Jayden/sharpemu
1
0
Fork 0
mirror of https://github.com/par274/sharpemu.git synced 2026-07-31 23:19:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

[AGC/Vulkan] Support multiple render targets (#149)

Browse Source 
* [AGC] Support multiple typed pixel outputs

Emit dense float, uint, and sint fragment outputs for sparse guest MRT slots. Preserve disabled components across partial exports, validate dense host locations, and retain the single-output compiler overload for compatibility.

* [Vulkan] Execute translated draws with multiple color attachments

Carry every active color target and its effective shader/register write mask through one Vulkan draw. Add per-attachment blending, independentBlend negotiation, device/format validation, multi-attachment synchronization, and safe image recreation after in-flight work completes.

* [ShaderDump] Add MRT edge-case coverage

Cover sparse mixed-type outputs, partial exports, merged partial exports, independent blend layouts, eight attachments, and invalid host locations. Run the synthetic shader suite in CI.

---------

Co-authored-by: Dafenx <196083014+Dafenxz0@users.noreply.github.com>
This commit is contained in:
Dafenx
2026-07-15 01:41:39 +02:00
committed by GitHub
parent e604fb606d
commit 081760be3f
6 changed files with 818 additions and 262 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/SharpEmu.Libs/Agc/AgcExports.cs
+79 -39
View File
@@ -157,7 +157,7 @@ public static class AgcExports
private static readonly HashSet<uint> _tracedSubmittedDrawOpcodes = new();
private static readonly Dictionary<(ulong Ps, ulong State, Gen5PixelOutputKind Output), byte[]> _pixelSpirvCache = new();
private static readonly Dictionary<
(ulong Es, ulong EsState, ulong Ps, ulong PsState, Gen5PixelOutputKind Output, uint Attributes),
(ulong Es, ulong EsState, ulong Ps, ulong PsState, string OutputLayout, uint Attributes),
(byte[] Vertex, byte[] Pixel)> _graphicsSpirvCache = new();
private static readonly Dictionary<
(ulong Cs, ulong State, uint LocalX, uint LocalY, uint LocalZ),
@@ -3329,12 +3329,13 @@ public static class AgcExports
textures,
globalMemoryBuffers,
translatedDraw.AttributeCount,
new VulkanGuestRenderTarget(
firstTarget.Address,
firstTarget.Width,
firstTarget.Height,
firstTarget.Format,
firstTarget.NumberType),
translatedDraw.RenderTargets.Select(target =>
new VulkanGuestRenderTarget(
target.Address,
target.Width,
target.Height,
target.Format,
target.NumberType)).ToArray(),
translatedDraw.VertexSpirv,
translatedDraw.VertexCount,
translatedDraw.InstanceCount,
@@ -3462,11 +3463,34 @@ public static class AgcExports
}
var renderTargets = GetRenderTargets(state.CxRegisters)
.Where(target =>
target.Slot == 0 &&
HasPixelColorExport(pixelState, target.Slot))
.Where(target => HasPixelColorExport(pixelState, target.Slot))
.OrderBy(target => target.Slot)
.ToArray();
var outputKind = GetPixelOutputKind(renderTargets.FirstOrDefault().NumberType);
var renderTargetFormats = new VulkanRenderTargetFormat[renderTargets.Length];
for (var index = 0; index < renderTargets.Length; index++)
{
var target = renderTargets[index];
if (!VulkanVideoPresenter.TryDecodeRenderTargetFormat(
target.Format,
target.NumberType,
out renderTargetFormats[index]))
{
error =
$"unsupported color target format={target.Format} number_type={target.NumberType}";
return false;
}
}
var pixelOutputs = renderTargets
.Select((target, location) => new Gen5PixelOutputBinding(
target.Slot,
(uint)location,
renderTargetFormats[location].OutputKind))
.ToArray();
var outputLayout = string.Join(
';',
pixelOutputs.Select(output =>
$"{output.GuestSlot}:{output.HostLocation}:{(int)output.Kind}"));
var attributeCount = GetInterpolatedAttributeCount(pixelState);
var exportStateFingerprint = ComputeShaderStructureFingerprint(exportEvaluation);
var pixelStateFingerprint = ComputeShaderStructureFingerprint(pixelEvaluation);
@@ -3475,7 +3499,7 @@ public static class AgcExports
exportStateFingerprint,
pixelShaderAddress,
pixelStateFingerprint,
outputKind,
outputLayout,
attributeCount);
var totalGlobalBuffers =
pixelEvaluation.GlobalMemoryBindings.Count +
@@ -3491,7 +3515,7 @@ public static class AgcExports
if (!Gen5SpirvTranslator.TryCompilePixelShader(
pixelState,
pixelEvaluation,
outputKind,
pixelOutputs,
out var pixelShader,
out error,
globalBufferBase: 0,
@@ -3579,7 +3603,7 @@ public static class AgcExports
vertexInputs,
renderTargets,
ApplyTransparentPremultipliedFillClear(
CreateRenderState(state.CxRegisters, renderTargets.FirstOrDefault()),
CreateRenderState(state.CxRegisters, renderTargets, pixelState),
textures,
vertexInputs,
pixelEvaluation.InitialScalarRegisters));
@@ -3595,7 +3619,8 @@ public static class AgcExports
/// Chowdren resets its effect layers with an untextured transparent-black
/// fill using premultiplied blending. With One/OneMinusSrcAlpha that draw
/// is otherwise a no-op, causing fog and vignette layers to accumulate.
/// Treat precisely that draw shape as an overwrite.
/// Treat precisely that draw shape as an overwrite only when every MRT
/// attachment uses the same premultiplied blend pattern.
/// </summary>
private static VulkanGuestRenderState ApplyTransparentPremultipliedFillClear(
VulkanGuestRenderState renderState,
@@ -3607,13 +3632,7 @@ public static class AgcExports
textures.Count != 0 ||
vertexInputs.Count != 0 ||
pixelUserData.Count < 4 ||
renderState.Blend is not
{
Enable: true,
ColorSrcFactor: 1,
ColorDstFactor: 5,
ColorFunc: 0,
})
!renderState.Blends.All(IsTransparentPremultipliedFillBlend))
{
return renderState;
}
@@ -3628,10 +3647,21 @@ public static class AgcExports
return renderState with
{
Blend = renderState.Blend with { Enable = false },
Blends = renderState.Blends
.Select(blend => blend with { Enable = false })
.ToArray(),
};
}
private static bool IsTransparentPremultipliedFillBlend(VulkanGuestBlendState blend) =>
blend is
{
Enable: true,
ColorSrcFactor: 1,
ColorDstFactor: 5,
ColorFunc: 0,
};
private static VulkanGuestIndexBuffer? CreateVulkanIndexBuffer(
CpuContext ctx,
SubmittedDcbState state,
@@ -3654,19 +3684,15 @@ public static class AgcExports
: null;
}
private static Gen5PixelOutputKind GetPixelOutputKind(uint numberType) =>
numberType switch
{
4 => Gen5PixelOutputKind.Uint,
5 => Gen5PixelOutputKind.Sint,
_ => Gen5PixelOutputKind.Float,
};
private static bool HasPixelColorExport(Gen5ShaderState state, uint target) =>
state.Program.Instructions.Any(instruction =>
instruction.Control is Gen5ExportControl export &&
export.Target == target &&
export.EnableMask != 0);
GetPixelColorExportMask(state, target) != 0;
private static uint GetPixelColorExportMask(Gen5ShaderState state, uint target) =>
state.Program.Instructions
.Select(instruction => instruction.Control)
.OfType<Gen5ExportControl>()
.Where(export => export.Target == target)
.Aggregate(0u, (mask, export) => mask | (export.EnableMask & 0xFu));
private static uint GetInterpolatedAttributeCount(Gen5ShaderState state)
{
@@ -3824,11 +3850,25 @@ public static class AgcExports
private static VulkanGuestRenderState CreateRenderState(
IReadOnlyDictionary<uint, uint> registers,
RenderTargetDescriptor target)
IReadOnlyList<RenderTargetDescriptor> targets,
Gen5ShaderState pixelState)
{
if (targets.Count == 0)
{
return VulkanGuestRenderState.Default;
}
var target = targets[0];
var scissor = DecodeScissor(registers, target.Width, target.Height);
return new VulkanGuestRenderState(
DecodeBlendState(registers, target.Slot),
targets.Select(target =>
{
var blend = DecodeBlendState(registers, target.Slot);
return blend with
{
WriteMask = blend.WriteMask & GetPixelColorExportMask(pixelState, target.Slot),
};
}).ToArray(),
scissor,
DecodeViewport(registers, target.Width, target.Height, scissor));
}
@@ -3853,7 +3893,7 @@ public static class AgcExports
(control >> 24) & 0x1Fu,
(control >> 21) & 0x7u,
((control >> 29) & 1u) != 0,
writeMask == 0 ? 0xFu : writeMask);
writeMask);
}
private static VulkanGuestRect? DecodeScissor(
@@ -5191,7 +5231,7 @@ public static class AgcExports
if (Gen5SpirvTranslator.TryCompilePixelShader(
pixelState,
evaluation,
Gen5PixelOutputKind.Float,
[new(0, 0, Gen5PixelOutputKind.Float)],
out var compiledPixel,
out var compileError))
{
src/SharpEmu.Libs/Agc/Gen5ShaderIr.cs
+5
View File
@@ -49,6 +49,11 @@ internal enum Gen5PixelOutputKind
Sint,
}
internal readonly record struct Gen5PixelOutputBinding(
uint GuestSlot,
uint HostLocation,
Gen5PixelOutputKind Kind);
internal enum Gen5SpirvStage
{
Vertex,
src/SharpEmu.Libs/Agc/Gen5SpirvTranslator.cs
+98 -33
View File
@@ -19,13 +19,59 @@ internal static partial class Gen5SpirvTranslator
int globalBufferBase = 0,
int totalGlobalBufferCount = -1,
int imageBindingBase = 0,
int scalarRegisterBufferIndex = -1) =>
TryCompilePixelShader(
state,
evaluation,
[new Gen5PixelOutputBinding(0, 0, outputKind)],
out shader,
out error,
globalBufferBase,
totalGlobalBufferCount,
imageBindingBase,
scalarRegisterBufferIndex);
public static bool TryCompilePixelShader(
Gen5ShaderState state,
Gen5ShaderEvaluation evaluation,
IReadOnlyList<Gen5PixelOutputBinding> outputs,
out Gen5SpirvShader shader,
out string error,
int globalBufferBase = 0,
int totalGlobalBufferCount = -1,
int imageBindingBase = 0,
int scalarRegisterBufferIndex = -1)
{
if (outputs.Count > 8 || outputs.Any(output => output.GuestSlot > 7))
{
shader = default!;
error = "pixel outputs must contain at most eight guest slots in the 0..7 range";
return false;
}
if (outputs.Select(output => output.GuestSlot).Distinct().Count() != outputs.Count ||
outputs.Select(output => output.HostLocation).Distinct().Count() != outputs.Count)
{
shader = default!;
error = "pixel output guest slots and host locations must be unique";
return false;
}
if (!outputs
.OrderBy(output => output.HostLocation)
.Select((output, index) => output.HostLocation == (uint)index)
.All(isDense => isDense))
{
shader = default!;
error = "pixel output host locations must be dense in the 0..N-1 range";
return false;
}
var context = new CompilationContext(
Gen5SpirvStage.Pixel,
state,
evaluation,
outputKind,
outputs,
1,
1,
1,
@@ -50,7 +96,7 @@ internal static partial class Gen5SpirvTranslator
Gen5SpirvStage.Vertex,
state,
evaluation,
Gen5PixelOutputKind.Float,
[],
1,
1,
1,
@@ -74,7 +120,7 @@ internal static partial class Gen5SpirvTranslator
Gen5SpirvStage.Compute,
state,
evaluation,
Gen5PixelOutputKind.Float,
[],
Math.Max(localSizeX, 1),
Math.Max(localSizeY, 1),
Math.Max(localSizeZ, 1),
@@ -91,7 +137,7 @@ internal static partial class Gen5SpirvTranslator
private readonly Gen5SpirvStage _stage;
private readonly Gen5ShaderState _state;
private readonly Gen5ShaderEvaluation _evaluation;
private readonly Gen5PixelOutputKind _outputKind;
private readonly IReadOnlyList<Gen5PixelOutputBinding> _pixelOutputBindings;
private readonly uint _localSizeX;
private readonly uint _localSizeY;
private readonly uint _localSizeZ;
@@ -101,6 +147,7 @@ internal static partial class Gen5SpirvTranslator
private readonly int _scalarRegisterBufferIndex;
private readonly List<uint> _interfaces = [];
private readonly Dictionary<uint, uint> _pixelInputs = [];
private readonly Dictionary<uint, SpirvPixelOutput> _pixelOutputs = [];
private readonly Dictionary<uint, uint> _vertexOutputs = [];
private readonly Dictionary<uint, SpirvVertexInput> _vertexInputsByPc = [];
private readonly List<SpirvImageResource> _imageResources = [];
@@ -133,7 +180,6 @@ internal static partial class Gen5SpirvTranslator
private uint _lds;
private uint _workgroupUintPointer;
private uint _positionOutput;
private uint _pixelOutput;
private uint _vertexIndexInput;
private uint _instanceIndexInput;
private uint _fragCoordInput;
@@ -163,11 +209,16 @@ internal static partial class Gen5SpirvTranslator
uint Type,
uint ComponentCount);
private readonly record struct SpirvPixelOutput(
uint Variable,
uint Type,
Gen5PixelOutputKind Kind);
public CompilationContext(
Gen5SpirvStage stage,
Gen5ShaderState state,
Gen5ShaderEvaluation evaluation,
Gen5PixelOutputKind outputKind,
IReadOnlyList<Gen5PixelOutputBinding> pixelOutputBindings,
uint localSizeX,
uint localSizeY,
uint localSizeZ,
@@ -179,7 +230,7 @@ internal static partial class Gen5SpirvTranslator
_stage = stage;
_state = state;
_evaluation = evaluation;
_outputKind = outputKind;
_pixelOutputBindings = pixelOutputBindings;
_localSizeX = localSizeX;
_localSizeY = localSizeY;
_localSizeZ = localSizeZ;
@@ -700,19 +751,24 @@ internal static partial class Gen5SpirvTranslator
(uint)SpirvBuiltIn.FragCoord);
_interfaces.Add(_fragCoordInput);
var outputType = _outputKind switch
foreach (var binding in _pixelOutputBindings)
{
Gen5PixelOutputKind.Uint => _uvec4Type,
Gen5PixelOutputKind.Sint => _module.TypeVector(_intType, 4),
_ => _vec4Type,
};
var outputPointer =
_module.TypePointer(SpirvStorageClass.Output, outputType);
_pixelOutput = _module.AddGlobalVariable(
outputPointer,
SpirvStorageClass.Output);
_module.AddDecoration(_pixelOutput, SpirvDecoration.Location, 0);
_interfaces.Add(_pixelOutput);
var outputType = GetPixelOutputType(binding.Kind);
var outputPointer =
_module.TypePointer(SpirvStorageClass.Output, outputType);
var variable = _module.AddGlobalVariable(
outputPointer,
SpirvStorageClass.Output);
_module.AddName(variable, $"mrt{binding.GuestSlot}");
_module.AddDecoration(
variable,
SpirvDecoration.Location,
binding.HostLocation);
_pixelOutputs.Add(
binding.GuestSlot,
new SpirvPixelOutput(variable, outputType, binding.Kind));
_interfaces.Add(variable);
}
}
else
{
@@ -831,7 +887,10 @@ internal static partial class Gen5SpirvTranslator
1);
StoreV(2, Bitcast(_uintType, x), guardWithExec: false);
StoreV(3, Bitcast(_uintType, y), guardWithExec: false);
Store(_pixelOutput, _module.ConstantNull(GetPixelOutputType()));
foreach (var output in _pixelOutputs.Values)
{
Store(output.Variable, _module.ConstantNull(output.Type));
}
}
else
{
@@ -2084,21 +2143,27 @@ internal static partial class Gen5SpirvTranslator
if (_stage == Gen5SpirvStage.Pixel)
{
if (export.Target != 0)
if (!_pixelOutputs.TryGetValue(export.Target, out var output))
{
return true;
}
var outputType = GetPixelOutputType();
var values = new uint[4];
for (var component = 0; component < 4; component++)
{
var enabled = (export.EnableMask & (1u << component)) != 0;
if (!enabled)
{
values[component] = _outputKind == Gen5PixelOutputKind.Sint
? Bitcast(_intType, UInt(0))
: UInt(0);
values[component] = _module.AddInstruction(
SpirvOp.CompositeExtract,
output.Kind switch
{
Gen5PixelOutputKind.Uint => _uintType,
Gen5PixelOutputKind.Sint => _intType,
_ => _floatType,
},
Load(output.Type, output.Variable),
(uint)component);
continue;
}
@@ -2107,7 +2172,7 @@ internal static partial class Gen5SpirvTranslator
var value = LoadCompressedExportComponent(
instruction,
component);
values[component] = _outputKind switch
values[component] = output.Kind switch
{
Gen5PixelOutputKind.Uint => _module.AddInstruction(
SpirvOp.ConvertFToU,
@@ -2123,7 +2188,7 @@ internal static partial class Gen5SpirvTranslator
}
var raw = LoadV(instruction.Sources[component].Value);
values[component] = _outputKind switch
values[component] = output.Kind switch
{
Gen5PixelOutputKind.Uint => raw,
Gen5PixelOutputKind.Sint => Bitcast(_intType, raw),
@@ -2133,15 +2198,15 @@ internal static partial class Gen5SpirvTranslator
var vector = _module.AddInstruction(
SpirvOp.CompositeConstruct,
outputType,
output.Type,
values);
vector = _module.AddInstruction(
SpirvOp.Select,
outputType,
output.Type,
Load(_boolType, _exec),
vector,
Load(outputType, _pixelOutput));
Store(_pixelOutput, vector);
Load(output.Type, output.Variable));
Store(output.Variable, vector);
return true;
}
@@ -2209,8 +2274,8 @@ internal static partial class Gen5SpirvTranslator
(uint)(component & 1));
}
private uint GetPixelOutputType() =>
_outputKind switch
private uint GetPixelOutputType(Gen5PixelOutputKind kind) =>
kind switch
{
Gen5PixelOutputKind.Uint => _uvec4Type,
Gen5PixelOutputKind.Sint => _module.TypeVector(_intType, 4),