _cachedDrawTextureIdentities[key] = 0;
-        GuestImageWriteTracker.Track(
-            texture.Address,
-            (ulong)texture.RgbaPixels.Length,
-            Volatile.Read(ref _executingGuestWorkSequence),
-            "metal.texture-cache");
-    }
-
-    /// <summary>Runs once per drain, before any queued draw executes: a draw
-    /// whose texels the submit thread skipped must never resolve to an entry
-    /// the guest has since rewritten.</summary>
-    private static void EvictDirtyCachedDrawTextures()
-    {
-        if (_drawTextureCache.Count == 0)
-        {
-            return;
-        }
-
-        // Evict by address rather than by identity: several identities can
-        // share one source address (same texels, different samplers), and
-        // ConsumeDirty clears the flag on first read — evicting only the
-        // first identity would leave the others sampling stale texels.
-        HashSet<ulong>? dirtyAddresses = null;
-        foreach (var entry in _drawTextureCache)
-        {
-            if (dirtyAddresses is not null && dirtyAddresses.Contains(entry.Key.Address))
-            {
-                continue;
-            }
-
-            if (GuestImageWriteTracker.ConsumeDirty(entry.Key.Address))
-            {
-                (dirtyAddresses ??= []).Add(entry.Key.Address);
-            }
-        }
-
-        if (dirtyAddresses is null && _drawTextureCache.Count <= MaxCachedDrawTextures)
-        {
-            return;
-        }
-
-        if (_drawTextureCache.Count > MaxCachedDrawTextures)
-        {
-            foreach (var entry in _drawTextureCache)
-            {
-                MetalNative.SendVoid(entry.Value, MetalNative.Selector("release"));
-            }
-
-            _drawTextureCache.Clear();
-            _cachedDrawTextureIdentities.Clear();
-            return;
-        }
-
-        List<TextureContentIdentity>? evicted = null;
-        foreach (var entry in _drawTextureCache)
-        {
-            if (dirtyAddresses!.Contains(entry.Key.Address))
-            {
-                (evicted ??= []).Add(entry.Key);
-            }
-        }
-
-        if (evicted is not null)
-        {
-            foreach (var key in evicted)
-            {
-                if (_drawTextureCache.Remove(key, out var handle))
-                {
-                    _cachedDrawTextureIdentities.TryRemove(key, out _);
-                    MetalNative.SendVoid(handle, MetalNative.Selector("release"));
-                }
-            }
-        }
-
-        foreach (var address in dirtyAddresses!)
-        {
-            GuestImageWriteTracker.Rearm(address);
-        }
-    }
-
-    /// <summary>Self-heal for the skip/eviction race: the submit thread saw a
-    /// cached identity and skipped the copy, but the entry was evicted before
-    /// this draw executed. Read the texels directly rather than rendering a
-    /// fallback texture for the frame, sized with the same block-aware math
-    /// the draw path expects.</summary>
-    private static byte[]? TryReadGuestDrawTexturePixels(GuestDrawTexture texture)
-    {
-        var memory = _guestMemory;
-        if (memory is null || texture.Address == 0)
-        {
-            return null;
-        }
-
-        var width = Math.Max(texture.Width, 1u);
-        var height = Math.Max(texture.Height, 1u);
-        var rowLength = texture.TileMode == 0
-            ? Math.Max(texture.Pitch, width)
-            : width;
-        var format = MetalGuestFormats.DecodeTextureFormat(texture.Format, texture.NumberType);
-        var byteCount = MetalGuestFormats.GetTextureByteCount(format, rowLength, height);
-        if (byteCount == 0 || byteCount > int.MaxValue)
-        {
-            return null;
-        }
-
-        var pixels = new byte[(int)byteCount];
-        return memory.TryRead(texture.Address, pixels) ? pixels : null;
-    }
-}

src/SharpEmu.Libs/Gpu/Metal/MetalVideoPresenter.Uploads.cs

@@ -1,162 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-namespace SharpEmu.Libs.Gpu.Metal;
-
-// Per-draw upload data (guest global buffers, uniforms, vertex and index
-// bytes) bump-allocates from shared-storage arena pages bound by offset,
-// instead of creating one MTLBuffer and one managed copy per binding per
-// draw — which dominated allocation churn (hundreds of MB/s) and held the
-// guest flip rate well under the display rate. Pages recycle once the last
-// command buffer that referenced them reports completion; everything here
-// runs on the render thread, so no state is locked.
-internal static partial class MetalVideoPresenter
-{
-    private const int UploadPageBytes = 8 * 1024 * 1024;
-
-    // Superset of every Metal bind-offset alignment rule (constant address
-    // space on Intel Macs is the strictest at 256), and conveniently the
-    // guest storage-buffer alignment the shader bias contract assumes.
-    private const int UploadAlignment = 256;
-
-    private sealed class UploadPage
-    {
-        public nint Buffer;
-        public nint Contents;
-        public int Capacity;
-        public int Offset;
-
-        /// <summary>Retained handle of the last command buffer that consumed
-        /// data from this page; the page is reusable once it completes.</summary>
-        public nint LastCommandBuffer;
-
-        /// <summary>Stamp of the last TagUploadPages call that saw this page,
-        /// so a commit only re-tags pages it actually touched.</summary>
-        public int TouchStamp;
-    }
-
-    private static readonly List<UploadPage> _retiredUploadPages = [];
-    private static readonly Stack<UploadPage> _freeUploadPages = new();
-    private static readonly List<UploadPage> _touchedUploadPages = [];
-    private static UploadPage? _currentUploadPage;
-    private static int _uploadTouchStamp;
-
-    /// <summary>Returns completed pages to the free stack. Called once per
-    /// render-loop drain; completion is polled (command buffer status) rather
-    /// than block-based so the ObjC interop stays block-free.</summary>
-    private static void RecycleCompletedUploadPages()
-    {
-        for (var index = _retiredUploadPages.Count - 1; index >= 0; index--)
-        {
-            var page = _retiredUploadPages[index];
-            if (page.LastCommandBuffer != 0)
-            {
-                // MTLCommandBufferStatus: Completed = 4, Error = 5.
-                var status = MetalNative.Send(
-                    page.LastCommandBuffer, MetalNative.Selector("status"));
-                if (status < 4)
-                {
-                    continue;
-                }
-
-                MetalNative.SendVoid(page.LastCommandBuffer, MetalNative.Selector("release"));
-                page.LastCommandBuffer = 0;
-            }
-
-            _retiredUploadPages.RemoveAt(index);
-            if (page.Capacity == UploadPageBytes)
-            {
-                page.Offset = 0;
-                _freeUploadPages.Push(page);
-            }
-            else
-            {
-                // Oversized one-off allocation; not worth pooling.
-                MetalNative.SendVoid(page.Buffer, MetalNative.Selector("release"));
-            }
-        }
-    }
-
-    /// <summary>Bump-allocates an aligned slice for CPU-written upload data.
-    /// The returned span is the slice's shared-storage memory; bind the
-    /// buffer at the returned offset.</summary>
-    private static unsafe Span<byte> AllocateUpload(
-        nint device,
-        int length,
-        out nint buffer,
-        out int offset)
-    {
-        var page = _currentUploadPage;
-        var aligned = page is null
-            ? 0
-            : (page.Offset + UploadAlignment - 1) & ~(UploadAlignment - 1);
-        if (page is null || aligned + length > page.Capacity)
-        {
-            if (page is not null)
-            {
-                _retiredUploadPages.Add(page);
-            }
-
-            page = AcquireUploadPage(device, length);
-            _currentUploadPage = page;
-            aligned = 0;
-        }
-
-        if (page.TouchStamp != _uploadTouchStamp)
-        {
-            page.TouchStamp = _uploadTouchStamp;
-            _touchedUploadPages.Add(page);
-        }
-
-        buffer = page.Buffer;
-        offset = aligned;
-        page.Offset = aligned + length;
-        return new Span<byte>((void*)(page.Contents + aligned), length);
-    }
-
-    private static UploadPage AcquireUploadPage(nint device, int minimumBytes)
-    {
-        if (minimumBytes <= UploadPageBytes && _freeUploadPages.Count > 0)
-        {
-            return _freeUploadPages.Pop();
-        }
-
-        var capacity = Math.Max(minimumBytes, UploadPageBytes);
-        // Options 0 = MTLResourceStorageModeShared: CPU writes are coherent
-        // and write-backs read the GPU's stores after waitUntilCompleted.
-        var handle = MetalNative.SendNewBuffer(
-            device, MetalNative.Selector("newBufferWithLength:options:"), (nuint)capacity, 0);
-        return new UploadPage
-        {
-            Buffer = handle,
-            Contents = MetalNative.Send(handle, MetalNative.Selector("contents")),
-            Capacity = capacity,
-        };
-    }
-
-    /// <summary>Marks every page touched since the previous tag as owing its
-    /// lifetime to <paramref name="commandBuffer"/>. Called after each commit
-    /// that consumed arena data.</summary>
-    private static void TagUploadPages(nint commandBuffer)
-    {
-        if (_touchedUploadPages.Count == 0)
-        {
-            _uploadTouchStamp++;
-            return;
-        }
-
-        foreach (var page in _touchedUploadPages)
-        {
-            if (page.LastCommandBuffer != 0)
-            {
-                MetalNative.SendVoid(page.LastCommandBuffer, MetalNative.Selector("release"));
-            }
-
-            page.LastCommandBuffer = MetalNative.Send(
-                commandBuffer, MetalNative.Selector("retain"));
-        }
-
-        _touchedUploadPages.Clear();
-        _uploadTouchStamp++;
-    }
-}

src/SharpEmu.Libs/Gpu/Vulkan/VulkanGuestGpuBackend.cs

@@ -15,8 +15,6 @@ namespace SharpEmu.Libs.Gpu.Vulkan;
 /// </summary>
 internal sealed class VulkanGuestGpuBackend : IGuestGpuBackend
 {
-    public string BackendName => "Vulkan";
-
     private static readonly IGuestCompiledShader DepthOnlyFragmentShader =
         new VulkanCompiledGuestShader(SpirvFixedShaders.CreateDepthOnlyFragment());
 
@@ -345,60 +343,6 @@ internal sealed class VulkanGuestGpuBackend : IGuestGpuBackend
         return false;
     }
 
-    public IDisposable EnterGuestQueue(string queueName, ulong submissionId) =>
-        VulkanVideoPresenter.EnterGuestQueue(queueName, submissionId);
-
-    public long SubmitOrderedGuestAction(Action action, string debugName) =>
-        VulkanVideoPresenter.SubmitOrderedGuestAction(action, debugName);
-
-    public long SubmitOrderedGuestFlipWait(int videoOutHandle, int displayBufferIndex) =>
-        VulkanVideoPresenter.SubmitOrderedGuestFlipWait(videoOutHandle, displayBufferIndex);
-
-    public bool WaitForGuestWork(long workSequence, int timeoutMilliseconds = Timeout.Infinite) =>
-        VulkanVideoPresenter.WaitForGuestWork(workSequence, timeoutMilliseconds);
-
-    public long CurrentGuestWorkSequenceForDiagnostics =>
-        VulkanVideoPresenter.CurrentGuestWorkSequenceForDiagnostics;
-
-    public bool IsGuestImageUploadKnown(ulong address, uint format, uint numberType) =>
-        VulkanVideoPresenter.IsGuestImageUploadKnown(address, format, numberType);
-
-    public bool GuestImageWantsInitialData(ulong address) =>
-        VulkanVideoPresenter.GuestImageWantsInitialData(address);
-
-    public void ProvideGuestImageInitialData(ulong address, byte[] rgbaPixels) =>
-        VulkanVideoPresenter.ProvideGuestImageInitialData(address, rgbaPixels);
-
-    public void SubmitGuestImageFill(ulong address, uint fillValue) =>
-        VulkanVideoPresenter.SubmitGuestImageFill(address, fillValue);
-
-    public void SubmitGuestImageWrite(ulong address, byte[] pixels) =>
-        VulkanVideoPresenter.SubmitGuestImageWrite(address, pixels);
-
-    public bool TryGetGuestImageExtent(ulong address, out uint width, out uint height, out ulong byteCount) =>
-        VulkanVideoPresenter.TryGetGuestImageExtent(address, out width, out height, out byteCount);
-
-    public IReadOnlyList<(ulong Address, uint Width, uint Height, ulong ByteCount)> GetGuestImageExtents() =>
-        VulkanVideoPresenter.GetGuestImageExtents();
-
-    public bool IsTextureContentCached(in TextureContentIdentity identity) =>
-        VulkanVideoPresenter.IsTextureContentCached(identity);
-
-    public void AttachGuestMemory(SharpEmu.HLE.ICpuMemory memory) =>
-        VulkanVideoPresenter.AttachGuestMemory(memory);
-
-    public ulong GuestStorageBufferOffsetAlignment =>
-        VulkanVideoPresenter.GuestStorageBufferOffsetAlignment;
-
-    public void CountShaderCompilation() =>
-        VulkanVideoPresenter.CountSpirvCompilation();
-
-    public (long Draws, double DrawMs, long Pipelines, long ShaderCompilations) ReadAndResetPerfCounters() =>
-        VulkanVideoPresenter.ReadAndResetPerfCounters();
-
-    public void RequestClose() =>
-        VulkanVideoPresenter.RequestClose();
-
     private static byte[] Spirv(IGuestCompiledShader shader) =>
         shader is VulkanCompiledGuestShader vulkanShader
             ? vulkanShader.Spirv

src/SharpEmu.Libs/Ime/ImeExports.cs

@@ -43,25 +43,4 @@ public static class ImeExports
         ctx[CpuRegister.Rax] = 0;
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
-
-    // No hardware keyboard is ever connected; zero the caller's info struct so
-    // it reads as "not connected" rather than uninitialized stack.
-    [SysAbiExport(
-        Nid = "VkqLPArfFdc",
-        ExportName = "sceImeKeyboardGetInfo",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceIme")]
-    public static int ImeKeyboardGetInfo(CpuContext ctx)
-    {
-        var infoAddress = ctx[CpuRegister.Rsi] != 0 ? ctx[CpuRegister.Rsi] : ctx[CpuRegister.Rdi];
-        if (infoAddress != 0)
-        {
-            Span<byte> info = stackalloc byte[0x40];
-            info.Clear();
-            _ = ctx.Memory.TryWrite(infoAddress, info);
-        }
-
-        ctx[CpuRegister.Rax] = 0;
-        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
-    }
 }

src/SharpEmu.Libs/Kernel/KernelEventFlagCompatExports.cs

@@ -5,12 +5,14 @@ using System.Buffers.Binary;
 using System.Collections.Concurrent;
 using System.Text;
 using SharpEmu.HLE;
+using SharpEmu.Libs.Fiber;
 
 namespace SharpEmu.Libs.Kernel;
 
 public static class KernelEventFlagCompatExports
 {
     private const int MaxEventFlagNameLength = 31;
+    private const int HostWaitPumpMilliseconds = 1;
     private const uint AttrThreadFifo = 0x01;
     private const uint AttrThreadPriority = 0x02;
     private const uint AttrSingle = 0x10;
@@ -23,7 +25,8 @@ public static class KernelEventFlagCompatExports
     private static readonly ConcurrentDictionary<ulong, EventFlagState> _eventFlags = new();
     private static long _nextEventFlagHandle = 1;
 
-    // Cached once: gating every call site avoids building the interpolated trace string when disabled.
+    // Cached once: gating every call site avoids building the interpolated
+    // trace string (and FormatFrameChain/FormatGuestWaitObject) when disabled.
     private static readonly bool _traceEventFlag = string.Equals(
         Environment.GetEnvironmentVariable("SHARPEMU_LOG_EVENT_FLAG"), "1", StringComparison.Ordinal);
 
@@ -125,11 +128,11 @@ public static class KernelEventFlagCompatExports
         lock (state.Gate)
         {
             state.Bits |= pattern;
-            // Wake threads parked in-place on the gate; each re-checks its pattern.
             Monitor.PulseAll(state.Gate);
             if (_traceEventFlag) TraceEventFlag($"set handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} ret=0x{returnRip:X16}");
         }
 
+        _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(GetEventFlagWakeKey(handle));
         return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
@@ -226,67 +229,134 @@ public static class KernelEventFlagCompatExports
             return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
         }
 
-        // A zero-microsecond timeout degrades to an instant poll because the
-        // deadline is already in the past.
-        var hostDeadlineMs = timeoutAddress != 0
-            ? Environment.TickCount64 + (timeoutUsec == 0
-                ? 0L
-                : Math.Max(1L, (timeoutUsec + 999L) / 1000L))
-            : long.MaxValue;
-
-        lock (state.Gate)
+        Monitor.Enter(state.Gate);
+        try
         {
             if (TryCompleteSatisfiedWait(ctx, state, pattern, waitMode, resultAddress, out var immediateWaitResult))
             {
-                if (_traceEventFlag) TraceEventFlag($"poll handle=0x{handle:X16} pattern=0x{pattern:X16} mode=0x{waitMode:X2} bits=0x{state.Bits:X16} ret=0x{returnRip:X16}");
                 return SetReturn(ctx, immediateWaitResult);
             }
 
-            // In-place block on the flag gate. Monitor.Wait releases the gate
-            // and parks atomically, so a concurrent SetEventFlag's PulseAll
-            // cannot be lost between the satisfy check and the park. On wake
-            // the predicate is re-evaluated (Set semantics on FreeBSD-style
-            // event flags: OR/AND over the bit pattern, optional clear).
-            state.WaitingThreads++;
-            var guestThreadHandle = GuestThreadExecution.CurrentGuestThreadHandle;
-            if (_traceEventFlag) TraceEventFlag($"wait-block handle=0x{handle:X16} pattern=0x{pattern:X16} waiters={state.WaitingThreads} guest_thread=0x{guestThreadHandle:X16} ret=0x{returnRip:X16}");
-            GuestThreadBlocking.NoteBlocked(guestThreadHandle, "sceKernelWaitEventFlag");
-            try
-            {
-                while (true)
+            // Timed waits block on a deadline instead of returning TIMED_OUT
+            // immediately; a zero-microsecond timeout still degrades to an
+            // instant poll because the deadline is already in the past.
+            var deadline = timeoutAddress != 0
+                ? GuestThreadExecution.ComputeDeadlineTimestamp(TimeSpan.FromMicroseconds(timeoutUsec))
+                : 0;
+            var hostDeadlineMs = timeoutAddress != 0
+                ? Environment.TickCount64 + (timeoutUsec == 0
+                    ? 0L
+                    : Math.Max(1L, (timeoutUsec + 999L) / 1000L))
+                : long.MaxValue;
+
+            var currentGuestThread = GuestThreadExecution.CurrentGuestThreadHandle;
+            var currentFiber = FiberExports.GetCurrentFiberAddressForDiagnostics(ctx);
+            var managedThread = Environment.CurrentManagedThreadId;
+            var blockedWaitResult = OrbisGen2Result.ORBIS_GEN2_OK;
+            var satisfied = false;
+            var requestedBlock = GuestThreadExecution.RequestCurrentThreadBlock(
+                ctx,
+                "sceKernelWaitEventFlag",
+                GetEventFlagWakeKey(handle),
+                () =>
                 {
-                    if (GuestThreadBlocking.ShutdownRequested)
+                    if (satisfied)
                     {
-                        if (timeoutAddress != 0) _ = TryWriteUInt32(ctx, timeoutAddress, 0);
-                        _ = TryWriteResultPattern(ctx, resultAddress, state.Bits);
-                        return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
+                        return (int)blockedWaitResult;
                     }
 
-                    if (TryCompleteSatisfiedWait(ctx, state, pattern, waitMode, resultAddress, out var wokeResult))
-                    {
-                        if (timeoutAddress != 0) _ = TryWriteUInt32(ctx, timeoutAddress, 0);
-                        if (_traceEventFlag) TraceEventFlag($"wait-wake handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} ret=0x{returnRip:X16}");
-                        return SetReturn(ctx, wokeResult);
-                    }
-
-                    var remaining = hostDeadlineMs - Environment.TickCount64;
-                    if (timeoutAddress != 0 && remaining <= 0)
+                    // Deadline expiry: report timeout with the current bits.
+                    if (timeoutAddress != 0)
                     {
                         _ = TryWriteUInt32(ctx, timeoutAddress, 0);
-                        _ = TryWriteResultPattern(ctx, resultAddress, state.Bits);
-                        if (_traceEventFlag) TraceEventFlag($"wait-timeout handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} ret=0x{returnRip:X16}");
-                        return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
                     }
 
-                    GuestThreadBlocking.Checkpoint(guestThreadHandle, state.Gate);
-                    _ = Monitor.Wait(state.Gate, (int)Math.Min(remaining, GuestThreadBlocking.WaitSliceMilliseconds));
+                    _ = TryWriteResultPattern(ctx, resultAddress, state.Bits);
+                    return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT;
+                },
+                () =>
+                {
+                    if (!TryPrepareBlockedWait(
+                            ctx,
+                            state,
+                            pattern,
+                            waitMode,
+                            resultAddress,
+                            out var preparedResult))
+                    {
+                        return false;
+                    }
+
+                    blockedWaitResult = preparedResult;
+                    satisfied = true;
+                    return true;
+                },
+                deadline);
+            if (_traceEventFlag) TraceEventFlag($"wait-unsatisfied handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} guest_thread=0x{currentGuestThread:X16} fiber=0x{currentFiber:X16} managed={managedThread} block={requestedBlock} ret=0x{returnRip:X16} frames={FormatFrameChain(ctx)}");
+            if (_traceEventFlag) TraceEventFlag($"wait-object handle=0x{handle:X16} name='{state.Name}' {FormatGuestWaitObject(ctx)}");
+            if (!requestedBlock)
+            {
+                var scheduler = GuestThreadExecution.Scheduler;
+                if (scheduler is null)
+                {
+                    return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN);
+                }
+
+                state.WaitingThreads++;
+                if (_traceEventFlag) TraceEventFlag($"wait-pump handle=0x{handle:X16} pattern=0x{pattern:X16} waiters={state.WaitingThreads} guest_thread=0x{currentGuestThread:X16} fiber=0x{currentFiber:X16} managed={managedThread} ret=0x{returnRip:X16}");
+                var releaseWaiter = true;
+                try
+                {
+                    while (true)
+                    {
+                        Monitor.Exit(state.Gate);
+                        try
+                        {
+                            scheduler.Pump(ctx, "sceKernelWaitEventFlag");
+                        }
+                        finally
+                        {
+                            Monitor.Enter(state.Gate);
+                        }
+
+                        if (TryCompleteSatisfiedWait(ctx, state, pattern, waitMode, resultAddress, out var pumpedWaitResult))
+                        {
+                            state.WaitingThreads = Math.Max(0, state.WaitingThreads - 1);
+                            releaseWaiter = false;
+                            if (_traceEventFlag) TraceEventFlag($"wait-wake handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} waiters={state.WaitingThreads} ret=0x{returnRip:X16}");
+                            return SetReturn(ctx, pumpedWaitResult);
+                        }
+
+                        var remaining = hostDeadlineMs - Environment.TickCount64;
+                        if (timeoutAddress != 0 && remaining <= 0)
+                        {
+                            state.WaitingThreads = Math.Max(0, state.WaitingThreads - 1);
+                            releaseWaiter = false;
+                            _ = TryWriteUInt32(ctx, timeoutAddress, 0);
+                            _ = TryWriteResultPattern(ctx, resultAddress, state.Bits);
+                            if (_traceEventFlag) TraceEventFlag($"wait-timeout handle=0x{handle:X16} pattern=0x{pattern:X16} bits=0x{state.Bits:X16} ret=0x{returnRip:X16}");
+                            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
+                        }
+
+                        Monitor.Wait(state.Gate, (int)Math.Min(remaining, HostWaitPumpMilliseconds));
+                    }
+                }
+                finally
+                {
+                    if (releaseWaiter)
+                    {
+                        state.WaitingThreads = Math.Max(0, state.WaitingThreads - 1);
+                    }
                 }
             }
-            finally
-            {
-                state.WaitingThreads = Math.Max(0, state.WaitingThreads - 1);
-                GuestThreadBlocking.NoteUnblocked(guestThreadHandle);
-            }
+
+            state.WaitingThreads++;
+            if (_traceEventFlag) TraceEventFlag($"wait-block handle=0x{handle:X16} pattern=0x{pattern:X16} waiters={state.WaitingThreads} guest_thread=0x{currentGuestThread:X16} fiber=0x{currentFiber:X16} managed={managedThread} ret=0x{returnRip:X16}");
+            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
+        }
+        finally
+        {
+            Monitor.Exit(state.Gate);
         }
     }
 
@@ -385,6 +455,41 @@ public static class KernelEventFlagCompatExports
         return true;
     }
 
+    private static bool TryPrepareBlockedWait(
+        CpuContext ctx,
+        EventFlagState state,
+        ulong pattern,
+        uint waitMode,
+        ulong resultAddress,
+        out OrbisGen2Result result)
+    {
+        lock (state.Gate)
+        {
+            result = OrbisGen2Result.ORBIS_GEN2_OK;
+            if (!IsSatisfied(state.Bits, pattern, waitMode))
+            {
+                return false;
+            }
+
+            if (!TryWriteResultPattern(ctx, resultAddress, state.Bits))
+            {
+                result = OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+            }
+            else
+            {
+                ApplyClearMode(state, pattern, waitMode);
+            }
+
+            state.WaitingThreads = Math.Max(0, state.WaitingThreads - 1);
+            if (_traceEventFlag) TraceEventFlag(
+                $"wait-wake pattern=0x{pattern:X16} mode=0x{waitMode:X2} bits=0x{state.Bits:X16} waiters={state.WaitingThreads}");
+            return true;
+        }
+    }
+
+    private static string GetEventFlagWakeKey(ulong handle) =>
+        $"event_flag:0x{handle:X16}";
+
     private static bool TryWriteResultPattern(CpuContext ctx, ulong address, ulong bits) =>
         address == 0 || ctx.TryWriteUInt64(address, bits);
 
@@ -414,6 +519,19 @@ public static class KernelEventFlagCompatExports
         return true;
     }
 
+    private static bool TryReadByte(CpuContext ctx, ulong address, out byte value)
+    {
+        Span<byte> buffer = stackalloc byte[1];
+        if (!ctx.Memory.TryRead(address, buffer))
+        {
+            value = 0;
+            return false;
+        }
+
+        value = buffer[0];
+        return true;
+    }
+
     private static bool TryWriteUInt32(CpuContext ctx, ulong address, uint value)
     {
         Span<byte> buffer = stackalloc byte[sizeof(uint)];
@@ -466,4 +584,95 @@ public static class KernelEventFlagCompatExports
             ? frame.ReturnRip
             : 0UL;
 
+    private static string FormatFrameChain(CpuContext ctx)
+    {
+        Span<ulong> returns = stackalloc ulong[4];
+        var count = 0;
+        var frame = ctx[CpuRegister.Rbp];
+        for (var index = 0; index < returns.Length && frame != 0; index++)
+        {
+            if (!ctx.TryReadUInt64(frame, out var nextFrame) ||
+                !ctx.TryReadUInt64(frame + sizeof(ulong), out var returnAddress))
+            {
+                break;
+            }
+
+            returns[count++] = returnAddress;
+            if (nextFrame <= frame)
+            {
+                break;
+            }
+
+            frame = nextFrame;
+        }
+
+        return count switch
+        {
+            0 => "none",
+            1 => $"0x{returns[0]:X16}",
+            2 => $"0x{returns[0]:X16},0x{returns[1]:X16}",
+            3 => $"0x{returns[0]:X16},0x{returns[1]:X16},0x{returns[2]:X16}",
+            _ => $"0x{returns[0]:X16},0x{returns[1]:X16},0x{returns[2]:X16},0x{returns[3]:X16}",
+        };
+    }
+
+    private static string FormatGuestWaitObject(CpuContext ctx)
+    {
+        var r12 = ctx[CpuRegister.R12];
+        var r13 = ctx[CpuRegister.R13];
+        var objectAddress = r12 != 0
+            ? r12
+            : r13 >= 0xA8
+                ? r13 - 0xA8
+                : 0;
+
+        var builder = new StringBuilder(256);
+        builder.Append($"r12=0x{r12:X16} r13=0x{r13:X16}");
+        if (objectAddress == 0)
+        {
+            return builder.ToString();
+        }
+
+        builder.Append($" obj=0x{objectAddress:X16}");
+        AppendUInt32(builder, ctx, objectAddress + 0x58, "o58");
+        AppendUInt32(builder, ctx, objectAddress + 0x5C, "o5C");
+        AppendUInt64(builder, ctx, objectAddress + 0x60, "o60");
+        AppendByte(builder, ctx, objectAddress + 0x6C, "state6C");
+        AppendByte(builder, ctx, objectAddress + 0x6D, "o6D");
+        AppendByte(builder, ctx, objectAddress + 0xA0, "waitA0");
+        AppendByte(builder, ctx, objectAddress + 0xA1, "stateA1");
+        AppendByte(builder, ctx, objectAddress + 0xA2, "oA2");
+        AppendUInt64(builder, ctx, objectAddress + 0xA8, "eventA8");
+        if (r13 != 0)
+        {
+            AppendUInt64(builder, ctx, r13, "r13_0");
+            AppendUInt64(builder, ctx, r13 + 8, "r13_8");
+        }
+
+        return builder.ToString();
+    }
+
+    private static void AppendByte(StringBuilder builder, CpuContext ctx, ulong address, string name)
+    {
+        if (TryReadByte(ctx, address, out var value))
+        {
+            builder.Append($" {name}=0x{value:X2}");
+        }
+    }
+
+    private static void AppendUInt32(StringBuilder builder, CpuContext ctx, ulong address, string name)
+    {
+        if (TryReadUInt32(ctx, address, out var value))
+        {
+            builder.Append($" {name}=0x{value:X8}");
+        }
+    }
+
+    private static void AppendUInt64(StringBuilder builder, CpuContext ctx, ulong address, string name)
+    {
+        if (TryReadUInt64(ctx, address, out var value))
+        {
+            builder.Append($" {name}=0x{value:X16}");
+        }
+    }
 }

src/SharpEmu.Libs/Kernel/KernelEventQueueCompatExports.cs

@@ -93,6 +93,19 @@ public static class KernelEventQueueCompatExports
         }
     }
 
+    private sealed class EqueueWaiter : IGuestThreadBlockWaiter
+    {
+        public required CpuContext Ctx { get; init; }
+        public required ulong Handle { get; init; }
+        public required ulong EventsAddress { get; init; }
+        public required int EventCapacity { get; init; }
+        public required ulong OutCountAddress { get; init; }
+
+        public int Resume() => ResumeWaitEqueue(Ctx, Handle, EventsAddress, EventCapacity, OutCountAddress);
+
+        public bool TryWake() => HasPendingEvents(Handle);
+    }
+
     [SysAbiExport(
         Nid = "D0OdFMjp46I",
         ExportName = "sceKernelCreateEqueue",
@@ -136,10 +149,10 @@ public static class KernelEventQueueCompatExports
             _eventQueues.Remove(handle);
             _pendingEvents.Remove(handle);
             _registeredEvents.Remove(handle);
-            // Wake any thread parked on this queue so it observes the deletion.
-            Monitor.PulseAll(_eventQueueGate);
         }
 
+        _wakeKeys.TryRemove(handle, out _);
+
         TraceEventQueue(ctx, "delete", handle);
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
@@ -399,81 +412,59 @@ public static class KernelEventQueueCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
 
-        // No events ready: block this host thread in place on the queue gate.
-        // Monitor.Wait releases the gate and parks atomically, so an
-        // EnqueueEvent/TriggerDisplayEvent PulseAll issued the instant after
-        // the emptiness check cannot be lost. kqueue/kevent semantics: sleep
-        // until an event matching a registration is delivered or the timeout
-        // (usec, infinite when the arg pointer is null) lapses; a zero timeout
-        // degrades to an instant poll.
-        long deadline;
-        if (timeoutAddress == 0)
-        {
-            deadline = long.MaxValue;
-        }
-        else if (timeoutUsec == 0)
-        {
-            deadline = 0;
-        }
-        else
-        {
-            deadline = Environment.TickCount64 + Math.Max(1L, timeoutUsec / 1000L);
-        }
-
-        TraceEventQueue(ctx, "wait-block", handle);
-        var guestThreadHandle = GuestThreadExecution.CurrentGuestThreadHandle;
-        GuestThreadBlocking.NoteBlocked(guestThreadHandle, "sceKernelWaitEqueue");
-        try
-        {
-            lock (_eventQueueGate)
-            {
-                while (true)
+        if (timeoutAddress == 0 &&
+            GuestThreadExecution.RequestCurrentThreadBlock(
+                ctx,
+                "sceKernelWaitEqueue",
+                GetEventQueueWakeKey(handle),
+                new EqueueWaiter
                 {
-                    if ((_pendingEvents.TryGetValue(handle, out var queue) && queue.Count != 0) ||
-                        !_eventQueues.Contains(handle) ||
-                        GuestThreadBlocking.ShutdownRequested)
-                    {
-                        break;
-                    }
-
-                    var remaining = deadline - Environment.TickCount64;
-                    if (timeoutAddress != 0 && remaining <= 0)
-                    {
-                        break;
-                    }
-
-                    var slice = timeoutAddress == 0
-                        ? GuestThreadBlocking.WaitSliceMilliseconds
-                        : (int)Math.Min(remaining, GuestThreadBlocking.WaitSliceMilliseconds);
-                    GuestThreadBlocking.Checkpoint(guestThreadHandle, _eventQueueGate);
-                    _ = Monitor.Wait(_eventQueueGate, slice);
-                }
-            }
-        }
-        finally
+                    Ctx = ctx,
+                    Handle = handle,
+                    EventsAddress = eventsAddress,
+                    EventCapacity = eventCapacity,
+                    OutCountAddress = outCountAddress,
+                }))
         {
-            GuestThreadBlocking.NoteUnblocked(guestThreadHandle);
-        }
-
-        deliveredCount = DequeueEvents(ctx, handle, eventsAddress, eventCapacity);
-        if (outCountAddress != 0 && !TryWriteUInt32(ctx, outCountAddress, (uint)deliveredCount))
-        {
-            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
-        }
-
-        if (deliveredCount > 0)
-        {
-            TraceEventQueue(ctx, "wait-deliver", handle);
+            TraceEventQueue(ctx, "wait-block", handle);
             return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
 
-        if (timeoutAddress != 0)
+        if (timeoutAddress != 0 && ctx.TryReadUInt64(timeoutAddress, out var timeoutRaw))
         {
+            var timeoutMicros = timeoutRaw & 0xFFFF_FFFFUL;
+            var deadline = Environment.TickCount64 +
+                Math.Max(1L, (long)Math.Min(timeoutMicros / 1000, int.MaxValue));
+            lock (_eventQueueGate)
+            {
+                while (!HasPendingEvents(handle))
+                {
+                    var remaining = deadline - Environment.TickCount64;
+                    if (remaining <= 0)
+                    {
+                        break;
+                    }
+
+                    Monitor.Wait(_eventQueueGate, (int)Math.Min(remaining, 100));
+                }
+            }
+
+            deliveredCount = DequeueEvents(ctx, handle, eventsAddress, eventCapacity);
+            if (outCountAddress != 0 && !TryWriteUInt32(ctx, outCountAddress, (uint)deliveredCount))
+            {
+                return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+            }
+
+            if (deliveredCount > 0)
+            {
+                TraceEventQueue(ctx, "wait-timed-deliver", handle);
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+
             TraceEventQueue(ctx, "wait-timeout", handle);
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT;
         }
 
-        // Reached only on queue deletion or teardown; the guest sees zero events.
         TraceEventQueue(ctx, "wait", handle);
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
@@ -807,6 +798,32 @@ public static class KernelEventQueueCompatExports
         return triggered;
     }
 
+    private static int ResumeWaitEqueue(
+        CpuContext ctx,
+        ulong handle,
+        ulong eventsAddress,
+        int eventCapacity,
+        ulong outCountAddress)
+    {
+        var deliveredCount = DequeueEvents(ctx, handle, eventsAddress, eventCapacity);
+        if (outCountAddress != 0 && !TryWriteUInt32(ctx, outCountAddress, (uint)deliveredCount))
+        {
+            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
+        }
+
+        return deliveredCount > 0
+            ? (int)OrbisGen2Result.ORBIS_GEN2_OK
+            : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT;
+    }
+
+    private static bool HasPendingEvents(ulong handle)
+    {
+        lock (_eventQueueGate)
+        {
+            return _pendingEvents.TryGetValue(handle, out var events) && events.Count != 0;
+        }
+    }
+
     private static void QueueOrUpdateEvent(
         KernelEventDeque queue,
         KernelQueuedEvent queuedEvent)
@@ -824,16 +841,16 @@ public static class KernelEventQueueCompatExports
         };
     }
 
-    // Wake threads parked in-place on the queue gate; each re-checks for a
-    // matching pending event. The handle is unused (all queues share one gate)
-    // but kept in the signature so call sites read intent-fully.
+    // Wake keys are formatted once per handle: WakeEventQueue runs on every event
+    // enqueue (vblank/flip edges included), so formatting there is steady string churn.
+    private static readonly ConcurrentDictionary<ulong, string> _wakeKeys = new();
+
+    private static string GetEventQueueWakeKey(ulong handle) =>
+        _wakeKeys.GetOrAdd(handle, static h => $"sceKernelWaitEqueue:{h:X16}");
+
     private static void WakeEventQueue(ulong handle)
     {
-        _ = handle;
-        lock (_eventQueueGate)
-        {
-            Monitor.PulseAll(_eventQueueGate);
-        }
+        _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(GetEventQueueWakeKey(handle));
     }
 
     private static int DequeueEvents(CpuContext ctx, ulong handle, ulong eventsAddress, int eventCapacity)

src/SharpEmu.Libs/Kernel/KernelMemoryCompatExports.cs

@@ -224,21 +224,6 @@ public static partial class KernelMemoryCompatExports
         }
     }
 
-    /// <summary>Removes a guest mount registered by <see cref="RegisterGuestPathMount"/>.</summary>
-    public static bool UnregisterGuestPathMount(string guestMountPoint)
-    {
-        var normalizedMountPoint = NormalizeGuestStatCachePath(guestMountPoint);
-        if (normalizedMountPoint is null)
-        {
-            return false;
-        }
-
-        lock (_guestMountGate)
-        {
-            return _guestMounts.Remove(normalizedMountPoint);
-        }
-    }
-
     internal static bool TryAllocateHleData(
         CpuContext ctx,
         ulong length,
@@ -1111,7 +1096,6 @@ public static partial class KernelMemoryCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
         }
 
-        ctx[CpuRegister.Rax] = destination;
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
@@ -1819,15 +1803,6 @@ public static partial class KernelMemoryCompatExports
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
-    // POSIX alias; same Orbis result convention as the other posix-named
-    // file exports in this module (mkdir/rmdir/open).
-    [SysAbiExport(
-        Nid = "VAzswvTOCzI",
-        ExportName = "unlink",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PosixUnlink(CpuContext ctx) => KernelUnlink(ctx);
-
     [SysAbiExport(
         Nid = "AUXVxWeJU-A",
         ExportName = "sceKernelUnlink",
@@ -6019,7 +5994,7 @@ public static partial class KernelMemoryCompatExports
         return highWaterMark;
     }
 
-    private static unsafe bool TryReadHostMemory(ulong address, Span<byte> destination)
+    private static bool TryReadHostMemory(ulong address, Span<byte> destination)
     {
         if (destination.IsEmpty || !IsHostRangeAccessible(address, (ulong)destination.Length, writeAccess: false))
         {
@@ -6028,7 +6003,9 @@ public static partial class KernelMemoryCompatExports
 
         try
         {
-            new ReadOnlySpan<byte>((void*)address, destination.Length).CopyTo(destination);
+            var temporary = new byte[destination.Length];
+            Marshal.Copy((nint)address, temporary, 0, temporary.Length);
+            temporary.AsSpan().CopyTo(destination);
             return true;
         }
         catch
@@ -6068,41 +6045,6 @@ public static partial class KernelMemoryCompatExports
         return false;
     }
 
-    internal static bool TryReadShaderGuestMemory(
-        ulong address,
-        Span<byte> destination)
-    {
-        if (destination.IsEmpty)
-        {
-            return true;
-        }
-
-        if (TryReadTrackedLibcHeap(address, destination))
-        {
-            return true;
-        }
-
-        var length = (ulong)destination.Length;
-        lock (_memoryGate)
-        {
-            if (TryFindVirtualQueryRegionLocked(
-                    address,
-                    findNext: false,
-                    out var region) &&
-                length <= region.Length &&
-                address >= region.Address &&
-                length <= region.Address + region.Length - address)
-            {
-                return TryReadHostMemory(address, destination);
-            }
-        }
-
-        // Direct execution uses guest virtual addresses as host virtual addresses.
-        // Some native mmap paths predate _mappedRegions tracking, so retain the same
-        // committed/readable-page fallback used by the libc compatibility layer.
-        return TryReadHostMemory(address, destination);
-    }
-
     internal static bool TryReadTrackedLibcHeapGpuAlias(
         ulong packedAddress,
         Span<byte> destination)
@@ -6382,7 +6324,7 @@ public static partial class KernelMemoryCompatExports
         return value != 0 && (value & (value - 1)) == 0;
     }
 
-    private static unsafe bool TryWriteHostMemory(ulong address, ReadOnlySpan<byte> source)
+    private static bool TryWriteHostMemory(ulong address, ReadOnlySpan<byte> source)
     {
         if (source.IsEmpty || !IsHostRangeAccessible(address, (ulong)source.Length, writeAccess: true))
         {
@@ -6391,7 +6333,8 @@ public static partial class KernelMemoryCompatExports
 
         try
         {
-            source.CopyTo(new Span<byte>((void*)address, source.Length));
+            var temporary = source.ToArray();
+            Marshal.Copy(temporary, 0, (nint)address, temporary.Length);
             return true;
         }
         catch
@@ -6418,37 +6361,20 @@ public static partial class KernelMemoryCompatExports
             return false;
         }
 
-        var endAddress = address + length - 1;
-        var currentAddress = address;
-        while (currentAddress <= endAddress)
+        if (!TryQueryHostPage(address, out var startInfo) || !HasRequiredProtection(startInfo.Protect, writeAccess))
         {
-            if (!TryQueryHostPage(currentAddress, out var info) ||
-                !HasRequiredProtection(info.Protect, writeAccess))
-            {
-                return false;
-            }
+            return false;
+        }
 
-            var regionBase = unchecked((ulong)info.BaseAddress);
-            var regionSize = (ulong)info.RegionSize;
-            if (regionSize == 0 ||
-                regionBase > currentAddress ||
-                ulong.MaxValue - regionBase < regionSize)
-            {
-                return false;
-            }
+        var endAddress = address + length - 1;
+        if (endAddress == address)
+        {
+            return true;
+        }
 
-            var regionEnd = regionBase + regionSize;
-            if (regionEnd <= currentAddress)
-            {
-                return false;
-            }
-
-            if (regionEnd > endAddress)
-            {
-                return true;
-            }
-
-            currentAddress = regionEnd;
+        if (!TryQueryHostPage(endAddress, out var endInfo) || !HasRequiredProtection(endInfo.Protect, writeAccess))
+        {
+            return false;
         }
 
         return true;

src/SharpEmu.Libs/Kernel/KernelPthreadCompatExports.cs

@@ -37,35 +37,55 @@ public static class KernelPthreadCompatExports
         string.Equals(Environment.GetEnvironmentVariable("SHARPEMU_LOG_PTHREAD_CONDS"), "1", StringComparison.Ordinal);
     private static readonly HashSet<ulong>? _tracePthreadMutexFilter = ParseTraceAddressFilter(
         Environment.GetEnvironmentVariable("SHARPEMU_LOG_PTHREAD_MUTEX_FILTER"));
+    private static long _nextSynchronizationWaiterId;
 
-    // Blocking model: waiters block their own host thread in place via
-    // Monitor.Wait on the state object (mutexes) or SyncRoot (condvars).
-    // Block-and-wake is therefore atomic — no waiter queues, wake keys, or
-    // continuation hand-offs, and no lost-wakeup window between a thread
-    // deciding to block and registering as blocked.
     private sealed class PthreadMutexState
     {
         public ulong OwnerThreadId { get; set; }
         public int RecursionCount { get; set; }
         public int Type { get; set; } = MutexTypeErrorCheck;
         public int Protocol { get; set; }
-        // Threads currently blocked in PthreadMutexLockCore; destroy reports BUSY while nonzero.
-        public int WaiterCount { get; set; }
+        public LinkedList<PthreadMutexWaiter> Waiters { get; } = new();
+    }
+
+    private sealed class PthreadMutexWaiter
+    {
+        public required ulong ThreadId { get; init; }
+        public required string WakeKey { get; init; }
+        public required bool Cooperative { get; init; }
+        public LinkedListNode<PthreadMutexWaiter>? Node { get; set; }
+        public int Granted;
     }
 
     private sealed class PthreadCondState
     {
         public object SyncRoot { get; } = new();
+        public LinkedList<PthreadCondWaiter> WaiterQueue { get; } = new();
         public ulong SignalEpoch { get; set; }
         public int Waiters { get; set; }
-        // Signals produced but not yet consumed by a waiter. A signal only
-        // increments this when an unserved waiter exists (POSIX: signaling an
-        // empty condvar is a no-op), so stale signals cannot accumulate.
-        public int SignalsPending { get; set; }
+    }
+
+    private sealed class PthreadCondWaiter
+    {
+        public required ulong ThreadId { get; init; }
+        public required PthreadMutexState MutexState { get; init; }
+        public required string WakeKey { get; init; }
+        public required bool Cooperative { get; init; }
+        public bool PosixErrors { get; init; }
+        public LinkedListNode<PthreadCondWaiter>? Node { get; set; }
+        public PthreadMutexWaiter? MutexWaiter { get; set; }
+        public Timer? TimeoutTimer { get; set; }
+        // 0 = waiting, 1 = signaled, 2 = timed out.
+        public int CompletionState { get; set; }
     }
 
     private readonly record struct PthreadMutexAttrState(int Type, int Protocol);
 
+    static KernelPthreadCompatExports()
+    {
+        RunSynchronizationSelfChecks();
+    }
+
     [SysAbiExport(
         Nid = "aI+OeCz8xrQ",
         ExportName = "scePthreadSelf",
@@ -119,13 +139,6 @@ public static class KernelPthreadCompatExports
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
-    [SysAbiExport(
-        Nid = "9vyP6Z7bqzc",
-        ExportName = "pthread_rename_np",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PosixPthreadRenameNp(CpuContext ctx) => PthreadRename(ctx);
-
     [SysAbiExport(
         Nid = "GBUY7ywdULE",
         ExportName = "scePthreadRename",
@@ -610,7 +623,7 @@ public static class KernelPthreadCompatExports
 
         lock (state)
         {
-            if (state.OwnerThreadId != 0 || state.RecursionCount != 0 || state.WaiterCount != 0)
+            if (state.OwnerThreadId != 0 || state.RecursionCount != 0 || state.Waiters.Count != 0)
             {
                 return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
             }
@@ -640,6 +653,10 @@ public static class KernelPthreadCompatExports
         }
 
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
+        var canCooperativelyBlock = !tryOnly &&
+            GuestThreadExecution.IsGuestThread &&
+            GuestThreadExecution.TryGetCurrentImportCallFrame(out _);
+        PthreadMutexWaiter? waiter = null;
         lock (state)
         {
             if (state.OwnerThreadId == currentThreadId)
@@ -679,7 +696,7 @@ public static class KernelPthreadCompatExports
                 }
             }
 
-            if (state.OwnerThreadId == 0)
+            if (state.OwnerThreadId == 0 && state.Waiters.Count == 0)
             {
                 state.OwnerThreadId = currentThreadId;
                 state.RecursionCount = 1;
@@ -693,39 +710,24 @@ public static class KernelPthreadCompatExports
                 return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
             }
 
-            // Contended: block this host thread in place until the owner
-            // releases. Monitor.Wait atomically releases the state lock and
-            // parks, so an unlock's PulseAll cannot be missed. Waits are
-            // sliced only so teardown can unwind parked threads.
+            waiter = EnqueueMutexWaiterLocked(state, currentThreadId, canCooperativelyBlock);
+        }
+
+        if (canCooperativelyBlock && waiter is not null &&
+            GuestThreadExecution.RequestCurrentThreadBlock(
+                ctx,
+                "pthread_mutex_lock",
+                waiter.WakeKey,
+                () => CompleteBlockedMutexLock(ctx, mutexAddress, resolvedAddress, state, waiter),
+                () => TryGrantBlockedMutexLock(ctx, mutexAddress, resolvedAddress, state, waiter)))
+        {
             TracePthreadMutex(ctx, "lock-block", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
-            GuestThreadBlocking.NoteBlocked(currentThreadId, "pthread_mutex_lock");
-            state.WaiterCount++;
-            try
-            {
-                while (state.OwnerThreadId != 0)
-                {
-                    if (GuestThreadBlocking.ShutdownRequested)
-                    {
-                        TracePthreadMutex(ctx, "lock-shutdown", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN);
-                        return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN;
-                    }
-
-                    GuestThreadBlocking.Checkpoint(currentThreadId, state);
-                    _ = Monitor.Wait(state, GuestThreadBlocking.WaitSliceMilliseconds);
-                }
-
-                state.OwnerThreadId = currentThreadId;
-                state.RecursionCount = 1;
-            }
-            finally
-            {
-                state.WaiterCount--;
-                GuestThreadBlocking.NoteUnblocked(currentThreadId);
-            }
-
-            TracePthreadMutex(ctx, "lock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
             return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
+
+        var hostResult = WaitForHostMutexLock(state, waiter!);
+        TracePthreadMutex(ctx, "lock", mutexAddress, resolvedAddress, state, currentThreadId, hostResult);
+        return hostResult;
     }
 
     private static int PthreadMutexUnlockCore(CpuContext ctx, ulong mutexAddress, bool requireOwner)
@@ -742,6 +744,7 @@ public static class KernelPthreadCompatExports
         }
 
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
+        string? nextWakeKey = null;
         lock (state)
         {
             if (state.RecursionCount <= 0)
@@ -760,13 +763,18 @@ public static class KernelPthreadCompatExports
             if (state.RecursionCount == 0)
             {
                 state.OwnerThreadId = 0;
-                if (state.WaiterCount != 0)
-                {
-                    Monitor.PulseAll(state);
-                }
+                nextWakeKey = state.Waiters.First?.Value.Cooperative == true
+                    ? state.Waiters.First.Value.WakeKey
+                    : null;
+                Monitor.PulseAll(state);
             }
         }
 
+        if (nextWakeKey is not null)
+        {
+            _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(nextWakeKey, 1);
+        }
+
         TracePthreadMutex(ctx, "unlock", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
@@ -1183,7 +1191,7 @@ public static class KernelPthreadCompatExports
 
             lock (state.SyncRoot)
             {
-                if (state.Waiters != 0)
+                if (state.WaiterQueue.Count != 0)
                 {
                     return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
                 }
@@ -1226,21 +1234,7 @@ public static class KernelPthreadCompatExports
         var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
         lock (mutexState)
         {
-            if (mutexState.OwnerThreadId == 0 && mutexState.RecursionCount == 0)
-            {
-                // The guest holds the mutex through a path our host-side tracking
-                // never observed — most commonly libkernel's uncontended userspace
-                // fast-path, which locks the mutex word directly without an HLE
-                // call. Real pthread_cond_wait requires the caller to own the
-                // mutex and does not verify it for normal mutexes, so returning
-                // EPERM here is wrong: it spins the guest and, worse, leaves the
-                // mutex held (the unlock below is skipped), wedging every thread
-                // that later blocks on pthread_mutex_lock. Adopt ownership so the
-                // unlock/wait/re-lock cycle is balanced and releases the mutex.
-                mutexState.OwnerThreadId = currentThreadId;
-                mutexState.RecursionCount = 1;
-            }
-            else if (mutexState.OwnerThreadId != currentThreadId || mutexState.RecursionCount != 1)
+            if (mutexState.OwnerThreadId != currentThreadId || mutexState.RecursionCount != 1)
             {
                 return mutexState.OwnerThreadId == currentThreadId
                     ? (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT
@@ -1248,80 +1242,94 @@ public static class KernelPthreadCompatExports
             }
         }
 
-        var signaled = false;
+        var cooperative = GuestThreadExecution.IsGuestThread &&
+            GuestThreadExecution.TryGetCurrentImportCallFrame(out _);
+        var waiter = new PthreadCondWaiter
+        {
+            ThreadId = currentThreadId,
+            MutexState = mutexState,
+            Cooperative = cooperative,
+            PosixErrors = posixErrors,
+            WakeKey = cooperative
+                ? $"pthread_cond_waiter:{Interlocked.Increment(ref _nextSynchronizationWaiterId)}"
+                : string.Empty,
+        };
+
         lock (state.SyncRoot)
         {
+            waiter.Node = state.WaiterQueue.AddLast(waiter);
             state.Waiters++;
             TracePthreadCond("wait-enter", condAddress, mutexAddress, state, timed, (int)OrbisGen2Result.ORBIS_GEN2_OK);
 
-            // POSIX atomicity: we are registered as a waiter (Waiters++ under
-            // SyncRoot) before the mutex is released, so a signal issued the
-            // instant the mutex unlocks already counts us and lands in
-            // SignalsPending — checked before the first Monitor.Wait. No
-            // window exists where a wake can be lost.
             var unlockResult = PthreadMutexUnlockCore(ctx, mutexAddress, requireOwner: true);
             if (unlockResult != (int)OrbisGen2Result.ORBIS_GEN2_OK)
             {
-                state.Waiters--;
+                RemoveCondWaiterLocked(state, waiter);
                 TracePthreadCond("wait-unlock-fail", condAddress, mutexAddress, state, timed, unlockResult);
                 return unlockResult;
             }
 
-            var deadline = timed
-                ? GuestThreadExecution.ComputeDeadlineTimestamp(GetCondWaitTimeout(timeoutUsec))
-                : long.MaxValue;
-            GuestThreadBlocking.NoteBlocked(currentThreadId, timed ? "pthread_cond_timedwait" : "pthread_cond_wait");
-            try
+            if (cooperative && timed)
             {
-                while (state.SignalsPending == 0 && !GuestThreadBlocking.ShutdownRequested)
-                {
-                    var remaining = timed
-                        ? GetRemainingTimeout(deadline)
-                        : TimeSpan.FromMilliseconds(GuestThreadBlocking.WaitSliceMilliseconds);
-                    if (timed && remaining <= TimeSpan.Zero)
+                waiter.TimeoutTimer = new Timer(
+                    static callbackState =>
                     {
-                        break;
-                    }
-
-                    if (remaining > TimeSpan.FromMilliseconds(GuestThreadBlocking.WaitSliceMilliseconds))
-                    {
-                        remaining = TimeSpan.FromMilliseconds(GuestThreadBlocking.WaitSliceMilliseconds);
-                    }
-
-                    GuestThreadBlocking.Checkpoint(currentThreadId, state.SyncRoot);
-                    _ = Monitor.Wait(state.SyncRoot, remaining);
-                }
-            }
-            finally
-            {
-                GuestThreadBlocking.NoteUnblocked(currentThreadId);
-            }
-
-            if (state.SignalsPending > 0)
-            {
-                state.SignalsPending--;
-                signaled = true;
-            }
-
-            state.Waiters--;
-            if (state.SignalsPending > state.Waiters)
-            {
-                // A timed-out waiter left a signal unconsumed with nobody
-                // remaining to take it; drop it so a future wait does not
-                // observe a phantom wake (signals on an empty condvar are
-                // no-ops on real hardware).
-                state.SignalsPending = state.Waiters;
+                        var (condState, condWaiter) = ((PthreadCondState, PthreadCondWaiter))callbackState!;
+                        CompleteCondWaiter(condState, condWaiter, timedOut: true);
+                    },
+                    (state, waiter),
+                    GetCondWaitTimeout(timeoutUsec),
+                    Timeout.InfiniteTimeSpan);
             }
         }
 
-        // POSIX guarantees the mutex is re-acquired on every return path,
-        // signaled or timed out. Blocks in place like any other locker.
-        _ = PthreadMutexLockCore(ctx, mutexAddress, tryOnly: false);
+        if (cooperative &&
+            GuestThreadExecution.RequestCurrentThreadBlock(
+                ctx,
+                timed ? "pthread_cond_timedwait" : "pthread_cond_wait",
+                waiter.WakeKey,
+                () => CompleteBlockedCondWait(ctx, condAddress, mutexAddress, state, waiter),
+                () => TryGrantCondWaiterMutex(waiter)))
+        {
+            TracePthreadCond("wait-block", condAddress, mutexAddress, state, timed, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+            return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+        }
 
-        var waitResult = signaled || !timed
-            ? (int)OrbisGen2Result.ORBIS_GEN2_OK
-            : CondTimedOutResult(posixErrors);
-        TracePthreadCond(signaled ? "wait-exit" : "wait-exit-timeout", condAddress, mutexAddress, state, timed, waitResult);
+        // Non-guest callers have no resumable CPU continuation. Park only
+        // those host-side compatibility callers, preserving the same FIFO
+        // mutex reacquisition rules as cooperative guest waiters.
+        lock (state.SyncRoot)
+        {
+            var deadline = timed
+                ? GuestThreadExecution.ComputeDeadlineTimestamp(GetCondWaitTimeout(timeoutUsec))
+                : long.MaxValue;
+            while (waiter.CompletionState == 0)
+            {
+                if (!timed)
+                {
+                    Monitor.Wait(state.SyncRoot);
+                    continue;
+                }
+
+                var remaining = GetRemainingTimeout(deadline);
+                if (remaining <= TimeSpan.Zero || !Monitor.Wait(state.SyncRoot, remaining))
+                {
+                    CompleteCondWaiterLocked(state, waiter, timedOut: true);
+                    break;
+                }
+            }
+        }
+
+        if (waiter.MutexWaiter is null)
+        {
+            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT;
+        }
+
+        _ = WaitForHostMutexLock(mutexState, waiter.MutexWaiter);
+        var waitResult = waiter.CompletionState == 2
+            ? CondTimedOutResult(waiter)
+            : (int)OrbisGen2Result.ORBIS_GEN2_OK;
+        TracePthreadCond(waiter.CompletionState == 2 ? "wait-exit-timeout" : "wait-exit", condAddress, mutexAddress, state, timed, waitResult);
         return waitResult;
     }
 
@@ -1337,36 +1345,280 @@ public static class KernelPthreadCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND;
         }
 
+        List<PthreadCondWaiter>? completedWaiters = null;
         lock (state.SyncRoot)
         {
             state.SignalEpoch++;
-            if (broadcast)
+            for (var node = state.WaiterQueue.First; node is not null;)
             {
-                state.SignalsPending = state.Waiters;
-            }
-            else if (state.SignalsPending < state.Waiters)
-            {
-                // Only count a signal an unserved waiter can consume; signaling
-                // an empty condvar is a no-op per POSIX.
-                state.SignalsPending++;
-            }
+                var next = node.Next;
+                var waiter = node.Value;
+                if (waiter.CompletionState == 0 && CompleteCondWaiterLocked(state, waiter, timedOut: false))
+                {
+                    (completedWaiters ??= new List<PthreadCondWaiter>()).Add(waiter);
+                    if (!broadcast)
+                    {
+                        break;
+                    }
+                }
 
-            if (state.Waiters != 0)
-            {
-                Monitor.PulseAll(state.SyncRoot);
+                node = next;
             }
 
             TracePthreadCond(broadcast ? "broadcast" : "signal", condAddress, mutexAddress: 0, state, timed: false, (int)OrbisGen2Result.ORBIS_GEN2_OK);
         }
 
+        if (completedWaiters is not null)
+        {
+            foreach (var waiter in completedWaiters)
+            {
+                WakeCooperativeWaiter(waiter);
+            }
+        }
+
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
-    private static int CondTimedOutResult(bool posixErrors) =>
-        posixErrors
+    private static PthreadMutexWaiter EnqueueMutexWaiterLocked(
+        PthreadMutexState state,
+        ulong threadId,
+        bool cooperative,
+        string? wakeKey = null)
+    {
+        var waiter = new PthreadMutexWaiter
+        {
+            ThreadId = threadId,
+            Cooperative = cooperative,
+            WakeKey = cooperative
+                ? wakeKey ?? $"pthread_mutex_waiter:{Interlocked.Increment(ref _nextSynchronizationWaiterId)}"
+                : string.Empty,
+        };
+        waiter.Node = state.Waiters.AddLast(waiter);
+        return waiter;
+    }
+
+    [Conditional("DEBUG")]
+    private static void RunSynchronizationSelfChecks()
+    {
+        var mutex = new PthreadMutexState();
+        PthreadMutexWaiter first;
+        PthreadMutexWaiter second;
+        lock (mutex)
+        {
+            first = EnqueueMutexWaiterLocked(mutex, 0x101, cooperative: false);
+            second = EnqueueMutexWaiterLocked(mutex, 0x202, cooperative: false);
+            Debug.Assert(!TryGrantMutexWaiterLocked(mutex, second), "A mutex waiter bypassed FIFO order.");
+            Debug.Assert(TryGrantMutexWaiterLocked(mutex, first), "The FIFO mutex head was not granted.");
+            Debug.Assert(mutex.OwnerThreadId == first.ThreadId && mutex.RecursionCount == 1, "Mutex ownership was not transferred atomically.");
+            mutex.OwnerThreadId = 0;
+            mutex.RecursionCount = 0;
+            Debug.Assert(TryGrantMutexWaiterLocked(mutex, second), "The second mutex waiter was not granted after release.");
+        }
+
+        var cond = new PthreadCondState();
+        var condMutex = new PthreadMutexState();
+        var condWaiter = new PthreadCondWaiter
+        {
+            ThreadId = 0x303,
+            MutexState = condMutex,
+            WakeKey = string.Empty,
+            Cooperative = false,
+        };
+        lock (cond.SyncRoot)
+        {
+            condWaiter.Node = cond.WaiterQueue.AddLast(condWaiter);
+            cond.Waiters++;
+            Debug.Assert(CompleteCondWaiterLocked(cond, condWaiter, timedOut: false), "A condition waiter was not completed.");
+            Debug.Assert(cond.WaiterQueue.Count == 0 && cond.Waiters == 0 && condWaiter.MutexWaiter is not null, "Condition completion did not atomically queue mutex reacquisition.");
+        }
+    }
+
+    private static bool TryGrantMutexWaiterLocked(PthreadMutexState state, PthreadMutexWaiter waiter)
+    {
+        if (Volatile.Read(ref waiter.Granted) != 0)
+        {
+            return true;
+        }
+
+        if (state.OwnerThreadId != 0 ||
+            waiter.Node is null ||
+            !ReferenceEquals(state.Waiters.First, waiter.Node))
+        {
+            return false;
+        }
+
+        state.Waiters.Remove(waiter.Node);
+        waiter.Node = null;
+        state.OwnerThreadId = waiter.ThreadId;
+        state.RecursionCount = 1;
+        Volatile.Write(ref waiter.Granted, 1);
+        Monitor.PulseAll(state);
+        return true;
+    }
+
+    private static int WaitForHostMutexLock(PthreadMutexState state, PthreadMutexWaiter waiter)
+    {
+        lock (state)
+        {
+            while (!TryGrantMutexWaiterLocked(state, waiter))
+            {
+                Monitor.Wait(state);
+            }
+        }
+
+        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+    }
+
+    private static bool TryGrantBlockedMutexLock(
+        CpuContext ctx,
+        ulong mutexAddress,
+        ulong resolvedAddress,
+        PthreadMutexState state,
+        PthreadMutexWaiter waiter)
+    {
+        var granted = false;
+        lock (state)
+        {
+            granted = TryGrantMutexWaiterLocked(state, waiter);
+        }
+
+        TracePthreadMutex(
+            ctx,
+            granted ? "lock-reserve" : "lock-reserve-busy",
+            mutexAddress,
+            resolvedAddress,
+            state,
+            waiter.ThreadId,
+            granted ? (int)OrbisGen2Result.ORBIS_GEN2_OK : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY);
+        return granted;
+    }
+
+    private static int CompleteBlockedMutexLock(
+        CpuContext ctx,
+        ulong mutexAddress,
+        ulong resolvedAddress,
+        PthreadMutexState state,
+        PthreadMutexWaiter waiter)
+    {
+        var currentThreadId = KernelPthreadState.GetCurrentThreadHandle();
+        if (Volatile.Read(ref waiter.Granted) == 1)
+        {
+            TracePthreadMutex(ctx, "lock-resume", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_OK);
+            return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+        }
+
+        TracePthreadMutex(ctx, "lock-resume-ungranted", mutexAddress, resolvedAddress, state, currentThreadId, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY);
+        return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
+    }
+
+    private static bool CompleteCondWaiterLocked(
+        PthreadCondState state,
+        PthreadCondWaiter waiter,
+        bool timedOut)
+    {
+        if (waiter.CompletionState != 0)
+        {
+            return false;
+        }
+
+        waiter.CompletionState = timedOut ? 2 : 1;
+        RemoveCondWaiterLocked(state, waiter);
+        waiter.TimeoutTimer?.Dispose();
+        waiter.TimeoutTimer = null;
+
+        lock (waiter.MutexState)
+        {
+            waiter.MutexWaiter = EnqueueMutexWaiterLocked(
+                waiter.MutexState,
+                waiter.ThreadId,
+                waiter.Cooperative,
+                waiter.WakeKey);
+        }
+
+        Monitor.PulseAll(state.SyncRoot);
+        return true;
+    }
+
+    private static void CompleteCondWaiter(
+        PthreadCondState state,
+        PthreadCondWaiter waiter,
+        bool timedOut)
+    {
+        var completed = false;
+        lock (state.SyncRoot)
+        {
+            completed = CompleteCondWaiterLocked(state, waiter, timedOut);
+        }
+
+        if (completed)
+        {
+            WakeCooperativeWaiter(waiter);
+        }
+    }
+
+    private static void RemoveCondWaiterLocked(PthreadCondState state, PthreadCondWaiter waiter)
+    {
+        if (waiter.Node is not null)
+        {
+            state.WaiterQueue.Remove(waiter.Node);
+            waiter.Node = null;
+            state.Waiters = Math.Max(0, state.Waiters - 1);
+        }
+    }
+
+    private static bool TryGrantCondWaiterMutex(PthreadCondWaiter waiter)
+    {
+        var mutexWaiter = waiter.MutexWaiter;
+        if (waiter.CompletionState == 0 || mutexWaiter is null)
+        {
+            return false;
+        }
+
+        lock (waiter.MutexState)
+        {
+            return TryGrantMutexWaiterLocked(waiter.MutexState, mutexWaiter);
+        }
+    }
+
+    private static int CompleteBlockedCondWait(
+        CpuContext ctx,
+        ulong condAddress,
+        ulong mutexAddress,
+        PthreadCondState state,
+        PthreadCondWaiter waiter)
+    {
+        waiter.TimeoutTimer?.Dispose();
+        waiter.TimeoutTimer = null;
+        var result = waiter.MutexWaiter is not null &&
+            Volatile.Read(ref waiter.MutexWaiter.Granted) == 1
+                ? (waiter.CompletionState == 2
+                    ? CondTimedOutResult(waiter)
+                    : (int)OrbisGen2Result.ORBIS_GEN2_OK)
+                : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY;
+        TracePthreadCond(
+            waiter.CompletionState == 2 ? "wait-resume-timeout" : "wait-resume",
+            condAddress,
+            mutexAddress,
+            state,
+            waiter.CompletionState == 2,
+            result);
+        _ = ctx;
+        return result;
+    }
+
+    private static int CondTimedOutResult(PthreadCondWaiter waiter) =>
+        waiter.PosixErrors
             ? 60 // ETIMEDOUT on Orbis/FreeBSD; pthread APIs return errno directly.
             : (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT;
 
+    private static void WakeCooperativeWaiter(PthreadCondWaiter waiter)
+    {
+        if (waiter.Cooperative)
+        {
+            _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(waiter.WakeKey, 1);
+        }
+    }
+
     private static TimeSpan GetCondWaitTimeout(uint timeoutUsec)
     {
         if (timeoutUsec == 0)

src/SharpEmu.Libs/Kernel/KernelPthreadExtendedCompatExports.cs

@@ -91,6 +91,10 @@ public static class KernelPthreadExtendedCompatExports
         public PthreadAttrState Attributes { get; set; } = PthreadAttrState.Default;
     }
 
+    // On the outer class deliberately: a static on the nested state class gives it a type
+    // initializer that first runs on a guest thread and fail-fasts the CLR.
+    private static long _nextRwlockWakeId;
+
     private sealed class PthreadRwlockState
     {
         public object SyncRoot { get; } = new();
@@ -101,6 +105,8 @@ public static class KernelPthreadExtendedCompatExports
         public ulong WriterThreadId { get; set; }
         public int WaitingWriters { get; set; }
 
+        // See PthreadMutexState.WakeKey.
+        public string WakeKey { get; } = "pthread_rwlock#" + Interlocked.Increment(ref _nextRwlockWakeId).ToString("X");
 
         public int GetReaderCount(ulong threadId)
         {
@@ -162,6 +168,17 @@ public static class KernelPthreadExtendedCompatExports
         }
     }
 
+    private sealed class RwlockWaiter : IGuestThreadBlockWaiter
+    {
+        public required PthreadRwlockState Rwlock { get; init; }
+        public required ulong ThreadId { get; init; }
+        public required bool Write { get; init; }
+
+        public int Resume() => (int)OrbisGen2Result.ORBIS_GEN2_OK;
+
+        public bool TryWake() => TryAcquireBlockedRwlock(Rwlock, ThreadId, Write);
+    }
+
     private readonly record struct TlsKeyState(ulong Destructor);
 
     private readonly record struct PthreadAttrState(
@@ -1167,6 +1184,7 @@ public static class KernelPthreadExtendedCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_PERMISSION_DENIED;
         }
 
+        _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(rwlock.WakeKey);
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
@@ -1461,30 +1479,35 @@ public static class KernelPthreadExtendedCompatExports
                     return (int)OrbisGen2Result.ORBIS_GEN2_OK;
                 }
 
-                // In-place block: Monitor.Wait releases SyncRoot and parks
-                // atomically, so an unlock's PulseAll cannot be lost. Sliced
-                // only so teardown can unwind parked threads.
                 rwlock.WaitingWriters++;
-                GuestThreadBlocking.NoteBlocked(currentThreadId, "pthread_rwlock_wrlock");
+                var transferredToScheduler = false;
                 try
                 {
+                    if (GuestThreadExecution.IsGuestThread &&
+                        GuestThreadExecution.TryGetCurrentImportCallFrame(out _) &&
+                        GuestThreadExecution.RequestCurrentThreadBlock(
+                            ctx,
+                            "pthread_rwlock_wrlock",
+                            rwlock.WakeKey,
+                            new RwlockWaiter { Rwlock = rwlock, ThreadId = currentThreadId, Write = true }))
+                    {
+                        transferredToScheduler = true;
+                        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+                    }
+
                     while (rwlock.WriterThreadId != 0 || rwlock.ReaderTotalCount != 0 || rwlock.CompatWriterTotalCount != 0)
                     {
-                        if (GuestThreadBlocking.ShutdownRequested)
-                        {
-                            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN;
-                        }
-
-                        GuestThreadBlocking.Checkpoint(currentThreadId, rwlock.SyncRoot);
-                        _ = Monitor.Wait(rwlock.SyncRoot, GuestThreadBlocking.WaitSliceMilliseconds);
+                        Monitor.Wait(rwlock.SyncRoot);
                     }
 
                     rwlock.WriterThreadId = currentThreadId;
                 }
                 finally
                 {
-                    rwlock.WaitingWriters = Math.Max(0, rwlock.WaitingWriters - 1);
-                    GuestThreadBlocking.NoteUnblocked(currentThreadId);
+                    if (!transferredToScheduler)
+                    {
+                        rwlock.WaitingWriters = Math.Max(0, rwlock.WaitingWriters - 1);
+                    }
                 }
             }
             else
@@ -1494,26 +1517,20 @@ public static class KernelPthreadExtendedCompatExports
                     return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_DEADLOCK;
                 }
 
-                if (ReaderMustWaitForRwlock(rwlock, currentThreadId))
+                while (ReaderMustWaitForRwlock(rwlock, currentThreadId))
                 {
-                    GuestThreadBlocking.NoteBlocked(currentThreadId, "pthread_rwlock_rdlock");
-                    try
+                    if (GuestThreadExecution.IsGuestThread &&
+                        GuestThreadExecution.TryGetCurrentImportCallFrame(out _) &&
+                        GuestThreadExecution.RequestCurrentThreadBlock(
+                            ctx,
+                            "pthread_rwlock_rdlock",
+                            rwlock.WakeKey,
+                            new RwlockWaiter { Rwlock = rwlock, ThreadId = currentThreadId, Write = false }))
                     {
-                        while (ReaderMustWaitForRwlock(rwlock, currentThreadId))
-                        {
-                            if (GuestThreadBlocking.ShutdownRequested)
-                            {
-                                return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN;
-                            }
+                        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+                    }
 
-                            GuestThreadBlocking.Checkpoint(currentThreadId, rwlock.SyncRoot);
-                            _ = Monitor.Wait(rwlock.SyncRoot, GuestThreadBlocking.WaitSliceMilliseconds);
-                        }
-                    }
-                    finally
-                    {
-                        GuestThreadBlocking.NoteUnblocked(currentThreadId);
-                    }
+                    Monitor.Wait(rwlock.SyncRoot);
                 }
 
                 if (rwlock.WriterThreadId != 0 ||
@@ -1530,6 +1547,33 @@ public static class KernelPthreadExtendedCompatExports
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
+    private static bool TryAcquireBlockedRwlock(PthreadRwlockState rwlock, ulong currentThreadId, bool write)
+    {
+        lock (rwlock.SyncRoot)
+        {
+            if (write)
+            {
+                if (rwlock.WriterThreadId != 0 || rwlock.ReaderTotalCount != 0 || rwlock.CompatWriterTotalCount != 0)
+                {
+                    return false;
+                }
+
+                DetectRwlockWriterConflict(0, rwlock, currentThreadId, "wrlock-resume");
+                rwlock.WriterThreadId = currentThreadId;
+                rwlock.WaitingWriters = Math.Max(0, rwlock.WaitingWriters - 1);
+                return true;
+            }
+
+            if (ReaderMustWaitForRwlock(rwlock, currentThreadId))
+            {
+                return false;
+            }
+
+            rwlock.AddReader(currentThreadId);
+            return true;
+        }
+    }
+
     // Call while holding lock(rwlock.SyncRoot): an existing reader/writer here means a
     // writer would share the rwlock with another holder — a data race.
     private static void DetectRwlockWriterConflict(ulong resolvedAddress, PthreadRwlockState rwlock, ulong currentThreadId, string site)
@@ -1560,6 +1604,8 @@ public static class KernelPthreadExtendedCompatExports
                rwlock.GetReaderCount(currentThreadId) == 0;
     }
 
+    private static string GetRwlockWakeKey(ulong rwlockAddress) => $"pthread_rwlock:0x{rwlockAddress:X16}";
+
     public static string? DumpRwlockStateForStall(ulong rwlockAddress)
     {
         PthreadRwlockState? rwlock;

src/SharpEmu.Libs/Kernel/KernelRuntimeCompatExports.cs

@@ -97,6 +97,8 @@ public static class KernelRuntimeCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
 
+        GuestThreadExecution.Scheduler?.Pump(ctx, "sceKernelUsleep");
+
         if (micros < 1000)
         {
             // Guest worker pools use usleep(1) as a polling backoff. Do not turn
@@ -1302,30 +1304,6 @@ public static class KernelRuntimeCompatExports
         return (int)OrbisGen2Result.ORBIS_GEN2_OK;
     }
 
-    // Same (pc, flags, out-info) contract as sceKernelGetModuleInfoForUnwind,
-    // surfaced through libSceSysmodule on Gen5; the unwinder threads whichever
-    // one the module's libc was linked against.
-    [SysAbiExport(
-        Nid = "4fU5yvOkVG4",
-        ExportName = "sceSysmoduleGetModuleInfoForUnwind",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceSysmodule")]
-    public static int SysmoduleGetModuleInfoForUnwind(CpuContext ctx) => KernelGetModuleInfoForUnwind(ctx);
-
-    // libc unwinder predicate: is this PC the kernel signal-return trampoline?
-    // Guest signal returns do not run through a guest-visible trampoline here,
-    // so no PC is ever one — report false and let the frame unwind normally.
-    [SysAbiExport(
-        Nid = "crb5j7mkk1c",
-        ExportName = "_is_signal_return",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libc")]
-    public static int IsSignalReturn(CpuContext ctx)
-    {
-        ctx[CpuRegister.Rax] = 0;
-        return (int)OrbisGen2Result.ORBIS_GEN2_OK;
-    }
-
     [SysAbiExport(
         Nid = "nu4a0-arQis",
         ExportName = "sceKernelAioInitializeParam",
@@ -2119,6 +2097,7 @@ public static class KernelRuntimeCompatExports
             return (int)OrbisGen2Result.ORBIS_GEN2_OK;
         }
 
+        GuestThreadExecution.Scheduler?.Pump(ctx, posix ? "nanosleep" : "sceKernelNanosleep");
         var totalTicks = tvSec * TimeSpan.TicksPerSecond + Math.Max(tvNsec / 100L, 1L);
         try
         {

src/SharpEmu.Libs/Kernel/KernelSemaphoreCompatExports.cs

@@ -17,6 +17,8 @@ public static class KernelSemaphoreCompatExports
     private sealed class KernelSemaphoreState
     {
         public required string Name { get; init; }
+        // Formatted once at creation; signal/wait/cancel/delete all wake through this key.
+        public required string WakeKey { get; init; }
         public required int InitialCount { get; init; }
         public required int MaxCount { get; init; }
         public int Count { get; set; }
@@ -63,6 +65,7 @@ public static class KernelSemaphoreCompatExports
         _semaphores[handle] = new KernelSemaphoreState
         {
             Name = name,
+            WakeKey = GetSemaphoreWakeKey(handle),
             InitialCount = initialCount,
             MaxCount = maxCount,
             Count = initialCount,
@@ -108,79 +111,148 @@ public static class KernelSemaphoreCompatExports
             return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
         }
 
-        // In-place block on the semaphore gate. Monitor.Wait releases the gate
-        // and parks atomically, so a concurrent SignalSema's PulseAll cannot be
-        // lost between the count check and the park. Semantics mirror FreeBSD
-        // ksem / sem_wait: acquire when count>=need, else sleep until posted or
-        // the deadline lapses. Waits are sliced only so teardown can unwind.
-        var deadlineMs = timeoutAddress != 0
-            ? Environment.TickCount64 + Math.Max(1L, timeoutUsec / 1000L)
-            : long.MaxValue;
-
         lock (semaphore.Gate)
         {
-            if (semaphore.Count < needCount)
+            if (semaphore.Count >= needCount)
             {
-                semaphore.WaitingThreads++;
+                semaphore.Count -= needCount;
+                if (timeoutAddress != 0)
+                {
+                    _ = TryWriteUInt32(ctx, timeoutAddress, timeoutUsec);
+                }
+
                 if (_traceSema)
                 {
-                    TraceSemaphore($"wait-block handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count} timeout={(timeoutAddress == 0 ? "infinite" : timeoutUsec)} waiters={semaphore.WaitingThreads} {FormatCallSite(ctx)}");
-                }
-
-                var guestThreadHandle = GuestThreadExecution.CurrentGuestThreadHandle;
-                GuestThreadBlocking.NoteBlocked(guestThreadHandle, "sceKernelWaitSema");
-                try
-                {
-                    while (semaphore.Count < needCount)
-                    {
-                        if (GuestThreadBlocking.ShutdownRequested)
-                        {
-                            if (timeoutAddress != 0)
-                            {
-                                _ = TryWriteUInt32(ctx, timeoutAddress, 0);
-                            }
-
-                            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
-                        }
-
-                        var remaining = deadlineMs - Environment.TickCount64;
-                        if (timeoutAddress != 0 && remaining <= 0)
-                        {
-                            if (_traceSema)
-                            {
-                                TraceSemaphore($"wait-timeout handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count}");
-                            }
-
-                            _ = TryWriteUInt32(ctx, timeoutAddress, 0);
-                            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
-                        }
-
-                        GuestThreadBlocking.Checkpoint(guestThreadHandle, semaphore.Gate);
-                        _ = Monitor.Wait(semaphore.Gate, (int)Math.Min(remaining, GuestThreadBlocking.WaitSliceMilliseconds));
-                    }
-                }
-                finally
-                {
-                    semaphore.WaitingThreads = Math.Max(0, semaphore.WaitingThreads - 1);
-                    GuestThreadBlocking.NoteUnblocked(guestThreadHandle);
+                    TraceSemaphore($"wait handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count} timeout={(timeoutAddress == 0 ? "infinite" : timeoutUsec)}");
                 }
+                return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
             }
 
-            semaphore.Count -= needCount;
+            semaphore.WaitingThreads++;
+        }
+
+        // Block cooperatively: the wake predicate atomically acquires the
+        // tokens (so a wake commits the acquisition), while the resume
+        // handler distinguishes a real acquisition from a deadline expiry.
+        var acquired = false;
+        var deadline = timeoutAddress != 0
+            ? GuestThreadExecution.ComputeDeadlineTimestamp(TimeSpan.FromMicroseconds(timeoutUsec))
+            : 0;
+
+        bool WakePredicate()
+        {
+            lock (semaphore.Gate)
+            {
+                if (semaphore.Count >= needCount)
+                {
+                    semaphore.Count -= needCount;
+                    semaphore.WaitingThreads = Math.Max(0, semaphore.WaitingThreads - 1);
+                    acquired = true;
+                    return true;
+                }
+
+                return false;
+            }
+        }
+
+        int ResumeWait()
+        {
             if (timeoutAddress != 0)
             {
                 _ = TryWriteUInt32(ctx, timeoutAddress, 0);
             }
 
+            if (acquired)
+            {
+                if (_traceSema)
+                {
+                    TraceSemaphore($"wait-wake handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count}");
+                }
+                return (int)OrbisGen2Result.ORBIS_GEN2_OK;
+            }
+
+            lock (semaphore.Gate)
+            {
+                semaphore.WaitingThreads = Math.Max(0, semaphore.WaitingThreads - 1);
+            }
+
             if (_traceSema)
             {
-                TraceSemaphore($"wait handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count} timeout={(timeoutAddress == 0 ? "infinite" : timeoutUsec)}");
+                TraceSemaphore($"wait-timeout handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count}");
+            }
+            return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT;
+        }
+
+        if (GuestThreadExecution.RequestCurrentThreadBlock(
+                ctx,
+                "sceKernelWaitSema",
+                GetSemaphoreWakeKey(handle),
+                ResumeWait,
+                WakePredicate,
+                deadline))
+        {
+            if (_traceSema)
+            {
+                TraceSemaphore($"wait-block handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count} timeout={(timeoutAddress == 0 ? "infinite" : timeoutUsec)} waiters={semaphore.WaitingThreads} {FormatCallSite(ctx)}");
+            }
+            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
+        }
+
+        // Not a guest thread (or no scheduler): fall back to a host-thread
+        // wait so the semantics still hold on non-cooperative callers.
+        return WaitSemaphoreOnHostThread(ctx, semaphore, handle, needCount, timeoutAddress, timeoutUsec);
+    }
+
+    private static int WaitSemaphoreOnHostThread(
+        CpuContext ctx,
+        KernelSemaphoreState semaphore,
+        uint handle,
+        int needCount,
+        ulong timeoutAddress,
+        uint timeoutUsec)
+    {
+        var deadlineMs = timeoutAddress != 0
+            ? Environment.TickCount64 + Math.Max(1L, timeoutUsec / 1000L)
+            : long.MaxValue;
+        lock (semaphore.Gate)
+        {
+            if (_traceSema)
+            {
+                TraceSemaphore(
+                    $"wait-host-block handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} " +
+                    $"count={semaphore.Count} timeout={(timeoutAddress == 0 ? "infinite" : timeoutUsec)} {FormatCallSite(ctx)}");
+            }
+            while (semaphore.Count < needCount)
+            {
+                var remaining = deadlineMs - Environment.TickCount64;
+                if (timeoutAddress != 0 && remaining <= 0)
+                {
+                    semaphore.WaitingThreads = Math.Max(0, semaphore.WaitingThreads - 1);
+                    _ = TryWriteUInt32(ctx, timeoutAddress, 0);
+                    return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TIMED_OUT);
+                }
+
+                Monitor.Wait(semaphore.Gate, (int)Math.Min(remaining, 100));
+            }
+
+            semaphore.Count -= needCount;
+            semaphore.WaitingThreads = Math.Max(0, semaphore.WaitingThreads - 1);
+            if (_traceSema)
+            {
+                TraceSemaphore(
+                    $"wait-host-wake handle=0x{handle:X8} name='{semaphore.Name}' need={needCount} count={semaphore.Count} {FormatCallSite(ctx)}");
+            }
+            if (timeoutAddress != 0)
+            {
+                _ = TryWriteUInt32(ctx, timeoutAddress, 0);
             }
 
             return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
         }
     }
 
+    private static string GetSemaphoreWakeKey(uint handle) => $"sceKernelWaitSema:{handle:X8}";
+
     [SysAbiExport(
         Nid = "12wOHk8ywb0",
         ExportName = "sceKernelPollSema",
@@ -243,7 +315,7 @@ public static class KernelSemaphoreCompatExports
             }
 
             semaphore.Count += signalCount;
-            // Wake threads parked in-place on the gate; each re-checks the count.
+            // Wake host-thread waiters parked in the fallback path.
             Monitor.PulseAll(semaphore.Gate);
             if (_traceSema)
             {
@@ -251,6 +323,9 @@ public static class KernelSemaphoreCompatExports
             }
         }
 
+        // Wake cooperatively-blocked guest threads; their wake predicate
+        // acquires the tokens atomically, so this respects the new count.
+        _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(GetSemaphoreWakeKey(handle));
         return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
@@ -279,6 +354,7 @@ public static class KernelSemaphoreCompatExports
             }
 
             semaphore.Count = setCount < 0 ? semaphore.InitialCount : setCount;
+            semaphore.WaitingThreads = 0;
             Monitor.PulseAll(semaphore.Gate);
             if (_traceSema)
             {
@@ -286,6 +362,7 @@ public static class KernelSemaphoreCompatExports
             }
         }
 
+        _ = GuestThreadExecution.Scheduler?.WakeBlockedThreads(GetSemaphoreWakeKey(handle));
         return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
@@ -333,6 +410,7 @@ public static class KernelSemaphoreCompatExports
         _semaphores[handle] = new KernelSemaphoreState
         {
             Name = $"posix@0x{semaphoreAddress:X16}",
+            WakeKey = GetSemaphoreWakeKey(handle),
             InitialCount = initialCount,
             MaxCount = int.MaxValue,
             Count = initialCount,
@@ -350,22 +428,6 @@ public static class KernelSemaphoreCompatExports
         return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
-    [SysAbiExport(
-        Nid = "GEnUkDZoUwY",
-        ExportName = "scePthreadSemInit",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PthreadSemInit(CpuContext ctx)
-    {
-        // scePthreadSemInit(sem, flag, value, name) seems to only support private semaphores
-        if (ctx[CpuRegister.Rsi] != 0)
-        {
-            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        return PosixSemInit(ctx);
-    }
-
     [SysAbiExport(
         Nid = "YCV5dGGBcCo",
         ExportName = "sem_wait",
@@ -384,13 +446,6 @@ public static class KernelSemaphoreCompatExports
         return KernelWaitSema(ctx);
     }
 
-    [SysAbiExport(
-        Nid = "C36iRE0F5sE",
-        ExportName = "scePthreadSemWait",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PthreadSemWait(CpuContext ctx) => PosixSemWait(ctx);
-
     [SysAbiExport(
         Nid = "WBWzsRifCEA",
         ExportName = "sem_trywait",
@@ -408,19 +463,6 @@ public static class KernelSemaphoreCompatExports
         return KernelPollSema(ctx, handle, 1);
     }
 
-    [SysAbiExport(
-        Nid = "H2a+IN9TP0E",
-        ExportName = "scePthreadSemTrywait",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PthreadSemTryWait(CpuContext ctx)
-    {
-        var result = PosixSemTryWait(ctx);
-        return result == (int)OrbisGen2Result.ORBIS_GEN2_ERROR_BUSY
-            ? SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_TRY_AGAIN)
-            : result;
-    }
-
     [SysAbiExport(
         Nid = "w5IHyvahg-o",
         ExportName = "sem_timedwait",
@@ -457,13 +499,6 @@ public static class KernelSemaphoreCompatExports
         return KernelSignalSema(ctx, handle, 1);
     }
 
-    [SysAbiExport(
-        Nid = "aishVAiFaYM",
-        ExportName = "scePthreadSemPost",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PthreadSemPost(CpuContext ctx) => PosixSemPost(ctx);
-
     [SysAbiExport(
         Nid = "Bq+LRV-N6Hk",
         ExportName = "sem_getvalue",
@@ -514,13 +549,6 @@ public static class KernelSemaphoreCompatExports
         return result;
     }
 
-    [SysAbiExport(
-        Nid = "Vwc+L05e6oE",
-        ExportName = "scePthreadSemDestroy",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int PthreadSemDestroy(CpuContext ctx) => PosixSemDestroy(ctx);
-
     private static bool TryGetPosixSemaphoreHandle(CpuContext ctx, ulong semaphoreAddress, out uint handle)
     {
         handle = 0;

src/SharpEmu.Libs/Kernel/KernelSyncOnAddressCompatExports.cs

@@ -1,127 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Collections.Concurrent;
-using System.Threading;
-using SharpEmu.HLE;
-
-namespace SharpEmu.Libs.Kernel;
-
-// libKernel's address-wait primitives (sceKernelSyncOnAddress*) are the PS5's
-// futex-style wait/wake: a thread parks on a guest address until another thread
-// wakes that address. Guest runtimes (seen driving Juicy Realm, PPSA19268)
-// build their own spinlocks/queues on top of it and call the wait in a hot
-// loop; left unimplemented, every wait returns immediately and the runtime
-// busy-spins forever (millions of calls, no forward progress).
-//
-// Waits block in place on a per-address gate (see GuestThreadBlocking):
-// Monitor.Wait releases the gate and parks atomically, so a wake's generation
-// bump + PulseAll cannot be lost between the generation check and the park.
-// The real primitive takes a compare value so the wait only sleeps while the
-// address still holds the expected value; that exact value is not recovered
-// here, so each wait is bounded by a self-heal deadline and treated as a
-// spurious-wakeup-tolerant park: the guest re-checks its own condition after
-// resuming, which futex callers already tolerate. Wake-one degrades to
-// wake-all for the same reason (each resumed waiter re-evaluates).
-public static class KernelSyncOnAddressCompatExports
-{
-    // Safety-net bound. Real releases come from the wake side; this only limits
-    // how long a wait that genuinely raced/missed its wake stays parked before
-    // the guest re-evaluates. Kept large: a short bound turns every parked
-    // waiter into a hot re-poll that steals CPU from the threads that would
-    // issue the wake, so it must be a rare last resort, not a spin substitute.
-    private static readonly TimeSpan WaitSelfHealTimeout = TimeSpan.FromMilliseconds(100);
-
-    private static readonly ConcurrentDictionary<ulong, object> _addressGates = new();
-
-    // Per-address wake generation. A wait captures the current generation and
-    // stays parked while it is unchanged; a wake bumps it first, then pulses
-    // the gate, so a wait between its generation check and its park still
-    // observes the bump (the check happens under the gate).
-    private static readonly ConcurrentDictionary<ulong, long> _wakeGenerations = new();
-
-    private static long CurrentGeneration(ulong address) =>
-        _wakeGenerations.TryGetValue(address, out var generation) ? generation : 0;
-
-    [SysAbiExport(
-        Nid = "Hc4CaR6JBL0",
-        ExportName = "sceKernelSyncOnAddressWait",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int SyncOnAddressWait(CpuContext ctx)
-    {
-        var address = ctx[CpuRegister.Rdi];
-        if (address == 0)
-        {
-            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        var observedGeneration = CurrentGeneration(address);
-        var gate = _addressGates.GetOrAdd(address, static _ => new object());
-        var deadlineMs = Environment.TickCount64 + (long)WaitSelfHealTimeout.TotalMilliseconds;
-        var guestThreadHandle = GuestThreadExecution.CurrentGuestThreadHandle;
-        GuestThreadBlocking.NoteBlocked(guestThreadHandle, "sceKernelSyncOnAddressWait");
-        try
-        {
-            lock (gate)
-            {
-                while (CurrentGeneration(address) == observedGeneration &&
-                       !GuestThreadBlocking.ShutdownRequested)
-                {
-                    var remaining = deadlineMs - Environment.TickCount64;
-                    if (remaining <= 0)
-                    {
-                        // Self-heal: resume and let the guest re-check its condition.
-                        break;
-                    }
-
-                    GuestThreadBlocking.Checkpoint(guestThreadHandle, gate);
-                    _ = Monitor.Wait(gate, (int)Math.Min(remaining, GuestThreadBlocking.WaitSliceMilliseconds));
-                }
-            }
-        }
-        finally
-        {
-            GuestThreadBlocking.NoteUnblocked(guestThreadHandle);
-        }
-
-        return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
-    }
-
-    [SysAbiExport(
-        Nid = "q2y-wDIVWZA",
-        ExportName = "sceKernelSyncOnAddressWake",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libKernel")]
-    public static int SyncOnAddressWake(CpuContext ctx)
-    {
-        var address = ctx[CpuRegister.Rdi];
-        if (address == 0)
-        {
-            return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        // Bump the generation first so a wait that has checked but not yet
-        // parked (it holds the gate for both) observes the change; then pulse
-        // parked waiters. rsi's wake count degrades to wake-all — resumed
-        // waiters re-evaluate their own condition, which futex callers tolerate.
-        _wakeGenerations.AddOrUpdate(address, 1, static (_, current) => current + 1);
-
-        if (_addressGates.TryGetValue(address, out var gate))
-        {
-            lock (gate)
-            {
-                Monitor.PulseAll(gate);
-            }
-        }
-
-        return SetReturn(ctx, OrbisGen2Result.ORBIS_GEN2_OK);
-    }
-
-    private static int SetReturn(CpuContext ctx, OrbisGen2Result result)
-    {
-        var value = (int)result;
-        ctx[CpuRegister.Rax] = unchecked((ulong)value);
-        return value;
-    }
-}

src/SharpEmu.Libs/Ngs2/Ngs2Exports.cs

@@ -3,7 +3,6 @@
 
 using SharpEmu.HLE;
 using SharpEmu.Libs.Kernel;
-using System.Buffers;
 using System.Buffers.Binary;
 using System.Threading;
 
@@ -26,44 +25,24 @@ public static class Ngs2Exports
     private static long _nextUid;
     private static long _renderCount;
 
-    // NGS2 renders one grain of interleaved float32 per sceNgs2SystemRender.
-    // The grain length defaults to 256 frames (matching the 8192-byte AudioOut
-    // buffers games copy it into) until the title overrides it.
-    private const int DefaultGrainSamples = 256;
-    private const double OutputSampleRate = 48000.0;
-
-    private sealed class SystemState
-    {
-        public SystemState(uint uid) => Uid = uid;
-
-        public uint Uid { get; }
-        public int GrainSamples { get; set; } = DefaultGrainSamples;
-    }
-
+    private sealed record SystemState(uint Uid);
     private sealed record RackState(ulong SystemHandle, uint RackId);
+    private sealed record VoiceState(ulong RackHandle, uint VoiceIndex);
 
-    private sealed class VoiceState
+    [SysAbiExport(
+        Nid = "koBbCMvOKWw",
+        ExportName = "sceNgs2SystemCreate",
+        Target = Generation.Gen4 | Generation.Gen5,
+        LibraryName = "libSceNgs2")]
+    public static int Ngs2SystemCreate(CpuContext ctx)
     {
-        public VoiceState(ulong rackHandle, uint voiceIndex)
+        var bufferInfoAddress = ctx[CpuRegister.Rsi];
+        if (!TryReadContextBuffer(ctx, bufferInfoAddress, out var hostBuffer))
         {
-            RackHandle = rackHandle;
-            VoiceIndex = voiceIndex;
+            return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
         }
 
-        public ulong RackHandle { get; }
-        public uint VoiceIndex { get; }
-
-        // Software-mixer playback state. Pcm is the fully decoded mono waveform;
-        // Position is a fractional read cursor advanced at the source/output rate
-        // ratio each output frame.
-        public short[]? Pcm { get; set; }
-        public ulong SourceAddr { get; set; }
-        public int SourceRate { get; set; }
-        public double Position { get; set; }
-        public bool Playing { get; set; }
-        public int LoopStart { get; set; } = -1;
-        public int LoopEnd { get; set; }
-        public float Gain { get; set; } = 1f;
+        return CreateSystem(ctx, ctx[CpuRegister.Rdx], hostBuffer);
     }
 
     [SysAbiExport(
@@ -79,34 +58,14 @@ public static class Ngs2Exports
             return SetReturn(ctx, OrbisNgs2ErrorInvalidOutAddress);
         }
 
-        if (!TryCreateHandle(ctx, type: 1, ownerHandle: 0, out var handle) ||
-            !ctx.TryWriteUInt64(outHandleAddress, handle))
+        if (!TryCreateHandle(ctx, type: 1, ownerHandle: 0, out var handle))
         {
             return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
         }
 
-        lock (StateGate)
-        {
-            Systems[handle] = new SystemState(unchecked((uint)Interlocked.Increment(ref _nextUid)));
-        }
-
-        return SetReturn(ctx, 0);
+        return CreateSystem(ctx, outHandleAddress, handle);
     }
 
-    // Non-allocator create: identical to the WithAllocator form for our purposes.
-    // The only signature difference is the caller-supplied buffer info in rsi
-    // (vs an allocator callback); the system option (rdi) and out-handle (rdx)
-    // sit at the same argument positions, so we reuse the same implementation.
-    // Dead Cells uses these variants — leaving sceNgs2SystemCreate unresolved
-    // gave the game a garbage system handle, so every later rack/voice call
-    // failed and it polled sceNgs2VoiceGetState forever, freezing at FLIP 0.
-    [SysAbiExport(
-        Nid = "koBbCMvOKWw",
-        ExportName = "sceNgs2SystemCreate",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceNgs2")]
-    public static int Ngs2SystemCreate(CpuContext ctx) => Ngs2SystemCreateWithAllocator(ctx);
-
     [SysAbiExport(
         Nid = "u-WrYDaJA3k",
         ExportName = "sceNgs2SystemDestroy",
@@ -135,6 +94,27 @@ public static class Ngs2Exports
         return SetReturn(ctx, 0);
     }
 
+    [SysAbiExport(
+        Nid = "cLV4aiT9JpA",
+        ExportName = "sceNgs2RackCreate",
+        Target = Generation.Gen4 | Generation.Gen5,
+        LibraryName = "libSceNgs2")]
+    public static int Ngs2RackCreate(CpuContext ctx)
+    {
+        var bufferInfoAddress = ctx[CpuRegister.Rcx];
+        if (!TryReadContextBuffer(ctx, bufferInfoAddress, out var hostBuffer))
+        {
+            return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
+        }
+
+        return CreateRack(
+            ctx,
+            ctx[CpuRegister.Rdi],
+            unchecked((uint)ctx[CpuRegister.Rsi]),
+            ctx[CpuRegister.R8],
+            hostBuffer);
+    }
+
     [SysAbiExport(
         Nid = "U546k6orxQo",
         ExportName = "sceNgs2RackCreateWithAllocator",
@@ -158,29 +138,14 @@ public static class Ngs2Exports
             return SetReturn(ctx, OrbisNgs2ErrorInvalidOutAddress);
         }
 
-        if (!TryCreateHandle(ctx, type: 2, systemHandle, out var handle) ||
-            !ctx.TryWriteUInt64(outHandleAddress, handle))
+        if (!TryCreateHandle(ctx, type: 2, systemHandle, out var handle))
         {
             return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
         }
 
-        lock (StateGate)
-        {
-            Racks[handle] = new RackState(systemHandle, rackId);
-        }
-
-        return SetReturn(ctx, 0);
+        return CreateRack(ctx, systemHandle, rackId, outHandleAddress, handle);
     }
 
-    // Non-allocator rack create: system handle (rdi), rack id (rsi) and the
-    // out-handle (r8) share the WithAllocator argument layout, so reuse it.
-    [SysAbiExport(
-        Nid = "cLV4aiT9JpA",
-        ExportName = "sceNgs2RackCreate",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceNgs2")]
-    public static int Ngs2RackCreate(CpuContext ctx) => Ngs2RackCreateWithAllocator(ctx);
-
     [SysAbiExport(
         Nid = "lCqD7oycmIM",
         ExportName = "sceNgs2RackDestroy",
@@ -255,217 +220,14 @@ public static class Ngs2Exports
         LibraryName = "libSceNgs2")]
     public static int Ngs2VoiceControl(CpuContext ctx)
     {
-        var voiceHandle = ctx[CpuRegister.Rdi];
-        var paramList = ctx[CpuRegister.Rsi];
         lock (StateGate)
         {
-            if (!Voices.ContainsKey(voiceHandle))
-            {
-                return SetReturn(ctx, OrbisNgs2ErrorInvalidVoiceHandle);
-            }
-        }
-
-        if (ShouldTrace())
-        {
-            TraceVoiceParamList(ctx, voiceHandle, paramList);
-        }
-
-        HandleVoiceParams(ctx, voiceHandle, paramList);
-        return SetReturn(ctx, 0);
-    }
-
-    // Parse the SceNgs2VoiceParamHead command list (header = u32 size, u32 id;
-    // params are laid out contiguously) and apply the ones the mixer needs:
-    // the waveform-blocks param arms a voice with decoded PCM, and the port
-    // matrix param carries its output gain.
-    private static void HandleVoiceParams(CpuContext ctx, ulong voiceHandle, ulong paramList)
-    {
-        if (paramList == 0)
-        {
-            return;
-        }
-
-        var offset = paramList;
-        for (var guard = 0; guard < 32; guard++)
-        {
-            if (!ctx.TryReadUInt32(offset, out var size) ||
-                !ctx.TryReadUInt32(offset + 4, out var id))
-            {
-                return;
-            }
-
-            switch (id)
-            {
-                case 0x10000001:
-                    ApplyWaveformParam(ctx, voiceHandle, offset);
-                    break;
-                case 0x20010001:
-                    ApplyPortMatrixParam(ctx, voiceHandle, offset);
-                    break;
-            }
-
-            // Advance to the next contiguous block; the game normally sends one
-            // param per call (size==whole block), so stop when size is degenerate.
-            if (size < 8 || size > 0x1000)
-            {
-                return;
-            }
-
-            offset += (size + 7) & ~7u;
+            return SetReturn(
+                ctx,
+                Voices.ContainsKey(ctx[CpuRegister.Rdi]) ? 0 : OrbisNgs2ErrorInvalidVoiceHandle);
         }
     }
 
-    // Waveform-blocks param: the guest pointer at +8 references a "VAGp"
-    // (PS-ADPCM) container. Decode it once and arm the voice for playback.
-    private static void ApplyWaveformParam(CpuContext ctx, ulong voiceHandle, ulong paramOffset)
-    {
-        if (!ctx.TryReadUInt64(paramOffset + 8, out var dataAddr) || dataAddr <= 0x10000)
-        {
-            return;
-        }
-
-        lock (StateGate)
-        {
-            if (Voices.TryGetValue(voiceHandle, out var existing) &&
-                existing.SourceAddr == dataAddr && existing.Pcm is not null)
-            {
-                // Same waveform already armed — don't restart it every frame.
-                return;
-            }
-        }
-
-        Span<byte> header = stackalloc byte[Ngs2VagDecoder.VagHeaderSize];
-        if (!ctx.Memory.TryRead(dataAddr, header) || !Ngs2VagDecoder.IsVag(header))
-        {
-            return;
-        }
-
-        var declaredSize = (int)BinaryPrimitives.ReadUInt32BigEndian(header[0x0C..]);
-        var totalBytes = Ngs2VagDecoder.VagHeaderSize + Math.Clamp(declaredSize, 0, 8 * 1024 * 1024);
-        var raw = System.Buffers.ArrayPool<byte>.Shared.Rent(totalBytes);
-        try
-        {
-            if (!ctx.Memory.TryRead(dataAddr, raw.AsSpan(0, totalBytes)) ||
-                !Ngs2VagDecoder.TryDecode(raw.AsSpan(0, totalBytes), out var waveform))
-            {
-                return;
-            }
-
-            lock (StateGate)
-            {
-                if (!Voices.TryGetValue(voiceHandle, out var voice))
-                {
-                    return;
-                }
-
-                voice.Pcm = waveform.Samples;
-                voice.SourceAddr = dataAddr;
-                voice.SourceRate = waveform.SampleRate;
-                voice.LoopStart = waveform.LoopStart;
-                voice.LoopEnd = waveform.LoopEnd > 0 ? waveform.LoopEnd : waveform.Samples.Length;
-                voice.Position = 0;
-                voice.Playing = true;
-            }
-
-            if (ShouldTrace())
-            {
-                var peak = 0;
-                for (var i = 0; i < waveform.Samples.Length; i++)
-                {
-                    peak = Math.Max(peak, Math.Abs((int)waveform.Samples[i]));
-                }
-
-                Console.Error.WriteLine(
-                    $"[LOADER][TRACE] ngs2.arm voice=0x{voiceHandle:X16} addr=0x{dataAddr:X} rate={waveform.SampleRate} samples={waveform.Samples.Length} loop={waveform.LoopStart} peak={peak}");
-            }
-        }
-        finally
-        {
-            System.Buffers.ArrayPool<byte>.Shared.Return(raw);
-        }
-    }
-
-    // Port matrix param: the first float level is a reasonable proxy for the
-    // voice's output gain until per-channel panning is implemented.
-    private static void ApplyPortMatrixParam(CpuContext ctx, ulong voiceHandle, ulong paramOffset)
-    {
-        if (!ctx.TryReadUInt32(paramOffset + 12, out var levelBits))
-        {
-            return;
-        }
-
-        var level = BitConverter.UInt32BitsToSingle(levelBits);
-        if (!float.IsFinite(level) || level < 0f || level > 8f)
-        {
-            return;
-        }
-
-        lock (StateGate)
-        {
-            if (Voices.TryGetValue(voiceHandle, out var voice))
-            {
-                voice.Gain = level;
-            }
-        }
-    }
-
-    // Empirically dump the SceNgs2VoiceParamHead-chained command list so we can
-    // confirm the real struct layout (size/next/id) against public NGS2 sources
-    // before building the software mixer. Assumed header: u16 size, s16 next
-    // (byte offset to the next block, 0 = end), u32 id.
-    private static void TraceVoiceParamList(CpuContext ctx, ulong voiceHandle, ulong paramList)
-    {
-        if (paramList == 0)
-        {
-            return;
-        }
-
-        Span<byte> peek = stackalloc byte[32];
-        var offset = paramList;
-        for (int guard = 0; guard < 32; guard++)
-        {
-            if (!ctx.TryReadUInt16(offset, out var size) ||
-                !ctx.TryReadUInt16(offset + 2, out var next) ||
-                !ctx.TryReadUInt32(offset + 4, out var id))
-            {
-                Console.Error.WriteLine($"[LOADER][TRACE] ngs2.voiceparam voice=0x{voiceHandle:X16} @0x{offset:X}: unreadable header");
-                return;
-            }
-
-            peek.Clear();
-            var readable = Math.Min((int)Math.Max((ushort)8, size), peek.Length);
-            ctx.Memory.TryRead(offset, peek[..readable]);
-            Console.Error.WriteLine(
-                $"[LOADER][TRACE] ngs2.voiceparam voice=0x{voiceHandle:X16} id=0x{id:X} size={size} next={unchecked((short)next)} bytes={Convert.ToHexString(peek[..readable])}");
-
-            // For the waveform-blocks param, follow the embedded pointers and
-            // dump the pointed-to bytes so we can tell PCM16 from ATRAC9.
-            if (id == 0x10000001 && Interlocked.Increment(ref _waveformDumps) <= 8)
-            {
-                for (int po = 8; po + 8 <= readable; po += 8)
-                {
-                    if (ctx.TryReadUInt64(offset + (ulong)po, out var ptr) && ptr > 0x10000 &&
-                        ctx.Memory.TryRead(ptr, peek))
-                    {
-                        Console.Error.WriteLine(
-                            $"[LOADER][TRACE] ngs2.waveform @+{po} ptr=0x{ptr:X} head={Convert.ToHexString(peek)}");
-                    }
-                }
-            }
-
-            var advance = unchecked((short)next);
-            if (advance <= 0)
-            {
-                return;
-            }
-
-            offset += (ulong)advance;
-        }
-    }
-
-    private static long _waveformDumps;
-    private static long _renderInfoDumps;
-
     [SysAbiExport(
         Nid = "AbYvTOZ8Pts",
         ExportName = "sceNgs2VoiceRunCommands",
@@ -511,32 +273,11 @@ public static class Ngs2Exports
                 {
                     return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
                 }
-
-                // SceNgs2RenderBufferInfo: {ptr@0, size@8, waveformType@16,
-                // channelsCount@20}. Mix the armed voices into the leading grain
-                // as interleaved float32 — this is what the game copies to
-                // sceAudioOutOutput, so it is where NGS2 audio must appear.
-                var channels = 2;
-                if (ctx.TryReadUInt32(entryAddress + 20, out var declaredChannels) &&
-                    declaredChannels is > 0 and <= 8)
-                {
-                    channels = (int)declaredChannels;
-                }
-
-                MixVoicesIntoGrain(ctx, systemHandle, bufferAddress, bufferSize, channels);
-
-                if (ShouldTrace() && Interlocked.Increment(ref _renderInfoDumps) <= 4)
-                {
-                    Span<byte> rbi = stackalloc byte[RenderBufferInfoSize];
-                    ctx.Memory.TryRead(entryAddress, rbi);
-                    Console.Error.WriteLine(
-                        $"[LOADER][TRACE] ngs2.renderbufinfo addr=0x{bufferAddress:X} size={bufferSize} ch={channels} raw={Convert.ToHexString(rbi)}");
-                }
             }
         }
 
         var count = Interlocked.Increment(ref _renderCount);
-        if (ShouldTrace() && (count <= 4 || count % 200 == 0))
+        if (ShouldTrace() && (count <= 4 || count % 10_000 == 0))
         {
             Console.Error.WriteLine(
                 $"[LOADER][TRACE] ngs2.render#{count} system=0x{systemHandle:X16} buffers={bufferInfoCount}");
@@ -545,135 +286,6 @@ public static class Ngs2Exports
         return SetReturn(ctx, 0);
     }
 
-    // Sum every armed voice belonging to this system into the leading grain of
-    // the render buffer as interleaved float32. The buffer was just zeroed, so
-    // this is a plain additive mix; silence stays silence when nothing plays.
-    private static void MixVoicesIntoGrain(
-        CpuContext ctx, ulong systemHandle, ulong bufferAddress, ulong bufferSize, int channels)
-    {
-        int grain;
-        lock (StateGate)
-        {
-            if (!Systems.TryGetValue(systemHandle, out var system))
-            {
-                return;
-            }
-
-            grain = system.GrainSamples;
-        }
-
-        var capacityFrames = (int)Math.Min((ulong)grain, bufferSize / (ulong)(channels * sizeof(float)));
-        if (capacityFrames <= 0)
-        {
-            return;
-        }
-
-        var floatCount = capacityFrames * channels;
-        var accum = ArrayPool<float>.Shared.Rent(floatCount);
-        var mixedAnything = false;
-        try
-        {
-            Array.Clear(accum, 0, floatCount);
-            lock (StateGate)
-            {
-                foreach (var pair in Voices)
-                {
-                    var voice = pair.Value;
-                    if (!voice.Playing || voice.Pcm is null || voice.Pcm.Length == 0)
-                    {
-                        continue;
-                    }
-
-                    if (!Racks.TryGetValue(voice.RackHandle, out var rack) ||
-                        rack.SystemHandle != systemHandle)
-                    {
-                        continue;
-                    }
-
-                    MixOneVoice(accum, capacityFrames, channels, voice);
-                    mixedAnything = true;
-                }
-            }
-
-            if (mixedAnything)
-            {
-                WriteGrain(ctx, bufferAddress, accum, floatCount);
-            }
-        }
-        finally
-        {
-            ArrayPool<float>.Shared.Return(accum);
-        }
-    }
-
-    // Resample one voice from its source rate to 48 kHz (nearest-sample) and add
-    // it to the front stereo pair. Advances the voice cursor and handles loop /
-    // one-shot end. Must be called under StateGate.
-    private static void MixOneVoice(float[] accum, int frames, int channels, VoiceState voice)
-    {
-        var pcm = voice.Pcm!;
-        var loopEnd = voice.LoopEnd > 0 && voice.LoopEnd <= pcm.Length ? voice.LoopEnd : pcm.Length;
-        var loopStart = voice.LoopStart;
-        var step = voice.SourceRate / OutputSampleRate;
-        var gain = voice.Gain / 32768f;
-        var pos = voice.Position;
-        for (var f = 0; f < frames; f++)
-        {
-            var idx = (int)pos;
-            if (idx >= loopEnd)
-            {
-                if (loopStart >= 0 && loopStart < loopEnd)
-                {
-                    pos = loopStart;
-                    idx = loopStart;
-                }
-                else
-                {
-                    voice.Playing = false;
-                    break;
-                }
-            }
-
-            if (idx < 0 || idx >= pcm.Length)
-            {
-                voice.Playing = false;
-                break;
-            }
-
-            var sample = pcm[idx] * gain;
-            var baseIndex = f * channels;
-            accum[baseIndex] += sample;
-            if (channels > 1)
-            {
-                accum[baseIndex + 1] += sample;
-            }
-
-            pos += step;
-        }
-
-        voice.Position = pos;
-    }
-
-    private static void WriteGrain(CpuContext ctx, ulong address, float[] accum, int count)
-    {
-        var bytes = ArrayPool<byte>.Shared.Rent(count * sizeof(float));
-        try
-        {
-            var span = bytes.AsSpan(0, count * sizeof(float));
-            for (var i = 0; i < count; i++)
-            {
-                var value = Math.Clamp(accum[i], -1f, 1f);
-                BinaryPrimitives.WriteSingleLittleEndian(span.Slice(i * sizeof(float), sizeof(float)), value);
-            }
-
-            ctx.Memory.TryWrite(address, span);
-        }
-        finally
-        {
-            ArrayPool<byte>.Shared.Return(bytes);
-        }
-    }
-
     [SysAbiExport(
         Nid = "pgFAiLR5qT4",
         ExportName = "sceNgs2SystemQueryBufferSize",
@@ -711,25 +323,7 @@ public static class Ngs2Exports
         ExportName = "sceNgs2SystemSetGrainSamples",
         Target = Generation.Gen4 | Generation.Gen5,
         LibraryName = "libSceNgs2")]
-    public static int Ngs2SystemSetGrainSamples(CpuContext ctx)
-    {
-        var systemHandle = ctx[CpuRegister.Rdi];
-        var grain = unchecked((int)ctx[CpuRegister.Rsi]);
-        lock (StateGate)
-        {
-            if (!Systems.TryGetValue(systemHandle, out var system))
-            {
-                return SetReturn(ctx, OrbisNgs2ErrorInvalidSystemHandle);
-            }
-
-            if (grain > 0 && grain <= 8192)
-            {
-                system.GrainSamples = grain;
-            }
-        }
-
-        return SetReturn(ctx, 0);
-    }
+    public static int Ngs2SystemSetGrainSamples(CpuContext ctx) => ValidateSystem(ctx);
 
     [SysAbiExport(
         Nid = "-tbc2SxQD60",
@@ -818,6 +412,67 @@ public static class Ngs2Exports
         }
     }
 
+    private static int CreateSystem(CpuContext ctx, ulong outHandleAddress, ulong handle)
+    {
+        if (outHandleAddress == 0)
+        {
+            return SetReturn(ctx, OrbisNgs2ErrorInvalidOutAddress);
+        }
+
+        if (handle == 0 || !ctx.TryWriteUInt64(outHandleAddress, handle))
+        {
+            return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
+        }
+
+        lock (StateGate)
+        {
+            Systems[handle] = new SystemState(unchecked((uint)Interlocked.Increment(ref _nextUid)));
+        }
+
+        return SetReturn(ctx, 0);
+    }
+
+    private static int CreateRack(
+        CpuContext ctx,
+        ulong systemHandle,
+        uint rackId,
+        ulong outHandleAddress,
+        ulong handle)
+    {
+        lock (StateGate)
+        {
+            if (!Systems.ContainsKey(systemHandle))
+            {
+                return SetReturn(ctx, OrbisNgs2ErrorInvalidSystemHandle);
+            }
+        }
+
+        if (outHandleAddress == 0)
+        {
+            return SetReturn(ctx, OrbisNgs2ErrorInvalidOutAddress);
+        }
+
+        if (handle == 0 || !ctx.TryWriteUInt64(outHandleAddress, handle))
+        {
+            return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
+        }
+
+        lock (StateGate)
+        {
+            Racks[handle] = new RackState(systemHandle, rackId);
+        }
+
+        return SetReturn(ctx, 0);
+    }
+
+    private static bool TryReadContextBuffer(CpuContext ctx, ulong address, out ulong hostBuffer)
+    {
+        hostBuffer = 0;
+        return address != 0 &&
+            ctx.TryReadUInt64(address, out hostBuffer) &&
+            hostBuffer != 0;
+    }
+
     private static bool TryCreateHandle(CpuContext ctx, uint type, ulong ownerHandle, out ulong handle)
     {
         handle = 0;

src/SharpEmu.Libs/Ngs2/Ngs2VagDecoder.cs

@@ -1,150 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Buffers.Binary;
-
-namespace SharpEmu.Libs.Ngs2;
-
-// Clean-room PS-ADPCM ("VAG") decoder. NGS2 sampler voices point at waveforms
-// wrapped in the classic Sony "VAGp" container: a 48-byte big-endian header
-// followed by 16-byte ADPCM frames (2-byte predictor/shift + flags, then 14
-// bytes = 28 nibbles = 28 samples). The predictor coefficient table and the
-// nibble decode are the publicly documented PSX SPU ADPCM algorithm.
-public static class Ngs2VagDecoder
-{
-    // Standard PS-ADPCM predictor filters (scaled by 1/64).
-    private static readonly int[] Coeff0 = { 0, 60, 115, 98, 122 };
-    private static readonly int[] Coeff1 = { 0, 0, -52, -55, -60 };
-
-    public const int VagHeaderSize = 0x30;
-    private const uint VagMagic = 0x56414770; // "VAGp"
-
-    public readonly struct Waveform
-    {
-        public Waveform(short[] samples, int sampleRate, int loopStart, int loopEnd)
-        {
-            Samples = samples;
-            SampleRate = sampleRate;
-            LoopStart = loopStart;
-            LoopEnd = loopEnd;
-        }
-
-        public short[] Samples { get; }
-        public int SampleRate { get; }
-        public int LoopStart { get; } // -1 when the waveform does not loop
-        public int LoopEnd { get; }
-    }
-
-    // True when the buffer begins with a recognizable "VAGp" container header.
-    public static bool IsVag(ReadOnlySpan<byte> data) =>
-        data.Length >= VagHeaderSize &&
-        BinaryPrimitives.ReadUInt32BigEndian(data) == VagMagic;
-
-    // Decode a full "VAGp" container into mono PCM16. Returns false when the
-    // header is missing/short so callers can skip unsupported formats safely.
-    public static bool TryDecode(ReadOnlySpan<byte> data, out Waveform waveform)
-    {
-        waveform = default;
-        if (!IsVag(data))
-        {
-            return false;
-        }
-
-        // Header (big-endian): +0x0C dataSize, +0x10 sampleRate.
-        var declaredSize = (int)BinaryPrimitives.ReadUInt32BigEndian(data[0x0C..]);
-        var sampleRate = (int)BinaryPrimitives.ReadUInt32BigEndian(data[0x10..]);
-        if (sampleRate <= 0)
-        {
-            sampleRate = 48000;
-        }
-
-        var body = data[VagHeaderSize..];
-        // Trust the declared payload size when it fits; otherwise decode what we
-        // actually have (some tools pad or under-report).
-        var available = body.Length - (body.Length % 16);
-        var frameBytes = declaredSize > 0 && declaredSize <= available ? declaredSize - (declaredSize % 16) : available;
-        if (frameBytes <= 0)
-        {
-            return false;
-        }
-
-        waveform = Decode(body[..frameBytes], sampleRate);
-        return waveform.Samples.Length > 0;
-    }
-
-    // Decode raw 16-byte-framed PS-ADPCM (no container header) into PCM16 and
-    // resolve loop points from the per-frame flag bytes.
-    public static Waveform Decode(ReadOnlySpan<byte> frames, int sampleRate)
-    {
-        var frameCount = frames.Length / 16;
-        var samples = new short[frameCount * 28];
-        var loopStart = -1;
-        var loopEnd = -1;
-
-        var hist1 = 0;
-        var hist2 = 0;
-        var outIndex = 0;
-        var ended = false;
-        for (var frame = 0; frame < frameCount && !ended; frame++)
-        {
-            var offset = frame * 16;
-            var header = frames[offset];
-            var shift = header & 0x0F;
-            var filter = (header >> 4) & 0x0F;
-            if (filter > 4)
-            {
-                filter = 0;
-            }
-
-            // Per-frame loop marker (exact PS-ADPCM values, not bit masks):
-            //   3 = loop start, 6 = loop end + jump back, 1/7 = one-shot end.
-            var flags = frames[offset + 1];
-            var blockStart = outIndex;
-            if (flags == 0x03)
-            {
-                loopStart = blockStart;
-            }
-
-            var f0 = Coeff0[filter];
-            var f1 = Coeff1[filter];
-            for (var i = 0; i < 14; i++)
-            {
-                var d = frames[offset + 2 + i];
-                for (var nibble = 0; nibble < 2; nibble++)
-                {
-                    var raw = nibble == 0 ? d & 0x0F : d >> 4;
-                    // Sign-extend the 4-bit sample into the top nibble, then scale.
-                    var s = (short)(raw << 12) >> shift;
-                    var predicted = (hist1 * f0 + hist2 * f1) >> 6;
-                    var sample = Math.Clamp(s + predicted, short.MinValue, short.MaxValue);
-                    samples[outIndex++] = (short)sample;
-                    hist2 = hist1;
-                    hist1 = sample;
-                }
-            }
-
-            if (flags == 0x06)
-            {
-                loopEnd = outIndex;
-            }
-            else if (flags == 0x01 || flags == 0x07)
-            {
-                ended = true;
-            }
-        }
-
-        // Trim to the samples we actually decoded (a one-shot end marker can stop
-        // us before the declared frame count).
-        if (outIndex != samples.Length)
-        {
-            Array.Resize(ref samples, outIndex);
-        }
-
-        if (loopStart >= 0 && loopEnd <= loopStart)
-        {
-            loopEnd = outIndex;
-        }
-
-        return new Waveform(samples, sampleRate, loopStart, loopEnd);
-    }
-}

src/SharpEmu.Libs/Np/NpEntitlementAccessExports.cs

@@ -58,36 +58,6 @@ public static class NpEntitlementAccessExports
         return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
     }
 
-    private const int EmptyAddcontInfoSize = 0x30;
-
-    // Singular lookup of one add-on-content entitlement (rdx = info out). We own
-    // no DLC, so report an empty/zeroed info and success — matching the list
-    // variant's "no entitlements" answer. Dead Cells calls this while loading a
-    // level; leaving it unresolved left the info struct uninitialized.
-    [SysAbiExport(
-        Nid = "xddD23+8TfQ",
-        ExportName = "sceNpEntitlementAccessGetAddcontEntitlementInfo",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceNpEntitlementAccess")]
-    public static int NpEntitlementAccessGetAddcontEntitlementInfo(CpuContext ctx)
-    {
-        var infoAddress = ctx[CpuRegister.Rdx];
-        if (infoAddress != 0)
-        {
-            Span<byte> info = stackalloc byte[EmptyAddcontInfoSize];
-            info.Clear();
-            if (!ctx.Memory.TryWrite(infoAddress, info))
-            {
-                return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-            }
-        }
-
-        TraceNpEntitlementAccess(
-            $"get_addcont_info service=0x{ctx[CpuRegister.Rdi]:X16} label=0x{ctx[CpuRegister.Rsi]:X16} " +
-            $"info=0x{infoAddress:X16} -> empty");
-        return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
-    }
-
     private static void TraceNpEntitlementAccess(string message)
     {
         if (!string.Equals(Environment.GetEnvironmentVariable("SHARPEMU_LOG_NP"), "1", StringComparison.Ordinal))

src/SharpEmu.Libs/Np/NpUniversalDataSystemExports.cs

@@ -197,16 +197,4 @@ public static class NpUniversalDataSystemExports
     {
         return ctx.SetReturn(0, typeof(long));
     }
-
-    // Telemetry property setter (event property array, string value). We do not
-    // upload analytics, so accept and drop it — matching the other Set* stubs.
-    [SysAbiExport(
-        Nid = "4llLk7YJRTE",
-        ExportName = "sceNpUniversalDataSystemEventPropertyArraySetString",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceNpUniversalDataSystem")]
-    public static int NpUniversalDataSystemEventPropertyArraySetString(CpuContext ctx)
-    {
-        return ctx.SetReturn(0, typeof(long));
-    }
 }

src/SharpEmu.Libs/Pad/PadExports.cs

@@ -65,35 +65,6 @@ public static class PadExports
         LibraryName = "libScePad")]
     public static int PadOpenExt(CpuContext ctx) => PadOpenCore(ctx, extended: true);
 
-    // scePadGetHandle(userId, type, index): returns the handle of an already-open
-    // pad without opening a new one. Dead Cells calls it every frame to poll
-    // input; leaving it unresolved returned a garbage handle so the input path
-    // (and the game loop that drives it) misbehaved. Same validation as
-    // scePadOpen — the one primary pad — returning its handle or a not-connected
-    // error, never opening or logging.
-    [SysAbiExport(
-        Nid = "u1GRHp+oWoY",
-        ExportName = "scePadGetHandle",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libScePad")]
-    public static int PadGetHandle(CpuContext ctx)
-    {
-        var userId = unchecked((int)ctx[CpuRegister.Rdi]);
-        var type = unchecked((int)ctx[CpuRegister.Rsi]);
-        var index = unchecked((int)ctx[CpuRegister.Rdx]);
-        if (!_initialized)
-        {
-            return ctx.SetReturn(OrbisPadErrorNotInitialized);
-        }
-
-        if (userId != PrimaryUserId || type is not (0 or 1 or 2) || index != 0)
-        {
-            return ctx.SetReturn(OrbisPadErrorDeviceNotConnected);
-        }
-
-        return ctx.SetReturn(PrimaryPadHandle);
-    }
-
     // scePadOpen rejects a non-null 4th arg and non-standard ports; scePadOpenExt accepts a
     // ScePadOpenExtParam* plus ports 1/2 (racing titles retry scePadOpenExt(type=2) forever if rejected).
     private static int PadOpenCore(CpuContext ctx, bool extended)
@@ -245,38 +216,6 @@ public static class PadExports
             : ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
     }
 
-    [SysAbiExport(
-        Nid = "AcslpN1jHR8",
-        ExportName = "scePadDeviceClassGetExtendedInformation",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libScePad")]
-    public static int PadDeviceClassGetExtendedInformation(CpuContext ctx)
-    {
-        var handle = unchecked((int)ctx[CpuRegister.Rdi]);
-        var informationAddress = ctx[CpuRegister.Rsi];
-        if (!IsPrimaryPadHandle(handle))
-        {
-            return ctx.SetReturn(OrbisPadErrorInvalidHandle);
-        }
-
-        if (informationAddress == 0)
-        {
-            return ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT);
-        }
-
-        // ScePadDeviceClassExtendedInformation: deviceClass 0 = standard pad
-        // (DualSense). We emulate no special peripheral (guitar/drums/wheel), so
-        // the class-data union stays zeroed — the guest treats it as a plain
-        // controller with no extended capabilities.
-        Span<byte> information = stackalloc byte[0x20];
-        information.Clear();
-        BinaryPrimitives.WriteInt32LittleEndian(information[0x00..], 0);
-
-        return ctx.Memory.TryWrite(informationAddress, information)
-            ? ctx.SetReturn(0)
-            : ctx.SetReturn((int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-    }
-
     [SysAbiExport(
         Nid = "YndgXqQVV7c",
         ExportName = "scePadReadState",

src/SharpEmu.Libs/Random/RandomExports.cs

@@ -1,39 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Security.Cryptography;
-using SharpEmu.HLE;
-
-namespace SharpEmu.Libs.Random;
-
-public static class RandomExports
-{
-    private const int RandomErrorInvalid = unchecked((int)0x817C0016);
-    private const int MaxRandomBytes = 64;
-
-    [SysAbiExport(
-        Nid = "PI7jIZj4pcE",
-        ExportName = "sceRandomGetRandomNumber",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceRandom")]
-    public static int RandomGetRandomNumber(CpuContext ctx)
-    {
-        var destination = ctx[CpuRegister.Rdi];
-        var size = ctx[CpuRegister.Rsi];
-        if ((destination == 0 && size != 0) || size > MaxRandomBytes)
-        {
-            return ctx.SetReturn(RandomErrorInvalid);
-        }
-
-        if (size == 0)
-        {
-            return ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK);
-        }
-
-        Span<byte> bytes = stackalloc byte[(int)size];
-        RandomNumberGenerator.Fill(bytes);
-        return ctx.Memory.TryWrite(destination, bytes)
-            ? ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_OK)
-            : ctx.SetReturn(OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-    }
-}

src/SharpEmu.Libs/SaveData/SaveDataExports.cs

@@ -45,530 +45,6 @@ public static class SaveDataExports
             _titleId = string.IsNullOrWhiteSpace(titleId) ? null : SanitizePathSegment(titleId.Trim());
             _preparedTransactionResources.Clear();
         }
-
-        lock (_eventGate)
-        {
-            _events.Clear();
-        }
-
-        lock (_mountGate)
-        {
-            _mounts.Clear();
-        }
-    }
-
-    // Additional error codes and the async-event model (see sceSaveDataGetEventResult).
-    private const int OrbisSaveDataErrorBusy = unchecked((int)0x809F0006);
-    private const int OrbisSaveDataErrorNoEvent = unchecked((int)0x809F0008); // NOT_FOUND: no pending event
-    private const int OrbisSaveDataErrorBadMounted = unchecked((int)0x809F0013);
-    // SceSaveDataEventType
-    private const uint EventTypeUmountBackupEnd = 1;
-    private const uint EventTypeBackupEnd = 2;
-    private const uint EventTypeSaveDataMemorySyncEnd = 3;
-    private const int SaveDataEventSize = 0x60;
-    private const int MountInfoSize = 0x40;
-    private const uint DefaultBlockSize = 32768;
-    private const ulong DefaultTotalBlocks = 0x8000; // 1 GiB of 32 KiB blocks
-
-    private static readonly object _eventGate = new();
-    private static readonly Queue<SaveDataEvent> _events = new();
-    private static readonly object _mountGate = new();
-    // mountPoint -> live mount, for umount/IsMounted/GetMountInfo.
-    private static readonly Dictionary<string, MountEntry> _mounts = new(StringComparer.Ordinal);
-
-    private readonly record struct SaveDataEvent(uint Type, int ErrorCode, int UserId, string DirName);
-    private sealed record MountEntry(string SlotDir, string DirName, int UserId);
-
-    private static void EnqueueEvent(uint type, int userId, string dirName, int errorCode = 0)
-    {
-        lock (_eventGate)
-        {
-            _events.Enqueue(new SaveDataEvent(type, errorCode, userId, dirName));
-        }
-        TraceSaveData($"event.enqueue type={type} user={userId} dir='{dirName}' err=0x{errorCode:X}");
-    }
-
-    [SysAbiExport(
-        Nid = "j8xKtiFj0SY",
-        ExportName = "sceSaveDataGetEventResult",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceSaveData")]
-    public static int SaveDataGetEventResult(CpuContext ctx)
-    {
-        // rdi: SceSaveDataEventParam* (filter, ignored). rsi: SceSaveDataEvent* out.
-        var eventAddress = ctx[CpuRegister.Rsi];
-        if (eventAddress == 0)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorParameter);
-        }
-
-        SaveDataEvent pending;
-        lock (_eventGate)
-        {
-            if (_events.Count == 0)
-            {
-                // No queued completion. Games poll this from a worker; report the
-                // defined "no event" status so the loop keeps polling instead of
-                // acting on an uninitialized event struct.
-                return SetReturn(ctx, OrbisSaveDataErrorNoEvent);
-            }
-
-            pending = _events.Dequeue();
-        }
-
-        Span<byte> ev = stackalloc byte[SaveDataEventSize];
-        ev.Clear();
-        BinaryPrimitives.WriteUInt32LittleEndian(ev[0x00..], pending.Type);
-        BinaryPrimitives.WriteInt32LittleEndian(ev[0x04..], pending.ErrorCode);
-        BinaryPrimitives.WriteInt32LittleEndian(ev[0x08..], pending.UserId);
-        WriteAscii(ev.Slice(0x10, SaveDataDirNameSize), pending.DirName);
-        if (!ctx.Memory.TryWrite(eventAddress, ev))
-        {
-            return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    [SysAbiExport(
-        Nid = "hsKd5c21sQc",
-        ExportName = "sceSaveDataRegisterEventCallback",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceSaveData")]
-    public static int SaveDataRegisterEventCallback(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(
-        Nid = "v-AK1AxQhS0",
-        ExportName = "sceSaveDataUnregisterEventCallback",
-        Target = Generation.Gen4 | Generation.Gen5,
-        LibraryName = "libSceSaveData")]
-    public static int SaveDataUnregisterEventCallback(CpuContext ctx) => SetReturn(ctx, 0);
-
-    // ---- lifecycle ----
-    [SysAbiExport(Nid = "ZkZhskCPXFw", ExportName = "sceSaveDataInitialize", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataInitialize(CpuContext ctx) => SaveDataInitializeCommon(ctx);
-
-    [SysAbiExport(Nid = "l1NmDeDpNGU", ExportName = "sceSaveDataInitialize2", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataInitialize2(CpuContext ctx) => SaveDataInitializeCommon(ctx);
-
-    private static int SaveDataInitializeCommon(CpuContext ctx)
-    {
-        try
-        {
-            Directory.CreateDirectory(ResolveSaveDataRoot());
-            return SetReturn(ctx, 0);
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorInternal);
-        }
-    }
-
-    [SysAbiExport(Nid = "yKDy8S5yLA0", ExportName = "sceSaveDataTerminate", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataTerminate(CpuContext ctx) => SetReturn(ctx, 0);
-
-    // ---- mount variants (all share the SceSaveDataMount layout) ----
-    [SysAbiExport(Nid = "32HQAQdwM2o", ExportName = "sceSaveDataMount", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataMount(CpuContext ctx) => SaveDataMount3(ctx);
-
-    [SysAbiExport(Nid = "0z45PIH+SNI", ExportName = "sceSaveDataMount2", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataMount2(CpuContext ctx) => SaveDataMount3(ctx);
-
-    [SysAbiExport(Nid = "xz0YMi6BfNk", ExportName = "sceSaveDataMount5", Target = Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataMount5(CpuContext ctx) => SaveDataMount3(ctx);
-
-    [SysAbiExport(Nid = "BMR4F-Uek3E", ExportName = "sceSaveDataUmount", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataUmount(CpuContext ctx) => SaveDataUmount2(ctx);
-
-    [SysAbiExport(Nid = "ieP6jP138Qo", ExportName = "sceSaveDataIsMounted", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataIsMounted(CpuContext ctx)
-    {
-        var outAddress = ctx[CpuRegister.Rsi];
-        int mountCount;
-        lock (_mountGate)
-        {
-            mountCount = _mounts.Count;
-        }
-
-        if (outAddress != 0)
-        {
-            TryWriteUInt32(ctx, outAddress, mountCount > 0 ? 1u : 0u);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    [SysAbiExport(Nid = "65VH0Qaaz6s", ExportName = "sceSaveDataGetMountInfo", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetMountInfo(CpuContext ctx)
-    {
-        var mountPointAddress = ctx[CpuRegister.Rdi];
-        var infoAddress = ctx[CpuRegister.Rsi];
-        if (mountPointAddress == 0 || infoAddress == 0 ||
-            !TryReadFixedAscii(ctx, mountPointAddress, 16, out var mountPoint))
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorParameter);
-        }
-
-        MountEntry? entry;
-        lock (_mountGate)
-        {
-            _mounts.TryGetValue(mountPoint, out entry);
-        }
-
-        if (entry is null)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorBadMounted);
-        }
-
-        var used = SafeDirectorySize(entry.SlotDir);
-        var usedBlocks = (ulong)((used + DefaultBlockSize - 1) / DefaultBlockSize);
-        Span<byte> info = stackalloc byte[MountInfoSize];
-        info.Clear();
-        BinaryPrimitives.WriteUInt64LittleEndian(info[0x00..], DefaultTotalBlocks);       // blocks
-        BinaryPrimitives.WriteUInt64LittleEndian(info[0x08..], usedBlocks);               // freeBlocks slot reused as used
-        return ctx.Memory.TryWrite(infoAddress, info)
-            ? SetReturn(ctx, 0)
-            : SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-    }
-
-    // ---- delete ----
-    [SysAbiExport(Nid = "S1GkePI17zQ", ExportName = "sceSaveDataDelete", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataDelete(CpuContext ctx) => SaveDataDeleteCommon(ctx);
-
-    [SysAbiExport(Nid = "SQWusLoK8Pw", ExportName = "sceSaveDataDelete5", Target = Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataDelete5(CpuContext ctx) => SaveDataDeleteCommon(ctx);
-
-    private static int SaveDataDeleteCommon(CpuContext ctx)
-    {
-        // SceSaveDataDelete: +0x00 userId, +0x08 dirName*, ... (dirName drives the slot).
-        var deleteAddress = ctx[CpuRegister.Rdi];
-        if (deleteAddress == 0 ||
-            !TryReadInt32(ctx, deleteAddress, out var userId) ||
-            !ctx.TryReadUInt64(deleteAddress + 0x08, out var dirNameAddress) ||
-            dirNameAddress == 0 ||
-            !TryReadFixedAscii(ctx, dirNameAddress, SaveDataDirNameSize, out var dirName) ||
-            string.IsNullOrWhiteSpace(dirName))
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorParameter);
-        }
-
-        try
-        {
-            var slotDir = SaveDataStorage.SlotDir(ResolveTitleSaveRoot(userId, ResolveConfiguredTitleId()), dirName);
-            if (!Directory.Exists(slotDir))
-            {
-                return SetReturn(ctx, OrbisSaveDataErrorNotFound);
-            }
-
-            Directory.Delete(slotDir, recursive: true);
-            TraceSaveData($"delete user={userId} dir='{dirName}' path='{slotDir}'");
-            return SetReturn(ctx, 0);
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorInternal);
-        }
-    }
-
-    // ---- params (metadata shown in the save UI) ----
-    [SysAbiExport(Nid = "XgvSuIdnMlw", ExportName = "sceSaveDataGetParam", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetParam(CpuContext ctx) => TransferParam(ctx, write: false);
-
-    [SysAbiExport(Nid = "85zul--eGXs", ExportName = "sceSaveDataSetParam", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSetParam(CpuContext ctx) => TransferParam(ctx, write: true);
-
-    private static int TransferParam(CpuContext ctx, bool write)
-    {
-        // rdi: mount-point string (16 bytes). rsi: paramType. rdx: SceSaveDataParam*. rcx: size.
-        var mountPointAddress = ctx[CpuRegister.Rdi];
-        var paramAddress = ctx[CpuRegister.Rdx];
-        if (mountPointAddress == 0 || paramAddress == 0 ||
-            !TryReadFixedAscii(ctx, mountPointAddress, 16, out var mountPoint))
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorParameter);
-        }
-
-        MountEntry? entry;
-        lock (_mountGate)
-        {
-            _mounts.TryGetValue(mountPoint, out entry);
-        }
-
-        if (entry is null)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorBadMounted);
-        }
-
-        try
-        {
-            if (write)
-            {
-                Span<byte> raw = stackalloc byte[SaveDataParamSize];
-                if (!ctx.Memory.TryRead(paramAddress, raw))
-                {
-                    return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-                }
-
-                var metadata = new SaveDataMetadata
-                {
-                    Title = ReadAsciiField(raw.Slice(0x00, 128)),
-                    SubTitle = ReadAsciiField(raw.Slice(0x80, 128)),
-                    Detail = ReadAsciiField(raw.Slice(0x100, 1024)),
-                    UserParam = BinaryPrimitives.ReadUInt32LittleEndian(raw[0x500..]),
-                };
-                SaveDataStorage.WriteMetadata(entry.SlotDir, metadata);
-                TraceSaveData($"set_param mount='{mountPoint}' title='{metadata.Title}'");
-                return SetReturn(ctx, 0);
-            }
-
-            var loaded = SaveDataStorage.ReadMetadata(entry.SlotDir);
-            var param = new byte[SaveDataParamSize];
-            WriteAscii(param.AsSpan(0x00, 128), loaded.Title);
-            WriteAscii(param.AsSpan(0x80, 128), loaded.SubTitle);
-            WriteAscii(param.AsSpan(0x100, 1024), loaded.Detail);
-            BinaryPrimitives.WriteUInt32LittleEndian(param.AsSpan(0x500), loaded.UserParam);
-            BinaryPrimitives.WriteInt64LittleEndian(
-                param.AsSpan(0x508),
-                new DateTimeOffset(SafeLastWriteUtc(entry.SlotDir)).ToUnixTimeSeconds());
-            return ctx.Memory.TryWrite(paramAddress, param)
-                ? SetReturn(ctx, 0)
-                : SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorInternal);
-        }
-    }
-
-    // ---- icons ----
-    [SysAbiExport(Nid = "c88Yy54Mx0w", ExportName = "sceSaveDataSaveIcon", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSaveIcon(CpuContext ctx) => TransferIconForMount(ctx, write: true);
-
-    [SysAbiExport(Nid = "cGjO3wM3V28", ExportName = "sceSaveDataLoadIcon", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataLoadIcon(CpuContext ctx) => TransferIconForMount(ctx, write: false);
-
-    private static int TransferIconForMount(CpuContext ctx, bool write)
-    {
-        // rdi: mount-point string. rsi: SceSaveDataIcon* {buf@+0x00, bufSize@+0x08, dataSize@+0x10}.
-        var mountPointAddress = ctx[CpuRegister.Rdi];
-        var iconAddress = ctx[CpuRegister.Rsi];
-        if (mountPointAddress == 0 || iconAddress == 0 ||
-            !TryReadFixedAscii(ctx, mountPointAddress, 16, out var mountPoint) ||
-            !ctx.TryReadUInt64(iconAddress + 0x00, out var bufferAddress) ||
-            !ctx.TryReadUInt64(iconAddress + 0x08, out var bufferSize))
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorParameter);
-        }
-
-        MountEntry? entry;
-        lock (_mountGate)
-        {
-            _mounts.TryGetValue(mountPoint, out entry);
-        }
-
-        if (entry is null)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorBadMounted);
-        }
-
-        var iconPath = SaveDataStorage.IconPath(entry.SlotDir);
-        try
-        {
-            if (write)
-            {
-                var length = checked((int)Math.Min(bufferSize, (ulong)16 * 1024 * 1024));
-                var bytes = ArrayPool<byte>.Shared.Rent(length);
-                try
-                {
-                    if (!ctx.Memory.TryRead(bufferAddress, bytes.AsSpan(0, length)))
-                    {
-                        return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-                    }
-
-                    Directory.CreateDirectory(Path.GetDirectoryName(iconPath)!);
-                    File.WriteAllBytes(iconPath, bytes.AsSpan(0, length).ToArray());
-                }
-                finally
-                {
-                    ArrayPool<byte>.Shared.Return(bytes);
-                }
-
-                return SetReturn(ctx, 0);
-            }
-
-            if (!File.Exists(iconPath))
-            {
-                return SetReturn(ctx, OrbisSaveDataErrorNotFound);
-            }
-
-            var data = File.ReadAllBytes(iconPath);
-            var copy = (int)Math.Min((ulong)data.Length, bufferSize);
-            if (bufferAddress != 0 && copy > 0 && !ctx.Memory.TryWrite(bufferAddress, data.AsSpan(0, copy)))
-            {
-                return SetReturn(ctx, (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT);
-            }
-
-            TryWriteUInt32(ctx, iconAddress + 0x10, (uint)data.Length); // dataSize
-            return SetReturn(ctx, 0);
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return SetReturn(ctx, OrbisSaveDataErrorInternal);
-        }
-    }
-
-    // ---- size / progress / abort ----
-    [SysAbiExport(Nid = "A1ThglSGUwA", ExportName = "sceSaveDataGetAllSize", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetAllSize(CpuContext ctx)
-    {
-        var outAddress = ctx[CpuRegister.Rsi];
-        long total = 0;
-        try
-        {
-            var titleRoot = ResolveTitleSaveRoot(0, ResolveConfiguredTitleId());
-            if (Directory.Exists(titleRoot))
-            {
-                total = SafeDirectorySize(titleRoot);
-            }
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            // Report zero on an unreadable tree rather than fail the query.
-        }
-
-        if (outAddress != 0)
-        {
-            var kib = (ulong)((total + 1023) / 1024);
-            ctx.TryWriteUInt64(outAddress, kib);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    [SysAbiExport(Nid = "ANmSWUiyyGQ", ExportName = "sceSaveDataGetProgress", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetProgress(CpuContext ctx)
-    {
-        // Our operations complete synchronously, so any in-flight progress is 100%.
-        var outAddress = ctx[CpuRegister.Rdi];
-        if (outAddress != 0)
-        {
-            Span<byte> progress = stackalloc byte[8];
-            progress.Clear();
-            BinaryPrimitives.WriteSingleLittleEndian(progress, 1.0f);
-            ctx.Memory.TryWrite(outAddress, progress);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    [SysAbiExport(Nid = "Wz-4JZfeO9g", ExportName = "sceSaveDataClearProgress", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataClearProgress(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(Nid = "dQ2GohUHXzk", ExportName = "sceSaveDataAbort", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataAbort(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(Nid = "eBSSNIG6hMk", ExportName = "sceSaveDataGetEventInfo", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetEventInfo(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(Nid = "52pL2GKkdjA", ExportName = "sceSaveDataSetEventInfo", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSetEventInfo(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(Nid = "Z7z6HXWORJY", ExportName = "sceSaveDataSaveIconByPath", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSaveIconByPath(CpuContext ctx) => SetReturn(ctx, 0);
-
-    [SysAbiExport(Nid = "SN7rTPHS+Cg", ExportName = "sceSaveDataGetSaveDataCount", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetSaveDataCount(CpuContext ctx)
-    {
-        var outAddress = ctx[CpuRegister.Rsi];
-        var count = 0;
-        try
-        {
-            var titleRoot = ResolveTitleSaveRoot(0, ResolveConfiguredTitleId());
-            if (Directory.Exists(titleRoot))
-            {
-                foreach (var dir in Directory.EnumerateDirectories(titleRoot))
-                {
-                    if (!string.Equals(Path.GetFileName(dir), "sce_sdmemory", StringComparison.Ordinal))
-                    {
-                        count++;
-                    }
-                }
-            }
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            // Report zero on an unreadable tree.
-        }
-
-        if (outAddress != 0)
-        {
-            TryWriteUInt32(ctx, outAddress, (uint)count);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    [SysAbiExport(Nid = "pc4guaUPVqA", ExportName = "sceSaveDataGetMountedSaveDataCount", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetMountedSaveDataCount(CpuContext ctx)
-    {
-        var outAddress = ctx[CpuRegister.Rsi];
-        int mounted;
-        lock (_mountGate)
-        {
-            mounted = _mounts.Count;
-        }
-
-        if (outAddress != 0)
-        {
-            TryWriteUInt32(ctx, outAddress, (uint)mounted);
-        }
-
-        return SetReturn(ctx, 0);
-    }
-
-    // ---- SaveDataMemory v1 aliases (identical arg layout to the v2 forms) ----
-    [SysAbiExport(Nid = "v7AAAMo0Lz4", ExportName = "sceSaveDataSetupSaveDataMemory", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSetupSaveDataMemory(CpuContext ctx) => SaveDataSetupSaveDataMemory2(ctx);
-
-    [SysAbiExport(Nid = "7Bt5pBC-Aco", ExportName = "sceSaveDataGetSaveDataMemory", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataGetSaveDataMemory(CpuContext ctx) => SaveDataGetSaveDataMemory2(ctx);
-
-    [SysAbiExport(Nid = "h3YURzXGSVQ", ExportName = "sceSaveDataSetSaveDataMemory", Target = Generation.Gen4 | Generation.Gen5, LibraryName = "libSceSaveData")]
-    public static int SaveDataSetSaveDataMemory(CpuContext ctx) => SaveDataSetSaveDataMemory2(ctx);
-
-    private static string ReadAsciiField(ReadOnlySpan<byte> field)
-    {
-        var length = field.IndexOf((byte)0);
-        if (length < 0)
-        {
-            length = field.Length;
-        }
-
-        return Encoding.ASCII.GetString(field[..length]);
-    }
-
-    private static long SafeDirectorySize(string root)
-    {
-        try
-        {
-            return Directory.Exists(root) ? GetDirectorySize(root) : 0;
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return 0;
-        }
-    }
-
-    private static DateTime SafeLastWriteUtc(string path)
-    {
-        try
-        {
-            return Directory.Exists(path) ? Directory.GetLastWriteTimeUtc(path) : DateTime.UtcNow;
-        }
-        catch (Exception exception) when (exception is IOException or UnauthorizedAccessException)
-        {
-            return DateTime.UtcNow;
-        }
     }
 
     [SysAbiExport(
@@ -745,10 +221,6 @@ public static class SaveDataExports
 
             const string mountPoint = "/savedata0";
             KernelMemoryCompatExports.RegisterGuestPathMount(mountPoint, savePath);
-            lock (_mountGate)
-            {
-                _mounts[mountPoint] = new MountEntry(savePath, dirName, userId);
-            }
 
             Span<byte> result = stackalloc byte[MountResultSize];
             result.Clear();
@@ -846,20 +318,10 @@ public static class SaveDataExports
         LibraryName = "libSceSaveData")]
     public static int SaveDataUmount2(CpuContext ctx)
     {
-        // rdi: SceSaveDataMountPoint* (16-byte mount point string) for umount2.
-        var mountPointAddress = ctx[CpuRegister.Rdi];
-        if (mountPointAddress != 0 && TryReadFixedAscii(ctx, mountPointAddress, 16, out var mountPoint) &&
-            !string.IsNullOrEmpty(mountPoint))
-        {
-            lock (_mountGate)
-            {
-                _mounts.Remove(mountPoint);
-            }
-
-            KernelMemoryCompatExports.UnregisterGuestPathMount(mountPoint);
-            TraceSaveData($"umount2 mount='{mountPoint}'");
-        }
-
+        // Unmounting a save directory always succeeds in the stub filesystem;
+        // returning an error here makes the game's save flow stall before it
+        // hands control to the title/gameplay state.
+        TraceSaveData($"umount2 user={unchecked((int)ctx[CpuRegister.Rdi])}");
         return SetReturn(ctx, 0);
     }
 
@@ -943,12 +405,9 @@ public static class SaveDataExports
 
     private static bool TryWriteParam(CpuContext ctx, ulong address, SaveEntry entry)
     {
-        var metadata = SaveDataStorage.ReadMetadata(entry.Path);
         var param = new byte[SaveDataParamSize];
-        WriteAscii(param.AsSpan(0x00, 128), metadata.Title);
-        WriteAscii(param.AsSpan(0x80, 128), metadata.SubTitle);
-        WriteAscii(param.AsSpan(0x100, 1024), string.IsNullOrEmpty(metadata.Detail) ? entry.Name : metadata.Detail);
-        BinaryPrimitives.WriteUInt32LittleEndian(param.AsSpan(0x500), metadata.UserParam);
+        WriteAscii(param.AsSpan(0x00, 128), "Saved Data");
+        WriteAscii(param.AsSpan(0x100, 1024), entry.Name);
         BinaryPrimitives.WriteInt64LittleEndian(
             param.AsSpan(0x508, sizeof(long)),
             new DateTimeOffset(entry.LastWriteUtc).ToUnixTimeSeconds());
@@ -1015,14 +474,11 @@ public static class SaveDataExports
         return false;
     }
 
-    // Saves are keyed by title id only (single-user emulation) under
-    // ~/SharpEmu/Saves/<titleId>/; userId is accepted for API fidelity but not
-    // part of the host path.
     private static string ResolveTitleSaveRoot(int userId, string titleId) =>
-        SaveDataStorage.TitleRoot(ResolveSaveDataRoot(), titleId);
+        Path.Combine(ResolveSaveDataRoot(), userId.ToString(), SanitizePathSegment(titleId));
 
     private static string ResolveSaveDataMemoryPath(int userId) =>
-        SaveDataStorage.MemoryPath(ResolveTitleSaveRoot(userId, ResolveConfiguredTitleId()));
+        Path.Combine(ResolveTitleSaveRoot(userId, ResolveConfiguredTitleId()), "sce_sdmemory", "memory.dat");
 
     private static bool TryReadMemoryData(
         CpuContext ctx, ulong address, out ulong buffer, out ulong size, out ulong offset)
@@ -1034,7 +490,14 @@ public static class SaveDataExports
             ctx.TryReadUInt64(address + 0x10, out offset);
     }
 
-    private static string ResolveSaveDataRoot() => SaveDataStorage.Root();
+    private static string ResolveSaveDataRoot()
+    {
+        var configured = Environment.GetEnvironmentVariable("SHARPEMU_SAVEDATA_DIR");
+        var root = string.IsNullOrWhiteSpace(configured)
+            ? Path.Combine(AppContext.BaseDirectory, "user", "savedata")
+            : configured;
+        return Path.GetFullPath(root);
+    }
 
     private static string ResolveConfiguredTitleId()
     {
@@ -1062,7 +525,12 @@ public static class SaveDataExports
         return "default";
     }
 
-    private static string SanitizePathSegment(string value) => SaveDataStorage.Sanitize(value);
+    private static string SanitizePathSegment(string value)
+    {
+        var invalid = Path.GetInvalidFileNameChars();
+        var sanitized = new string(value.Select(ch => invalid.Contains(ch) ? '_' : ch).ToArray());
+        return string.IsNullOrWhiteSpace(sanitized) ? "default" : sanitized;
+    }
 
     private static bool TryReadFixedAscii(CpuContext ctx, ulong address, int length, out string value)
     {
@@ -1322,17 +790,8 @@ public static class SaveDataExports
             return ctx.SetReturn(OrbisSaveDataErrorParameter);
         }
 
-        if (!File.Exists(ResolveSaveDataMemoryPath(userId)))
-        {
-            return ctx.SetReturn(OrbisSaveDataErrorMemoryNotReady);
-        }
-
-        // The write already reached disk synchronously, but the guest treats
-        // sync as asynchronous and blocks a worker on sceSaveDataGetEventResult
-        // until the SAVE_DATA_MEMORY_SYNC_END event arrives. Post it so that
-        // poll completes (this is what wedged Dead Cells at FLIP 0 in-level).
-        EnqueueEvent(EventTypeSaveDataMemorySyncEnd, userId, string.Empty);
-        return ctx.SetReturn(0);
+        return ctx.SetReturn(
+            File.Exists(ResolveSaveDataMemoryPath(userId)) ? 0 : OrbisSaveDataErrorMemoryNotReady);
     }
 
     private static int TransferSaveDataMemory(CpuContext ctx, bool write)

src/SharpEmu.Libs/SaveData/SaveDataStorage.cs

@@ -1,130 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Text.Json;
-using System.Text.Json.Serialization;
-
-namespace SharpEmu.Libs.SaveData;
-
-/// <summary>
-/// Host-side layout and metadata for PS5 save data. Saves live under
-/// <c>~/SharpEmu/Saves/&lt;titleId&gt;/&lt;dirName&gt;/</c> (overridable via
-/// <c>SHARPEMU_SAVEDATA_DIR</c>); the game's files are written directly inside a
-/// slot through the mounted <c>/savedata0</c> filesystem, and the PS5 UI
-/// metadata (title/subtitle/detail/userParam) plus icon live under
-/// <c>&lt;slot&gt;/sce_sys/</c>. This type is pure filesystem logic with no guest
-/// interop so the path and metadata handling can be unit-tested.
-/// </summary>
-public static class SaveDataStorage
-{
-    /// <summary>Root of all saves: the env override, else <c>~/SharpEmu/Saves</c>.</summary>
-    public static string Root(string? overrideDir = null)
-    {
-        var configured = overrideDir ?? Environment.GetEnvironmentVariable("SHARPEMU_SAVEDATA_DIR");
-        var root = string.IsNullOrWhiteSpace(configured)
-            ? Path.Combine(
-                Environment.GetFolderPath(Environment.SpecialFolder.UserProfile),
-                "SharpEmu",
-                "Saves")
-            : configured;
-        return Path.GetFullPath(root);
-    }
-
-    /// <summary>Per-title directory: <c>&lt;root&gt;/&lt;titleId&gt;</c>.</summary>
-    public static string TitleRoot(string root, string titleId) =>
-        Path.Combine(root, Sanitize(titleId));
-
-    /// <summary>A single save slot: <c>&lt;titleRoot&gt;/&lt;dirName&gt;</c>.</summary>
-    public static string SlotDir(string titleRoot, string dirName) =>
-        Path.Combine(titleRoot, Sanitize(dirName));
-
-    /// <summary>The SaveDataMemory blob shared by a title.</summary>
-    public static string MemoryPath(string titleRoot) =>
-        Path.Combine(titleRoot, "sce_sdmemory", "memory.dat");
-
-    public static string ParamPath(string slotDir) =>
-        Path.Combine(slotDir, "sce_sys", "param.json");
-
-    public static string IconPath(string slotDir) =>
-        Path.Combine(slotDir, "sce_sys", "icon0.png");
-
-    /// <summary>
-    /// Replaces characters that are invalid in a host path segment. Empty or
-    /// all-invalid input collapses to "default" so a bad guest name can never
-    /// escape the save root or produce an empty segment.
-    /// </summary>
-    public static string Sanitize(string value)
-    {
-        if (string.IsNullOrEmpty(value))
-        {
-            return "default";
-        }
-
-        var invalid = Path.GetInvalidFileNameChars();
-        Span<char> buffer = value.Length <= 128 ? stackalloc char[value.Length] : new char[value.Length];
-        for (var i = 0; i < value.Length; i++)
-        {
-            var ch = value[i];
-            buffer[i] = Array.IndexOf(invalid, ch) >= 0 ? '_' : ch;
-        }
-
-        var sanitized = new string(buffer).Trim();
-        return string.IsNullOrWhiteSpace(sanitized) ? "default" : sanitized;
-    }
-
-    /// <summary>Reads a slot's metadata, or defaults if none has been written.</summary>
-    public static SaveDataMetadata ReadMetadata(string slotDir)
-    {
-        var path = ParamPath(slotDir);
-        if (File.Exists(path))
-        {
-            try
-            {
-                var parsed = JsonSerializer.Deserialize(File.ReadAllText(path), SaveDataMetadataContext.Default.SaveDataMetadata);
-                if (parsed is not null)
-                {
-                    return parsed;
-                }
-            }
-            catch (Exception exception) when (exception is JsonException or IOException or UnauthorizedAccessException)
-            {
-                // Fall through to defaults on a corrupt or unreadable metadata file.
-            }
-        }
-
-        return SaveDataMetadata.CreateDefault(Path.GetFileName(slotDir.TrimEnd(Path.DirectorySeparatorChar)));
-    }
-
-    /// <summary>Writes a slot's metadata, creating <c>sce_sys/</c> as needed.</summary>
-    public static void WriteMetadata(string slotDir, SaveDataMetadata metadata)
-    {
-        var path = ParamPath(slotDir);
-        Directory.CreateDirectory(Path.GetDirectoryName(path)!);
-        File.WriteAllText(path, JsonSerializer.Serialize(metadata, SaveDataMetadataContext.Default.SaveDataMetadata));
-    }
-}
-
-/// <summary>PS5 save-slot metadata surfaced by sceSaveDataGetParam / the save UI.</summary>
-public sealed record SaveDataMetadata
-{
-    [JsonPropertyName("title")]
-    public string Title { get; init; } = "Saved Data";
-
-    [JsonPropertyName("subTitle")]
-    public string SubTitle { get; init; } = string.Empty;
-
-    [JsonPropertyName("detail")]
-    public string Detail { get; init; } = string.Empty;
-
-    [JsonPropertyName("userParam")]
-    public uint UserParam { get; init; }
-
-    public static SaveDataMetadata CreateDefault(string dirName) =>
-        new() { Title = string.IsNullOrWhiteSpace(dirName) ? "Saved Data" : dirName };
-}
-
-[JsonSerializable(typeof(SaveDataMetadata))]
-[JsonSourceGenerationOptions(WriteIndented = true)]
-internal sealed partial class SaveDataMetadataContext : JsonSerializerContext
-{
-}

src/SharpEmu.Libs/SharpEmu.Libs.csproj

@@ -7,7 +7,6 @@ SPDX-License-Identifier: GPL-2.0-or-later
   <ItemGroup>
     <ProjectReference Include="..\SharpEmu.HLE\SharpEmu.HLE.csproj" />
     <ProjectReference Include="..\SharpEmu.ShaderCompiler\SharpEmu.ShaderCompiler.csproj" />
-    <ProjectReference Include="..\SharpEmu.ShaderCompiler.Metal\SharpEmu.ShaderCompiler.Metal.csproj" />
     <ProjectReference Include="..\SharpEmu.ShaderCompiler.Vulkan\SharpEmu.ShaderCompiler.Vulkan.csproj" />
     <!-- SysAbi export generator + analyzers (compile-time registry, NID validation). -->
     <ProjectReference Include="..\SharpEmu.SourceGenerators\SharpEmu.SourceGenerators.csproj"

src/SharpEmu.Libs/VideoOut/BoundedByteArrayPool.cs

@@ -0,0 +1,122 @@
+// Copyright (C) 2026 SharpEmu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+using System.Buffers;
+using System.Numerics;
+
+namespace SharpEmu.Libs.VideoOut;
+
+internal sealed class BoundedByteArrayPool : ArrayPool<byte>
+{
+    private readonly object _gate = new();
+    private readonly int _maxArrayLength;
+    private readonly ulong _maxCachedBytes;
+    private readonly int _maxArraysPerBucket;
+    private readonly Dictionary<int, Stack<byte[]>> _cachedByBucket = [];
+    private readonly HashSet<byte[]> _leases =
+        new(System.Collections.Generic.ReferenceEqualityComparer.Instance);
+    private ulong _cachedBytes;
+
+    public BoundedByteArrayPool(
+        int maxArrayLength,
+        ulong maxCachedBytes,
+        int maxArraysPerBucket)
+    {
+        ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArrayLength);
+        ArgumentOutOfRangeException.ThrowIfZero(maxCachedBytes);
+        ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxArraysPerBucket);
+        _maxArrayLength = maxArrayLength;
+        _maxCachedBytes = maxCachedBytes;
+        _maxArraysPerBucket = maxArraysPerBucket;
+    }
+
+    public override byte[] Rent(int minimumLength)
+    {
+        ArgumentOutOfRangeException.ThrowIfNegative(minimumLength);
+        var length = GetAllocationLength(minimumLength);
+        byte[]? array = null;
+        lock (_gate)
+        {
+            if (length <= _maxArrayLength &&
+                _cachedByBucket.TryGetValue(length, out var bucket) &&
+                bucket.TryPop(out array))
+            {
+                _cachedBytes -= (ulong)array.LongLength;
+            }
+
+            array ??= new byte[length];
+            _leases.Add(array);
+        }
+
+        return array;
+    }
+
+    public override void Return(byte[] array, bool clearArray = false)
+    {
+        ArgumentNullException.ThrowIfNull(array);
+        lock (_gate)
+        {
+            if (!_leases.Remove(array))
+            {
+                return;
+            }
+        }
+
+        if (clearArray)
+        {
+            Array.Clear(array);
+        }
+
+        lock (_gate)
+        {
+            if (array.Length > _maxArrayLength ||
+                !IsBucketLength(array.Length) ||
+                (ulong)array.LongLength > _maxCachedBytes -
+                    Math.Min(_cachedBytes, _maxCachedBytes))
+            {
+                return;
+            }
+
+            if (!_cachedByBucket.TryGetValue(array.Length, out var bucket))
+            {
+                bucket = new Stack<byte[]>();
+                _cachedByBucket.Add(array.Length, bucket);
+            }
+
+            if (bucket.Count >= _maxArraysPerBucket)
+            {
+                return;
+            }
+
+            bucket.Push(array);
+            _cachedBytes += (ulong)array.LongLength;
+        }
+    }
+
+    public void Trim()
+    {
+        lock (_gate)
+        {
+            _cachedByBucket.Clear();
+            _cachedBytes = 0;
+        }
+    }
+
+    private int GetAllocationLength(int minimumLength)
+    {
+        if (minimumLength <= 16)
+        {
+            return 16;
+        }
+
+        if (minimumLength > _maxArrayLength)
+        {
+            return minimumLength;
+        }
+
+        return checked((int)BitOperations.RoundUpToPowerOf2((uint)minimumLength));
+    }
+
+    private static bool IsBucketLength(int length) =>
+        length >= 16 && (length & (length - 1)) == 0;
+}

src/SharpEmu.Libs/VideoOut/PerfOverlay.cs

@@ -36,7 +36,6 @@ public static class PerfOverlay
     private static long _presentedInWindow;
     private static long _submittedInWindow;
     private static long _drawsInWindow;
-    private static long _guestBufferCacheBytes;
 
     // Refreshed once per second so per-frame fills never allocate.
     private static long _statsWindowStart = Stopwatch.GetTimestamp();
@@ -75,8 +74,11 @@ public static class PerfOverlay
         if (last != 0)
         {
             var milliseconds = (now - last) * 1000.0 / Stopwatch.Frequency;
-            _frameMilliseconds[_frameHistoryIndex] = milliseconds;
-            _frameHistoryIndex = (_frameHistoryIndex + 1) % FrameHistorySize;
+            if (milliseconds < 1000.0)
+            {
+                _frameMilliseconds[_frameHistoryIndex] = milliseconds;
+                _frameHistoryIndex = (_frameHistoryIndex + 1) % FrameHistorySize;
+            }
         }
     }
 
@@ -86,9 +88,6 @@ public static class PerfOverlay
     /// <summary>Called per translated draw/dispatch executed.</summary>
     public static void RecordDraw() => Interlocked.Increment(ref _drawsInWindow);
 
-    public static void SetGuestBufferCacheBytes(ulong bytes) =>
-        Interlocked.Exchange(ref _guestBufferCacheBytes, checked((long)bytes));
-
     /// <summary>
     /// Rasterizes the panel into a BGRA byte span of PanelWidth x PanelHeight.
     /// Runs on the render thread.
@@ -166,7 +165,7 @@ public static class PerfOverlay
                 Environment.ProcessorCount;
             _lastCpuTime = cpuTime;
 
-            var drawsPerFrame = _fps > 0 ? _drawsPerSecond / _fps : 0;
+            var drawsPerFrame = _fps > 0.5 ? _drawsPerSecond / _fps : 0;
             var sessionStart = Interlocked.Read(ref _sessionStartTimestamp);
             var elapsedSeconds = sessionStart == 0
                 ? 0L
@@ -177,9 +176,7 @@ public static class PerfOverlay
             _line1 = $"FPS {_fps:0.0}  FLIP {_submittedFps:0.0}  {_averageFrameMs:0.0} MS";
             _line2 = $"DRAWS {_drawsPerSecond:0}/S  {drawsPerFrame:0}/F  Q {pendingWork}+{inFlightSubmissions}";
             _line3 = $"ALLOC {_allocatedMbPerSecond:0.0} MB/S  GC {_gen0PerWindow}/{_gen1PerWindow}/{_gen2PerWindow}";
-            var heapMb = GC.GetTotalMemory(false) / (1024 * 1024);
-            var guestBufferMb = Interlocked.Read(ref _guestBufferCacheBytes) / (1024 * 1024);
-            _line4 = $"MEM {heapMb}M BUF {guestBufferMb}M CPU {_cpuPercent:0}%";
+            _line4 = $"CPU {_cpuPercent:0}%  HEAP {GC.GetTotalMemory(false) / (1024 * 1024)} MB  F1 HIDE";
             _line5 = $"TIME {elapsedHours:00}:{elapsedMinutes:00}:{elapsedRemainingSeconds:00}";
         }
     }

src/SharpEmu.Libs/VideoOut/VideoOutExports.cs

@@ -131,14 +131,9 @@ public static class VideoOutExports
             return;
         }
 
-        // macOS can run either backend (Vulkan through MoltenVK, or Metal), so
-        // name the active one in the title to make which is in use unambiguous.
-        var backendSuffix = OperatingSystem.IsMacOS()
-            ? $" ({GuestGpu.Current.BackendName})"
-            : string.Empty;
         lock (_stateGate)
         {
-            _windowTitle = $"{_windowTitle} · {gpuName.Trim()}{backendSuffix}";
+            _windowTitle = $"{_windowTitle} · {gpuName.Trim()}";
         }
     }
 
@@ -171,12 +166,11 @@ public static class VideoOutExports
         HostSessionControl.RequestShutdown(reason);
 
         // A hosted game can still be issuing AGC work after it requests its
-        // own shutdown. Keep the presenter's resources alive until the GUI
-        // session reaches its guest-safe exit path and disposes the host
-        // surface.
+        // own shutdown. Keep the Vulkan resources alive until the GUI session
+        // reaches its guest-safe exit path and disposes the host surface.
         if (!embedded)
         {
-            GuestGpu.Current.RequestClose();
+            VulkanVideoPresenter.RequestClose();
         }
 
         // The embedded GUI owns the process lifetime. A guest shutdown should
@@ -1076,12 +1070,6 @@ public static class VideoOutExports
             return (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT;
         }
 
-        // SceVideoOutBufferCategory is a 32-bit enum passed on the stack; the
-        // upper 32 bits of the slot are stale (games leave GNM magic there), so
-        // mask before validating. UNCOMPRESSED (0) and COMPRESSED (1) are both
-        // valid — we present either identically, so accept both.
-        var category = (uint)categoryRaw;
-
         if (!TryGetPort(handle, out var port))
         {
             return OrbisVideoOutErrorInvalidHandle;
@@ -1102,7 +1090,7 @@ public static class VideoOutExports
             return OrbisVideoOutErrorInvalidValue;
         }
 
-        if (category > 1 || option != 0)
+        if (categoryRaw != 0 || option != 0)
         {
             return OrbisVideoOutErrorInvalidValue;
         }
@@ -1221,7 +1209,7 @@ public static class VideoOutExports
         {
             TriggerFlipEvents();
         }
-        else if (GuestGpu.Current.SubmitOrderedGuestAction(
+        else if (VulkanVideoPresenter.SubmitOrderedGuestAction(
                      TriggerFlipEvents,
                      $"videoout flip complete handle={handle} index={bufferIndex}") == 0)
         {
@@ -1275,7 +1263,7 @@ public static class VideoOutExports
         var elapsedSeconds = (double)elapsedTicks / Stopwatch.Frequency;
         var submitted = Interlocked.Exchange(ref _submittedFrameCount, 0);
         var presentedCount = Interlocked.Exchange(ref _presentedFrameCount, 0);
-        var (draws, drawMs, pipelines, spirvCompiles) = GuestGpu.Current.ReadAndResetPerfCounters();
+        var (draws, drawMs, pipelines, spirvCompiles) = VulkanVideoPresenter.ReadAndResetPerfCounters();
         Console.Error.WriteLine(
             $"[LOADER][PERF] videoout submitted_fps={submitted / elapsedSeconds:F1} " +
             $"presented_fps={presentedCount / elapsedSeconds:F1} " +
@@ -1714,7 +1702,7 @@ public static class VideoOutExports
             SceVideoOutPixelFormat2B10G10R10A2Bt2100Pq;
 
     // Maps the PS5 VideoOut pixel format space to the AGC "guest texture format" tags
-    // the backend keys its guest-image registry on (see the presenter's
+    // the backend keys its guest-image registry on (see VulkanVideoPresenter.
     // GetGuestTextureFormat: format=10 => 56 for 8-bit RGBA variants, format=9 => 9 for 10-bit).
     // Unknown formats default to 56 (8-bit RGBA) with a logged warning so games
     // display something rather than silently failing the flip pipeline.

src/SharpEmu.ShaderCompiler.Metal/Gen5MslShader.cs

@@ -1,58 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.ShaderCompiler;
-
-namespace SharpEmu.ShaderCompiler.Metal;
-
-// MSL-specific shader artifact types. These stay beside the MSL emitter (not in the
-// backend-neutral SharpEmu.ShaderCompiler project): each codegen owns its own
-// compiled-shader shape, mirroring Gen5SpirvShader on the Vulkan side.
-public enum Gen5MslStage
-{
-    Vertex,
-    Pixel,
-    Compute,
-}
-
-/// <summary>
-/// A translated Metal shader: MSL source text plus the reflection data the Metal
-/// backend needs to bind it. Buffer argument indices follow the translation
-/// contract documented on <see cref="Gen5MslTranslator"/>: global memory buffers
-/// occupy [[buffer(globalBufferBase + i)]] in <see cref="GlobalMemoryBindings"/>
-/// order, and compute shaders reserve one trailing slot for the dispatch-limit
-/// uniform. Unlike SPIR-V, Metal fixes the threadgroup size at dispatch time, so
-/// the size the shader was translated for is carried here.
-/// </summary>
-/// <remarks>
-/// <para><see cref="UniformsBufferIndex"/> is the [[buffer(N)]] slot this stage's
-/// SharpEmuUniforms argument was emitted at (globalBufferBase +
-/// totalGlobalBufferCount, both translation-time inputs). Stages sharing a draw
-/// can disagree — a vertex stage whose guest buffers sit after the pixel
-/// stage's has a higher base — so the presenter must bind the uniforms buffer
-/// per stage at this exact index rather than assuming one shared slot.</para>
-/// <para>Texture slots are global across a draw's stages ([[texture(
-/// ImageBindingBase + i)]]). Samplers live in a per-stage argument buffer
-/// bound at <see cref="SamplerArgBufferIndex"/> (Metal caps direct
-/// [[sampler(N)]] slots at 16 per stage, but shaders sample more), holding one
-/// sampler per sampled image. <see cref="SamplerSlots"/> maps this stage's
-/// image binding index to its [[id(N)]] entry in that argument buffer, -1 for
-/// storage images that take none; <see cref="SamplerCount"/> is the entry
-/// count.</para>
-/// </remarks>
-public sealed record Gen5MslShader(
-    string Source,
-    string EntryPoint,
-    Gen5MslStage Stage,
-    IReadOnlyList<Gen5GlobalMemoryBinding> GlobalMemoryBindings,
-    IReadOnlyList<Gen5ImageBinding> ImageBindings,
-    uint AttributeCount,
-    IReadOnlyList<Gen5VertexInputBinding> VertexInputs,
-    uint ThreadgroupSizeX = 1,
-    uint ThreadgroupSizeY = 1,
-    uint ThreadgroupSizeZ = 1,
-    int UniformsBufferIndex = -1,
-    int ImageBindingBase = 0,
-    IReadOnlyList<int>? SamplerSlots = null,
-    int SamplerCount = 0,
-    int SamplerArgBufferIndex = -1);

src/SharpEmu.ShaderCompiler.Metal/Gen5MslTranslator.Pixel.cs

@@ -1,888 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Text;
-using SharpEmu.ShaderCompiler;
-
-namespace SharpEmu.ShaderCompiler.Metal;
-
-public static partial class Gen5MslTranslator
-{
-    private sealed partial class CompilationContext
-    {
-        private const uint ImageDescriptorDwords = 8;
-        private const uint SamplerDescriptorDwords = 4;
-
-        // ---- image resources ----
-
-        /// <summary>
-        /// Classifies every image binding (storage vs sampled, component kind
-        /// from the descriptor's unified format) and seeds the PC lookup,
-        /// mirroring DeclareImages on the SPIR-V side. MSL needs no format on
-        /// the texture type — only the component type and access.
-        /// </summary>
-        private void DeclareImageKinds()
-        {
-            for (var index = 0; index < _evaluation.ImageBindings.Count; index++)
-            {
-                var binding = _evaluation.ImageBindings[index];
-                _imageBindingByPc.TryAdd(binding.Pc, index);
-                var isStorage = Gen5ShaderTranslator.IsStorageImageOperation(binding.Opcode);
-                _imageKinds.Add((isStorage, DecodeImageComponentKind(binding.ResourceDescriptor)));
-            }
-
-            // Seed each binding's access from the opcode that defined it; the body
-            // emission (TryEmitImage) then ORs in the access of every instruction
-            // that resolves to the same binding, so a load and a store sharing one
-            // binding correctly become read_write.
-            _imageBindingReads = new bool[_imageKinds.Count];
-            _imageBindingWrites = new bool[_imageKinds.Count];
-            for (var index = 0; index < _evaluation.ImageBindings.Count; index++)
-            {
-                MarkImageBindingAccess(index, _evaluation.ImageBindings[index].Opcode);
-            }
-
-            // Assign one sampler per sampled image (storage images take none).
-            // Computed before body emission because the sample calls reference
-            // the slots. Samplers live in an argument buffer (see
-            // EmitImageArguments), so there is no 16-slot cap to dedup against —
-            // each image keeps its own sampler, matching the SPIR-V/Vulkan path.
-            _samplerSlots = new int[_imageKinds.Count];
-            _samplerCount = 0;
-            for (var index = 0; index < _imageKinds.Count; index++)
-            {
-                _samplerSlots[index] = _imageKinds[index].IsStorage ? -1 : _samplerCount++;
-            }
-        }
-
-        /// <summary>Records that <paramref name="opcode"/> reads and/or writes the
-        /// storage image at <paramref name="bindingIndex"/>, so EmitImageArguments
-        /// can pick the minimal Metal access qualifier.</summary>
-        private void MarkImageBindingAccess(int bindingIndex, string opcode)
-        {
-            if ((uint)bindingIndex >= (uint)_imageBindingReads.Length)
-            {
-                return;
-            }
-
-            if (opcode.StartsWith("ImageStore", StringComparison.Ordinal))
-            {
-                _imageBindingWrites[bindingIndex] = true;
-            }
-            else if (opcode.StartsWith("ImageAtomic", StringComparison.Ordinal))
-            {
-                _imageBindingReads[bindingIndex] = true;
-                _imageBindingWrites[bindingIndex] = true;
-            }
-            else
-            {
-                // ImageLoad/ImageLoadMip and ImageGetResinfo read the texture;
-                // sampled ops are non-storage and ignore these flags.
-                _imageBindingReads[bindingIndex] = true;
-            }
-        }
-
-        /// <summary>"float", "int", or "uint" from the descriptor's unified format.</summary>
-        private static string DecodeImageComponentKind(IReadOnlyList<uint> descriptor)
-        {
-            if (descriptor.Count < 2)
-            {
-                return "float";
-            }
-
-            var unifiedFormat = (descriptor[1] >> 20) & 0x1FFu;
-            if (!Gfx10UnifiedFormat.TryDecode(unifiedFormat, out _, out var numberType))
-            {
-                return "float";
-            }
-
-            return numberType switch
-            {
-                4 => "uint",
-                5 => "int",
-                _ => "float",
-            };
-        }
-
-        /// <summary>Per image binding: its sampler's [[id(N)]] inside the sampler
-        /// argument buffer, or -1 for storage images. Set by DeclareImageKinds.</summary>
-        private int[] _samplerSlots = [];
-
-        /// <summary>Number of sampled images (= sampler argument-buffer entries).</summary>
-        private int _samplerCount;
-
-        /// <summary>Buffer slot the sampler argument buffer binds to, past this
-        /// stage's global buffers, uniforms, and scalar-state buffer.</summary>
-        private int SamplerArgBufferIndex =>
-            Math.Max(UniformsBufferIndex, _initialScalarBufferIndex) + 1;
-
-        /// <summary>Emits the texture arguments (direct [[texture(N)]] slots, which
-        /// run to 31 — enough) plus, when the stage samples anything, the sampler
-        /// argument buffer. Samplers go through an argument buffer rather than
-        /// [[sampler(N)]] slots because Metal caps those at 16 per stage while
-        /// real shaders sample more (void Terrarium's scene shader: 17); argument
-        /// buffers have no such limit on Apple Silicon.</summary>
-        private void EmitImageArguments(StringBuilder source)
-        {
-            for (var index = 0; index < _imageKinds.Count; index++)
-            {
-                var (isStorage, kind) = _imageKinds[index];
-                var textureSlot = _imageBindingBase + index;
-                if (isStorage)
-                {
-                    // Minimal access keeps read_write textures under Metal's cap
-                    // of 8 per function: only images that are both read and
-                    // written (or resolve a load and a store to one binding) need
-                    // read_write; the rest are read-only or write-only.
-                    var access = _imageBindingWrites[index]
-                        ? (_imageBindingReads[index] ? "read_write" : "write")
-                        : "read";
-                    source.AppendLine(
-                        $"    texture2d<{kind}, access::{access}> tex{index} [[texture({textureSlot})]],");
-                }
-                else
-                {
-                    source.AppendLine($"    texture2d<{kind}> tex{index} [[texture({textureSlot})]],");
-                }
-            }
-
-            if (_samplerCount > 0)
-            {
-                source.AppendLine(
-                    $"    constant Gen5Samplers& sharpemu_samplers [[buffer({SamplerArgBufferIndex})]],");
-            }
-        }
-
-        /// <summary>Declares the sampler argument-buffer struct at file scope (one
-        /// sampler per sampled image). Empty when the stage samples nothing.</summary>
-        private void EmitSamplerArgumentBufferStruct(StringBuilder source)
-        {
-            if (_samplerCount == 0)
-            {
-                return;
-            }
-
-            source.AppendLine("struct Gen5Samplers");
-            source.AppendLine("{");
-            for (var slot = 0; slot < _samplerCount; slot++)
-            {
-                source.AppendLine($"    sampler smp{slot} [[id({slot})]];");
-            }
-
-            source.AppendLine("};");
-            source.AppendLine();
-        }
-
-        private bool TryResolveDominatingImageBinding(
-            Gen5ShaderInstruction instruction,
-            Gen5ImageControl control,
-            out int bindingIndex)
-        {
-            if (_imageBindingByPc.TryGetValue(instruction.Pc, out bindingIndex) &&
-                bindingIndex < _imageKinds.Count)
-            {
-                return true;
-            }
-
-            var storage = Gen5ShaderTranslator.IsStorageImageOperation(instruction.Opcode);
-            for (var index = 0; index < _evaluation.ImageBindings.Count; index++)
-            {
-                var candidate = _evaluation.ImageBindings[index];
-                if (candidate.Control.ScalarResource != control.ScalarResource ||
-                    candidate.Control.ScalarSampler != control.ScalarSampler ||
-                    Gen5ShaderTranslator.IsStorageImageOperation(candidate.Opcode) != storage ||
-                    !HasSameScalarDefinitions(
-                        candidate.Pc,
-                        instruction.Pc,
-                        control.ScalarResource,
-                        ImageDescriptorDwords) ||
-                    (UsesSampler(instruction.Opcode) &&
-                     !HasSameScalarDefinitions(
-                         candidate.Pc,
-                         instruction.Pc,
-                         control.ScalarSampler,
-                         SamplerDescriptorDwords)))
-                {
-                    continue;
-                }
-
-                bindingIndex = index;
-                _imageBindingByPc.Add(instruction.Pc, index);
-                return true;
-            }
-
-            bindingIndex = -1;
-            return false;
-        }
-
-        private bool HasSameScalarDefinitions(
-            uint candidatePc,
-            uint targetPc,
-            uint firstRegister,
-            uint registerCount)
-        {
-            if (firstRegister + registerCount > ScalarRegisterFileCount ||
-                !_scalarDefinitionsBeforePc.TryGetValue(candidatePc, out var candidate) ||
-                !_scalarDefinitionsBeforePc.TryGetValue(targetPc, out var target))
-            {
-                return false;
-            }
-
-            for (var register = firstRegister;
-                 register < firstRegister + registerCount;
-                 register++)
-            {
-                var definition = candidate[register];
-                if (definition is ConflictingScalarDefinition or UnreachableScalarDefinition ||
-                    target[register] != definition)
-                {
-                    return false;
-                }
-            }
-
-            return true;
-        }
-
-        private static bool UsesSampler(string opcode) =>
-            opcode.StartsWith("ImageSample", StringComparison.Ordinal) ||
-            opcode.StartsWith("ImageGather", StringComparison.Ordinal);
-
-        // ---- image instruction emission ----
-
-        private bool TryEmitImage(
-            Gen5ShaderInstruction instruction,
-            Gen5ImageControl image,
-            out string error)
-        {
-            error = string.Empty;
-            if (!TryResolveDominatingImageBinding(instruction, image, out var bindingIndex))
-            {
-                error = $"unresolved image binding t=s{image.ScalarResource} s=s{image.ScalarSampler}";
-                return false;
-            }
-
-            // The resolving instruction may differ from the one that defined the
-            // binding (a store can dominate a load's binding); fold its access in.
-            MarkImageBindingAccess(bindingIndex, instruction.Opcode);
-            var (isStorage, kind) = _imageKinds[bindingIndex];
-            var texture = $"tex{bindingIndex}";
-
-            if (instruction.Opcode == "ImageGetResinfo")
-            {
-                var width = Temp("uint", isStorage
-                    ? $"{texture}.get_width()"
-                    : $"{texture}.get_width(0)");
-                var height = Temp("uint", isStorage
-                    ? $"{texture}.get_height()"
-                    : $"{texture}.get_height(0)");
-                uint outputIndex = 0;
-                for (var component = 0; component < 4; component++)
-                {
-                    if ((image.Dmask & (1u << component)) == 0)
-                    {
-                        continue;
-                    }
-
-                    StoreVector(
-                        image.VectorData + outputIndex++,
-                        component switch
-                        {
-                            0 => width,
-                            1 => height,
-                            _ => "1u",
-                        });
-                }
-
-                return true;
-            }
-
-            if (instruction.Opcode is "ImageStore" or "ImageStoreMip")
-            {
-                if (!isStorage)
-                {
-                    error = "image store is not bound as storage";
-                    return false;
-                }
-
-                var x = Temp("int", $"as_type<int>({ImageIntegerAddress(image, 0)})");
-                var y = Temp("int", $"as_type<int>({ImageIntegerAddress(image, 1)})");
-                var components = new string[4];
-                uint sourceIndex = 0;
-                for (var component = 0; component < 4; component++)
-                {
-                    components[component] = (image.Dmask & (1u << component)) != 0
-                        ? ImageTexelComponent(kind, ImageStoreComponent(image, kind, sourceIndex++))
-                        : kind == "float" ? "0.0f" : "0";
-                }
-
-                // Bounds-checked, EXEC-guarded write.
-                Line($"if (exec && {x} >= 0 && {y} >= 0 && {x} < (int){texture}.get_width() && {y} < (int){texture}.get_height())");
-                Line("{");
-                _indent++;
-                Line($"{texture}.write({VectorLiteral(kind)}({components[0]}, {components[1]}, {components[2]}, {components[3]}), uint2((uint){x}, (uint){y}));");
-                _indent--;
-                Line("}");
-                return true;
-            }
-
-            if (isStorage && instruction.Opcode is not ("ImageLoad" or "ImageLoadMip"))
-            {
-                error = $"unsupported storage image opcode {instruction.Opcode}";
-                return false;
-            }
-
-            string sampled;
-            var writeAllComponents = false;
-            if (instruction.Opcode is "ImageLoad" or "ImageLoadMip")
-            {
-                var mip = _evaluation.ImageBindings[bindingIndex].MipLevel ?? 0;
-                var widthQuery = isStorage ? $"{texture}.get_width()" : $"{texture}.get_width({mip}u)";
-                var heightQuery = isStorage ? $"{texture}.get_height()" : $"{texture}.get_height({mip}u)";
-                var x = Temp(
-                    "uint",
-                    $"(uint)clamp(as_type<int>({ImageIntegerAddress(image, 0)}), 0, (int){widthQuery} - 1)");
-                var y = Temp(
-                    "uint",
-                    $"(uint)clamp(as_type<int>({ImageIntegerAddress(image, 1)}), 0, (int){heightQuery} - 1)");
-                sampled = Temp(
-                    $"vec<{kind}, 4>",
-                    isStorage
-                        ? $"{texture}.read(uint2({x}, {y}))"
-                        : $"{texture}.read(uint2({x}, {y}), {mip}u)");
-            }
-            else if (instruction.Opcode.StartsWith("ImageSample", StringComparison.Ordinal))
-            {
-                if (!TryEmitImageSample(instruction, image, bindingIndex, kind, out sampled, out error))
-                {
-                    return false;
-                }
-            }
-            else if (instruction.Opcode.StartsWith("ImageGather4", StringComparison.Ordinal))
-            {
-                if (!TryEmitImageGather(instruction, image, bindingIndex, kind, out sampled, out error))
-                {
-                    return false;
-                }
-
-                writeAllComponents = true;
-            }
-            else
-            {
-                error = $"unsupported image opcode {instruction.Opcode}";
-                return false;
-            }
-
-            var outputValues = new List<string>(4);
-            for (var component = 0; component < 4; component++)
-            {
-                if (!writeAllComponents && (image.Dmask & (1u << component)) == 0)
-                {
-                    continue;
-                }
-
-                var value = $"{sampled}[{component}]";
-                outputValues.Add(kind == "uint" ? value : AsUInt(value));
-            }
-
-            if (image.D16)
-            {
-                for (var index = 0; index < outputValues.Count; index += 2)
-                {
-                    var low = outputValues[index];
-                    var high = index + 1 < outputValues.Count ? outputValues[index + 1] : "0u";
-                    StoreVector(
-                        image.VectorData + (uint)(index / 2),
-                        PackImageD16(kind, low, high));
-                }
-            }
-            else
-            {
-                for (var index = 0; index < outputValues.Count; index++)
-                {
-                    StoreVector(image.VectorData + (uint)index, outputValues[index]);
-                }
-            }
-
-            return true;
-        }
-
-        private bool TryEmitImageSample(
-            Gen5ShaderInstruction instruction,
-            Gen5ImageControl image,
-            int bindingIndex,
-            string kind,
-            out string sampled,
-            out string error)
-        {
-            sampled = string.Empty;
-            error = string.Empty;
-            var opcode = instruction.Opcode;
-            var texture = $"tex{bindingIndex}";
-            var samplerName = $"sharpemu_samplers.smp{_samplerSlots[bindingIndex]}";
-            var hasOffset = opcode.EndsWith("O", StringComparison.Ordinal);
-            var hasCompare = opcode.Contains("SampleC", StringComparison.Ordinal);
-            var hasGradients = opcode.Contains("SampleD", StringComparison.Ordinal);
-            var hasZeroLod = opcode.Contains("Lz", StringComparison.Ordinal);
-            var hasLod = !hasZeroLod && opcode.Contains("SampleL", StringComparison.Ordinal);
-            var hasBias = opcode.Contains("SampleB", StringComparison.Ordinal);
-
-            // RDNA MIMG address operands are ordered
-            // {offset}{bias}{z-compare}{derivatives}{body}; SAMPLE_L carries LOD
-            // as the final body component instead.
-            var addressCursor = 0;
-            var offsetX = "0";
-            var offsetY = "0";
-            if (hasOffset)
-            {
-                addressCursor = AlignFullImageAddress(image, addressCursor);
-                var packed = Temp(
-                    "int",
-                    $"as_type<int>(v[{image.GetAddressRegister(ImageAddressRegister(image, addressCursor))}])");
-                offsetX = Temp("int", $"extract_bits({packed}, 0u, 6u)");
-                offsetY = Temp("int", $"extract_bits({packed}, 8u, 6u)");
-                addressCursor += ImageFullAddressSlots(image);
-            }
-
-            var bias = hasBias ? Temp("float", ImageFloatAddress(image, addressCursor++)) : "0.0f";
-            var reference = "0.0f";
-            if (hasCompare)
-            {
-                addressCursor = AlignFullImageAddress(image, addressCursor);
-                reference = Temp(
-                    "float",
-                    $"as_type<float>(v[{image.GetAddressRegister(ImageAddressRegister(image, addressCursor))}])");
-                addressCursor += ImageFullAddressSlots(image);
-            }
-
-            var gradientX = "float2(0.0f)";
-            var gradientY = "float2(0.0f)";
-            if (hasGradients)
-            {
-                gradientX = Temp(
-                    "float2",
-                    $"float2({ImageFloatAddress(image, addressCursor)}, {ImageFloatAddress(image, addressCursor + 1)})");
-                gradientY = Temp(
-                    "float2",
-                    $"float2({ImageFloatAddress(image, addressCursor + 2)}, {ImageFloatAddress(image, addressCursor + 3)})");
-                addressCursor += 4;
-            }
-
-            var coordinates = Temp(
-                "float2",
-                $"float2({ImageFloatAddress(image, addressCursor)}, {ImageFloatAddress(image, addressCursor + 1)})");
-            var lod = hasZeroLod
-                ? "0.0f"
-                : hasLod
-                    ? Temp("float", ImageFloatAddress(image, addressCursor + 2))
-                    : bias;
-            if (hasOffset)
-            {
-                // Per-lane texel offsets fold into normalized coordinates using
-                // the selected mip extent, mirroring the SPIR-V translator
-                // (Metal sample offsets must be compile-time constants).
-                var explicitLod = hasGradients || hasZeroLod || hasLod;
-                var offsetLod = explicitLod && !hasGradients ? lod : "0.0f";
-                var mipLevel = Temp("uint", $"(uint)max((int)({offsetLod}), 0)");
-                coordinates = Temp(
-                    "float2",
-                    $"{coordinates} + float2((float){offsetX} / (float){texture}.get_width({mipLevel}), " +
-                    $"(float){offsetY} / (float){texture}.get_height({mipLevel}))");
-            }
-
-            var samplerArguments = hasGradients
-                ? $", gradient2d({gradientX}, {gradientY})"
-                : hasZeroLod || hasLod
-                    ? $", level({lod})"
-                    : hasBias
-                        ? $", bias({bias})"
-                        : string.Empty;
-            sampled = Temp(
-                $"vec<{kind}, 4>",
-                $"{texture}.sample({samplerName}, {coordinates}{samplerArguments})");
-            if (hasCompare)
-            {
-                // Manual PCF: reference passes when <= texel, broadcast (r,r,r,1).
-                var passes = Temp("bool", $"{reference} <= (float){sampled}[0]");
-                var one = kind == "float" ? "1.0f" : "1";
-                var zero = kind == "float" ? "0.0f" : "0";
-                sampled = Temp(
-                    $"vec<{kind}, 4>",
-                    $"{VectorLiteral(kind)}({passes} ? {one} : {zero}, {passes} ? {one} : {zero}, {passes} ? {one} : {zero}, {one})");
-            }
-
-            return true;
-        }
-
-        private bool TryEmitImageGather(
-            Gen5ShaderInstruction instruction,
-            Gen5ImageControl image,
-            int bindingIndex,
-            string kind,
-            out string sampled,
-            out string error)
-        {
-            sampled = string.Empty;
-            error = string.Empty;
-            var opcode = instruction.Opcode;
-            var texture = $"tex{bindingIndex}";
-            var samplerName = $"sharpemu_samplers.smp{_samplerSlots[bindingIndex]}";
-            var hasOffset = opcode.EndsWith("O", StringComparison.Ordinal);
-            var hasCompare = opcode.Contains("Gather4C", StringComparison.Ordinal);
-            var addressCursor = 0;
-            var offset = "int2(0)";
-            if (hasOffset)
-            {
-                var packed = Temp(
-                    "int",
-                    $"as_type<int>(v[{image.GetAddressRegister(ImageAddressRegister(image, addressCursor))}])");
-                offset = Temp(
-                    "int2",
-                    $"int2(extract_bits({packed}, 0u, 6u), extract_bits({packed}, 8u, 6u))");
-                addressCursor += ImageFullAddressSlots(image);
-            }
-
-            var reference = "0.0f";
-            if (hasCompare)
-            {
-                addressCursor = AlignFullImageAddress(image, addressCursor);
-                reference = Temp(
-                    "float",
-                    $"as_type<float>(v[{image.GetAddressRegister(ImageAddressRegister(image, addressCursor))}])");
-                addressCursor += ImageFullAddressSlots(image);
-            }
-
-            var coordinates = Temp(
-                "float2",
-                $"float2({ImageFloatAddress(image, addressCursor)}, {ImageFloatAddress(image, addressCursor + 1)})");
-
-            // The gathered component is selected from the first dmask bit.
-            uint component = 0;
-            while (component < 3 && (image.Dmask & (1u << (int)component)) == 0)
-            {
-                component++;
-            }
-
-            var componentName = hasCompare ? "x" : component switch
-            {
-                0 => "x",
-                1 => "y",
-                2 => "z",
-                _ => "w",
-            };
-            sampled = Temp(
-                $"vec<{kind}, 4>",
-                $"{texture}.gather({samplerName}, {coordinates}, {offset}, component::{componentName})");
-            if (hasCompare)
-            {
-                var one = kind == "float" ? "1.0f" : "1";
-                var zero = kind == "float" ? "0.0f" : "0";
-                var compared = Temp(
-                    $"vec<{kind}, 4>",
-                    $"{VectorLiteral(kind)}(" +
-                    $"{reference} <= (float){sampled}[0] ? {one} : {zero}, " +
-                    $"{reference} <= (float){sampled}[1] ? {one} : {zero}, " +
-                    $"{reference} <= (float){sampled}[2] ? {one} : {zero}, " +
-                    $"{reference} <= (float){sampled}[3] ? {one} : {zero})");
-                sampled = compared;
-            }
-
-            return true;
-        }
-
-        private static string VectorLiteral(string kind) => $"vec<{kind}, 4>";
-
-        private static int ImageAddressRegister(Gen5ImageControl image, int component) =>
-            image.A16 ? component / 2 : component;
-
-        private static int ImageFullAddressSlots(Gen5ImageControl image) =>
-            image.A16 ? 2 : 1;
-
-        private static int AlignFullImageAddress(Gen5ImageControl image, int component) =>
-            image.A16 ? (component + 1) & ~1 : component;
-
-        /// <summary>Float address component, unpacking A16 half pairs.</summary>
-        private string ImageFloatAddress(Gen5ImageControl image, int component)
-        {
-            var register = image.GetAddressRegister(ImageAddressRegister(image, component));
-            return image.A16
-                ? $"(float)as_type<half2>(v[{register}])[{component & 1}]"
-                : $"as_type<float>(v[{register}])";
-        }
-
-        /// <summary>Integer address component, unpacking A16 16-bit pairs.</summary>
-        private string ImageIntegerAddress(Gen5ImageControl image, int component)
-        {
-            var register = image.GetAddressRegister(ImageAddressRegister(image, component));
-            return image.A16
-                ? $"((v[{register}] >> {(component & 1) * 16}) & 0xFFFFu)"
-                : $"v[{register}]";
-        }
-
-        /// <summary>One store-source component, unpacking D16 halves.</summary>
-        private string ImageStoreComponent(Gen5ImageControl image, string kind, uint component)
-        {
-            if (!image.D16)
-            {
-                return $"v[{image.VectorData + component}]";
-            }
-
-            var packed = $"v[{image.VectorData + (component / 2)}]";
-            if (kind == "float")
-            {
-                return AsUInt($"(float)as_type<half2>({packed})[{component & 1}]");
-            }
-
-            var low = $"(({packed} >> {(component & 1) * 16}) & 0xFFFFu)";
-            return kind == "int"
-                ? $"(uint)extract_bits(as_type<int>({low}), 0u, 16u)"
-                : low;
-        }
-
-        private static string ImageTexelComponent(string kind, string raw) => kind switch
-        {
-            "int" => $"as_type<int>({raw})",
-            "uint" => raw,
-            _ => $"as_type<float>({raw})",
-        };
-
-        private string PackImageD16(string kind, string low, string high)
-        {
-            if (kind == "float")
-            {
-                return $"(((uint)as_type<ushort>(half(as_type<float>({low})))) | (((uint)as_type<ushort>(half(as_type<float>({high})))) << 16))";
-            }
-
-            return $"((({low}) & 0xFFFFu) | ((({high}) & 0xFFFFu) << 16))";
-        }
-
-        // ---- exports ----
-
-        private bool TryEmitExport(
-            Gen5ShaderInstruction instruction,
-            Gen5ExportControl export,
-            out string error)
-        {
-            error = string.Empty;
-            if (instruction.Sources.Count < 4)
-            {
-                error = "missing export sources";
-                return false;
-            }
-
-            if (_stage == Gen5MslStage.Vertex)
-            {
-                return TryEmitVertexExport(instruction, export);
-            }
-
-            if (_stage != Gen5MslStage.Pixel)
-            {
-                // Compute programs have no export interface.
-                return true;
-            }
-
-            Gen5PixelOutputBinding? binding = null;
-            foreach (var candidate in _pixelOutputBindings)
-            {
-                if (candidate.GuestSlot == export.Target)
-                {
-                    binding = candidate;
-                    break;
-                }
-            }
-
-            if (binding is null)
-            {
-                return true;
-            }
-
-            var field = $"sharpemu_out.mrt{binding.Value.GuestSlot}";
-            var componentType = binding.Value.Kind switch
-            {
-                Gen5PixelOutputKind.Uint => "uint",
-                Gen5PixelOutputKind.Sint => "int",
-                _ => "float",
-            };
-            var values = new string[4];
-            for (var component = 0; component < 4; component++)
-            {
-                if ((export.EnableMask & (1u << component)) == 0)
-                {
-                    values[component] = $"{field}[{component}]";
-                    continue;
-                }
-
-                if (export.Compressed)
-                {
-                    var packed = $"v[{instruction.Sources[component >> 1].Value}]";
-                    var half = $"(float)as_type<half2>({packed})[{component & 1}]";
-                    values[component] = binding.Value.Kind switch
-                    {
-                        Gen5PixelOutputKind.Uint => $"(uint)({half})",
-                        Gen5PixelOutputKind.Sint => $"(int)({half})",
-                        _ => half,
-                    };
-                    continue;
-                }
-
-                var raw = $"v[{instruction.Sources[component].Value}]";
-                values[component] = binding.Value.Kind switch
-                {
-                    Gen5PixelOutputKind.Uint => raw,
-                    Gen5PixelOutputKind.Sint => $"as_type<int>({raw})",
-                    _ => $"as_type<float>({raw})",
-                };
-            }
-
-            // A lane removed from EXEC keeps the previous output value; killed
-            // fragments are discarded in the epilogue.
-            Line($"{field} = exec ? vec<{componentType}, 4>({values[0]}, {values[1]}, {values[2]}, {values[3]}) : {field};");
-            return true;
-        }
-
-        private bool TryEmitVertexExport(
-            Gen5ShaderInstruction instruction,
-            Gen5ExportControl export)
-        {
-            // Target 12 is POS0; 32..63 are the param outputs. Everything else
-            // (other position slots, MRTZ) is ignored like the SPIR-V side.
-            string field;
-            if (export.Target == 12)
-            {
-                field = "sharpemu_out.sharpemu_position";
-            }
-            else if (export.Target is >= 32 and < 64 &&
-                     _vertexOutputs.Contains(export.Target - 32))
-            {
-                field = $"sharpemu_out.param{export.Target - 32}";
-            }
-            else
-            {
-                return true;
-            }
-
-            var values = new string[4];
-            for (var component = 0; component < 4; component++)
-            {
-                if ((export.EnableMask & (1u << component)) == 0)
-                {
-                    values[component] = component == 3 ? "1.0f" : "0.0f";
-                    continue;
-                }
-
-                if (export.Compressed)
-                {
-                    var packed = $"v[{instruction.Sources[component >> 1].Value}]";
-                    values[component] = $"(float)as_type<half2>({packed})[{component & 1}]";
-                    continue;
-                }
-
-                values[component] = $"as_type<float>(v[{instruction.Sources[component].Value}])";
-            }
-
-            Line($"{field} = exec ? float4({values[0]}, {values[1]}, {values[2]}, {values[3]}) : {field};");
-            return true;
-        }
-
-        /// <summary>
-        /// Vertex attribute fetch: the evaluator captured this buffer load as a
-        /// fixed-function vertex input, so read the stage_in field instead of
-        /// guest memory (bound via MTLVertexDescriptor by the backend).
-        /// </summary>
-        private bool TryEmitVertexInputFetch(
-            Gen5BufferMemoryControl control,
-            Gen5VertexInputBinding input,
-            out string error)
-        {
-            error = string.Empty;
-            if (control.DwordCount == 0 || control.DwordCount > input.ComponentCount)
-            {
-                error =
-                    $"invalid vertex input fetch components={control.DwordCount} " +
-                    $"input={input.ComponentCount}";
-                return false;
-            }
-
-            for (uint component = 0; component < control.DwordCount; component++)
-            {
-                var value = input.ComponentCount == 1
-                    ? $"sharpemu_vin.in{input.Location}"
-                    : $"sharpemu_vin.in{input.Location}[{component}]";
-                StoreVector(control.VectorData + component, AsUInt(value));
-            }
-
-            return true;
-        }
-
-        // ---- interpolation / pixel inputs ----
-
-        private bool TryEmitInterpolation(
-            Gen5ShaderInstruction instruction,
-            Gen5InterpolationControl interpolation,
-            out string error)
-        {
-            error = string.Empty;
-            if (_stage != Gen5MslStage.Pixel ||
-                !_pixelAttributes.Contains(interpolation.Attribute) ||
-                instruction.Destinations.Count == 0 ||
-                instruction.Destinations[0].Kind != Gen5OperandKind.VectorRegister)
-            {
-                error = "invalid interpolated attribute";
-                return false;
-            }
-
-            StoreVector(
-                instruction.Destinations[0].Value,
-                AsUInt($"sharpemu_in.attr{interpolation.Attribute}[{interpolation.Channel}]"));
-            return true;
-        }
-
-        /// <summary>
-        /// Seeds pixel input VGPRs in SPI_PS_INPUT_ADDR compact order: the
-        /// interpolation slots reserve registers even though V_INTERP reads MSL
-        /// varyings directly, and the position inputs land in the
-        /// hardware-selected VGPRs from the fragment coordinate.
-        /// </summary>
-        private void EmitPixelInputState(StringBuilder source)
-        {
-            uint vgpr = 0;
-
-            void Advance(int bit, uint dwordCount)
-            {
-                if ((_pixelInputAddress & (1u << bit)) != 0)
-                {
-                    vgpr += dwordCount;
-                }
-            }
-
-            void Position(int bit, string component)
-            {
-                var mask = 1u << bit;
-                if ((_pixelInputAddress & mask) == 0)
-                {
-                    return;
-                }
-
-                if ((_pixelInputEnable & mask) != 0)
-                {
-                    source.AppendLine(
-                        $"    v[{vgpr}] = as_type<uint>(sharpemu_in.sharpemu_frag_coord.{component});");
-                }
-
-                vgpr++;
-            }
-
-            Advance(0, 2);  // PERSP_SAMPLE
-            Advance(1, 2);  // PERSP_CENTER
-            Advance(2, 2);  // PERSP_CENTROID
-            Advance(3, 3);  // PERSP_PULL_MODEL
-            Advance(4, 2);  // LINEAR_SAMPLE
-            Advance(5, 2);  // LINEAR_CENTER
-            Advance(6, 2);  // LINEAR_CENTROID
-            Advance(7, 1);  // LINE_STIPPLE
-            Position(8, "x");
-            Position(9, "y");
-            Position(10, "z");
-            Position(11, "w");
-        }
-    }
-}

src/SharpEmu.ShaderCompiler.Metal/MslFixedShaders.cs

@@ -1,81 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Globalization;
-using System.Text;
-
-namespace SharpEmu.ShaderCompiler.Metal;
-
-/// <summary>
-/// The fixed presenter shaders, mirroring SpirvFixedShaders semantically. The
-/// MSL lives in Templates/*.msl (authored as real Metal source); this class
-/// only substitutes the per-call parameters. Entry point names are stable
-/// (Metal forbids "main"); textures and samplers bind at index 0; attributes
-/// use the same user(locn) convention as the translated stages.
-/// </summary>
-public static class MslFixedShaders
-{
-    /// <summary>
-    /// Fullscreen triangle from the vertex index; every attribute location in
-    /// 0..attributeCount-1 carries (x, y, 0, 1) so paired fragment stages can
-    /// read a screen-space UV from any location.
-    /// </summary>
-    public static string CreateFullscreenVertex(uint attributeCount)
-    {
-        var fields = new StringBuilder();
-        var stores = new StringBuilder();
-        for (uint index = 0; index < attributeCount; index++)
-        {
-            if (index != 0)
-            {
-                fields.AppendLine();
-                stores.AppendLine();
-            }
-
-            fields.Append($"    float4 attr{index} [[user(locn{index})]];");
-            stores.Append($"    out.attr{index} = float4(x, y, 0.0f, 1.0f);");
-        }
-
-        return MslTemplates.Render(
-            "fullscreen_vertex",
-            ("attribute_fields", fields.ToString()),
-            ("attribute_stores", stores.ToString()));
-    }
-
-    /// <summary>Samples texture 0 at the interpolated location-0 UV.</summary>
-    public static string CreateCopyFragment() => MslTemplates.Render("copy_fragment");
-
-    /// <summary>
-    /// The presenter's blit stage: samples texture 0 with V flipped, because
-    /// pairing the shared fullscreen triangle with Metal's y-up NDC puts UV
-    /// (0,0) at the bottom of the screen while textures keep v=0 at the top.
-    /// </summary>
-    public static string CreatePresentFragment() => MslTemplates.Render("present_fragment");
-
-    public static string CreateSolidFragment(float red, float green, float blue, float alpha) =>
-        MslTemplates.Render(
-            "solid_fragment",
-            ("red", Format(red)),
-            ("green", Format(green)),
-            ("blue", Format(blue)),
-            ("alpha", Format(alpha)));
-
-    /// <summary>
-    /// Diagnostic fragment stage exposing one interpolated vertex output
-    /// directly as color, isolating fragment translation from interface data.
-    /// </summary>
-    public static string CreateAttributeFragment(uint location) =>
-        MslTemplates.Render(
-            "attribute_fragment",
-            ("location", location.ToString(CultureInfo.InvariantCulture)));
-
-    /// <summary>
-    /// Output-free fragment stage for fixed-function depth-only passes: the
-    /// guest has no pixel shader, so no color may be written while depth
-    /// testing still runs for the translated vertex shader.
-    /// </summary>
-    public static string CreateDepthOnlyFragment() => MslTemplates.Render("depth_only_fragment");
-
-    private static string Format(float value) =>
-        value.ToString("0.0######", CultureInfo.InvariantCulture) + "f";
-}

src/SharpEmu.ShaderCompiler.Metal/MslTemplates.cs

@@ -1,55 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Collections.Concurrent;
-using System.Text;
-
-namespace SharpEmu.ShaderCompiler.Metal;
-
-/// <summary>
-/// Loads the static MSL blocks from embedded Templates/*.msl resources and
-/// substitutes {{placeholder}} tokens. The static prelude and fixed shaders
-/// are authored as real Metal source files; only the per-instruction body
-/// emission stays programmatic in the translator.
-/// </summary>
-internal static class MslTemplates
-{
-    private static readonly ConcurrentDictionary<string, string> _cache = new(StringComparer.Ordinal);
-
-    public static string Render(string name, params (string Key, string Value)[] substitutions)
-    {
-        var template = _cache.GetOrAdd(name, Load);
-        if (substitutions.Length == 0)
-        {
-            return template;
-        }
-
-        var builder = new StringBuilder(template);
-        foreach (var (key, value) in substitutions)
-        {
-            builder.Replace("{{" + key + "}}", value);
-        }
-
-        var rendered = builder.ToString();
-        var marker = rendered.IndexOf("{{", StringComparison.Ordinal);
-        if (marker >= 0)
-        {
-            var end = rendered.IndexOf("}}", marker, StringComparison.Ordinal);
-            var token = end > marker ? rendered[marker..(end + 2)] : "{{...";
-            throw new InvalidOperationException(
-                $"template '{name}' has an unsubstituted placeholder {token}");
-        }
-
-        return rendered;
-    }
-
-    private static string Load(string name)
-    {
-        var assembly = typeof(MslTemplates).Assembly;
-        var resourceName = $"SharpEmu.ShaderCompiler.Metal.Templates.{name}.msl";
-        using var stream = assembly.GetManifestResourceStream(resourceName)
-            ?? throw new InvalidOperationException($"missing embedded MSL template {resourceName}");
-        using var reader = new StreamReader(stream, Encoding.UTF8);
-        return reader.ReadToEnd();
-    }
-}

src/SharpEmu.ShaderCompiler.Metal/SharpEmu.ShaderCompiler.Metal.csproj

@@ -1,26 +0,0 @@
-<!--
-Copyright (C) 2026 SharpEmu Emulator Project
-SPDX-License-Identifier: GPL-2.0-or-later
--->
-
-<Project Sdk="Microsoft.NET.Sdk">
-
-  <!-- The Metal codegen backend: consumes the backend-neutral shader IR from
-       SharpEmu.ShaderCompiler and emits Metal Shading Language source text.
-       Deliberately has no dependency on Metal bindings — emitters produce text;
-       renderers own APIs (the Metal backend compiles the source via MTLLibrary). -->
-  <PropertyGroup>
-    <GenerateDocumentationFile>false</GenerateDocumentationFile>
-  </PropertyGroup>
-
-  <ItemGroup>
-    <ProjectReference Include="..\SharpEmu.ShaderCompiler\SharpEmu.ShaderCompiler.csproj" />
-  </ItemGroup>
-
-  <ItemGroup>
-    <!-- Static MSL blocks (prelude helpers, fixed shaders) authored as real
-         Metal source; the emitter renders them with placeholder substitution. -->
-    <EmbeddedResource Include="Templates\**\*.msl" />
-  </ItemGroup>
-
-</Project>

src/SharpEmu.ShaderCompiler.Metal/Templates/attribute_fragment.msl

@@ -1,13 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-struct AttributeIn
-{
-    float4 attr{{location}} [[user(locn{{location}})]];
-};
-
-fragment float4 attribute_fs(AttributeIn in [[stage_in]])
-{
-    return in.attr{{location}};
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/copy_fragment.msl

@@ -1,16 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-struct CopyIn
-{
-    float4 attr0 [[user(locn0)]];
-};
-
-fragment float4 copy_fs(
-    CopyIn in [[stage_in]],
-    texture2d<float> tex0 [[texture(0)]],
-    sampler smp0 [[sampler(0)]])
-{
-    return tex0.sample(smp0, in.attr0.xy);
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/depth_only_fragment.msl

@@ -1,7 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-fragment void depth_only_fs()
-{
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/format_prelude.msl

@@ -1,68 +0,0 @@
-static constant uint sharpemu_gfx10_formats[128] = {
-{{format_table}}
-};
-
-static inline void sharpemu_format_layout(uint dfmt, uint component, thread uint& byteOff, thread uint& bitOff, thread uint& bits)
-{
-    byteOff = 0u; bitOff = 0u; bits = 0u;
-    switch (component * 16u + dfmt)
-    {
-{{layout_cases}}
-    default: break;
-    }
-}
-
-static inline uint sharpemu_minifloat(uint raw, uint bits)
-{
-    uint mantissaBits = bits - 5u;
-    uint mantissa = raw & ((1u << mantissaBits) - 1u);
-    uint exponent = (raw >> mantissaBits) & 0x1Fu;
-    uint shift = 23u - mantissaBits;
-    if (exponent == 31u)
-    {
-        return 0x7F800000u | (mantissa << shift);
-    }
-    if (exponent == 0u)
-    {
-        float scale = mantissaBits == 6u ? (1.0f / 1048576.0f) : (1.0f / 524288.0f);
-        return as_type<uint>((float)mantissa * scale);
-    }
-    return ((exponent + 112u) << 23) | (mantissa << shift);
-}
-
-static inline uint sharpemu_format_one(uint nfmt)
-{
-    return (nfmt == 4u || nfmt == 5u) ? 1u : 0x3F800000u;
-}
-
-static inline uint sharpemu_format_convert(uint raw, uint bits, uint nfmt, uint dfmt)
-{
-    uint lowMask = bits >= 32u ? 0xFFFFFFFFu : ((1u << bits) - 1u);
-    int signedRaw = extract_bits(as_type<int>(raw), 0u, bits);
-    switch (nfmt)
-    {
-    case 0u: return as_type<uint>((float)raw / (float)lowMask);
-    case 1u:
-    {
-        float snorm = (float)signedRaw / (float)(lowMask >> 1);
-        return as_type<uint>(fmax(snorm, -1.0f));
-    }
-    case 2u: return as_type<uint>((float)raw);
-    case 3u: return as_type<uint>((float)signedRaw);
-    case 5u: return (uint)signedRaw;
-    case 7u:
-    {
-        // 10_11_11/11_11_10 packed floats are unsigned mini-floats.
-        if (dfmt == 6u || dfmt == 7u)
-        {
-            return sharpemu_minifloat(raw, bits);
-        }
-        if (bits == 16u)
-        {
-            return as_type<uint>((float)as_type<half>((ushort)(raw & 0xFFFFu)));
-        }
-        return raw;
-    }
-    default: return raw;
-    }
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/fullscreen_vertex.msl

@@ -1,19 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-struct FullscreenOut
-{
-    float4 position [[position]];
-{{attribute_fields}}
-};
-
-vertex FullscreenOut fullscreen_vs(uint vertex_id [[vertex_id]])
-{
-    float x = (float)((vertex_id << 1) & 2u);
-    float y = (float)(vertex_id & 2u);
-    FullscreenOut out = {};
-    out.position = float4(x * 2.0f - 1.0f, y * 2.0f - 1.0f, 0.0f, 1.0f);
-{{attribute_stores}}
-    return out;
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/prelude.msl

@@ -1,59 +0,0 @@
-static inline uint sharpemu_load_word(device uint* b, uint bytes, uint addr)
-{
-    if ((addr & 3u) == 0u)
-    {
-        return addr + 4u <= bytes ? b[addr >> 2] : 0u;
-    }
-    uint value = 0u;
-    device const uchar* p = (device const uchar*)b;
-    for (uint i = 0u; i < 4u; i++)
-    {
-        if (addr + i < bytes)
-        {
-            value |= (uint)p[addr + i] << (i * 8u);
-        }
-    }
-    return value;
-}
-
-static inline uint sharpemu_load_bytes(device uint* b, uint bytes, uint addr, uint count, bool signExtend)
-{
-    uint value = 0u;
-    device const uchar* p = (device const uchar*)b;
-    for (uint i = 0u; i < count; i++)
-    {
-        if (addr + i < bytes)
-        {
-            value |= (uint)p[addr + i] << (i * 8u);
-        }
-    }
-    if (signExtend && count < 4u)
-    {
-        uint shift = 32u - (count * 8u);
-        value = (uint)(((int)(value << shift)) >> shift);
-    }
-    return value;
-}
-
-static inline void sharpemu_store_bytes(device uint* b, uint bytes, uint addr, uint value, uint count)
-{
-    device uchar* p = (device uchar*)b;
-    for (uint i = 0u; i < count; i++)
-    {
-        if (addr + i < bytes)
-        {
-            p[addr + i] = (uchar)((value >> (i * 8u)) & 0xFFu);
-        }
-    }
-}
-
-static inline uint sharpemu_ballot(bool value)
-{
-    return {{ballot_return}};
-}
-
-static constant float sharpemu_off_i4_table[16] =
-{
-    0.0f, 0.0625f, 0.1250f, 0.1875f, 0.2500f, 0.3125f, 0.3750f, 0.4375f,
-    -0.5000f, -0.4375f, -0.3750f, -0.3125f, -0.2500f, -0.1875f, -0.1250f, -0.0625f,
-};

src/SharpEmu.ShaderCompiler.Metal/Templates/present_fragment.msl

@@ -1,16 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-struct PresentIn
-{
-    float4 attr0 [[user(locn0)]];
-};
-
-fragment float4 present_fs(
-    PresentIn in [[stage_in]],
-    texture2d<float> tex0 [[texture(0)]],
-    sampler smp0 [[sampler(0)]])
-{
-    return tex0.sample(smp0, float2(in.attr0.x, 1.0f - in.attr0.y));
-}

src/SharpEmu.ShaderCompiler.Metal/Templates/solid_fragment.msl

@@ -1,8 +0,0 @@
-#include <metal_stdlib>
-
-using namespace metal;
-
-fragment float4 solid_fs()
-{
-    return float4({{red}}, {{green}}, {{blue}}, {{alpha}});
-}

src/SharpEmu.ShaderCompiler.Vulkan/Gen5SpirvTranslator.Alu.cs

@@ -953,13 +953,22 @@ public static partial class Gen5SpirvTranslator
                 case "VPkMulF16":
                 case "VPkMinF16":
                 case "VPkMaxF16":
-                case "VPkFmaF16":
                     if (!TryEmitPackedF16(instruction, out result, out error))
                     {
                         return false;
                     }
 
                     break;
+                case "VPkFmaF16":
+                    // Deliberately loud: a fused f16 FMA rounds the product+add once,
+                    // whereas doing the multiply-add in f32 and rounding to f16 at the
+                    // end double-rounds. Concrete miss: fma(0x4100, 0x7522, 0x04EA) is
+                    // 0x7A6B fused but 0x7A6A via f32. Exact emulation (round-to-odd
+                    // f32 product then RNE pack) is a planned follow-up slice.
+                    error =
+                        $"unsupported vop3p opcode {instruction.Opcode} " +
+                        "(fused f16 FMA requires single-rounding; deferred to a later slice)";
+                    return false;
                 default:
                     error = $"unsupported vector opcode {instruction.Opcode}";
                     return false;
@@ -999,9 +1008,8 @@ public static partial class Gen5SpirvTranslator
         // even. For add and mul this is bit-exact to a true f16 op (the f32 result
         // rounds losslessly to f16 by the double-rounding theorem; a f16 product even
         // fits in f32 exactly). min/max carry no rounding, so they are exact once the
-        // conversions are. v_pk_fma_f16 cannot be reproduced by a plain f32
-        // multiply-add plus a pack (that double-rounds), so it goes through the
-        // round-to-odd sequence in EmitPackedF16FusedMultiplyAdd instead.
+        // conversions are. v_pk_fma_f16 is intentionally not routed here because a
+        // fused f16 FMA cannot be reproduced by an f32 multiply-add plus a pack.
         private bool TryEmitPackedF16(
             Gen5ShaderInstruction instruction,
             out uint result,
@@ -1021,8 +1029,7 @@ public static partial class Gen5SpirvTranslator
                 return false;
             }
 
-            var sourceCount = instruction.Opcode == "VPkFmaF16" ? 3 : 2;
-            for (var index = 0; index < sourceCount; index++)
+            for (var index = 0; index < 2; index++)
             {
                 var source = instruction.Sources[index];
                 if (source.Kind is not (Gen5OperandKind.VectorRegister or Gen5OperandKind.ScalarRegister))
@@ -1047,12 +1054,6 @@ public static partial class Gen5SpirvTranslator
         {
             var left = EmitPackedF16Operand(instruction, control, 0, highLane);
             var right = EmitPackedF16Operand(instruction, control, 1, highLane);
-            if (instruction.Opcode == "VPkFmaF16")
-            {
-                var addend = EmitPackedF16Operand(instruction, control, 2, highLane);
-                return EmitFloatToHalf(EmitPackedF16FusedMultiplyAdd(left, right, addend));
-            }
-
             var value = instruction.Opcode switch
             {
                 "VPkAddF16" => _module.AddInstruction(SpirvOp.FAdd, _floatType, left, right),
@@ -1064,75 +1065,6 @@ public static partial class Gen5SpirvTranslator
             return EmitFloatToHalf(Bitcast(_uintType, value));
         }
 
-        // Fused f16 multiply-add with a single rounding, emulated in f32 without the
-        // Float16 capability. The f32 product of two widened f16 values is exact
-        // (11-bit significands, and the exponent stays inside the f32 normal range:
-        // any non-zero product magnitude is in [2^-48, 2^33]), so only the addition
-        // rounds. An f32 add then an f16 pack would round twice; instead the add is
-        // corrected to round-to-odd, which a following round-to-nearest-even pack
-        // turns into the exactly-once-rounded fused result (innocuous double rounding
-        // holds because f32 carries 24 significand bits >= 11 + 2).
-        //
-        // sum = RN(product + addend); Knuth's 2Sum recovers the exact residual
-        // (product + addend) - sum from four more RN ops. 2Sum is exact for any two
-        // finite f32 inputs; no intermediate here can overflow (|product| < 2^33,
-        // |addend| < 2^16) and none can enter the f32 subnormal range (every finite
-        // value in play is a multiple of 2^-48 by construction), so implementation
-        // f32 denorm-flush modes never see a denormal. If the residual says the sum
-        // was inexact and the sum's significand is even, step one ulp towards the
-        // true value: consecutive floats have consecutive sign-magnitude encodings,
-        // so that neighbour is the enclosing float with the odd significand.
-        //
-        // Inf/NaN inputs make the residual NaN (e.g. sum - addend = Inf - Inf); the
-        // ordered compare below is then false and the IEEE sum passes through
-        // unchanged. A residual of zero also covers the exact-sum case, where the
-        // parity fix must not fire. Returns the round-to-odd f32 bit pattern.
-        private uint EmitPackedF16FusedMultiplyAdd(uint left, uint right, uint addend)
-        {
-            var product = EmitPreciseFloat(SpirvOp.FMul, left, right);
-            var sum = EmitPreciseFloat(SpirvOp.FAdd, product, addend);
-
-            var productPart = EmitPreciseFloat(SpirvOp.FSub, sum, addend);
-            var addendPart = EmitPreciseFloat(SpirvOp.FSub, sum, productPart);
-            var productError = EmitPreciseFloat(SpirvOp.FSub, product, productPart);
-            var addendError = EmitPreciseFloat(SpirvOp.FSub, addend, addendPart);
-            var residual = EmitPreciseFloat(SpirvOp.FAdd, productError, addendError);
-
-            var sumBits = Bitcast(_uintType, sum);
-            var residualBits = Bitcast(_uintType, residual);
-            var inexact = _module.AddInstruction(
-                SpirvOp.FOrdNotEqual, _boolType, residual, Float(0));
-            var evenSignificand = Equal(BitwiseAnd(sumBits, UInt(1)), 0);
-            var adjust = _module.AddInstruction(
-                SpirvOp.LogicalAnd, _boolType, inexact, evenSignificand);
-
-            // Residual sign relative to the sum picks the step direction: same sign
-            // means the true value lies away from zero (encoding + 1), opposite sign
-            // means towards zero (encoding - 1). The sum cannot be zero here (any
-            // inexact sum has magnitude >= 2^-48) and cannot be the largest finite
-            // value (its significand is odd), so the step never crosses zero or Inf.
-            var towardZero = IsNotZero(
-                BitwiseAnd(BitwiseXor(sumBits, residualBits), UInt(0x8000_0000)));
-            var stepped = SelectU(
-                towardZero,
-                ISubU(sumBits, UInt(1)),
-                IAdd(sumBits, UInt(1)));
-            return SelectU(adjust, stepped, sumBits);
-        }
-
-        // A float op the driver must evaluate exactly as written. The 2Sum
-        // residual above is error-free only op by op; without NoContraction
-        // driver compilers fold the sequence (e.g. contract product+sum into an
-        // f32 fma and simplify the rebuilt terms), collapsing the residual to
-        // zero. Observed on AMD RDNA3 Windows: the pinned midpoint case decays
-        // to the double-rounded result unless every op in the chain is marked.
-        private uint EmitPreciseFloat(SpirvOp operation, uint left, uint right)
-        {
-            var value = _module.AddInstruction(operation, _floatType, left, right);
-            _module.AddDecoration(value, SpirvDecoration.NoContraction);
-            return value;
-        }
-
         // Reads source `index`, selects the half feeding this lane (op_sel / op_sel_hi),
         // widens it exactly to f32 and applies the lane's negate modifier (neg_lo / neg_hi).
         private uint EmitPackedF16Operand(

src/SharpEmu.ShaderCompiler.Vulkan/Gen5SpirvTranslator.cs

@@ -1754,10 +1754,6 @@ public static partial class Gen5SpirvTranslator
                 "SWaitcnt" or
                 "SInstPrefetch" or
                 "STtraceData" or
-                // NGG shaders bracket their exports with s_sendmsg
-                // (GS_ALLOC_REQ/DEALLOC) to reserve hardware export space;
-                // exports are translated directly, so the message is moot.
-                "SSendmsg" or
                 "VInterpMovF32")
             {
                 return true;

src/SharpEmu.ShaderCompiler.Vulkan/SpirvModuleBuilder.cs

@@ -238,7 +238,6 @@ public enum SpirvDecoration : uint
     Binding = 33,
     DescriptorSet = 34,
     Offset = 35,
-    NoContraction = 42,
 }
 
 public enum SpirvBuiltIn : uint

src/SharpEmu.ShaderCompiler/Gen5ShaderScalarEvaluator.cs

@@ -2350,8 +2350,7 @@ public static class Gen5ShaderScalarEvaluator
     private static bool TryReadUInt32(CpuContext ctx, ulong address, out uint value)
     {
         Span<byte> bytes = stackalloc byte[sizeof(uint)];
-        if (!ctx.Memory.TryRead(address, bytes) &&
-            FallbackMemoryReader?.Invoke(address, bytes) != true)
+        if (!ctx.Memory.TryRead(address, bytes))
         {
             value = 0;
             return false;

tests/SharpEmu.Libs.Tests/Agc/Gen5ScalarMemoryFallbackTests.cs

@@ -1,99 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Buffers.Binary;
-using SharpEmu.HLE;
-using SharpEmu.ShaderCompiler;
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.Agc;
-
-public sealed class Gen5ScalarMemoryFallbackTests
-{
-    private const ulong ScalarTableAddress = 0x4_4665_4FD0;
-    private static readonly object FallbackReaderGate = new();
-
-    [Fact]
-    public void ScalarLoadReadsTrackedFallbackMemory()
-    {
-        var expected = new uint[]
-        {
-            0x4665_4F70,
-            0x0000_0004,
-            0x4EA7_FCE0,
-            0x0000_0004,
-        };
-        var table = new byte[expected.Length * sizeof(uint)];
-        for (var index = 0; index < expected.Length; index++)
-        {
-            BinaryPrimitives.WriteUInt32LittleEndian(
-                table.AsSpan(index * sizeof(uint), sizeof(uint)),
-                expected[index]);
-        }
-
-        var load = new Gen5ShaderInstruction(
-            0,
-            Gen5ShaderEncoding.Smem,
-            "SLoadDwordx4",
-            [],
-            [Gen5Operand.Scalar(0)],
-            [
-                Gen5Operand.Scalar(16),
-                Gen5Operand.Scalar(17),
-                Gen5Operand.Scalar(18),
-                Gen5Operand.Scalar(19),
-            ],
-            new Gen5ScalarMemoryControl(4, 0, null));
-        var end = new Gen5ShaderInstruction(
-            8,
-            Gen5ShaderEncoding.Sopp,
-            "SEndpgm",
-            [],
-            [],
-            [],
-            null);
-        var state = new Gen5ShaderState(
-            new Gen5ShaderProgram(0, [load, end]),
-            [unchecked((uint)ScalarTableAddress), (uint)(ScalarTableAddress >> 32)],
-            null);
-        var ctx = new CpuContext(new FakeCpuMemory(0x1000, 0x100), Generation.Gen5);
-
-        lock (FallbackReaderGate)
-        {
-            var previousReader = Gen5ShaderScalarEvaluator.FallbackMemoryReader;
-            try
-            {
-                Gen5ShaderScalarEvaluator.FallbackMemoryReader = ReadFallback;
-                Assert.True(
-                    Gen5ShaderScalarEvaluator.TryEvaluate(
-                        ctx,
-                        state,
-                        out var evaluation,
-                        out var error),
-                    error);
-                Assert.Equal(expected, evaluation.ScalarRegisters.Skip(16).Take(4));
-            }
-            finally
-            {
-                Gen5ShaderScalarEvaluator.FallbackMemoryReader = previousReader;
-            }
-        }
-
-        bool ReadFallback(ulong address, Span<byte> destination)
-        {
-            if (address < ScalarTableAddress)
-            {
-                return false;
-            }
-
-            var offset = address - ScalarTableAddress;
-            if (offset + (ulong)destination.Length > (ulong)table.Length)
-            {
-                return false;
-            }
-
-            table.AsSpan((int)offset, destination.Length).CopyTo(destination);
-            return true;
-        }
-    }
-}

tests/SharpEmu.Libs.Tests/Cpu/GuestThreadBlockWaiterRepresentationTests.cs

@@ -0,0 +1,112 @@
+// Copyright (C) 2026 SharpEmu Emulator Project
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+using System.Reflection;
+using SharpEmu.Core.Cpu.Native;
+using SharpEmu.HLE;
+using Xunit;
+
+namespace SharpEmu.Libs.Tests.Cpu;
+
+public sealed class GuestThreadBlockWaiterRepresentationTests
+{
+    [Fact]
+    public void SchedulerStoresOnlyTheWaiterObjectRepresentation()
+    {
+        var stateType = typeof(DirectExecutionBackend).GetNestedType(
+            "GuestThreadState",
+            BindingFlags.NonPublic);
+        Assert.NotNull(stateType);
+
+        var waiterProperty = stateType.GetProperty(
+            "BlockWaiter",
+            BindingFlags.Instance | BindingFlags.Public | BindingFlags.NonPublic);
+        Assert.NotNull(waiterProperty);
+        Assert.Equal(typeof(IGuestThreadBlockWaiter), waiterProperty.PropertyType);
+        Assert.Null(stateType.GetProperty(
+            "BlockResumeHandler",
+            BindingFlags.Instance | BindingFlags.Public | BindingFlags.NonPublic));
+        Assert.Null(stateType.GetProperty(
+            "BlockWakeHandler",
+            BindingFlags.Instance | BindingFlags.Public | BindingFlags.NonPublic));
+
+        var registerMethods = typeof(DirectExecutionBackend)
+            .GetMethods(BindingFlags.Instance | BindingFlags.NonPublic)
+            .Where(method => method.Name == "RegisterBlockedGuestThreadContinuation")
+            .ToArray();
+        var registerMethod = Assert.Single(registerMethods);
+        Assert.Contains(
+            registerMethod.GetParameters(),
+            parameter => parameter.ParameterType == typeof(IGuestThreadBlockWaiter));
+        Assert.DoesNotContain(
+            registerMethod.GetParameters(),
+            parameter => IsFuncParameter(parameter.ParameterType));
+
+        var consumeMethods = typeof(GuestThreadExecution)
+            .GetMethods(BindingFlags.Static | BindingFlags.Public)
+            .Where(method => method.Name == nameof(GuestThreadExecution.TryConsumeCurrentThreadBlock));
+        Assert.DoesNotContain(
+            consumeMethods.SelectMany(method => method.GetParameters()),
+            parameter => IsFuncParameter(parameter.ParameterType));
+    }
+
+    [Fact]
+    public void DelegateCompatibilityBridgeIsConsumedAsOneWaiterObject()
+    {
+        var previousThread = GuestThreadExecution.EnterGuestThread(0x1234);
+        try
+        {
+            var canWake = false;
+            var wakeCalls = 0;
+            var resumeCalls = 0;
+            Assert.True(GuestThreadExecution.RequestCurrentThreadBlock(
+                context: null,
+                reason: "test_wait",
+                wakeKey: "test_waiter:1",
+                resumeHandler: () =>
+                {
+                    resumeCalls++;
+                    return 42;
+                },
+                wakeHandler: () =>
+                {
+                    wakeCalls++;
+                    return canWake;
+                }));
+
+            Assert.True(GuestThreadExecution.TryConsumeCurrentThreadBlock(
+                out var reason,
+                out _,
+                out var hasContinuation,
+                out var wakeKey,
+                out IGuestThreadBlockWaiter? waiter,
+                out var deadline));
+            Assert.Equal("test_wait", reason);
+            Assert.Equal("test_waiter:1", wakeKey);
+            Assert.False(hasContinuation);
+            Assert.Equal(0, deadline);
+            Assert.NotNull(waiter);
+
+            Assert.False(waiter.TryWake());
+            canWake = true;
+            Assert.True(waiter.TryWake());
+            Assert.Equal(42, waiter.Resume());
+            Assert.Equal(2, wakeCalls);
+            Assert.Equal(1, resumeCalls);
+        }
+        finally
+        {
+            GuestThreadExecution.RestoreGuestThread(previousThread);
+        }
+    }
+
+    private static bool IsFuncParameter(Type parameterType)
+    {
+        var type = parameterType.IsByRef
+            ? parameterType.GetElementType()
+            : parameterType;
+        return type is not null &&
+            type.IsGenericType &&
+            type.GetGenericTypeDefinition() == typeof(Func<>);
+    }
+}

tests/SharpEmu.Libs.Tests/Cpu/JitStubsTests.cs

@@ -1,26 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.Core.Cpu.Native;
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.Cpu;
-
-public sealed unsafe class JitStubsTests
-{
-    [Fact]
-    public void FindTlsAccessPatterns_IncludesLastValidOffset()
-    {
-        var pattern = JitStubs.TlsAccessPattern;
-        var code = new byte[pattern.Length + 3];
-        pattern.CopyTo(code.AsSpan(3));
-
-        fixed (byte* codePointer = code)
-        {
-            var matches = JitStubs.FindTlsAccessPatterns(codePointer, code.Length);
-
-            var match = Assert.Single(matches);
-            Assert.Equal((nint)(codePointer + 3), match);
-        }
-    }
-}

tests/SharpEmu.Libs.Tests/Cpu/MemcpyHleRoutingTests.cs

@@ -1,153 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.Core.Cpu.Native;
-using SharpEmu.HLE;
-using System.Reflection;
-using System.Runtime.CompilerServices;
-using System.Runtime.InteropServices;
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.Cpu;
-
-public sealed class MemcpyHleRoutingTests
-{
-    private const string MemcpyNid = "Q3VBxCXhUHs";
-    private const string MemsetNid = "QrZZdJ8XsX0";
-    private const string RdtscNid = "-2IRUCO--PM";
-
-    [Fact]
-    public void IsHlePreferredNid_PrefersHleForMemcpy_OnEveryPlatform()
-    {
-        Assert.True(
-            InvokeIsHlePreferredNid(MemcpyNid),
-            $"memcpy ({MemcpyNid}) must route through HLE on every platform. It was previously " +
-            "gated behind OperatingSystem.IsWindows(), which left Linux and macOS on the LLE " +
-            "intrinsic stub and faulted in guest code. Do not reintroduce an OS condition here.");
-    }
-
-    [Fact]
-    public void IsHlePreferredNid_PrefersHleForMemset()
-    {
-        Assert.True(
-            InvokeIsHlePreferredNid(MemsetNid),
-            $"memset ({MemsetNid}) must route through HLE on every platform.");
-    }
-
-    [Fact]
-    public void TryCreateNativeImportIntrinsic_DoesNotClaimMemcpy()
-    {
-        if (RuntimeInformation.ProcessArchitecture != Architecture.X64)
-        {
-            return;
-        }
-
-        var claimed = InvokeTryCreateNativeImportIntrinsic(MemcpyNid, out var address);
-
-        Assert.False(
-            claimed,
-            $"memcpy ({MemcpyNid}) must fall through to the HLE trampoline. SetupImportStubs tries " +
-            "the intrinsic stub before the trampoline, so without an IsHlePreferredNid guard here " +
-            "the intrinsic claims memcpy and the HLE routing never takes effect.");
-        Assert.Equal(0, address);
-    }
-
-    [Fact]
-    public void TryCreateNativeImportIntrinsic_StillClaimsNonHleNids()
-    {
-        if (RuntimeInformation.ProcessArchitecture != Architecture.X64)
-        {
-            return;
-        }
-
-        var claimed = InvokeTryCreateNativeImportIntrinsic(RdtscNid, out var address);
-
-        Assert.True(
-            claimed,
-            $"rdtsc ({RdtscNid}) has no HLE handler and must still receive an intrinsic stub. If " +
-            "this fails the memcpy assertions above may be passing vacuously.");
-        Assert.NotEqual(0, address);
-
-        unsafe
-        {
-            Assert.True(HostMemory.Free((void*)address, 0, HostMemory.MEM_RELEASE));
-        }
-    }
-
-    [Fact]
-    public void IsHlePreferredNid_DoesNotBranchOnHostOperatingSystem()
-    {
-        var method = typeof(DirectExecutionBackend).GetMethod(
-            "IsHlePreferredNid",
-            BindingFlags.Static | BindingFlags.NonPublic);
-        Assert.NotNull(method);
-
-        var callees = ResolveCallees(method);
-
-        Assert.DoesNotContain(callees, static name =>
-            name is "IsWindows" or "IsLinux" or "IsMacOS" or "IsOSPlatform" or "IsFreeBSD");
-    }
-
-    private static HashSet<string> ResolveCallees(MethodBase method)
-    {
-        var il = method.GetMethodBody()?.GetILAsByteArray();
-        Assert.NotNull(il);
-
-        var module = method.Module;
-        var generic = method.DeclaringType?.GetGenericArguments();
-        var callees = new HashSet<string>(StringComparer.Ordinal);
-
-        for (var i = 0; i + 4 < il.Length; i++)
-        {
-            if (il[i] is not (0x28 or 0x6F))
-            {
-                continue;
-            }
-
-            var token = BitConverter.ToInt32(il, i + 1);
-            try
-            {
-                var callee = module.ResolveMethod(token, generic, null);
-                if (callee?.Name is { } name)
-                {
-                    callees.Add(name);
-                }
-            }
-            catch (ArgumentException)
-            {
-            }
-        }
-
-        return callees;
-    }
-
-    private static bool InvokeIsHlePreferredNid(string nid)
-    {
-        var method = typeof(DirectExecutionBackend).GetMethod(
-            "IsHlePreferredNid",
-            BindingFlags.Static | BindingFlags.NonPublic);
-        Assert.NotNull(method);
-        return (bool)method.Invoke(null, [nid])!;
-    }
-
-    private static bool InvokeTryCreateNativeImportIntrinsic(string nid, out nint address)
-    {
-        var backend = (DirectExecutionBackend)RuntimeHelpers.GetUninitializedObject(
-            typeof(DirectExecutionBackend));
-        var trampolineList = typeof(DirectExecutionBackend).GetField(
-            "_importHandlerTrampolines",
-            BindingFlags.Instance | BindingFlags.NonPublic);
-        Assert.NotNull(trampolineList);
-        trampolineList.SetValue(backend, new List<nint>());
-
-        var method = typeof(DirectExecutionBackend).GetMethod(
-            "TryCreateNativeImportIntrinsic",
-            BindingFlags.Instance | BindingFlags.NonPublic);
-        Assert.NotNull(method);
-
-        object?[] args = [nid, null];
-        var claimed = (bool)method.Invoke(backend, args)!;
-        address = (nint)args[1]!;
-        return claimed;
-    }
-}

tests/SharpEmu.Libs.Tests/Cpu/Sha1InstructionEmulatorTests.cs

@@ -1,56 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using SharpEmu.Core.Cpu.Emulation;
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.Cpu;
-
-public sealed class Sha1InstructionEmulatorTests
-{
-    private static readonly Sha1Vector Destination = new(
-        0x0123_4567u, 0x89AB_CDEFu, 0x0F1E_2D3Cu, 0x4B5A_6978u);
-    private static readonly Sha1Vector Source = new(
-        0xFEDC_BA98u, 0x7654_3210u, 0xF0E1_D2C3u, 0xB4A5_9687u);
-
-    [Fact]
-    public void MessageSchedule1_MatchesIntelLaneSemantics()
-    {
-        Assert.Equal(
-            new Sha1Vector(0xF1C2_97A4u, 0x3D0E_5B68u, 0x0E3D_685Bu, 0xC2F1_A497u),
-            Sha1InstructionEmulator.MessageSchedule1(Destination, Source));
-    }
-
-    [Fact]
-    public void MessageSchedule2_MatchesIntelLaneSemantics()
-    {
-        Assert.Equal(
-            new Sha1Vector(0xECA8_6420u, 0xEEEE_EEEEu, 0xF294_3E58u, 0x7777_7777u),
-            Sha1InstructionEmulator.MessageSchedule2(Destination, Source));
-    }
-
-    [Fact]
-    public void NextE_MatchesIntelLaneSemantics()
-    {
-        Assert.Equal(
-            new Sha1Vector(0xFEDC_BA98u, 0x7654_3210u, 0xF0E1_D2C3u, 0xC77C_30E5u),
-            Sha1InstructionEmulator.NextE(Destination, Source));
-    }
-
-    [Theory]
-    [InlineData(0, 0x20E8_2326u, 0x911F_2CA8u, 0xECE0_593Fu, 0x0C1C_11FBu)]
-    [InlineData(1, 0x4598_D5B9u, 0x7BA0_0411u, 0x464E_3C51u, 0xF514_1B52u)]
-    [InlineData(2, 0xEE0E_73F6u, 0x2509_A67Bu, 0x26C6_85CCu, 0x0097_5845u)]
-    [InlineData(3, 0x9C7B_0B46u, 0xAEC8_EB49u, 0x8FD5_A2B7u, 0xFD49_9AECu)]
-    public void FourRounds_MatchesAllFourSha1Functions(
-        byte function,
-        uint lane0,
-        uint lane1,
-        uint lane2,
-        uint lane3)
-    {
-        Assert.Equal(
-            new Sha1Vector(lane0, lane1, lane2, lane3),
-            Sha1InstructionEmulator.FourRounds(Destination, Source, function));
-    }
-}

tests/SharpEmu.Libs.Tests/Kernel/KernelEventQueueCompatExportsTests.cs

@@ -1,180 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Buffers.Binary;
-using SharpEmu.HLE;
-using SharpEmu.Libs.Kernel;
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.Kernel;
-
-public sealed class KernelEventQueueCompatExportsTests
-{
-    private const ulong MemoryBase = 0x1_0000_0000;
-    private const int MemorySize = 0x4000;
-
-    [Fact]
-    public void CreateEqueue_WritesNonZeroHandleAndSucceeds()
-    {
-        var (context, outAddress) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = outAddress;
-
-        var result = KernelEventQueueCompatExports.KernelCreateEqueue(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK, result);
-        Assert.True(context.TryReadUInt64(outAddress, out var handle));
-        Assert.NotEqual(0UL, handle);
-        Assert.True(KernelEventQueueCompatExports.IsValidEqueue(handle));
-    }
-
-    [Fact]
-    public void CreateEqueue_NullOutAddressReturnsInvalidArgument()
-    {
-        var (context, _) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = 0;
-
-        var result = KernelEventQueueCompatExports.KernelCreateEqueue(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void DeleteEqueue_RemovesQueueFromRegistry()
-    {
-        var (context, outAddress) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = outAddress;
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK, KernelEventQueueCompatExports.KernelCreateEqueue(context));
-        Assert.True(context.TryReadUInt64(outAddress, out var handle));
-
-        context[CpuRegister.Rdi] = handle;
-        var result = KernelEventQueueCompatExports.KernelDeleteEqueue(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK, result);
-        Assert.False(KernelEventQueueCompatExports.IsValidEqueue(handle));
-    }
-
-    [Fact]
-    public void AddUserEvent_OnUnknownQueueReturnsNotFound()
-    {
-        var (context, _) = NewContextWithOutSlot();
-        const ulong unknownHandle = 0xDEAD_BEEF;
-        context[CpuRegister.Rdi] = unknownHandle;
-        context[CpuRegister.Rsi] = 42;
-
-        var result = KernelEventQueueCompatExports.KernelAddUserEvent(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND, result);
-    }
-
-    [Fact]
-    public void AddUserEvent_OnValidQueueSucceeds()
-    {
-        var handle = CreateEqueue();
-        var (context, _) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = handle;
-        context[CpuRegister.Rsi] = 0x1234;
-
-        var result = KernelEventQueueCompatExports.KernelAddUserEvent(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK, result);
-    }
-
-    [Fact]
-    public void TriggerUserEvent_OnUnknownQueueReturnsNotFound()
-    {
-        var (context, _) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = 0xDEAD_BEEF;
-        context[CpuRegister.Rsi] = 1;
-        context[CpuRegister.Rdx] = 0;
-
-        var result = KernelEventQueueCompatExports.KernelTriggerUserEvent(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND, result);
-    }
-
-    [Fact]
-    public void TriggerUserEvent_OnUnregisteredEventReturnsNotFound()
-    {
-        var handle = CreateEqueue();
-        var (context, _) = NewContextWithOutSlot();
-        context[CpuRegister.Rdi] = handle;
-        context[CpuRegister.Rsi] = 0xABCD; // never registered
-        context[CpuRegister.Rdx] = 0;
-
-        var result = KernelEventQueueCompatExports.KernelTriggerUserEvent(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND, result);
-    }
-
-    // Full lifecycle: create -> register user event -> trigger -> wait delivers
-    // the queued event with the registered ident/filter and the trigger data.
-    // DequeueEvents runs before the blocking path, so a pre-triggered queue
-    // returns immediately without touching the guest thread scheduler.
-    [Fact]
-    public void CreateAddTriggerWait_DeliversTriggeredUserEvent()
-    {
-        const ulong eventIdent = 0x4242;
-        const ulong triggerData = 0x55AA_55AA;
-        var handle = CreateEqueue();
-
-        // Register the user event on the queue.
-        var (addCtx, _) = NewContextWithOutSlot();
-        addCtx[CpuRegister.Rdi] = handle;
-        addCtx[CpuRegister.Rsi] = eventIdent;
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK,
-            KernelEventQueueCompatExports.KernelAddUserEvent(addCtx));
-
-        // Trigger it with a distinct data payload.
-        var (triggerCtx, _) = NewContextWithOutSlot();
-        triggerCtx[CpuRegister.Rdi] = handle;
-        triggerCtx[CpuRegister.Rsi] = eventIdent;
-        triggerCtx[CpuRegister.Rdx] = triggerData;
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK,
-            KernelEventQueueCompatExports.KernelTriggerUserEvent(triggerCtx));
-
-        // Wait should deliver the single pending event without blocking.
-        var memory = new FakeCpuMemory(MemoryBase, MemorySize);
-        var waitContext = new CpuContext(memory, Generation.Gen5);
-        const ulong eventsAddress = MemoryBase + 0x100;
-        const ulong outCountAddress = MemoryBase + 0x300;
-        waitContext[CpuRegister.Rdi] = handle;
-        waitContext[CpuRegister.Rsi] = eventsAddress;
-        waitContext[CpuRegister.Rdx] = 1; // capacity
-        waitContext[CpuRegister.Rcx] = outCountAddress;
-        waitContext[CpuRegister.R8] = 0; // no timeout -> would block, but event is pending
-
-        var result = KernelEventQueueCompatExports.KernelWaitEqueue(waitContext);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK, result);
-        Assert.True(waitContext.TryReadUInt32(outCountAddress, out var delivered));
-        Assert.Equal(1u, delivered);
-
-        // KernelEvent layout (0x20): ident(0x00) filter(0x08) flags(0x0A)
-        // fflags(0x0C) data(0x10) userdata(0x18).
-        Span<byte> evt = stackalloc byte[0x20];
-        Assert.True(memory.TryRead(eventsAddress, evt));
-        Assert.Equal(eventIdent, BinaryPrimitives.ReadUInt64LittleEndian(evt[0x00..]));
-        Assert.Equal(KernelEventQueueCompatExports.KernelEventFilterUser,
-            BinaryPrimitives.ReadInt16LittleEndian(evt[0x08..]));
-        Assert.Equal(triggerData, BinaryPrimitives.ReadUInt64LittleEndian(evt[0x10..]));
-    }
-
-    private static ulong CreateEqueue()
-    {
-        var memory = new FakeCpuMemory(MemoryBase, MemorySize);
-        var context = new CpuContext(memory, Generation.Gen5);
-        const ulong outAddress = MemoryBase + 0x10;
-        context[CpuRegister.Rdi] = outAddress;
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_OK,
-            KernelEventQueueCompatExports.KernelCreateEqueue(context));
-        Assert.True(context.TryReadUInt64(outAddress, out var handle));
-        return handle;
-    }
-
-    private static (CpuContext Context, ulong OutAddress) NewContextWithOutSlot()
-    {
-        var memory = new FakeCpuMemory(MemoryBase, MemorySize);
-        var context = new CpuContext(memory, Generation.Gen5);
-        return (context, MemoryBase + 0x10);
-    }
-}

tests/SharpEmu.Libs.Tests/Kernel/KernelMemoryCompatExportsTests.cs

@@ -164,149 +164,4 @@ public sealed class KernelMemoryCompatExportsTests
 
         Assert.Equal(0, KernelMemoryCompatExports.KernelReleaseDirectMemory(context));
     }
-
-    [Fact]
-    public void MapNamedFlexibleMemory_NullInOutPointerReturnsInvalidArgument()
-    {
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = 0;
-        context[CpuRegister.Rsi] = 0x1000;
-        context[CpuRegister.Rdx] = 0x03; // CPU read|write
-        context[CpuRegister.Rcx] = 0;
-
-        var result = KernelMemoryCompatExports.KernelMapNamedFlexibleMemory(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void MapNamedFlexibleMemory_ZeroLengthReturnsInvalidArgument()
-    {
-        const ulong memoryBase = 0x1_0000_0000;
-        const ulong inOutAddress = memoryBase + 0x100;
-        var memory = new FakeCpuMemory(memoryBase, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        memory.TryWrite(inOutAddress, BitConverter.GetBytes(0UL));
-        context[CpuRegister.Rdi] = inOutAddress;
-        context[CpuRegister.Rsi] = 0;
-        context[CpuRegister.Rdx] = 0x03;
-        context[CpuRegister.Rcx] = 0;
-
-        var result = KernelMemoryCompatExports.KernelMapNamedFlexibleMemory(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void MapNamedFlexibleMemory_UnreadableInOutPointerReturnsMemoryFault()
-    {
-        // The in-out pointer points outside the FakeCpuMemory backing store, so
-        // the first TryReadUInt64 must fail before any reservation is attempted.
-        const ulong memoryBase = 0x1_0000_0000;
-        const ulong unreachableInOut = memoryBase + 0x10_0000;
-        var memory = new FakeCpuMemory(memoryBase, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = unreachableInOut;
-        context[CpuRegister.Rsi] = 0x1000;
-        context[CpuRegister.Rdx] = 0x03;
-        context[CpuRegister.Rcx] = 0;
-
-        var result = KernelMemoryCompatExports.KernelMapNamedFlexibleMemory(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT, result);
-    }
-
-    [Fact]
-    public void Mprotect_ZeroAddressReturnsInvalidArgument()
-    {
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = 0;
-        context[CpuRegister.Rsi] = 0x4000;
-        context[CpuRegister.Rdx] = 0x03;
-
-        var result = KernelMemoryCompatExports.KernelMprotect(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void Mprotect_ZeroLengthReturnsInvalidArgument()
-    {
-        const ulong memoryBase = 0x1_0000_0000;
-        var memory = new FakeCpuMemory(memoryBase, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = memoryBase;
-        context[CpuRegister.Rsi] = 0;
-        context[CpuRegister.Rdx] = 0x03;
-
-        var result = KernelMemoryCompatExports.KernelMprotect(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void Mprotect_UnmappedRangeReturnsNotFound()
-    {
-        // A plausible guest address that FakeCpuMemory does not back and that
-        // has no host reservation. TryProtectHostRange calls VirtualProtect,
-        // which fails on an unmapped range, yielding NOT_FOUND rather than
-        // mutating protection or throwing.
-        const ulong unmappedAddress = 0x2_0000_0000;
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = unmappedAddress;
-        context[CpuRegister.Rsi] = 0x4000;
-        context[CpuRegister.Rdx] = 0x03;
-
-        var result = KernelMemoryCompatExports.KernelMprotect(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND, result);
-    }
-
-    [Fact]
-    public void Munmap_ZeroAddressReturnsInvalidArgument()
-    {
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = 0;
-        context[CpuRegister.Rsi] = 0x4000;
-
-        var result = KernelMemoryCompatExports.KernelMunmap(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void Munmap_OverflowRangeReturnsInvalidArgument()
-    {
-        // address + length would overflow; KernelMunmap guards this explicitly
-        // before touching any region accounting.
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = ulong.MaxValue - 0x10;
-        context[CpuRegister.Rsi] = 0x20;
-
-        var result = KernelMemoryCompatExports.KernelMunmap(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT, result);
-    }
-
-    [Fact]
-    public void Munmap_UnmappedRangeReturnsNotFound()
-    {
-        // No flexible region is registered at this address and FakeCpuMemory
-        // does not back it, so both physicallyBacked and removedRegions are
-        // empty and the export reports NOT_FOUND.
-        const ulong unmappedAddress = 0x2_0000_0000;
-        var memory = new FakeCpuMemory(0x1_0000_0000, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-        context[CpuRegister.Rdi] = unmappedAddress;
-        context[CpuRegister.Rsi] = 0x4000;
-
-        var result = KernelMemoryCompatExports.KernelMunmap(context);
-
-        Assert.Equal((int)OrbisGen2Result.ORBIS_GEN2_ERROR_NOT_FOUND, result);
-    }
 }

tests/SharpEmu.Libs.Tests/LibcInternal/LibcInternalExportsTests.cs

@@ -1,137 +0,0 @@
-// Copyright (C) 2026 SharpEmu Emulator Project
-// SPDX-License-Identifier: GPL-2.0-or-later
-
-using System.Buffers.Binary;
-
-using SharpEmu.HLE;
-using SharpEmu.Libs.LibcInternal;
-
-using Xunit;
-
-namespace SharpEmu.Libs.Tests.LibcInternal;
-
-public sealed class LibcInternalExportsTests
-{
-    private const ulong Base = 0x3_0000_0000;
-    private const ulong InfoAddress = Base + 0x100;
-    private const ulong ExpectedInfoSize = 32;
-
-    [Fact]
-    public void HeapGetTraceInfo_NullPointer_ReturnsInvalidArgument()
-    {
-        var memory = new FakeCpuMemory(Base, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-
-        context[CpuRegister.Rdi] = 0;
-
-        var result = LibcInternalExports.LibcHeapGetTraceInfo(context);
-
-        Assert.Equal(
-            (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT,
-            result);
-        Assert.Equal(0UL, context[CpuRegister.Rax]);
-    }
-
-    [Fact]
-    public void HeapGetTraceInfo_WrongSize_ReturnsInvalidArgument()
-    {
-        var memory = new FakeCpuMemory(Base, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-
-        Span<byte> sizeBytes = stackalloc byte[sizeof(ulong)];
-        BinaryPrimitives.WriteUInt64LittleEndian(
-            sizeBytes,
-            ExpectedInfoSize - 1);
-
-        Assert.True(memory.TryWrite(InfoAddress, sizeBytes));
-
-        context[CpuRegister.Rdi] = InfoAddress;
-
-        var result = LibcInternalExports.LibcHeapGetTraceInfo(context);
-
-        Assert.Equal(
-            (int)OrbisGen2Result.ORBIS_GEN2_ERROR_INVALID_ARGUMENT,
-            result);
-        Assert.Equal(0UL, context[CpuRegister.Rax]);
-    }
-
-    [Fact]
-    public void HeapGetTraceInfo_ValidBuffer_WritesStablePointers()
-    {
-        var memory = new FakeCpuMemory(Base, 0x1000);
-        var context = new CpuContext(memory, Generation.Gen5);
-
-        Span<byte> sizeBytes = stackalloc byte[sizeof(ulong)];
-        BinaryPrimitives.WriteUInt64LittleEndian(
-            sizeBytes,
-            ExpectedInfoSize);
-
-        Assert.True(memory.TryWrite(InfoAddress, sizeBytes));
-
-        context[CpuRegister.Rdi] = InfoAddress;
-
-        var firstResult =
-            LibcInternalExports.LibcHeapGetTraceInfo(context);
-
-        Assert.Equal(
-            (int)OrbisGen2Result.ORBIS_GEN2_OK,
-            firstResult);
-        Assert.Equal(0UL, context[CpuRegister.Rax]);
-
-        Assert.True(
-            context.TryReadUInt64(
-                InfoAddress + 16,
-                out var firstMaskAddress));
-
-        Assert.True(
-            context.TryReadUInt64(
-                InfoAddress + 24,
-                out var firstTableAddress));
-
-        Assert.NotEqual(0UL, firstMaskAddress);
-        Assert.Equal(firstMaskAddress + 8UL, firstTableAddress);
-
-        var secondResult =
-            LibcInternalExports.LibcHeapGetTraceInfo(context);
-
-        Assert.Equal(
-            (int)OrbisGen2Result.ORBIS_GEN2_OK,
-            secondResult);
-
-        Assert.True(
-            context.TryReadUInt64(
-                InfoAddress + 16,
-                out var secondMaskAddress));
-
-        Assert.True(
-            context.TryReadUInt64(
-                InfoAddress + 24,
-                out var secondTableAddress));
-
-        Assert.Equal(firstMaskAddress, secondMaskAddress);
-        Assert.Equal(firstTableAddress, secondTableAddress);
-    }
-
-    [Fact]
-    public void HeapGetTraceInfo_TruncatedOutput_ReturnsMemoryFault()
-    {
-        var memory = new FakeCpuMemory(Base, 31);
-        var context = new CpuContext(memory, Generation.Gen5);
-
-        Span<byte> sizeBytes = stackalloc byte[sizeof(ulong)];
-        BinaryPrimitives.WriteUInt64LittleEndian(
-            sizeBytes,
-            ExpectedInfoSize);
-
-        Assert.True(memory.TryWrite(Base, sizeBytes));
-
-        context[CpuRegister.Rdi] = Base;
-
-        var result = LibcInternalExports.LibcHeapGetTraceInfo(context);
-
-        Assert.Equal(
-            (int)OrbisGen2Result.ORBIS_GEN2_ERROR_MEMORY_FAULT,
-            result);
-        Assert.Equal(0UL, context[CpuRegister.Rax]);
-    }
-}