video_core/gpu: Remove unused functions

Merge pull request #3425 from ReinUsesLisp/layered-framebuffer
texture_cache: Implement layered framebuffer attachments
2020-02-25 16:53:47 -03:00 · 2020-02-24 10:14:50 -05:00 · 2020-02-22 23:45:16 -05:00 · 2020-02-22 23:09:50 -05:00 · 2020-02-22 22:32:21 -05:00 · 2020-02-22 12:39:17 -04:00
95 changed files with 3098 additions and 1501 deletions
@@ -151,15 +151,22 @@ if (ENABLE_SDL2)
        set(SDL2_INCLUDE_DIR "${SDL2_PREFIX}/include" CACHE PATH "Path to SDL2 headers")
        set(SDL2_LIBRARY "${SDL2_PREFIX}/lib/x64/SDL2.lib" CACHE PATH "Path to SDL2 library")
        set(SDL2_DLL_DIR "${SDL2_PREFIX}/lib/x64/" CACHE PATH "Path to SDL2.dll")
-    else()
-        find_package(SDL2 REQUIRED)
-    endif()

-    if (SDL2_FOUND)
-        # TODO(yuriks): Make FindSDL2.cmake export an IMPORTED library instead
        add_library(SDL2 INTERFACE)
        target_link_libraries(SDL2 INTERFACE "${SDL2_LIBRARY}")
        target_include_directories(SDL2 INTERFACE "${SDL2_INCLUDE_DIR}")
+    else()
+        find_package(SDL2 REQUIRED)
+
+        # Some installations don't set SDL2_LIBRARIES
+        if("${SDL2_LIBRARIES}" STREQUAL "")
+            message(WARNING "SDL2_LIBRARIES wasn't set, manually setting to SDL2::SDL2")
+            set(SDL2_LIBRARIES "SDL2::SDL2")
+        endif()
+
+        include_directories(${SDL2_INCLUDE_DIRS})
+        add_library(SDL2 INTERFACE)
+        target_link_libraries(SDL2 INTERFACE "${SDL2_LIBRARIES}")
    endif()
 else()
    set(SDL2_FOUND NO)
@@ -1,239 +0,0 @@
-
-# This module defines
-# SDL2_LIBRARY, the name of the library to link against
-# SDL2_FOUND, if false, do not try to link to SDL2
-# SDL2_INCLUDE_DIR, where to find SDL.h
-# SDL2_DLL_DIR, where to find SDL2.dll if it exists
-#
-# This module responds to the the flag:
-# SDL2_BUILDING_LIBRARY
-# If this is defined, then no SDL2main will be linked in because
-# only applications need main().
-# Otherwise, it is assumed you are building an application and this
-# module will attempt to locate and set the the proper link flags
-# as part of the returned SDL2_LIBRARY variable.
-#
-# Don't forget to include SDLmain.h and SDLmain.m your project for the
-# OS X framework based version. (Other versions link to -lSDL2main which
-# this module will try to find on your behalf.) Also for OS X, this
-# module will automatically add the -framework Cocoa on your behalf.
-#
-#
-# Additional Note: If you see an empty SDL2_LIBRARY_TEMP in your configuration
-# and no SDL2_LIBRARY, it means CMake did not find your SDL2 library
-# (SDL2.dll, libsdl2.so, SDL2.framework, etc).
-# Set SDL2_LIBRARY_TEMP to point to your SDL2 library, and configure again.
-# Similarly, if you see an empty SDL2MAIN_LIBRARY, you should set this value
-# as appropriate. These values are used to generate the final SDL2_LIBRARY
-# variable, but when these values are unset, SDL2_LIBRARY does not get created.
-#
-#
-# $SDL2DIR is an environment variable that would
-# correspond to the ./configure --prefix=$SDL2DIR
-# used in building SDL2.
-# l.e.galup  9-20-02
-#
-# Modified by Eric Wing.
-# Added code to assist with automated building by using environmental variables
-# and providing a more controlled/consistent search behavior.
-# Added new modifications to recognize OS X frameworks and
-# additional Unix paths (FreeBSD, etc).
-# Also corrected the header search path to follow "proper" SDL guidelines.
-# Added a search for SDL2main which is needed by some platforms.
-# Added a search for threads which is needed by some platforms.
-# Added needed compile switches for MinGW.
-#
-# On OSX, this will prefer the Framework version (if found) over others.
-# People will have to manually change the cache values of
-# SDL2_LIBRARY to override this selection or set the CMake environment
-# CMAKE_INCLUDE_PATH to modify the search paths.
-#
-# Note that the header path has changed from SDL2/SDL.h to just SDL.h
-# This needed to change because "proper" SDL convention
-# is #include "SDL.h", not <SDL2/SDL.h>. This is done for portability
-# reasons because not all systems place things in SDL2/ (see FreeBSD).
-
-#=============================================================================
-# Copyright 2003-2009 Kitware, Inc.
-#
-# Distributed under the OSI-approved BSD License (the "License").
-#
-# This software is distributed WITHOUT ANY WARRANTY; without even the
-# implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
-# See the License for more information.
-#=============================================================================
-# CMake - Cross Platform Makefile Generator
-# Copyright 2000-2016 Kitware, Inc.
-# Copyright 2000-2011 Insight Software Consortium
-# All rights reserved.
-# 
-# Redistribution and use in source and binary forms, with or without
-# modification, are permitted provided that the following conditions
-# are met:
-# 
-# * Redistributions of source code must retain the above copyright
-#   notice, this list of conditions and the following disclaimer.
-# 
-# * Redistributions in binary form must reproduce the above copyright
-#   notice, this list of conditions and the following disclaimer in the
-#   documentation and/or other materials provided with the distribution.
-# 
-# * Neither the names of Kitware, Inc., the Insight Software Consortium,
-#   nor the names of their contributors may be used to endorse or promote
-#   products derived from this software without specific prior written
-#   permission.
-# 
-# THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-# "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-# LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-# A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-# HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-# LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-# DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-# THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-# (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-# OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-# 
-# ------------------------------------------------------------------------------
-# 
-# The above copyright and license notice applies to distributions of
-# CMake in source and binary form.  Some source files contain additional
-# notices of original copyright by their contributors; see each source
-# for details.  Third-party software packages supplied with CMake under
-# compatible licenses provide their own copyright notices documented in
-# corresponding subdirectories.
-# 
-# ------------------------------------------------------------------------------
-# 
-# CMake was initially developed by Kitware with the following sponsorship:
-# 
-#  * National Library of Medicine at the National Institutes of Health
-#    as part of the Insight Segmentation and Registration Toolkit (ITK).
-# 
-#  * US National Labs (Los Alamos, Livermore, Sandia) ASC Parallel
-#    Visualization Initiative.
-# 
-#  * National Alliance for Medical Image Computing (NAMIC) is funded by the
-#    National Institutes of Health through the NIH Roadmap for Medical Research,
-#    Grant U54 EB005149.
-# 
-#  * Kitware, Inc.
-#
-
-message("<FindSDL2.cmake>")
-
-SET(SDL2_SEARCH_PATHS
-    ~/Library/Frameworks
-    /Library/Frameworks
-    /usr/local
-    /usr
-    /sw # Fink
-    /opt/local # DarwinPorts
-    /opt/csw # Blastwave
-    /opt
-    ${SDL2_PATH}
-)
-
-if(CMAKE_SIZEOF_VOID_P EQUAL 8)
-    set(VC_LIB_PATH_SUFFIX lib/x64)
-else()
-    set(VC_LIB_PATH_SUFFIX lib/x86)
-endif()
-
-FIND_LIBRARY(SDL2_LIBRARY_TEMP
-    NAMES SDL2
-    HINTS
-    $ENV{SDL2DIR}
-    PATH_SUFFIXES lib64 lib ${VC_LIB_PATH_SUFFIX}
-    PATHS ${SDL2_SEARCH_PATHS}
-)
-
-IF(SDL2_LIBRARY_TEMP)
-    if(MSVC)
-        get_filename_component(SDL2_DLL_DIR_TEMP ${SDL2_LIBRARY_TEMP} DIRECTORY)
-        if(EXISTS ${SDL2_DLL_DIR_TEMP}/SDL2.dll)
-            set(SDL2_DLL_DIR ${SDL2_DLL_DIR_TEMP})
-            unset(SDL2_DLL_DIR_TEMP)
-        endif()
-    endif()
-
-    FIND_PATH(SDL2_INCLUDE_DIR SDL.h
-        HINTS
-        $ENV{SDL2DIR}
-        PATH_SUFFIXES include/SDL2 include
-        PATHS ${SDL2_SEARCH_PATHS}
-    )
-
-    IF(NOT SDL2_BUILDING_LIBRARY)
-        IF(NOT ${SDL2_INCLUDE_DIR} MATCHES ".framework")
-            # Non-OS X framework versions expect you to also dynamically link to
-            # SDL2main. This is mainly for Windows and OS X. Other (Unix) platforms
-            # seem to provide SDL2main for compatibility even though they don't
-            # necessarily need it.
-            FIND_LIBRARY(SDL2MAIN_LIBRARY
-                NAMES SDL2main
-                HINTS
-                $ENV{SDL2DIR}
-                PATH_SUFFIXES lib64 lib
-                PATHS ${SDL2_SEARCH_PATHS}
-            )
-        ENDIF(NOT ${SDL2_INCLUDE_DIR} MATCHES ".framework")
-    ENDIF(NOT SDL2_BUILDING_LIBRARY)
-
-    # SDL2 may require threads on your system.
-    # The Apple build may not need an explicit flag because one of the
-    # frameworks may already provide it.
-    # But for non-OSX systems, I will use the CMake Threads package.
-    IF(NOT APPLE)
-        FIND_PACKAGE(Threads)
-    ENDIF(NOT APPLE)
-
-    # MinGW needs an additional library, mwindows
-    # It's total link flags should look like -lmingw32 -lSDL2main -lSDL2 -lmwindows
-    # (Actually on second look, I think it only needs one of the m* libraries.)
-    IF(MINGW)
-        SET(MINGW32_LIBRARY mingw32 CACHE STRING "mwindows for MinGW")
-    ENDIF(MINGW)
-
-    # For SDL2main
-    IF(NOT SDL2_BUILDING_LIBRARY)
-        IF(SDL2MAIN_LIBRARY)
-            SET(SDL2_LIBRARY_TEMP ${SDL2MAIN_LIBRARY} ${SDL2_LIBRARY_TEMP})
-        ENDIF(SDL2MAIN_LIBRARY)
-    ENDIF(NOT SDL2_BUILDING_LIBRARY)
-
-    # For OS X, SDL2 uses Cocoa as a backend so it must link to Cocoa.
-    # CMake doesn't display the -framework Cocoa string in the UI even
-    # though it actually is there if I modify a pre-used variable.
-    # I think it has something to do with the CACHE STRING.
-    # So I use a temporary variable until the end so I can set the
-    # "real" variable in one-shot.
-    IF(APPLE)
-        SET(SDL2_LIBRARY_TEMP ${SDL2_LIBRARY_TEMP} "-framework Cocoa")
-    ENDIF(APPLE)
-
-    # For threads, as mentioned Apple doesn't need this.
-    # In fact, there seems to be a problem if I used the Threads package
-    # and try using this line, so I'm just skipping it entirely for OS X.
-    IF(NOT APPLE)
-        SET(SDL2_LIBRARY_TEMP ${SDL2_LIBRARY_TEMP} ${CMAKE_THREAD_LIBS_INIT})
-    ENDIF(NOT APPLE)
-
-    # For MinGW library
-    IF(MINGW)
-        SET(SDL2_LIBRARY_TEMP ${MINGW32_LIBRARY} ${SDL2_LIBRARY_TEMP})
-    ENDIF(MINGW)
-
-    # Set the final string here so the GUI reflects the final state.
-    SET(SDL2_LIBRARY ${SDL2_LIBRARY_TEMP} CACHE STRING "Where the SDL2 Library can be found")
-
-    # Unset the temp variable to INTERNAL so it is not seen in the CMake GUI
-    UNSET(SDL2_LIBRARY_TEMP)
-ENDIF(SDL2_LIBRARY_TEMP)
-
-message("</FindSDL2.cmake>")
-
-INCLUDE(FindPackageHandleStandardArgs)
-
-FIND_PACKAGE_HANDLE_STANDARD_ARGS(SDL2 REQUIRED_VARS SDL2_LIBRARY SDL2_INCLUDE_DIR)
@@ -1,4 +1,4 @@
-From https://github.com/yhirose/cpp-httplib/commit/d9479bc0b12e8a1e8bce2d34da4feeef488581f3
+From https://github.com/yhirose/cpp-httplib/tree/fce8e6fefdab4ad48bc5b25c98e5ebfda4f3cf53

 MIT License

@@ -5,6 +5,7 @@
 #define _USE_MATH_DEFINES

 #include <algorithm>
+#include <climits>
 #include <cmath>
 #include <vector>
 #include "audio_core/algorithm/interpolate.h"
@@ -13,13 +14,131 @@

 namespace AudioCore {

-/// The Lanczos kernel
-static double Lanczos(std::size_t a, double x) {
-    if (x == 0.0)
-        return 1.0;
-    const double px = M_PI * x;
-    return a * std::sin(px) * std::sin(px / a) / (px * px);
-}
+constexpr std::array<s16, 512> curve_lut0 = {
+    6600,  19426, 6722,  3,     6479,  19424, 6845,  9,     6359,  19419, 6968,  15,    6239,
+    19412, 7093,  22,    6121,  19403, 7219,  28,    6004,  19391, 7345,  34,    5888,  19377,
+    7472,  41,    5773,  19361, 7600,  48,    5659,  19342, 7728,  55,    5546,  19321, 7857,
+    62,    5434,  19298, 7987,  69,    5323,  19273, 8118,  77,    5213,  19245, 8249,  84,
+    5104,  19215, 8381,  92,    4997,  19183, 8513,  101,   4890,  19148, 8646,  109,   4785,
+    19112, 8780,  118,   4681,  19073, 8914,  127,   4579,  19031, 9048,  137,   4477,  18988,
+    9183,  147,   4377,  18942, 9318,  157,   4277,  18895, 9454,  168,   4179,  18845, 9590,
+    179,   4083,  18793, 9726,  190,   3987,  18738, 9863,  202,   3893,  18682, 10000, 215,
+    3800,  18624, 10137, 228,   3709,  18563, 10274, 241,   3618,  18500, 10411, 255,   3529,
+    18436, 10549, 270,   3441,  18369, 10687, 285,   3355,  18300, 10824, 300,   3269,  18230,
+    10962, 317,   3186,  18157, 11100, 334,   3103,  18082, 11238, 351,   3022,  18006, 11375,
+    369,   2942,  17927, 11513, 388,   2863,  17847, 11650, 408,   2785,  17765, 11788, 428,
+    2709,  17681, 11925, 449,   2635,  17595, 12062, 471,   2561,  17507, 12198, 494,   2489,
+    17418, 12334, 517,   2418,  17327, 12470, 541,   2348,  17234, 12606, 566,   2280,  17140,
+    12741, 592,   2213,  17044, 12876, 619,   2147,  16946, 13010, 647,   2083,  16846, 13144,
+    675,   2020,  16745, 13277, 704,   1958,  16643, 13409, 735,   1897,  16539, 13541, 766,
+    1838,  16434, 13673, 798,   1780,  16327, 13803, 832,   1723,  16218, 13933, 866,   1667,
+    16109, 14062, 901,   1613,  15998, 14191, 937,   1560,  15885, 14318, 975,   1508,  15772,
+    14445, 1013,  1457,  15657, 14571, 1052,  1407,  15540, 14695, 1093,  1359,  15423, 14819,
+    1134,  1312,  15304, 14942, 1177,  1266,  15185, 15064, 1221,  1221,  15064, 15185, 1266,
+    1177,  14942, 15304, 1312,  1134,  14819, 15423, 1359,  1093,  14695, 15540, 1407,  1052,
+    14571, 15657, 1457,  1013,  14445, 15772, 1508,  975,   14318, 15885, 1560,  937,   14191,
+    15998, 1613,  901,   14062, 16109, 1667,  866,   13933, 16218, 1723,  832,   13803, 16327,
+    1780,  798,   13673, 16434, 1838,  766,   13541, 16539, 1897,  735,   13409, 16643, 1958,
+    704,   13277, 16745, 2020,  675,   13144, 16846, 2083,  647,   13010, 16946, 2147,  619,
+    12876, 17044, 2213,  592,   12741, 17140, 2280,  566,   12606, 17234, 2348,  541,   12470,
+    17327, 2418,  517,   12334, 17418, 2489,  494,   12198, 17507, 2561,  471,   12062, 17595,
+    2635,  449,   11925, 17681, 2709,  428,   11788, 17765, 2785,  408,   11650, 17847, 2863,
+    388,   11513, 17927, 2942,  369,   11375, 18006, 3022,  351,   11238, 18082, 3103,  334,
+    11100, 18157, 3186,  317,   10962, 18230, 3269,  300,   10824, 18300, 3355,  285,   10687,
+    18369, 3441,  270,   10549, 18436, 3529,  255,   10411, 18500, 3618,  241,   10274, 18563,
+    3709,  228,   10137, 18624, 3800,  215,   10000, 18682, 3893,  202,   9863,  18738, 3987,
+    190,   9726,  18793, 4083,  179,   9590,  18845, 4179,  168,   9454,  18895, 4277,  157,
+    9318,  18942, 4377,  147,   9183,  18988, 4477,  137,   9048,  19031, 4579,  127,   8914,
+    19073, 4681,  118,   8780,  19112, 4785,  109,   8646,  19148, 4890,  101,   8513,  19183,
+    4997,  92,    8381,  19215, 5104,  84,    8249,  19245, 5213,  77,    8118,  19273, 5323,
+    69,    7987,  19298, 5434,  62,    7857,  19321, 5546,  55,    7728,  19342, 5659,  48,
+    7600,  19361, 5773,  41,    7472,  19377, 5888,  34,    7345,  19391, 6004,  28,    7219,
+    19403, 6121,  22,    7093,  19412, 6239,  15,    6968,  19419, 6359,  9,     6845,  19424,
+    6479,  3,     6722,  19426, 6600};
+
+constexpr std::array<s16, 512> curve_lut1 = {
+    -68,   32639, 69,    -5,    -200,  32630, 212,   -15,   -328,  32613, 359,   -26,   -450,
+    32586, 512,   -36,   -568,  32551, 669,   -47,   -680,  32507, 832,   -58,   -788,  32454,
+    1000,  -69,   -891,  32393, 1174,  -80,   -990,  32323, 1352,  -92,   -1084, 32244, 1536,
+    -103,  -1173, 32157, 1724,  -115,  -1258, 32061, 1919,  -128,  -1338, 31956, 2118,  -140,
+    -1414, 31844, 2322,  -153,  -1486, 31723, 2532,  -167,  -1554, 31593, 2747,  -180,  -1617,
+    31456, 2967,  -194,  -1676, 31310, 3192,  -209,  -1732, 31157, 3422,  -224,  -1783, 30995,
+    3657,  -240,  -1830, 30826, 3897,  -256,  -1874, 30649, 4143,  -272,  -1914, 30464, 4393,
+    -289,  -1951, 30272, 4648,  -307,  -1984, 30072, 4908,  -325,  -2014, 29866, 5172,  -343,
+    -2040, 29652, 5442,  -362,  -2063, 29431, 5716,  -382,  -2083, 29203, 5994,  -403,  -2100,
+    28968, 6277,  -424,  -2114, 28727, 6565,  -445,  -2125, 28480, 6857,  -468,  -2133, 28226,
+    7153,  -490,  -2139, 27966, 7453,  -514,  -2142, 27700, 7758,  -538,  -2142, 27428, 8066,
+    -563,  -2141, 27151, 8378,  -588,  -2136, 26867, 8694,  -614,  -2130, 26579, 9013,  -641,
+    -2121, 26285, 9336,  -668,  -2111, 25987, 9663,  -696,  -2098, 25683, 9993,  -724,  -2084,
+    25375, 10326, -753,  -2067, 25063, 10662, -783,  -2049, 24746, 11000, -813,  -2030, 24425,
+    11342, -844,  -2009, 24100, 11686, -875,  -1986, 23771, 12033, -907,  -1962, 23438, 12382,
+    -939,  -1937, 23103, 12733, -972,  -1911, 22764, 13086, -1005, -1883, 22422, 13441, -1039,
+    -1855, 22077, 13798, -1072, -1825, 21729, 14156, -1107, -1795, 21380, 14516, -1141, -1764,
+    21027, 14877, -1176, -1732, 20673, 15239, -1211, -1700, 20317, 15602, -1246, -1667, 19959,
+    15965, -1282, -1633, 19600, 16329, -1317, -1599, 19239, 16694, -1353, -1564, 18878, 17058,
+    -1388, -1530, 18515, 17423, -1424, -1495, 18151, 17787, -1459, -1459, 17787, 18151, -1495,
+    -1424, 17423, 18515, -1530, -1388, 17058, 18878, -1564, -1353, 16694, 19239, -1599, -1317,
+    16329, 19600, -1633, -1282, 15965, 19959, -1667, -1246, 15602, 20317, -1700, -1211, 15239,
+    20673, -1732, -1176, 14877, 21027, -1764, -1141, 14516, 21380, -1795, -1107, 14156, 21729,
+    -1825, -1072, 13798, 22077, -1855, -1039, 13441, 22422, -1883, -1005, 13086, 22764, -1911,
+    -972,  12733, 23103, -1937, -939,  12382, 23438, -1962, -907,  12033, 23771, -1986, -875,
+    11686, 24100, -2009, -844,  11342, 24425, -2030, -813,  11000, 24746, -2049, -783,  10662,
+    25063, -2067, -753,  10326, 25375, -2084, -724,  9993,  25683, -2098, -696,  9663,  25987,
+    -2111, -668,  9336,  26285, -2121, -641,  9013,  26579, -2130, -614,  8694,  26867, -2136,
+    -588,  8378,  27151, -2141, -563,  8066,  27428, -2142, -538,  7758,  27700, -2142, -514,
+    7453,  27966, -2139, -490,  7153,  28226, -2133, -468,  6857,  28480, -2125, -445,  6565,
+    28727, -2114, -424,  6277,  28968, -2100, -403,  5994,  29203, -2083, -382,  5716,  29431,
+    -2063, -362,  5442,  29652, -2040, -343,  5172,  29866, -2014, -325,  4908,  30072, -1984,
+    -307,  4648,  30272, -1951, -289,  4393,  30464, -1914, -272,  4143,  30649, -1874, -256,
+    3897,  30826, -1830, -240,  3657,  30995, -1783, -224,  3422,  31157, -1732, -209,  3192,
+    31310, -1676, -194,  2967,  31456, -1617, -180,  2747,  31593, -1554, -167,  2532,  31723,
+    -1486, -153,  2322,  31844, -1414, -140,  2118,  31956, -1338, -128,  1919,  32061, -1258,
+    -115,  1724,  32157, -1173, -103,  1536,  32244, -1084, -92,   1352,  32323, -990,  -80,
+    1174,  32393, -891,  -69,   1000,  32454, -788,  -58,   832,   32507, -680,  -47,   669,
+    32551, -568,  -36,   512,   32586, -450,  -26,   359,   32613, -328,  -15,   212,   32630,
+    -200,  -5,    69,    32639, -68};
+
+constexpr std::array<s16, 512> curve_lut2 = {
+    3195,  26287, 3329,  -32,   3064,  26281, 3467,  -34,   2936,  26270, 3608,  -38,   2811,
+    26253, 3751,  -42,   2688,  26230, 3897,  -46,   2568,  26202, 4046,  -50,   2451,  26169,
+    4199,  -54,   2338,  26130, 4354,  -58,   2227,  26085, 4512,  -63,   2120,  26035, 4673,
+    -67,   2015,  25980, 4837,  -72,   1912,  25919, 5004,  -76,   1813,  25852, 5174,  -81,
+    1716,  25780, 5347,  -87,   1622,  25704, 5522,  -92,   1531,  25621, 5701,  -98,   1442,
+    25533, 5882,  -103,  1357,  25440, 6066,  -109,  1274,  25342, 6253,  -115,  1193,  25239,
+    6442,  -121,  1115,  25131, 6635,  -127,  1040,  25018, 6830,  -133,  967,   24899, 7027,
+    -140,  897,   24776, 7227,  -146,  829,   24648, 7430,  -153,  764,   24516, 7635,  -159,
+    701,   24379, 7842,  -166,  641,   24237, 8052,  -174,  583,   24091, 8264,  -181,  526,
+    23940, 8478,  -187,  472,   23785, 8695,  -194,  420,   23626, 8914,  -202,  371,   23462,
+    9135,  -209,  324,   23295, 9358,  -215,  279,   23123, 9583,  -222,  236,   22948, 9809,
+    -230,  194,   22769, 10038, -237,  154,   22586, 10269, -243,  117,   22399, 10501, -250,
+    81,    22208, 10735, -258,  47,    22015, 10970, -265,  15,    21818, 11206, -271,  -16,
+    21618, 11444, -277,  -44,   21415, 11684, -283,  -71,   21208, 11924, -290,  -97,   20999,
+    12166, -296,  -121,  20786, 12409, -302,  -143,  20571, 12653, -306,  -163,  20354, 12898,
+    -311,  -183,  20134, 13143, -316,  -201,  19911, 13389, -321,  -218,  19686, 13635, -325,
+    -234,  19459, 13882, -328,  -248,  19230, 14130, -332,  -261,  18998, 14377, -335,  -273,
+    18765, 14625, -337,  -284,  18531, 14873, -339,  -294,  18295, 15121, -341,  -302,  18057,
+    15369, -341,  -310,  17817, 15617, -341,  -317,  17577, 15864, -340,  -323,  17335, 16111,
+    -340,  -328,  17092, 16357, -338,  -332,  16848, 16603, -336,  -336,  16603, 16848, -332,
+    -338,  16357, 17092, -328,  -340,  16111, 17335, -323,  -340,  15864, 17577, -317,  -341,
+    15617, 17817, -310,  -341,  15369, 18057, -302,  -341,  15121, 18295, -294,  -339,  14873,
+    18531, -284,  -337,  14625, 18765, -273,  -335,  14377, 18998, -261,  -332,  14130, 19230,
+    -248,  -328,  13882, 19459, -234,  -325,  13635, 19686, -218,  -321,  13389, 19911, -201,
+    -316,  13143, 20134, -183,  -311,  12898, 20354, -163,  -306,  12653, 20571, -143,  -302,
+    12409, 20786, -121,  -296,  12166, 20999, -97,   -290,  11924, 21208, -71,   -283,  11684,
+    21415, -44,   -277,  11444, 21618, -16,   -271,  11206, 21818, 15,    -265,  10970, 22015,
+    47,    -258,  10735, 22208, 81,    -250,  10501, 22399, 117,   -243,  10269, 22586, 154,
+    -237,  10038, 22769, 194,   -230,  9809,  22948, 236,   -222,  9583,  23123, 279,   -215,
+    9358,  23295, 324,   -209,  9135,  23462, 371,   -202,  8914,  23626, 420,   -194,  8695,
+    23785, 472,   -187,  8478,  23940, 526,   -181,  8264,  24091, 583,   -174,  8052,  24237,
+    641,   -166,  7842,  24379, 701,   -159,  7635,  24516, 764,   -153,  7430,  24648, 829,
+    -146,  7227,  24776, 897,   -140,  7027,  24899, 967,   -133,  6830,  25018, 1040,  -127,
+    6635,  25131, 1115,  -121,  6442,  25239, 1193,  -115,  6253,  25342, 1274,  -109,  6066,
+    25440, 1357,  -103,  5882,  25533, 1442,  -98,   5701,  25621, 1531,  -92,   5522,  25704,
+    1622,  -87,   5347,  25780, 1716,  -81,   5174,  25852, 1813,  -76,   5004,  25919, 1912,
+    -72,   4837,  25980, 2015,  -67,   4673,  26035, 2120,  -63,   4512,  26085, 2227,  -58,
+    4354,  26130, 2338,  -54,   4199,  26169, 2451,  -50,   4046,  26202, 2568,  -46,   3897,
+    26230, 2688,  -42,   3751,  26253, 2811,  -38,   3608,  26270, 2936,  -34,   3467,  26281,
+    3064,  -32,   3329,  26287, 3195};

 std::vector<s16> Interpolate(InterpolationState& state, std::vector<s16> input, double ratio) {
    if (input.size() < 2)
@@ -30,40 +149,39 @@ std::vector<s16> Interpolate(InterpolationState& state, std::vector<s16> input,
        ratio = 1.0;
    }

-    if (ratio != state.current_ratio) {
-        const double cutoff_frequency = std::min(0.5 / ratio, 0.5 * ratio);
-        state.nyquist = CascadingFilter::LowPass(std::clamp(cutoff_frequency, 0.0, 0.4), 3);
-        state.current_ratio = ratio;
-    }
-    state.nyquist.Process(input);
-
-    constexpr std::size_t taps = InterpolationState::lanczos_taps;
-    const std::size_t num_frames = input.size() / 2;
-
-    std::vector<s16> output;
-    output.reserve(static_cast<std::size_t>(input.size() / ratio + 4));
-
-    double& pos = state.position;
-    auto& h = state.history;
-    for (std::size_t i = 0; i < num_frames; ++i) {
-        std::rotate(h.begin(), h.end() - 1, h.end());
-        h[0][0] = input[i * 2 + 0];
-        h[0][1] = input[i * 2 + 1];
-
-        while (pos <= 1.0) {
-            double l = 0.0;
-            double r = 0.0;
-            for (std::size_t j = 0; j < h.size(); j++) {
-                const double lanczos_calc = Lanczos(taps, pos + j - taps + 1);
-                l += lanczos_calc * h[j][0];
-                r += lanczos_calc * h[j][1];
-            }
-            output.emplace_back(static_cast<s16>(std::clamp(l, -32768.0, 32767.0)));
-            output.emplace_back(static_cast<s16>(std::clamp(r, -32768.0, 32767.0)));
-
-            pos += ratio;
+    const int step = static_cast<int>(ratio * 0x8000);
+    const std::array<s16, 512>& lut = [step] {
+        if (step > 0xaaaa) {
+            return curve_lut0;
        }
-        pos -= 1.0;
+        if (step <= 0x8000) {
+            return curve_lut1;
+        }
+        return curve_lut2;
+    }();
+
+    std::vector<s16> output(static_cast<std::size_t>(input.size() / ratio));
+    int in_offset = 0;
+    for (std::size_t out_offset = 0; out_offset < output.size(); out_offset += 2) {
+        const int lut_index = (state.fraction >> 8) * 4;
+
+        const int l = input[(in_offset + 0) * 2 + 0] * lut[lut_index + 0] +
+                      input[(in_offset + 1) * 2 + 0] * lut[lut_index + 1] +
+                      input[(in_offset + 2) * 2 + 0] * lut[lut_index + 2] +
+                      input[(in_offset + 3) * 2 + 0] * lut[lut_index + 3];
+
+        const int r = input[(in_offset + 0) * 2 + 1] * lut[lut_index + 0] +
+                      input[(in_offset + 1) * 2 + 1] * lut[lut_index + 1] +
+                      input[(in_offset + 2) * 2 + 1] * lut[lut_index + 2] +
+                      input[(in_offset + 3) * 2 + 1] * lut[lut_index + 3];
+
+        const int new_offset = state.fraction + step;
+
+        in_offset += new_offset >> 15;
+        state.fraction = new_offset & 0x7fff;
+
+        output[out_offset + 0] = static_cast<s16>(std::clamp(l >> 15, SHRT_MIN, SHRT_MAX));
+        output[out_offset + 1] = static_cast<s16>(std::clamp(r >> 15, SHRT_MIN, SHRT_MAX));
    }

    return output;
@@ -6,19 +6,12 @@

 #include <array>
 #include <vector>
-#include "audio_core/algorithm/filter.h"
 #include "common/common_types.h"

 namespace AudioCore {

 struct InterpolationState {
-    static constexpr std::size_t lanczos_taps = 4;
-    static constexpr std::size_t history_size = lanczos_taps * 2 - 1;
-
-    double current_ratio = 0.0;
-    CascadingFilter nyquist;
-    std::array<std::array<s16, 2>, history_size> history = {};
-    double position = 0;
+    int fraction = 0;
 };

 /// Interpolates input signal to produce output signal.
@@ -181,14 +181,18 @@ add_library(core STATIC
    hle/kernel/svc.cpp
    hle/kernel/svc.h
    hle/kernel/svc_wrap.h
+    hle/kernel/synchronization_object.cpp
+    hle/kernel/synchronization_object.h
+    hle/kernel/synchronization.cpp
+    hle/kernel/synchronization.h
    hle/kernel/thread.cpp
    hle/kernel/thread.h
+    hle/kernel/time_manager.cpp
+    hle/kernel/time_manager.h
    hle/kernel/transfer_memory.cpp
    hle/kernel/transfer_memory.h
    hle/kernel/vm_manager.cpp
    hle/kernel/vm_manager.h
-    hle/kernel/wait_object.cpp
-    hle/kernel/wait_object.h
    hle/kernel/writable_event.cpp
    hle/kernel/writable_event.h
    hle/lock.cpp
@@ -14,6 +14,7 @@
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
 #include "core/gdbstub/gdbstub.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/process.h"
 #include "core/hle/kernel/scheduler.h"
 #include "core/hle/kernel/svc.h"
@@ -153,7 +154,7 @@ std::unique_ptr<Dynarmic::A64::Jit> ARM_Dynarmic::MakeJit(Common::PageTable& pag
    config.tpidr_el0 = &cb->tpidr_el0;
    config.dczid_el0 = 4;
    config.ctr_el0 = 0x8444c004;
-    config.cntfrq_el0 = Timing::CNTFREQ;
+    config.cntfrq_el0 = Hardware::CNTFREQ;

    // Unpredictable instructions
    config.define_unpredictable_behaviour = true;
@@ -707,4 +707,12 @@ const Service::SM::ServiceManager& System::ServiceManager() const {
    return *impl->service_manager;
 }

+void System::RegisterCoreThread(std::size_t id) {
+    impl->kernel.RegisterCoreThread(id);
+}
+
+void System::RegisterHostThread() {
+    impl->kernel.RegisterHostThread();
+}
+
 } // namespace Core
@@ -360,6 +360,12 @@ public:

    const CurrentBuildProcessID& GetCurrentProcessBuildID() const;

+    /// Register a host thread as an emulated CPU Core.
+    void RegisterCoreThread(std::size_t id);
+
+    /// Register a host thread as an auxiliary thread.
+    void RegisterHostThread();
+
 private:
    System();

@@ -12,6 +12,7 @@
 #include "common/assert.h"
 #include "common/thread.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"

 namespace Core::Timing {

@@ -215,7 +216,7 @@ void CoreTiming::Idle() {
 }

 std::chrono::microseconds CoreTiming::GetGlobalTimeUs() const {
-    return std::chrono::microseconds{GetTicks() * 1000000 / BASE_CLOCK_RATE};
+    return std::chrono::microseconds{GetTicks() * 1000000 / Hardware::BASE_CLOCK_RATE};
 }

 s64 CoreTiming::GetDowncount() const {
@@ -11,7 +11,7 @@

 namespace Core::Timing {

-constexpr u64 MAX_VALUE_TO_MULTIPLY = std::numeric_limits<s64>::max() / BASE_CLOCK_RATE;
+constexpr u64 MAX_VALUE_TO_MULTIPLY = std::numeric_limits<s64>::max() / Hardware::BASE_CLOCK_RATE;

 s64 msToCycles(std::chrono::milliseconds ms) {
    if (static_cast<u64>(ms.count() / 1000) > MAX_VALUE_TO_MULTIPLY) {
@@ -20,9 +20,9 @@ s64 msToCycles(std::chrono::milliseconds ms) {
    }
    if (static_cast<u64>(ms.count()) > MAX_VALUE_TO_MULTIPLY) {
        LOG_DEBUG(Core_Timing, "Time very big, do rounding");
-        return BASE_CLOCK_RATE * (ms.count() / 1000);
+        return Hardware::BASE_CLOCK_RATE * (ms.count() / 1000);
    }
-    return (BASE_CLOCK_RATE * ms.count()) / 1000;
+    return (Hardware::BASE_CLOCK_RATE * ms.count()) / 1000;
 }

 s64 usToCycles(std::chrono::microseconds us) {
@@ -32,9 +32,9 @@ s64 usToCycles(std::chrono::microseconds us) {
    }
    if (static_cast<u64>(us.count()) > MAX_VALUE_TO_MULTIPLY) {
        LOG_DEBUG(Core_Timing, "Time very big, do rounding");
-        return BASE_CLOCK_RATE * (us.count() / 1000000);
+        return Hardware::BASE_CLOCK_RATE * (us.count() / 1000000);
    }
-    return (BASE_CLOCK_RATE * us.count()) / 1000000;
+    return (Hardware::BASE_CLOCK_RATE * us.count()) / 1000000;
 }

 s64 nsToCycles(std::chrono::nanoseconds ns) {
@@ -44,14 +44,14 @@ s64 nsToCycles(std::chrono::nanoseconds ns) {
    }
    if (static_cast<u64>(ns.count()) > MAX_VALUE_TO_MULTIPLY) {
        LOG_DEBUG(Core_Timing, "Time very big, do rounding");
-        return BASE_CLOCK_RATE * (ns.count() / 1000000000);
+        return Hardware::BASE_CLOCK_RATE * (ns.count() / 1000000000);
    }
-    return (BASE_CLOCK_RATE * ns.count()) / 1000000000;
+    return (Hardware::BASE_CLOCK_RATE * ns.count()) / 1000000000;
 }

 u64 CpuCyclesToClockCycles(u64 ticks) {
-    const u128 temporal = Common::Multiply64Into128(ticks, CNTFREQ);
-    return Common::Divide128On32(temporal, static_cast<u32>(BASE_CLOCK_RATE)).first;
+    const u128 temporal = Common::Multiply64Into128(ticks, Hardware::CNTFREQ);
+    return Common::Divide128On32(temporal, static_cast<u32>(Hardware::BASE_CLOCK_RATE)).first;
 }

 } // namespace Core::Timing
@@ -6,28 +6,24 @@

 #include <chrono>
 #include "common/common_types.h"
+#include "core/hardware_properties.h"

 namespace Core::Timing {

-// The below clock rate is based on Switch's clockspeed being widely known as 1.020GHz
-// The exact value used is of course unverified.
-constexpr u64 BASE_CLOCK_RATE = 1019215872; // Switch clock speed is 1020MHz un/docked
-constexpr u64 CNTFREQ = 19200000;           // Value from fusee.
-
 s64 msToCycles(std::chrono::milliseconds ms);
 s64 usToCycles(std::chrono::microseconds us);
 s64 nsToCycles(std::chrono::nanoseconds ns);

 inline std::chrono::milliseconds CyclesToMs(s64 cycles) {
-    return std::chrono::milliseconds(cycles * 1000 / BASE_CLOCK_RATE);
+    return std::chrono::milliseconds(cycles * 1000 / Hardware::BASE_CLOCK_RATE);
 }

 inline std::chrono::nanoseconds CyclesToNs(s64 cycles) {
-    return std::chrono::nanoseconds(cycles * 1000000000 / BASE_CLOCK_RATE);
+    return std::chrono::nanoseconds(cycles * 1000000000 / Hardware::BASE_CLOCK_RATE);
 }

 inline std::chrono::microseconds CyclesToUs(s64 cycles) {
-    return std::chrono::microseconds(cycles * 1000000 / BASE_CLOCK_RATE);
+    return std::chrono::microseconds(cycles * 1000000 / Hardware::BASE_CLOCK_RATE);
 }

 u64 CpuCyclesToClockCycles(u64 ticks);
@@ -6,6 +6,7 @@

 #include <array>
 #include <memory>
+#include "core/hardware_properties.h"

 namespace Core {

@@ -39,9 +40,7 @@ public:
    void RunLoop(bool tight_loop);

 private:
-    static constexpr std::size_t NUM_CPU_CORES = 4;
-
-    std::array<std::unique_ptr<CoreManager>, NUM_CPU_CORES> core_managers;
+    std::array<std::unique_ptr<CoreManager>, Hardware::NUM_CPU_CORES> core_managers;
    std::size_t active_core{}; ///< Active core, only used in single thread mode

    System& system;
@@ -27,9 +27,9 @@ FramebufferLayout DefaultFrameLayout(u32 width, u32 height) {
    // so just calculate them both even if the other isn't showing.
    FramebufferLayout res{width, height};

-    const float emulation_aspect_ratio{static_cast<float>(ScreenUndocked::Height) /
-                                       ScreenUndocked::Width};
-    const auto window_aspect_ratio = static_cast<float>(height) / width;
+    const float window_aspect_ratio = static_cast<float>(height) / width;
+    const float emulation_aspect_ratio = EmulationAspectRatio(
+        static_cast<AspectRatio>(Settings::values.aspect_ratio), window_aspect_ratio);

    const Common::Rectangle<u32> screen_window_area{0, 0, width, height};
    Common::Rectangle<u32> screen = MaxRectangle(screen_window_area, emulation_aspect_ratio);
@@ -58,4 +58,19 @@ FramebufferLayout FrameLayoutFromResolutionScale(u32 res_scale) {
    return DefaultFrameLayout(width, height);
 }

+float EmulationAspectRatio(AspectRatio aspect, float window_aspect_ratio) {
+    switch (aspect) {
+    case AspectRatio::Default:
+        return static_cast<float>(ScreenUndocked::Height) / ScreenUndocked::Width;
+    case AspectRatio::R4_3:
+        return 3.0f / 4.0f;
+    case AspectRatio::R21_9:
+        return 9.0f / 21.0f;
+    case AspectRatio::StretchToWindow:
+        return window_aspect_ratio;
+    default:
+        return static_cast<float>(ScreenUndocked::Height) / ScreenUndocked::Width;
+    }
+}
+
 } // namespace Layout
@@ -18,6 +18,13 @@ enum ScreenDocked : u32 {
    HeightDocked = 1080,
 };

+enum class AspectRatio {
+    Default,
+    R4_3,
+    R21_9,
+    StretchToWindow,
+};
+
 /// Describes the layout of the window framebuffer
 struct FramebufferLayout {
    u32 width{ScreenUndocked::Width};
@@ -48,4 +55,12 @@ FramebufferLayout DefaultFrameLayout(u32 width, u32 height);
 */
 FramebufferLayout FrameLayoutFromResolutionScale(u32 res_scale);

+/**
+ * Convenience method to determine emulation aspect ratio
+ * @param aspect Represents the index of aspect ratio stored in Settings::values.aspect_ratio
+ * @param window_aspect_ratio Current window aspect ratio
+ * @return Emulation render window aspect ratio
+ */
+float EmulationAspectRatio(AspectRatio aspect, float window_aspect_ratio);
+
 } // namespace Layout
@@ -0,0 +1,47 @@
+// Copyright 2020 yuzu Emulator Project
+// Licensed under GPLv2 or any later version
+// Refer to the license.txt file included.
+
+#pragma once
+
+#include <tuple>
+
+#include "common/common_types.h"
+
+namespace Core {
+
+namespace Hardware {
+
+// The below clock rate is based on Switch's clockspeed being widely known as 1.020GHz
+// The exact value used is of course unverified.
+constexpr u64 BASE_CLOCK_RATE = 1019215872; // Switch cpu frequency is 1020MHz un/docked
+constexpr u64 CNTFREQ = 19200000;           // Switch's hardware clock speed
+constexpr u32 NUM_CPU_CORES = 4;            // Number of CPU Cores
+
+} // namespace Hardware
+
+constexpr u32 INVALID_HOST_THREAD_ID = 0xFFFFFFFF;
+
+struct EmuThreadHandle {
+    u32 host_handle;
+    u32 guest_handle;
+
+    u64 GetRaw() const {
+        return (static_cast<u64>(host_handle) << 32) | guest_handle;
+    }
+
+    bool operator==(const EmuThreadHandle& rhs) const {
+        return std::tie(host_handle, guest_handle) == std::tie(rhs.host_handle, rhs.guest_handle);
+    }
+
+    bool operator!=(const EmuThreadHandle& rhs) const {
+        return !operator==(rhs);
+    }
+
+    static constexpr EmuThreadHandle InvalidHandle() {
+        constexpr u32 invalid_handle = 0xFFFFFFFF;
+        return {invalid_handle, invalid_handle};
+    }
+};
+
+} // namespace Core
@@ -12,7 +12,7 @@

 namespace Kernel {

-ClientSession::ClientSession(KernelCore& kernel) : WaitObject{kernel} {}
+ClientSession::ClientSession(KernelCore& kernel) : SynchronizationObject{kernel} {}

 ClientSession::~ClientSession() {
    // This destructor will be called automatically when the last ClientSession handle is closed by
@@ -31,6 +31,11 @@ void ClientSession::Acquire(Thread* thread) {
    UNIMPLEMENTED();
 }

+bool ClientSession::IsSignaled() const {
+    UNIMPLEMENTED();
+    return true;
+}
+
 ResultVal<std::shared_ptr<ClientSession>> ClientSession::Create(KernelCore& kernel,
                                                                std::shared_ptr<Session> parent,
                                                                std::string name) {
@@ -7,7 +7,7 @@
 #include <memory>
 #include <string>

-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/result.h"

 union ResultCode;
@@ -22,7 +22,7 @@ class KernelCore;
 class Session;
 class Thread;

-class ClientSession final : public WaitObject {
+class ClientSession final : public SynchronizationObject {
 public:
    explicit ClientSession(KernelCore& kernel);
    ~ClientSession() override;
@@ -48,6 +48,8 @@ public:

    void Acquire(Thread* thread) override;

+    bool IsSignaled() const override;
+
 private:
    static ResultVal<std::shared_ptr<ClientSession>> Create(KernelCore& kernel,
                                                            std::shared_ptr<Session> parent,
@@ -47,15 +47,15 @@ std::shared_ptr<WritableEvent> HLERequestContext::SleepClientThread(
    const std::string& reason, u64 timeout, WakeupCallback&& callback,
    std::shared_ptr<WritableEvent> writable_event) {
    // Put the client thread to sleep until the wait event is signaled or the timeout expires.
-    thread->SetWakeupCallback([context = *this, callback](ThreadWakeupReason reason,
-                                                          std::shared_ptr<Thread> thread,
-                                                          std::shared_ptr<WaitObject> object,
-                                                          std::size_t index) mutable -> bool {
-        ASSERT(thread->GetStatus() == ThreadStatus::WaitHLEEvent);
-        callback(thread, context, reason);
-        context.WriteToOutgoingCommandBuffer(*thread);
-        return true;
-    });
+    thread->SetWakeupCallback(
+        [context = *this, callback](ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
+                                    std::shared_ptr<SynchronizationObject> object,
+                                    std::size_t index) mutable -> bool {
+            ASSERT(thread->GetStatus() == ThreadStatus::WaitHLEEvent);
+            callback(thread, context, reason);
+            context.WriteToOutgoingCommandBuffer(*thread);
+            return true;
+        });

    auto& kernel = Core::System::GetInstance().Kernel();
    if (!writable_event) {
@@ -67,7 +67,7 @@ std::shared_ptr<WritableEvent> HLERequestContext::SleepClientThread(
    const auto readable_event{writable_event->GetReadableEvent()};
    writable_event->Clear();
    thread->SetStatus(ThreadStatus::WaitHLEEvent);
-    thread->SetWaitObjects({readable_event});
+    thread->SetSynchronizationObjects({readable_event});
    readable_event->AddWaitingThread(thread);

    if (timeout > 0) {
@@ -3,9 +3,12 @@
 // Refer to the license.txt file included.

 #include <atomic>
+#include <bitset>
 #include <functional>
 #include <memory>
 #include <mutex>
+#include <thread>
+#include <unordered_map>
 #include <utility>

 #include "common/assert.h"
@@ -15,6 +18,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/client_port.h"
 #include "core/hle/kernel/errors.h"
 #include "core/hle/kernel/handle_table.h"
@@ -23,7 +27,9 @@
 #include "core/hle/kernel/process.h"
 #include "core/hle/kernel/resource_limit.h"
 #include "core/hle/kernel/scheduler.h"
+#include "core/hle/kernel/synchronization.h"
 #include "core/hle/kernel/thread.h"
+#include "core/hle/kernel/time_manager.h"
 #include "core/hle/lock.h"
 #include "core/hle/result.h"
 #include "core/memory.h"
@@ -43,7 +49,7 @@ static void ThreadWakeupCallback(u64 thread_handle, [[maybe_unused]] s64 cycles_
    std::lock_guard lock{HLE::g_hle_lock};

    std::shared_ptr<Thread> thread =
-        system.Kernel().RetrieveThreadFromWakeupCallbackHandleTable(proper_handle);
+        system.Kernel().RetrieveThreadFromGlobalHandleTable(proper_handle);
    if (thread == nullptr) {
        LOG_CRITICAL(Kernel, "Callback fired for invalid thread {:08X}", proper_handle);
        return;
@@ -54,10 +60,10 @@ static void ThreadWakeupCallback(u64 thread_handle, [[maybe_unused]] s64 cycles_
    if (thread->GetStatus() == ThreadStatus::WaitSynch ||
        thread->GetStatus() == ThreadStatus::WaitHLEEvent) {
        // Remove the thread from each of its waiting objects' waitlists
-        for (const auto& object : thread->GetWaitObjects()) {
+        for (const auto& object : thread->GetSynchronizationObjects()) {
            object->RemoveWaitingThread(thread);
        }
-        thread->ClearWaitObjects();
+        thread->ClearSynchronizationObjects();

        // Invoke the wakeup callback before clearing the wait objects
        if (thread->HasWakeupCallback()) {
@@ -96,7 +102,8 @@ static void ThreadWakeupCallback(u64 thread_handle, [[maybe_unused]] s64 cycles_
 }

 struct KernelCore::Impl {
-    explicit Impl(Core::System& system) : system{system}, global_scheduler{system} {}
+    explicit Impl(Core::System& system, KernelCore& kernel)
+        : system{system}, global_scheduler{kernel}, synchronization{system}, time_manager{system} {}

    void Initialize(KernelCore& kernel) {
        Shutdown();
@@ -118,7 +125,7 @@ struct KernelCore::Impl {

        system_resource_limit = nullptr;

-        thread_wakeup_callback_handle_table.Clear();
+        global_handle_table.Clear();
        thread_wakeup_event_type = nullptr;
        preemption_event = nullptr;

@@ -136,8 +143,8 @@ struct KernelCore::Impl {

    void InitializePhysicalCores() {
        exclusive_monitor =
-            Core::MakeExclusiveMonitor(system.Memory(), global_scheduler.CpuCoresCount());
-        for (std::size_t i = 0; i < global_scheduler.CpuCoresCount(); i++) {
+            Core::MakeExclusiveMonitor(system.Memory(), Core::Hardware::NUM_CPU_CORES);
+        for (std::size_t i = 0; i < Core::Hardware::NUM_CPU_CORES; i++) {
            cores.emplace_back(system, i, *exclusive_monitor);
        }
    }
@@ -182,6 +189,50 @@ struct KernelCore::Impl {
        system.Memory().SetCurrentPageTable(*process);
    }

+    void RegisterCoreThread(std::size_t core_id) {
+        std::unique_lock lock{register_thread_mutex};
+        const std::thread::id this_id = std::this_thread::get_id();
+        const auto it = host_thread_ids.find(this_id);
+        ASSERT(core_id < Core::Hardware::NUM_CPU_CORES);
+        ASSERT(it == host_thread_ids.end());
+        ASSERT(!registered_core_threads[core_id]);
+        host_thread_ids[this_id] = static_cast<u32>(core_id);
+        registered_core_threads.set(core_id);
+    }
+
+    void RegisterHostThread() {
+        std::unique_lock lock{register_thread_mutex};
+        const std::thread::id this_id = std::this_thread::get_id();
+        const auto it = host_thread_ids.find(this_id);
+        ASSERT(it == host_thread_ids.end());
+        host_thread_ids[this_id] = registered_thread_ids++;
+    }
+
+    u32 GetCurrentHostThreadID() const {
+        const std::thread::id this_id = std::this_thread::get_id();
+        const auto it = host_thread_ids.find(this_id);
+        if (it == host_thread_ids.end()) {
+            return Core::INVALID_HOST_THREAD_ID;
+        }
+        return it->second;
+    }
+
+    Core::EmuThreadHandle GetCurrentEmuThreadID() const {
+        Core::EmuThreadHandle result = Core::EmuThreadHandle::InvalidHandle();
+        result.host_handle = GetCurrentHostThreadID();
+        if (result.host_handle >= Core::Hardware::NUM_CPU_CORES) {
+            return result;
+        }
+        const Kernel::Scheduler& sched = cores[result.host_handle].Scheduler();
+        const Kernel::Thread* current = sched.GetCurrentThread();
+        if (current != nullptr) {
+            result.guest_handle = current->GetGlobalHandle();
+        } else {
+            result.guest_handle = InvalidHandle;
+        }
+        return result;
+    }
+
    std::atomic<u32> next_object_id{0};
    std::atomic<u64> next_kernel_process_id{Process::InitialKIPIDMin};
    std::atomic<u64> next_user_process_id{Process::ProcessIDMin};
@@ -191,15 +242,17 @@ struct KernelCore::Impl {
    std::vector<std::shared_ptr<Process>> process_list;
    Process* current_process = nullptr;
    Kernel::GlobalScheduler global_scheduler;
+    Kernel::Synchronization synchronization;
+    Kernel::TimeManager time_manager;

    std::shared_ptr<ResourceLimit> system_resource_limit;

    std::shared_ptr<Core::Timing::EventType> thread_wakeup_event_type;
    std::shared_ptr<Core::Timing::EventType> preemption_event;

-    // TODO(yuriks): This can be removed if Thread objects are explicitly pooled in the future,
-    // allowing us to simply use a pool index or similar.
-    Kernel::HandleTable thread_wakeup_callback_handle_table;
+    // This is the kernel's handle table or supervisor handle table which
+    // stores all the objects in place.
+    Kernel::HandleTable global_handle_table;

    /// Map of named ports managed by the kernel, which can be retrieved using
    /// the ConnectToPort SVC.
@@ -208,11 +261,17 @@ struct KernelCore::Impl {
    std::unique_ptr<Core::ExclusiveMonitor> exclusive_monitor;
    std::vector<Kernel::PhysicalCore> cores;

+    // 0-3 IDs represent core threads, >3 represent others
+    std::unordered_map<std::thread::id, u32> host_thread_ids;
+    u32 registered_thread_ids{Core::Hardware::NUM_CPU_CORES};
+    std::bitset<Core::Hardware::NUM_CPU_CORES> registered_core_threads;
+    std::mutex register_thread_mutex;
+
    // System context
    Core::System& system;
 };

-KernelCore::KernelCore(Core::System& system) : impl{std::make_unique<Impl>(system)} {}
+KernelCore::KernelCore(Core::System& system) : impl{std::make_unique<Impl>(system, *this)} {}
 KernelCore::~KernelCore() {
    Shutdown();
 }
@@ -229,9 +288,8 @@ std::shared_ptr<ResourceLimit> KernelCore::GetSystemResourceLimit() const {
    return impl->system_resource_limit;
 }

-std::shared_ptr<Thread> KernelCore::RetrieveThreadFromWakeupCallbackHandleTable(
-    Handle handle) const {
-    return impl->thread_wakeup_callback_handle_table.Get<Thread>(handle);
+std::shared_ptr<Thread> KernelCore::RetrieveThreadFromGlobalHandleTable(Handle handle) const {
+    return impl->global_handle_table.Get<Thread>(handle);
 }

 void KernelCore::AppendNewProcess(std::shared_ptr<Process> process) {
@@ -262,6 +320,14 @@ const Kernel::GlobalScheduler& KernelCore::GlobalScheduler() const {
    return impl->global_scheduler;
 }

+Kernel::Scheduler& KernelCore::Scheduler(std::size_t id) {
+    return impl->cores[id].Scheduler();
+}
+
+const Kernel::Scheduler& KernelCore::Scheduler(std::size_t id) const {
+    return impl->cores[id].Scheduler();
+}
+
 Kernel::PhysicalCore& KernelCore::PhysicalCore(std::size_t id) {
    return impl->cores[id];
 }
@@ -270,6 +336,22 @@ const Kernel::PhysicalCore& KernelCore::PhysicalCore(std::size_t id) const {
    return impl->cores[id];
 }

+Kernel::Synchronization& KernelCore::Synchronization() {
+    return impl->synchronization;
+}
+
+const Kernel::Synchronization& KernelCore::Synchronization() const {
+    return impl->synchronization;
+}
+
+Kernel::TimeManager& KernelCore::TimeManager() {
+    return impl->time_manager;
+}
+
+const Kernel::TimeManager& KernelCore::TimeManager() const {
+    return impl->time_manager;
+}
+
 Core::ExclusiveMonitor& KernelCore::GetExclusiveMonitor() {
    return *impl->exclusive_monitor;
 }
@@ -327,12 +409,28 @@ const std::shared_ptr<Core::Timing::EventType>& KernelCore::ThreadWakeupCallback
    return impl->thread_wakeup_event_type;
 }

-Kernel::HandleTable& KernelCore::ThreadWakeupCallbackHandleTable() {
-    return impl->thread_wakeup_callback_handle_table;
+Kernel::HandleTable& KernelCore::GlobalHandleTable() {
+    return impl->global_handle_table;
 }

-const Kernel::HandleTable& KernelCore::ThreadWakeupCallbackHandleTable() const {
-    return impl->thread_wakeup_callback_handle_table;
+const Kernel::HandleTable& KernelCore::GlobalHandleTable() const {
+    return impl->global_handle_table;
+}
+
+void KernelCore::RegisterCoreThread(std::size_t core_id) {
+    impl->RegisterCoreThread(core_id);
+}
+
+void KernelCore::RegisterHostThread() {
+    impl->RegisterHostThread();
+}
+
+u32 KernelCore::GetCurrentHostThreadID() const {
+    return impl->GetCurrentHostThreadID();
+}
+
+Core::EmuThreadHandle KernelCore::GetCurrentEmuThreadID() const {
+    return impl->GetCurrentEmuThreadID();
 }

 } // namespace Kernel
@@ -11,6 +11,7 @@
 #include "core/hle/kernel/object.h"

 namespace Core {
+struct EmuThreadHandle;
 class ExclusiveMonitor;
 class System;
 } // namespace Core
@@ -29,7 +30,10 @@ class HandleTable;
 class PhysicalCore;
 class Process;
 class ResourceLimit;
+class Scheduler;
+class Synchronization;
 class Thread;
+class TimeManager;

 /// Represents a single instance of the kernel.
 class KernelCore {
@@ -63,7 +67,7 @@ public:
    std::shared_ptr<ResourceLimit> GetSystemResourceLimit() const;

    /// Retrieves a shared pointer to a Thread instance within the thread wakeup handle table.
-    std::shared_ptr<Thread> RetrieveThreadFromWakeupCallbackHandleTable(Handle handle) const;
+    std::shared_ptr<Thread> RetrieveThreadFromGlobalHandleTable(Handle handle) const;

    /// Adds the given shared pointer to an internal list of active processes.
    void AppendNewProcess(std::shared_ptr<Process> process);
@@ -86,12 +90,30 @@ public:
    /// Gets the sole instance of the global scheduler
    const Kernel::GlobalScheduler& GlobalScheduler() const;

+    /// Gets the sole instance of the Scheduler assoviated with cpu core 'id'
+    Kernel::Scheduler& Scheduler(std::size_t id);
+
+    /// Gets the sole instance of the Scheduler assoviated with cpu core 'id'
+    const Kernel::Scheduler& Scheduler(std::size_t id) const;
+
    /// Gets the an instance of the respective physical CPU core.
    Kernel::PhysicalCore& PhysicalCore(std::size_t id);

    /// Gets the an instance of the respective physical CPU core.
    const Kernel::PhysicalCore& PhysicalCore(std::size_t id) const;

+    /// Gets the an instance of the Synchronization Interface.
+    Kernel::Synchronization& Synchronization();
+
+    /// Gets the an instance of the Synchronization Interface.
+    const Kernel::Synchronization& Synchronization() const;
+
+    /// Gets the an instance of the TimeManager Interface.
+    Kernel::TimeManager& TimeManager();
+
+    /// Gets the an instance of the TimeManager Interface.
+    const Kernel::TimeManager& TimeManager() const;
+
    /// Stops execution of 'id' core, in order to reschedule a new thread.
    void PrepareReschedule(std::size_t id);

@@ -113,6 +135,18 @@ public:
    /// Determines whether or not the given port is a valid named port.
    bool IsValidNamedPort(NamedPortTable::const_iterator port) const;

+    /// Gets the current host_thread/guest_thread handle.
+    Core::EmuThreadHandle GetCurrentEmuThreadID() const;
+
+    /// Gets the current host_thread handle.
+    u32 GetCurrentHostThreadID() const;
+
+    /// Register the current thread as a CPU Core Thread.
+    void RegisterCoreThread(std::size_t core_id);
+
+    /// Register the current thread as a non CPU core thread.
+    void RegisterHostThread();
+
 private:
    friend class Object;
    friend class Process;
@@ -133,11 +167,11 @@ private:
    /// Retrieves the event type used for thread wakeup callbacks.
    const std::shared_ptr<Core::Timing::EventType>& ThreadWakeupCallbackEventType() const;

-    /// Provides a reference to the thread wakeup callback handle table.
-    Kernel::HandleTable& ThreadWakeupCallbackHandleTable();
+    /// Provides a reference to the global handle table.
+    Kernel::HandleTable& GlobalHandleTable();

-    /// Provides a const reference to the thread wakeup callback handle table.
-    const Kernel::HandleTable& ThreadWakeupCallbackHandleTable() const;
+    /// Provides a const reference to the global handle table.
+    const Kernel::HandleTable& GlobalHandleTable() const;

    struct Impl;
    std::unique_ptr<Impl> impl;
@@ -337,7 +337,7 @@ void Process::LoadModule(CodeSet module_, VAddr base_addr) {
 }

 Process::Process(Core::System& system)
-    : WaitObject{system.Kernel()}, vm_manager{system},
+    : SynchronizationObject{system.Kernel()}, vm_manager{system},
      address_arbiter{system}, mutex{system}, system{system} {}

 Process::~Process() = default;
@@ -357,7 +357,7 @@ void Process::ChangeStatus(ProcessStatus new_status) {

    status = new_status;
    is_signaled = true;
-    WakeupAllWaitingThreads();
+    Signal();
 }

 void Process::AllocateMainThreadStack(u64 stack_size) {
@@ -15,8 +15,8 @@
 #include "core/hle/kernel/handle_table.h"
 #include "core/hle/kernel/mutex.h"
 #include "core/hle/kernel/process_capability.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/kernel/vm_manager.h"
-#include "core/hle/kernel/wait_object.h"
 #include "core/hle/result.h"

 namespace Core {
@@ -60,7 +60,7 @@ enum class ProcessStatus {
    DebugBreak,
 };

-class Process final : public WaitObject {
+class Process final : public SynchronizationObject {
 public:
    explicit Process(Core::System& system);
    ~Process() override;
@@ -359,10 +359,6 @@ private:
    /// specified by metadata provided to the process during loading.
    bool is_64bit_process = true;

-    /// Whether or not this process is signaled. This occurs
-    /// upon the process changing to a different state.
-    bool is_signaled = false;
-
    /// Total running time for the process in ticks.
    u64 total_process_running_time_ticks = 0;

@@ -11,30 +11,30 @@

 namespace Kernel {

-ReadableEvent::ReadableEvent(KernelCore& kernel) : WaitObject{kernel} {}
+ReadableEvent::ReadableEvent(KernelCore& kernel) : SynchronizationObject{kernel} {}
 ReadableEvent::~ReadableEvent() = default;

 bool ReadableEvent::ShouldWait(const Thread* thread) const {
-    return !signaled;
+    return !is_signaled;
 }

 void ReadableEvent::Acquire(Thread* thread) {
-    ASSERT_MSG(!ShouldWait(thread), "object unavailable!");
+    ASSERT_MSG(IsSignaled(), "object unavailable!");
 }

 void ReadableEvent::Signal() {
-    if (!signaled) {
-        signaled = true;
-        WakeupAllWaitingThreads();
+    if (!is_signaled) {
+        is_signaled = true;
+        SynchronizationObject::Signal();
    };
 }

 void ReadableEvent::Clear() {
-    signaled = false;
+    is_signaled = false;
 }

 ResultCode ReadableEvent::Reset() {
-    if (!signaled) {
+    if (!is_signaled) {
        return ERR_INVALID_STATE;
    }

@@ -5,7 +5,7 @@
 #pragma once

 #include "core/hle/kernel/object.h"
-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"

 union ResultCode;

@@ -14,7 +14,7 @@ namespace Kernel {
 class KernelCore;
 class WritableEvent;

-class ReadableEvent final : public WaitObject {
+class ReadableEvent final : public SynchronizationObject {
    friend class WritableEvent;

 public:
@@ -46,13 +46,11 @@ public:
    ///      then ERR_INVALID_STATE will be returned.
    ResultCode Reset();

+    void Signal() override;
+
 private:
    explicit ReadableEvent(KernelCore& kernel);

-    void Signal();
-
-    bool signaled{};
-
    std::string name; ///< Name of event (optional)
 };

@@ -18,10 +18,11 @@
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/kernel/process.h"
 #include "core/hle/kernel/scheduler.h"
+#include "core/hle/kernel/time_manager.h"

 namespace Kernel {

-GlobalScheduler::GlobalScheduler(Core::System& system) : system{system} {}
+GlobalScheduler::GlobalScheduler(KernelCore& kernel) : kernel{kernel} {}

 GlobalScheduler::~GlobalScheduler() = default;

@@ -35,7 +36,7 @@ void GlobalScheduler::RemoveThread(std::shared_ptr<Thread> thread) {
 }

 void GlobalScheduler::UnloadThread(std::size_t core) {
-    Scheduler& sched = system.Scheduler(core);
+    Scheduler& sched = kernel.Scheduler(core);
    sched.UnloadThread();
 }

@@ -50,7 +51,7 @@ void GlobalScheduler::SelectThread(std::size_t core) {
        sched.is_context_switch_pending = sched.selected_thread != sched.current_thread;
        std::atomic_thread_fence(std::memory_order_seq_cst);
    };
-    Scheduler& sched = system.Scheduler(core);
+    Scheduler& sched = kernel.Scheduler(core);
    Thread* current_thread = nullptr;
    // Step 1: Get top thread in schedule queue.
    current_thread = scheduled_queue[core].empty() ? nullptr : scheduled_queue[core].front();
@@ -124,8 +125,8 @@ bool GlobalScheduler::YieldThreadAndBalanceLoad(Thread* yielding_thread) {
               "Thread yielding without being in front");
    scheduled_queue[core_id].yield(priority);

-    std::array<Thread*, NUM_CPU_CORES> current_threads;
-    for (u32 i = 0; i < NUM_CPU_CORES; i++) {
+    std::array<Thread*, Core::Hardware::NUM_CPU_CORES> current_threads;
+    for (std::size_t i = 0; i < current_threads.size(); i++) {
        current_threads[i] = scheduled_queue[i].empty() ? nullptr : scheduled_queue[i].front();
    }

@@ -177,8 +178,8 @@ bool GlobalScheduler::YieldThreadAndWaitForLoadBalancing(Thread* yielding_thread
    // function...
    if (scheduled_queue[core_id].empty()) {
        // Here, "current_threads" is calculated after the ""yield"", unlike yield -1
-        std::array<Thread*, NUM_CPU_CORES> current_threads;
-        for (u32 i = 0; i < NUM_CPU_CORES; i++) {
+        std::array<Thread*, Core::Hardware::NUM_CPU_CORES> current_threads;
+        for (std::size_t i = 0; i < current_threads.size(); i++) {
            current_threads[i] = scheduled_queue[i].empty() ? nullptr : scheduled_queue[i].front();
        }
        for (auto& thread : suggested_queue[core_id]) {
@@ -208,7 +209,7 @@ bool GlobalScheduler::YieldThreadAndWaitForLoadBalancing(Thread* yielding_thread
 }

 void GlobalScheduler::PreemptThreads() {
-    for (std::size_t core_id = 0; core_id < NUM_CPU_CORES; core_id++) {
+    for (std::size_t core_id = 0; core_id < Core::Hardware::NUM_CPU_CORES; core_id++) {
        const u32 priority = preemption_priorities[core_id];

        if (scheduled_queue[core_id].size(priority) > 0) {
@@ -349,13 +350,39 @@ bool GlobalScheduler::AskForReselectionOrMarkRedundant(Thread* current_thread,
 }

 void GlobalScheduler::Shutdown() {
-    for (std::size_t core = 0; core < NUM_CPU_CORES; core++) {
+    for (std::size_t core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
        scheduled_queue[core].clear();
        suggested_queue[core].clear();
    }
    thread_list.clear();
 }

+void GlobalScheduler::Lock() {
+    Core::EmuThreadHandle current_thread = kernel.GetCurrentEmuThreadID();
+    if (current_thread == current_owner) {
+        ++scope_lock;
+    } else {
+        inner_lock.lock();
+        current_owner = current_thread;
+        ASSERT(current_owner != Core::EmuThreadHandle::InvalidHandle());
+        scope_lock = 1;
+    }
+}
+
+void GlobalScheduler::Unlock() {
+    if (--scope_lock != 0) {
+        ASSERT(scope_lock > 0);
+        return;
+    }
+    for (std::size_t i = 0; i < Core::Hardware::NUM_CPU_CORES; i++) {
+        SelectThread(i);
+    }
+    current_owner = Core::EmuThreadHandle::InvalidHandle();
+    scope_lock = 1;
+    inner_lock.unlock();
+    // TODO(Blinkhawk): Setup the interrupts and change context on current core.
+}
+
 Scheduler::Scheduler(Core::System& system, Core::ARM_Interface& cpu_core, std::size_t core_id)
    : system(system), cpu_core(cpu_core), core_id(core_id) {}

@@ -485,4 +512,27 @@ void Scheduler::Shutdown() {
    selected_thread = nullptr;
 }

+SchedulerLock::SchedulerLock(KernelCore& kernel) : kernel{kernel} {
+    kernel.GlobalScheduler().Lock();
+}
+
+SchedulerLock::~SchedulerLock() {
+    kernel.GlobalScheduler().Unlock();
+}
+
+SchedulerLockAndSleep::SchedulerLockAndSleep(KernelCore& kernel, Handle& event_handle,
+                                             Thread* time_task, s64 nanoseconds)
+    : SchedulerLock{kernel}, event_handle{event_handle}, time_task{time_task}, nanoseconds{
+                                                                                   nanoseconds} {
+    event_handle = InvalidHandle;
+}
+
+SchedulerLockAndSleep::~SchedulerLockAndSleep() {
+    if (sleep_cancelled) {
+        return;
+    }
+    auto& time_manager = kernel.TimeManager();
+    time_manager.ScheduleTimeEvent(event_handle, time_task, nanoseconds);
+}
+
 } // namespace Kernel
@@ -6,10 +6,12 @@

 #include <atomic>
 #include <memory>
+#include <mutex>
 #include <vector>

 #include "common/common_types.h"
 #include "common/multi_level_queue.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/thread.h"

 namespace Core {
@@ -19,13 +21,13 @@ class System;

 namespace Kernel {

+class KernelCore;
 class Process;
+class SchedulerLock;

 class GlobalScheduler final {
 public:
-    static constexpr u32 NUM_CPU_CORES = 4;
-
-    explicit GlobalScheduler(Core::System& system);
+    explicit GlobalScheduler(KernelCore& kernel);
    ~GlobalScheduler();

    /// Adds a new thread to the scheduler
@@ -125,7 +127,7 @@ public:
    void PreemptThreads();

    u32 CpuCoresCount() const {
-        return NUM_CPU_CORES;
+        return Core::Hardware::NUM_CPU_CORES;
    }

    void SetReselectionPending() {
@@ -139,6 +141,14 @@ public:
    void Shutdown();

 private:
+    friend class SchedulerLock;
+
+    /// Lock the scheduler to the current thread.
+    void Lock();
+
+    /// Unlocks the scheduler, reselects threads, interrupts cores for rescheduling
+    /// and reschedules current core if needed.
+    void Unlock();
    /**
     * Transfers a thread into an specific core. If the destination_core is -1
     * it will be unscheduled from its source code and added into its suggested
@@ -149,17 +159,24 @@ private:
    bool AskForReselectionOrMarkRedundant(Thread* current_thread, const Thread* winner);

    static constexpr u32 min_regular_priority = 2;
-    std::array<Common::MultiLevelQueue<Thread*, THREADPRIO_COUNT>, NUM_CPU_CORES> scheduled_queue;
-    std::array<Common::MultiLevelQueue<Thread*, THREADPRIO_COUNT>, NUM_CPU_CORES> suggested_queue;
+    std::array<Common::MultiLevelQueue<Thread*, THREADPRIO_COUNT>, Core::Hardware::NUM_CPU_CORES>
+        scheduled_queue;
+    std::array<Common::MultiLevelQueue<Thread*, THREADPRIO_COUNT>, Core::Hardware::NUM_CPU_CORES>
+        suggested_queue;
    std::atomic<bool> is_reselection_pending{false};

    // The priority levels at which the global scheduler preempts threads every 10 ms. They are
    // ordered from Core 0 to Core 3.
-    std::array<u32, NUM_CPU_CORES> preemption_priorities = {59, 59, 59, 62};
+    std::array<u32, Core::Hardware::NUM_CPU_CORES> preemption_priorities = {59, 59, 59, 62};
+
+    /// Scheduler lock mechanisms.
+    std::mutex inner_lock{}; // TODO(Blinkhawk): Replace for a SpinLock
+    std::atomic<s64> scope_lock{};
+    Core::EmuThreadHandle current_owner{Core::EmuThreadHandle::InvalidHandle()};

    /// Lists all thread ids that aren't deleted/etc.
    std::vector<std::shared_ptr<Thread>> thread_list;
-    Core::System& system;
+    KernelCore& kernel;
 };

 class Scheduler final {
@@ -226,4 +243,30 @@ private:
    bool is_context_switch_pending = false;
 };

+class SchedulerLock {
+public:
+    explicit SchedulerLock(KernelCore& kernel);
+    ~SchedulerLock();
+
+protected:
+    KernelCore& kernel;
+};
+
+class SchedulerLockAndSleep : public SchedulerLock {
+public:
+    explicit SchedulerLockAndSleep(KernelCore& kernel, Handle& event_handle, Thread* time_task,
+                                   s64 nanoseconds);
+    ~SchedulerLockAndSleep();
+
+    void CancelSleep() {
+        sleep_cancelled = true;
+    }
+
+private:
+    Handle& event_handle;
+    Thread* time_task;
+    s64 nanoseconds;
+    bool sleep_cancelled{};
+};
+
 } // namespace Kernel
@@ -13,7 +13,7 @@

 namespace Kernel {

-ServerPort::ServerPort(KernelCore& kernel) : WaitObject{kernel} {}
+ServerPort::ServerPort(KernelCore& kernel) : SynchronizationObject{kernel} {}
 ServerPort::~ServerPort() = default;

 ResultVal<std::shared_ptr<ServerSession>> ServerPort::Accept() {
@@ -39,6 +39,10 @@ void ServerPort::Acquire(Thread* thread) {
    ASSERT_MSG(!ShouldWait(thread), "object unavailable!");
 }

+bool ServerPort::IsSignaled() const {
+    return !pending_sessions.empty();
+}
+
 ServerPort::PortPair ServerPort::CreatePortPair(KernelCore& kernel, u32 max_sessions,
                                                std::string name) {
    std::shared_ptr<ServerPort> server_port = std::make_shared<ServerPort>(kernel);
@@ -10,7 +10,7 @@
 #include <vector>
 #include "common/common_types.h"
 #include "core/hle/kernel/object.h"
-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/result.h"

 namespace Kernel {
@@ -20,7 +20,7 @@ class KernelCore;
 class ServerSession;
 class SessionRequestHandler;

-class ServerPort final : public WaitObject {
+class ServerPort final : public SynchronizationObject {
 public:
    explicit ServerPort(KernelCore& kernel);
    ~ServerPort() override;
@@ -82,6 +82,8 @@ public:
    bool ShouldWait(const Thread* thread) const override;
    void Acquire(Thread* thread) override;

+    bool IsSignaled() const override;
+
 private:
    /// ServerSessions waiting to be accepted by the port
    std::vector<std::shared_ptr<ServerSession>> pending_sessions;
@@ -24,7 +24,7 @@

 namespace Kernel {

-ServerSession::ServerSession(KernelCore& kernel) : WaitObject{kernel} {}
+ServerSession::ServerSession(KernelCore& kernel) : SynchronizationObject{kernel} {}
 ServerSession::~ServerSession() = default;

 ResultVal<std::shared_ptr<ServerSession>> ServerSession::Create(KernelCore& kernel,
@@ -50,6 +50,16 @@ bool ServerSession::ShouldWait(const Thread* thread) const {
    return pending_requesting_threads.empty() || currently_handling != nullptr;
 }

+bool ServerSession::IsSignaled() const {
+    // Closed sessions should never wait, an error will be returned from svcReplyAndReceive.
+    if (!parent->Client()) {
+        return true;
+    }
+
+    // Wait if we have no pending requests, or if we're currently handling a request.
+    return !pending_requesting_threads.empty() && currently_handling == nullptr;
+}
+
 void ServerSession::Acquire(Thread* thread) {
    ASSERT_MSG(!ShouldWait(thread), "object unavailable!");
    // We are now handling a request, pop it from the stack.
@@ -10,7 +10,7 @@
 #include <vector>

 #include "common/threadsafe_queue.h"
-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/result.h"

 namespace Memory {
@@ -41,7 +41,7 @@ class Thread;
 * After the server replies to the request, the response is marshalled back to the caller's
 * TLS buffer and control is transferred back to it.
 */
-class ServerSession final : public WaitObject {
+class ServerSession final : public SynchronizationObject {
 public:
    explicit ServerSession(KernelCore& kernel);
    ~ServerSession() override;
@@ -73,6 +73,8 @@ public:
        return parent.get();
    }

+    bool IsSignaled() const override;
+
    /**
     * Sets the HLE handler for the session. This handler will be called to service IPC requests
     * instead of the regular IPC machinery. (The regular IPC machinery is currently not
@@ -9,7 +9,7 @@

 namespace Kernel {

-Session::Session(KernelCore& kernel) : WaitObject{kernel} {}
+Session::Session(KernelCore& kernel) : SynchronizationObject{kernel} {}
 Session::~Session() = default;

 Session::SessionPair Session::Create(KernelCore& kernel, std::string name) {
@@ -29,6 +29,11 @@ bool Session::ShouldWait(const Thread* thread) const {
    return {};
 }

+bool Session::IsSignaled() const {
+    UNIMPLEMENTED();
+    return true;
+}
+
 void Session::Acquire(Thread* thread) {
    UNIMPLEMENTED();
 }
@@ -8,7 +8,7 @@
 #include <string>
 #include <utility>

-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"

 namespace Kernel {

@@ -19,7 +19,7 @@ class ServerSession;
 * Parent structure to link the client and server endpoints of a session with their associated
 * client port.
 */
-class Session final : public WaitObject {
+class Session final : public SynchronizationObject {
 public:
    explicit Session(KernelCore& kernel);
    ~Session() override;
@@ -39,6 +39,8 @@ public:

    bool ShouldWait(const Thread* thread) const override;

+    bool IsSignaled() const override;
+
    void Acquire(Thread* thread) override;

    std::shared_ptr<ClientSession> Client() {
@@ -32,6 +32,7 @@
 #include "core/hle/kernel/shared_memory.h"
 #include "core/hle/kernel/svc.h"
 #include "core/hle/kernel/svc_wrap.h"
+#include "core/hle/kernel/synchronization.h"
 #include "core/hle/kernel/thread.h"
 #include "core/hle/kernel/transfer_memory.h"
 #include "core/hle/kernel/writable_event.h"
@@ -433,22 +434,6 @@ static ResultCode GetProcessId(Core::System& system, u64* process_id, Handle han
    return ERR_INVALID_HANDLE;
 }

-/// Default thread wakeup callback for WaitSynchronization
-static bool DefaultThreadWakeupCallback(ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
-                                        std::shared_ptr<WaitObject> object, std::size_t index) {
-    ASSERT(thread->GetStatus() == ThreadStatus::WaitSynch);
-
-    if (reason == ThreadWakeupReason::Timeout) {
-        thread->SetWaitSynchronizationResult(RESULT_TIMEOUT);
-        return true;
-    }
-
-    ASSERT(reason == ThreadWakeupReason::Signal);
-    thread->SetWaitSynchronizationResult(RESULT_SUCCESS);
-    thread->SetWaitSynchronizationOutput(static_cast<u32>(index));
-    return true;
-};
-
 /// Wait for the given handles to synchronize, timeout after the specified nanoseconds
 static ResultCode WaitSynchronization(Core::System& system, Handle* index, VAddr handles_address,
                                      u64 handle_count, s64 nano_seconds) {
@@ -472,14 +457,14 @@ static ResultCode WaitSynchronization(Core::System& system, Handle* index, VAddr
    }

    auto* const thread = system.CurrentScheduler().GetCurrentThread();
-
-    using ObjectPtr = Thread::ThreadWaitObjects::value_type;
-    Thread::ThreadWaitObjects objects(handle_count);
-    const auto& handle_table = system.Kernel().CurrentProcess()->GetHandleTable();
+    auto& kernel = system.Kernel();
+    using ObjectPtr = Thread::ThreadSynchronizationObjects::value_type;
+    Thread::ThreadSynchronizationObjects objects(handle_count);
+    const auto& handle_table = kernel.CurrentProcess()->GetHandleTable();

    for (u64 i = 0; i < handle_count; ++i) {
        const Handle handle = memory.Read32(handles_address + i * sizeof(Handle));
-        const auto object = handle_table.Get<WaitObject>(handle);
+        const auto object = handle_table.Get<SynchronizationObject>(handle);

        if (object == nullptr) {
            LOG_ERROR(Kernel_SVC, "Object is a nullptr");
@@ -488,47 +473,10 @@ static ResultCode WaitSynchronization(Core::System& system, Handle* index, VAddr

        objects[i] = object;
    }
-
-    // Find the first object that is acquirable in the provided list of objects
-    auto itr = std::find_if(objects.begin(), objects.end(), [thread](const ObjectPtr& object) {
-        return !object->ShouldWait(thread);
-    });
-
-    if (itr != objects.end()) {
-        // We found a ready object, acquire it and set the result value
-        WaitObject* object = itr->get();
-        object->Acquire(thread);
-        *index = static_cast<s32>(std::distance(objects.begin(), itr));
-        return RESULT_SUCCESS;
-    }
-
-    // No objects were ready to be acquired, prepare to suspend the thread.
-
-    // If a timeout value of 0 was provided, just return the Timeout error code instead of
-    // suspending the thread.
-    if (nano_seconds == 0) {
-        return RESULT_TIMEOUT;
-    }
-
-    if (thread->IsSyncCancelled()) {
-        thread->SetSyncCancelled(false);
-        return ERR_SYNCHRONIZATION_CANCELED;
-    }
-
-    for (auto& object : objects) {
-        object->AddWaitingThread(SharedFrom(thread));
-    }
-
-    thread->SetWaitObjects(std::move(objects));
-    thread->SetStatus(ThreadStatus::WaitSynch);
-
-    // Create an event to wake the thread up after the specified nanosecond delay has passed
-    thread->WakeAfterDelay(nano_seconds);
-    thread->SetWakeupCallback(DefaultThreadWakeupCallback);
-
-    system.PrepareReschedule(thread->GetProcessorID());
-
-    return RESULT_TIMEOUT;
+    auto& synchronization = kernel.Synchronization();
+    const auto [result, handle_result] = synchronization.WaitFor(objects, nano_seconds);
+    *index = handle_result;
+    return result;
 }

 /// Resumes a thread waiting on WaitSynchronization
@@ -0,0 +1,87 @@
+// Copyright 2020 yuzu Emulator Project
+// Licensed under GPLv2 or any later version
+// Refer to the license.txt file included.
+
+#include "core/core.h"
+#include "core/hle/kernel/errors.h"
+#include "core/hle/kernel/handle_table.h"
+#include "core/hle/kernel/kernel.h"
+#include "core/hle/kernel/scheduler.h"
+#include "core/hle/kernel/synchronization.h"
+#include "core/hle/kernel/synchronization_object.h"
+#include "core/hle/kernel/thread.h"
+
+namespace Kernel {
+
+/// Default thread wakeup callback for WaitSynchronization
+static bool DefaultThreadWakeupCallback(ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
+                                        std::shared_ptr<SynchronizationObject> object,
+                                        std::size_t index) {
+    ASSERT(thread->GetStatus() == ThreadStatus::WaitSynch);
+
+    if (reason == ThreadWakeupReason::Timeout) {
+        thread->SetWaitSynchronizationResult(RESULT_TIMEOUT);
+        return true;
+    }
+
+    ASSERT(reason == ThreadWakeupReason::Signal);
+    thread->SetWaitSynchronizationResult(RESULT_SUCCESS);
+    thread->SetWaitSynchronizationOutput(static_cast<u32>(index));
+    return true;
+}
+
+Synchronization::Synchronization(Core::System& system) : system{system} {}
+
+void Synchronization::SignalObject(SynchronizationObject& obj) const {
+    if (obj.IsSignaled()) {
+        obj.WakeupAllWaitingThreads();
+    }
+}
+
+std::pair<ResultCode, Handle> Synchronization::WaitFor(
+    std::vector<std::shared_ptr<SynchronizationObject>>& sync_objects, s64 nano_seconds) {
+    auto* const thread = system.CurrentScheduler().GetCurrentThread();
+    // Find the first object that is acquirable in the provided list of objects
+    const auto itr = std::find_if(sync_objects.begin(), sync_objects.end(),
+                                  [thread](const std::shared_ptr<SynchronizationObject>& object) {
+                                      return object->IsSignaled();
+                                  });
+
+    if (itr != sync_objects.end()) {
+        // We found a ready object, acquire it and set the result value
+        SynchronizationObject* object = itr->get();
+        object->Acquire(thread);
+        const u32 index = static_cast<s32>(std::distance(sync_objects.begin(), itr));
+        return {RESULT_SUCCESS, index};
+    }
+
+    // No objects were ready to be acquired, prepare to suspend the thread.
+
+    // If a timeout value of 0 was provided, just return the Timeout error code instead of
+    // suspending the thread.
+    if (nano_seconds == 0) {
+        return {RESULT_TIMEOUT, InvalidHandle};
+    }
+
+    if (thread->IsSyncCancelled()) {
+        thread->SetSyncCancelled(false);
+        return {ERR_SYNCHRONIZATION_CANCELED, InvalidHandle};
+    }
+
+    for (auto& object : sync_objects) {
+        object->AddWaitingThread(SharedFrom(thread));
+    }
+
+    thread->SetSynchronizationObjects(std::move(sync_objects));
+    thread->SetStatus(ThreadStatus::WaitSynch);
+
+    // Create an event to wake the thread up after the specified nanosecond delay has passed
+    thread->WakeAfterDelay(nano_seconds);
+    thread->SetWakeupCallback(DefaultThreadWakeupCallback);
+
+    system.PrepareReschedule(thread->GetProcessorID());
+
+    return {RESULT_TIMEOUT, InvalidHandle};
+}
+
+} // namespace Kernel
@@ -0,0 +1,44 @@
+// Copyright 2020 yuzu Emulator Project
+// Licensed under GPLv2 or any later version
+// Refer to the license.txt file included.
+
+#pragma once
+
+#include <memory>
+#include <utility>
+#include <vector>
+
+#include "core/hle/kernel/object.h"
+#include "core/hle/result.h"
+
+namespace Core {
+class System;
+} // namespace Core
+
+namespace Kernel {
+
+class SynchronizationObject;
+
+/**
+ * The 'Synchronization' class is an interface for handling synchronization methods
+ * used by Synchronization objects and synchronization SVCs. This centralizes processing of
+ * such
+ */
+class Synchronization {
+public:
+    explicit Synchronization(Core::System& system);
+
+    /// Signals a synchronization object, waking up all its waiting threads
+    void SignalObject(SynchronizationObject& obj) const;
+
+    /// Tries to see if waiting for any of the sync_objects is necessary, if not
+    /// it returns Success and the handle index of the signaled sync object. In
+    /// case not, the current thread will be locked and wait for nano_seconds or
+    /// for a synchronization object to signal.
+    std::pair<ResultCode, Handle> WaitFor(
+        std::vector<std::shared_ptr<SynchronizationObject>>& sync_objects, s64 nano_seconds);
+
+private:
+    Core::System& system;
+};
+} // namespace Kernel
@@ -10,20 +10,26 @@
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/kernel/object.h"
 #include "core/hle/kernel/process.h"
+#include "core/hle/kernel/synchronization.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/kernel/thread.h"

 namespace Kernel {

-WaitObject::WaitObject(KernelCore& kernel) : Object{kernel} {}
-WaitObject::~WaitObject() = default;
+SynchronizationObject::SynchronizationObject(KernelCore& kernel) : Object{kernel} {}
+SynchronizationObject::~SynchronizationObject() = default;

-void WaitObject::AddWaitingThread(std::shared_ptr<Thread> thread) {
+void SynchronizationObject::Signal() {
+    kernel.Synchronization().SignalObject(*this);
+}
+
+void SynchronizationObject::AddWaitingThread(std::shared_ptr<Thread> thread) {
    auto itr = std::find(waiting_threads.begin(), waiting_threads.end(), thread);
    if (itr == waiting_threads.end())
        waiting_threads.push_back(std::move(thread));
 }

-void WaitObject::RemoveWaitingThread(std::shared_ptr<Thread> thread) {
+void SynchronizationObject::RemoveWaitingThread(std::shared_ptr<Thread> thread) {
    auto itr = std::find(waiting_threads.begin(), waiting_threads.end(), thread);
    // If a thread passed multiple handles to the same object,
    // the kernel might attempt to remove the thread from the object's
@@ -32,7 +38,7 @@ void WaitObject::RemoveWaitingThread(std::shared_ptr<Thread> thread) {
        waiting_threads.erase(itr);
 }

-std::shared_ptr<Thread> WaitObject::GetHighestPriorityReadyThread() const {
+std::shared_ptr<Thread> SynchronizationObject::GetHighestPriorityReadyThread() const {
    Thread* candidate = nullptr;
    u32 candidate_priority = THREADPRIO_LOWEST + 1;

@@ -57,7 +63,7 @@ std::shared_ptr<Thread> WaitObject::GetHighestPriorityReadyThread() const {
    return SharedFrom(candidate);
 }

-void WaitObject::WakeupWaitingThread(std::shared_ptr<Thread> thread) {
+void SynchronizationObject::WakeupWaitingThread(std::shared_ptr<Thread> thread) {
    ASSERT(!ShouldWait(thread.get()));

    if (!thread) {
@@ -65,7 +71,7 @@ void WaitObject::WakeupWaitingThread(std::shared_ptr<Thread> thread) {
    }

    if (thread->IsSleepingOnWait()) {
-        for (const auto& object : thread->GetWaitObjects()) {
+        for (const auto& object : thread->GetSynchronizationObjects()) {
            ASSERT(!object->ShouldWait(thread.get()));
            object->Acquire(thread.get());
        }
@@ -73,9 +79,9 @@ void WaitObject::WakeupWaitingThread(std::shared_ptr<Thread> thread) {
        Acquire(thread.get());
    }

-    const std::size_t index = thread->GetWaitObjectIndex(SharedFrom(this));
+    const std::size_t index = thread->GetSynchronizationObjectIndex(SharedFrom(this));

-    thread->ClearWaitObjects();
+    thread->ClearSynchronizationObjects();

    thread->CancelWakeupTimer();

@@ -90,13 +96,13 @@ void WaitObject::WakeupWaitingThread(std::shared_ptr<Thread> thread) {
    }
 }

-void WaitObject::WakeupAllWaitingThreads() {
+void SynchronizationObject::WakeupAllWaitingThreads() {
    while (auto thread = GetHighestPriorityReadyThread()) {
        WakeupWaitingThread(thread);
    }
 }

-const std::vector<std::shared_ptr<Thread>>& WaitObject::GetWaitingThreads() const {
+const std::vector<std::shared_ptr<Thread>>& SynchronizationObject::GetWaitingThreads() const {
    return waiting_threads;
 }

@@ -15,10 +15,10 @@ class KernelCore;
 class Thread;

 /// Class that represents a Kernel object that a thread can be waiting on
-class WaitObject : public Object {
+class SynchronizationObject : public Object {
 public:
-    explicit WaitObject(KernelCore& kernel);
-    ~WaitObject() override;
+    explicit SynchronizationObject(KernelCore& kernel);
+    ~SynchronizationObject() override;

    /**
     * Check if the specified thread should wait until the object is available
@@ -30,6 +30,13 @@ public:
    /// Acquire/lock the object for the specified thread if it is available
    virtual void Acquire(Thread* thread) = 0;

+    /// Signal this object
+    virtual void Signal();
+
+    virtual bool IsSignaled() const {
+        return is_signaled;
+    }
+
    /**
     * Add a thread to wait on this object
     * @param thread Pointer to thread to add
@@ -60,16 +67,20 @@ public:
    /// Get a const reference to the waiting threads list for debug use
    const std::vector<std::shared_ptr<Thread>>& GetWaitingThreads() const;

+protected:
+    bool is_signaled{}; // Tells if this sync object is signalled;
+
 private:
    /// Threads waiting for this object to become available
    std::vector<std::shared_ptr<Thread>> waiting_threads;
 };

-// Specialization of DynamicObjectCast for WaitObjects
+// Specialization of DynamicObjectCast for SynchronizationObjects
 template <>
-inline std::shared_ptr<WaitObject> DynamicObjectCast<WaitObject>(std::shared_ptr<Object> object) {
+inline std::shared_ptr<SynchronizationObject> DynamicObjectCast<SynchronizationObject>(
+    std::shared_ptr<Object> object) {
    if (object != nullptr && object->IsWaitable()) {
-        return std::static_pointer_cast<WaitObject>(object);
+        return std::static_pointer_cast<SynchronizationObject>(object);
    }
    return nullptr;
 }
@@ -15,6 +15,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/errors.h"
 #include "core/hle/kernel/handle_table.h"
 #include "core/hle/kernel/kernel.h"
@@ -31,21 +32,25 @@ bool Thread::ShouldWait(const Thread* thread) const {
    return status != ThreadStatus::Dead;
 }

+bool Thread::IsSignaled() const {
+    return status == ThreadStatus::Dead;
+}
+
 void Thread::Acquire(Thread* thread) {
    ASSERT_MSG(!ShouldWait(thread), "object unavailable!");
 }

-Thread::Thread(KernelCore& kernel) : WaitObject{kernel} {}
+Thread::Thread(KernelCore& kernel) : SynchronizationObject{kernel} {}
 Thread::~Thread() = default;

 void Thread::Stop() {
    // Cancel any outstanding wakeup events for this thread
    Core::System::GetInstance().CoreTiming().UnscheduleEvent(kernel.ThreadWakeupCallbackEventType(),
-                                                             callback_handle);
-    kernel.ThreadWakeupCallbackHandleTable().Close(callback_handle);
-    callback_handle = 0;
+                                                             global_handle);
+    kernel.GlobalHandleTable().Close(global_handle);
+    global_handle = 0;
    SetStatus(ThreadStatus::Dead);
-    WakeupAllWaitingThreads();
+    Signal();

    // Clean up any dangling references in objects that this thread was waiting for
    for (auto& wait_object : wait_objects) {
@@ -68,12 +73,12 @@ void Thread::WakeAfterDelay(s64 nanoseconds) {
    // thread-safe version of ScheduleEvent.
    const s64 cycles = Core::Timing::nsToCycles(std::chrono::nanoseconds{nanoseconds});
    Core::System::GetInstance().CoreTiming().ScheduleEvent(
-        cycles, kernel.ThreadWakeupCallbackEventType(), callback_handle);
+        cycles, kernel.ThreadWakeupCallbackEventType(), global_handle);
 }

 void Thread::CancelWakeupTimer() {
    Core::System::GetInstance().CoreTiming().UnscheduleEvent(kernel.ThreadWakeupCallbackEventType(),
-                                                             callback_handle);
+                                                             global_handle);
 }

 void Thread::ResumeFromWait() {
@@ -185,7 +190,7 @@ ResultVal<std::shared_ptr<Thread>> Thread::Create(KernelCore& kernel, std::strin
    thread->condvar_wait_address = 0;
    thread->wait_handle = 0;
    thread->name = std::move(name);
-    thread->callback_handle = kernel.ThreadWakeupCallbackHandleTable().Create(thread).Unwrap();
+    thread->global_handle = kernel.GlobalHandleTable().Create(thread).Unwrap();
    thread->owner_process = &owner_process;
    auto& scheduler = kernel.GlobalScheduler();
    scheduler.AddThread(thread);
@@ -215,7 +220,7 @@ void Thread::SetWaitSynchronizationOutput(s32 output) {
    context.cpu_registers[1] = output;
 }

-s32 Thread::GetWaitObjectIndex(std::shared_ptr<WaitObject> object) const {
+s32 Thread::GetSynchronizationObjectIndex(std::shared_ptr<SynchronizationObject> object) const {
    ASSERT_MSG(!wait_objects.empty(), "Thread is not waiting for anything");
    const auto match = std::find(wait_objects.rbegin(), wait_objects.rend(), object);
    return static_cast<s32>(std::distance(match, wait_objects.rend()) - 1);
@@ -336,14 +341,16 @@ void Thread::ChangeCore(u32 core, u64 mask) {
    SetCoreAndAffinityMask(core, mask);
 }

-bool Thread::AllWaitObjectsReady() const {
-    return std::none_of(
-        wait_objects.begin(), wait_objects.end(),
-        [this](const std::shared_ptr<WaitObject>& object) { return object->ShouldWait(this); });
+bool Thread::AllSynchronizationObjectsReady() const {
+    return std::none_of(wait_objects.begin(), wait_objects.end(),
+                        [this](const std::shared_ptr<SynchronizationObject>& object) {
+                            return object->ShouldWait(this);
+                        });
 }

 bool Thread::InvokeWakeupCallback(ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
-                                  std::shared_ptr<WaitObject> object, std::size_t index) {
+                                  std::shared_ptr<SynchronizationObject> object,
+                                  std::size_t index) {
    ASSERT(wakeup_callback);
    return wakeup_callback(reason, std::move(thread), std::move(object), index);
 }
@@ -425,7 +432,7 @@ ResultCode Thread::SetCoreAndAffinityMask(s32 new_core, u64 new_affinity_mask) {
            const s32 old_core = processor_id;
            if (processor_id >= 0 && ((affinity_mask >> processor_id) & 1) == 0) {
                if (static_cast<s32>(ideal_core) < 0) {
-                    processor_id = HighestSetCore(affinity_mask, GlobalScheduler::NUM_CPU_CORES);
+                    processor_id = HighestSetCore(affinity_mask, Core::Hardware::NUM_CPU_CORES);
                } else {
                    processor_id = ideal_core;
                }
@@ -449,7 +456,7 @@ void Thread::AdjustSchedulingOnStatus(u32 old_flags) {
            scheduler.Unschedule(current_priority, static_cast<u32>(processor_id), this);
        }

-        for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+        for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
            if (core != static_cast<u32>(processor_id) && ((affinity_mask >> core) & 1) != 0) {
                scheduler.Unsuggest(current_priority, core, this);
            }
@@ -460,7 +467,7 @@ void Thread::AdjustSchedulingOnStatus(u32 old_flags) {
            scheduler.Schedule(current_priority, static_cast<u32>(processor_id), this);
        }

-        for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+        for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
            if (core != static_cast<u32>(processor_id) && ((affinity_mask >> core) & 1) != 0) {
                scheduler.Suggest(current_priority, core, this);
            }
@@ -479,7 +486,7 @@ void Thread::AdjustSchedulingOnPriority(u32 old_priority) {
        scheduler.Unschedule(old_priority, static_cast<u32>(processor_id), this);
    }

-    for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+    for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
        if (core != static_cast<u32>(processor_id) && ((affinity_mask >> core) & 1) != 0) {
            scheduler.Unsuggest(old_priority, core, this);
        }
@@ -496,7 +503,7 @@ void Thread::AdjustSchedulingOnPriority(u32 old_priority) {
        }
    }

-    for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+    for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
        if (core != static_cast<u32>(processor_id) && ((affinity_mask >> core) & 1) != 0) {
            scheduler.Suggest(current_priority, core, this);
        }
@@ -512,7 +519,7 @@ void Thread::AdjustSchedulingOnAffinity(u64 old_affinity_mask, s32 old_core) {
        return;
    }

-    for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+    for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
        if (((old_affinity_mask >> core) & 1) != 0) {
            if (core == static_cast<u32>(old_core)) {
                scheduler.Unschedule(current_priority, core, this);
@@ -522,7 +529,7 @@ void Thread::AdjustSchedulingOnAffinity(u64 old_affinity_mask, s32 old_core) {
        }
    }

-    for (u32 core = 0; core < GlobalScheduler::NUM_CPU_CORES; core++) {
+    for (u32 core = 0; core < Core::Hardware::NUM_CPU_CORES; core++) {
        if (((affinity_mask >> core) & 1) != 0) {
            if (core == static_cast<u32>(processor_id)) {
                scheduler.Schedule(current_priority, core, this);
@@ -11,7 +11,7 @@
 #include "common/common_types.h"
 #include "core/arm/arm_interface.h"
 #include "core/hle/kernel/object.h"
-#include "core/hle/kernel/wait_object.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/result.h"

 namespace Kernel {
@@ -95,7 +95,7 @@ enum class ThreadSchedMasks : u32 {
    ForcePauseMask = 0x0070,
 };

-class Thread final : public WaitObject {
+class Thread final : public SynchronizationObject {
 public:
    explicit Thread(KernelCore& kernel);
    ~Thread() override;
@@ -104,11 +104,11 @@ public:

    using ThreadContext = Core::ARM_Interface::ThreadContext;

-    using ThreadWaitObjects = std::vector<std::shared_ptr<WaitObject>>;
+    using ThreadSynchronizationObjects = std::vector<std::shared_ptr<SynchronizationObject>>;

    using WakeupCallback =
        std::function<bool(ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
-                           std::shared_ptr<WaitObject> object, std::size_t index)>;
+                           std::shared_ptr<SynchronizationObject> object, std::size_t index)>;

    /**
     * Creates and returns a new thread. The new thread is immediately scheduled
@@ -146,6 +146,7 @@ public:

    bool ShouldWait(const Thread* thread) const override;
    void Acquire(Thread* thread) override;
+    bool IsSignaled() const override;

    /**
     * Gets the thread's current priority
@@ -233,7 +234,7 @@ public:
     *
     * @param object Object to query the index of.
     */
-    s32 GetWaitObjectIndex(std::shared_ptr<WaitObject> object) const;
+    s32 GetSynchronizationObjectIndex(std::shared_ptr<SynchronizationObject> object) const;

    /**
     * Stops a thread, invalidating it from further use
@@ -314,15 +315,15 @@ public:
        return owner_process;
    }

-    const ThreadWaitObjects& GetWaitObjects() const {
+    const ThreadSynchronizationObjects& GetSynchronizationObjects() const {
        return wait_objects;
    }

-    void SetWaitObjects(ThreadWaitObjects objects) {
+    void SetSynchronizationObjects(ThreadSynchronizationObjects objects) {
        wait_objects = std::move(objects);
    }

-    void ClearWaitObjects() {
+    void ClearSynchronizationObjects() {
        for (const auto& waiting_object : wait_objects) {
            waiting_object->RemoveWaitingThread(SharedFrom(this));
        }
@@ -330,7 +331,7 @@ public:
    }

    /// Determines whether all the objects this thread is waiting on are ready.
-    bool AllWaitObjectsReady() const;
+    bool AllSynchronizationObjectsReady() const;

    const MutexWaitingThreads& GetMutexWaitingThreads() const {
        return wait_mutex_threads;
@@ -395,7 +396,7 @@ public:
     *      will cause an assertion to trigger.
     */
    bool InvokeWakeupCallback(ThreadWakeupReason reason, std::shared_ptr<Thread> thread,
-                              std::shared_ptr<WaitObject> object, std::size_t index);
+                              std::shared_ptr<SynchronizationObject> object, std::size_t index);

    u32 GetIdealCore() const {
        return ideal_core;
@@ -452,6 +453,10 @@ public:
        is_sync_cancelled = value;
    }

+    Handle GetGlobalHandle() const {
+        return global_handle;
+    }
+
 private:
    void SetSchedulingStatus(ThreadSchedStatus new_status);
    void SetCurrentPriority(u32 new_priority);
@@ -494,7 +499,7 @@ private:

    /// Objects that the thread is waiting on, in the same order as they were
    /// passed to WaitSynchronization.
-    ThreadWaitObjects wait_objects;
+    ThreadSynchronizationObjects wait_objects;

    /// List of threads that are waiting for a mutex that is held by this thread.
    MutexWaitingThreads wait_mutex_threads;
@@ -513,7 +518,7 @@ private:
    VAddr arb_wait_address{0};

    /// Handle used as userdata to reference this object when inserting into the CoreTiming queue.
-    Handle callback_handle = 0;
+    Handle global_handle = 0;

    /// Callback that will be invoked when the thread is resumed from a waiting state. If the thread
    /// was waiting via WaitSynchronization then the object will be the last object that became
@@ -0,0 +1,44 @@
+// Copyright 2020 yuzu Emulator Project
+// Licensed under GPLv2 or any later version
+// Refer to the license.txt file included.
+
+#include "common/assert.h"
+#include "core/core.h"
+#include "core/core_timing.h"
+#include "core/core_timing_util.h"
+#include "core/hle/kernel/handle_table.h"
+#include "core/hle/kernel/kernel.h"
+#include "core/hle/kernel/thread.h"
+#include "core/hle/kernel/time_manager.h"
+
+namespace Kernel {
+
+TimeManager::TimeManager(Core::System& system) : system{system} {
+    time_manager_event_type = Core::Timing::CreateEvent(
+        "Kernel::TimeManagerCallback", [this](u64 thread_handle, [[maybe_unused]] s64 cycles_late) {
+            Handle proper_handle = static_cast<Handle>(thread_handle);
+            std::shared_ptr<Thread> thread =
+                this->system.Kernel().RetrieveThreadFromGlobalHandleTable(proper_handle);
+            thread->ResumeFromWait();
+        });
+}
+
+void TimeManager::ScheduleTimeEvent(Handle& event_handle, Thread* timetask, s64 nanoseconds) {
+    if (nanoseconds > 0) {
+        ASSERT(timetask);
+        event_handle = timetask->GetGlobalHandle();
+        const s64 cycles = Core::Timing::nsToCycles(std::chrono::nanoseconds{nanoseconds});
+        system.CoreTiming().ScheduleEvent(cycles, time_manager_event_type, event_handle);
+    } else {
+        event_handle = InvalidHandle;
+    }
+}
+
+void TimeManager::UnscheduleTimeEvent(Handle event_handle) {
+    if (event_handle == InvalidHandle) {
+        return;
+    }
+    system.CoreTiming().UnscheduleEvent(time_manager_event_type, event_handle);
+}
+
+} // namespace Kernel
@@ -0,0 +1,43 @@
+// Copyright 2020 yuzu Emulator Project
+// Licensed under GPLv2 or any later version
+// Refer to the license.txt file included.
+
+#pragma once
+
+#include <memory>
+
+#include "core/hle/kernel/object.h"
+
+namespace Core {
+class System;
+} // namespace Core
+
+namespace Core::Timing {
+struct EventType;
+} // namespace Core::Timing
+
+namespace Kernel {
+
+class Thread;
+
+/**
+ * The `TimeManager` takes care of scheduling time events on threads and executes their TimeUp
+ * method when the event is triggered.
+ */
+class TimeManager {
+public:
+    explicit TimeManager(Core::System& system);
+
+    /// Schedule a time event on `timetask` thread that will expire in 'nanoseconds'
+    /// returns a non-invalid handle in `event_handle` if correctly scheduled
+    void ScheduleTimeEvent(Handle& event_handle, Thread* timetask, s64 nanoseconds);
+
+    /// Unschedule an existing time event
+    void UnscheduleTimeEvent(Handle event_handle);
+
+private:
+    Core::System& system;
+    std::shared_ptr<Core::Timing::EventType> time_manager_event_type;
+};
+
+} // namespace Kernel
@@ -22,7 +22,6 @@ EventPair WritableEvent::CreateEventPair(KernelCore& kernel, std::string name) {
    writable_event->name = name + ":Writable";
    writable_event->readable = readable_event;
    readable_event->name = name + ":Readable";
-    readable_event->signaled = false;

    return {std::move(readable_event), std::move(writable_event)};
 }
@@ -40,7 +39,7 @@ void WritableEvent::Clear() {
 }

 bool WritableEvent::IsSignaled() const {
-    return readable->signaled;
+    return readable->IsSignaled();
 }

 } // namespace Kernel
@@ -170,8 +170,10 @@ public:
            {3, nullptr, "SetContextForMultiStream"},
            {4, &IHardwareOpusDecoderManager::DecodeInterleavedWithPerfOld, "DecodeInterleavedWithPerfOld"},
            {5, nullptr, "DecodeInterleavedForMultiStreamWithPerfOld"},
-            {6, &IHardwareOpusDecoderManager::DecodeInterleaved, "DecodeInterleaved"},
-            {7, nullptr, "DecodeInterleavedForMultiStream"},
+            {6, &IHardwareOpusDecoderManager::DecodeInterleaved, "DecodeInterleavedWithPerfAndResetOld"},
+            {7, nullptr, "DecodeInterleavedForMultiStreamWithPerfAndResetOld"},
+            {8, &IHardwareOpusDecoderManager::DecodeInterleaved, "DecodeInterleaved"},
+            {9, nullptr, "DecodeInterleavedForMultiStream"},
        };
        // clang-format on

@@ -200,7 +200,8 @@ private:
    DownloadResult DownloadInternal(const std::string& resolved_path, u32 timeout_seconds,
                                    const std::string& content_type_name) {
        if (client == nullptr) {
-            client = std::make_unique<httplib::SSLClient>(BOXCAT_HOSTNAME, PORT, timeout_seconds);
+            client = std::make_unique<httplib::SSLClient>(BOXCAT_HOSTNAME, PORT);
+            client->set_timeout_sec(timeout_seconds);
        }

        httplib::Headers headers{
@@ -448,8 +449,8 @@ std::optional<std::vector<u8>> Boxcat::GetLaunchParameter(TitleIDVersion title)

 Boxcat::StatusResult Boxcat::GetStatus(std::optional<std::string>& global,
                                       std::map<std::string, EventStatus>& games) {
-    httplib::SSLClient client{BOXCAT_HOSTNAME, static_cast<int>(PORT),
-                              static_cast<int>(TIMEOUT_SECONDS)};
+    httplib::SSLClient client{BOXCAT_HOSTNAME, static_cast<int>(PORT)};
+    client.set_timeout_sec(static_cast<int>(TIMEOUT_SECONDS));

    httplib::Headers headers{
        {std::string("Game-Assets-API-Version"), std::string(BOXCAT_API_VERSION)},
@@ -10,6 +10,7 @@
 #include "core/core_timing_util.h"
 #include "core/frontend/emu_window.h"
 #include "core/frontend/input.h"
+#include "core/hardware_properties.h"
 #include "core/hle/ipc_helpers.h"
 #include "core/hle/kernel/client_port.h"
 #include "core/hle/kernel/client_session.h"
@@ -37,11 +38,11 @@ namespace Service::HID {

 // Updating period for each HID device.
 // TODO(ogniK): Find actual polling rate of hid
-constexpr s64 pad_update_ticks = static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 66);
+constexpr s64 pad_update_ticks = static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 66);
 [[maybe_unused]] constexpr s64 accelerometer_update_ticks =
-    static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 100);
+    static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 100);
 [[maybe_unused]] constexpr s64 gyroscope_update_ticks =
-    static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 100);
+    static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 100);
 constexpr std::size_t SHARED_MEMORY_SIZE = 0x40000;

 IAppletResource::IAppletResource(Core::System& system)
@@ -129,12 +129,20 @@ public:
            {304, nullptr, "Disconnect"},
            {400, nullptr, "Initialize"},
            {401, nullptr, "Finalize"},
-            {402, nullptr, "SetOperationMode"},
+            {402, &IUserLocalCommunicationService::Initialize2, "Initialize2"}, // 7.0.0+
        };
        // clang-format on

        RegisterHandlers(functions);
    }
+
+    void Initialize2(Kernel::HLERequestContext& ctx) {
+        LOG_WARNING(Service_LDN, "(STUBBED) called");
+        // Result success seem make this services start network and continue.
+        // If we just pass result error then it will stop and maybe try again and again.
+        IPC::ResponseBuilder rb{ctx, 2};
+        rb.Push(RESULT_UNKNOWN);
+    }
 };

 class LDNS final : public ServiceFramework<LDNS> {
@@ -44,6 +44,8 @@ u32 nvhost_gpu::ioctl(Ioctl command, const std::vector<u8>& input, const std::ve
        return GetWaitbase(input, output);
    case IoctlCommand::IocChannelSetTimeoutCommand:
        return ChannelSetTimeout(input, output);
+    case IoctlCommand::IocChannelSetTimeslice:
+        return ChannelSetTimeslice(input, output);
    default:
        break;
    }
@@ -228,4 +230,14 @@ u32 nvhost_gpu::ChannelSetTimeout(const std::vector<u8>& input, std::vector<u8>&
    return 0;
 }

+u32 nvhost_gpu::ChannelSetTimeslice(const std::vector<u8>& input, std::vector<u8>& output) {
+    IoctlSetTimeslice params{};
+    std::memcpy(&params, input.data(), sizeof(IoctlSetTimeslice));
+    LOG_INFO(Service_NVDRV, "called, timeslice=0x{:X}", params.timeslice);
+
+    channel_timeslice = params.timeslice;
+
+    return 0;
+}
+
 } // namespace Service::Nvidia::Devices
@@ -48,6 +48,7 @@ private:
        IocAllocObjCtxCommand = 0xC0104809,
        IocChannelGetWaitbaseCommand = 0xC0080003,
        IocChannelSetTimeoutCommand = 0x40044803,
+        IocChannelSetTimeslice = 0xC004481D,
    };

    enum class CtxObjects : u32_le {
@@ -101,6 +102,11 @@ private:
    static_assert(sizeof(IoctlChannelSetPriority) == 4,
                  "IoctlChannelSetPriority is incorrect size");

+    struct IoctlSetTimeslice {
+        u32_le timeslice;
+    };
+    static_assert(sizeof(IoctlSetTimeslice) == 4, "IoctlSetTimeslice is incorrect size");
+
    struct IoctlEventIdControl {
        u32_le cmd; // 0=disable, 1=enable, 2=clear
        u32_le id;
@@ -174,6 +180,7 @@ private:
    u64_le user_data{};
    IoctlZCullBind zcull_params{};
    u32_le channel_priority{};
+    u32_le channel_timeslice{};

    u32 SetNVMAPfd(const std::vector<u8>& input, std::vector<u8>& output);
    u32 SetClientData(const std::vector<u8>& input, std::vector<u8>& output);
@@ -188,6 +195,7 @@ private:
                  const std::vector<u8>& input2, IoctlVersion version);
    u32 GetWaitbase(const std::vector<u8>& input, std::vector<u8>& output);
    u32 ChannelSetTimeout(const std::vector<u8>& input, std::vector<u8>& output);
+    u32 ChannelSetTimeslice(const std::vector<u8>& input, std::vector<u8>& output);

    std::shared_ptr<nvmap> nvmap_dev;
    u32 assigned_syncpoints{};
@@ -12,6 +12,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/kernel.h"
 #include "core/hle/kernel/readable_event.h"
 #include "core/hle/service/nvdrv/devices/nvdisp_disp0.h"
@@ -26,8 +27,8 @@

 namespace Service::NVFlinger {

-constexpr s64 frame_ticks = static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 60);
-constexpr s64 frame_ticks_30fps = static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 30);
+constexpr s64 frame_ticks = static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 60);
+constexpr s64 frame_ticks_30fps = static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 30);

 NVFlinger::NVFlinger(Core::System& system) : system(system) {
    displays.emplace_back(0, "Default", system);
@@ -222,7 +223,7 @@ void NVFlinger::Compose() {

 s64 NVFlinger::GetNextTicks() const {
    constexpr s64 max_hertz = 120LL;
-    return (Core::Timing::BASE_CLOCK_RATE * (1LL << swap_interval)) / max_hertz;
+    return (Core::Hardware::BASE_CLOCK_RATE * (1LL << swap_interval)) / max_hertz;
 }

 } // namespace Service::NVFlinger
@@ -5,6 +5,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/service/time/standard_steady_clock_core.h"

 namespace Service::Time::Clock {
@@ -12,7 +13,7 @@ namespace Service::Time::Clock {
 TimeSpanType StandardSteadyClockCore::GetCurrentRawTimePoint(Core::System& system) {
    const TimeSpanType ticks_time_span{TimeSpanType::FromTicks(
        Core::Timing::CpuCyclesToClockCycles(system.CoreTiming().GetTicks()),
-        Core::Timing::CNTFREQ)};
+        Core::Hardware::CNTFREQ)};
    TimeSpanType raw_time_point{setup_value.nanoseconds + ticks_time_span.nanoseconds};

    if (raw_time_point.nanoseconds < cached_raw_time_point.nanoseconds) {
@@ -5,6 +5,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/service/time/tick_based_steady_clock_core.h"

 namespace Service::Time::Clock {
@@ -12,7 +13,7 @@ namespace Service::Time::Clock {
 SteadyClockTimePoint TickBasedSteadyClockCore::GetTimePoint(Core::System& system) {
    const TimeSpanType ticks_time_span{TimeSpanType::FromTicks(
        Core::Timing::CpuCyclesToClockCycles(system.CoreTiming().GetTicks()),
-        Core::Timing::CNTFREQ)};
+        Core::Hardware::CNTFREQ)};

    return {ticks_time_span.ToSeconds(), GetClockSourceId()};
 }
@@ -6,6 +6,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/ipc_helpers.h"
 #include "core/hle/kernel/client_port.h"
 #include "core/hle/kernel/client_session.h"
@@ -233,7 +234,7 @@ void Module::Interface::CalculateMonotonicSystemClockBaseTimePoint(Kernel::HLERe
    if (current_time_point.clock_source_id == context.steady_time_point.clock_source_id) {
        const auto ticks{Clock::TimeSpanType::FromTicks(
            Core::Timing::CpuCyclesToClockCycles(system.CoreTiming().GetTicks()),
-            Core::Timing::CNTFREQ)};
+            Core::Hardware::CNTFREQ)};
        const s64 base_time_point{context.offset + current_time_point.time_point -
                                  ticks.ToSeconds()};
        IPC::ResponseBuilder rb{ctx, (sizeof(s64) / 4) + 2};
@@ -5,6 +5,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/service/time/clock_types.h"
 #include "core/hle/service/time/steady_clock_core.h"
 #include "core/hle/service/time/time_sharedmemory.h"
@@ -31,7 +32,7 @@ void SharedMemory::SetupStandardSteadyClock(Core::System& system,
                                            Clock::TimeSpanType current_time_point) {
    const Clock::TimeSpanType ticks_time_span{Clock::TimeSpanType::FromTicks(
        Core::Timing::CpuCyclesToClockCycles(system.CoreTiming().GetTicks()),
-        Core::Timing::CNTFREQ)};
+        Core::Hardware::CNTFREQ)};
    const Clock::SteadyClockContext context{
        static_cast<u64>(current_time_point.nanoseconds - ticks_time_span.nanoseconds),
        clock_source_id};
@@ -9,6 +9,7 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/hle/kernel/process.h"
 #include "core/hle/service/hid/controllers/npad.h"
 #include "core/hle/service/hid/hid.h"
@@ -17,7 +18,7 @@

 namespace Memory {

-constexpr s64 CHEAT_ENGINE_TICKS = static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 12);
+constexpr s64 CHEAT_ENGINE_TICKS = static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 12);
 constexpr u32 KEYPAD_BITMASK = 0x3FFFFFF;

 StandardVmCallbacks::StandardVmCallbacks(Core::System& system, const CheatProcessMetadata& metadata)
@@ -429,6 +429,7 @@ struct Values {
    int vulkan_device;

    float resolution_factor;
+    int aspect_ratio;
    bool use_frame_limit;
    u16 frame_limit;
    bool use_disk_shader_cache;
@@ -7,13 +7,14 @@
 #include "core/core.h"
 #include "core/core_timing.h"
 #include "core/core_timing_util.h"
+#include "core/hardware_properties.h"
 #include "core/memory.h"
 #include "core/tools/freezer.h"

 namespace Tools {
 namespace {

-constexpr s64 MEMORY_FREEZER_TICKS = static_cast<s64>(Core::Timing::BASE_CLOCK_RATE / 60);
+constexpr s64 MEMORY_FREEZER_TICKS = static_cast<s64>(Core::Hardware::BASE_CLOCK_RATE / 60);

 u64 MemoryReadWidth(Memory::Memory& memory, u32 width, VAddr addr) {
    switch (width) {
@@ -489,7 +489,7 @@ void Maxwell3D::FlushMMEInlineDraw() {

    const bool is_indexed = mme_draw.current_mode == MMEDrawMode::Indexed;
    if (ShouldExecute()) {
-        rasterizer.DrawMultiBatch(is_indexed);
+        rasterizer.Draw(is_indexed, true);
    }

    // TODO(bunnei): Below, we reset vertex count so that we can use these registers to determine if
@@ -654,7 +654,7 @@ void Maxwell3D::DrawArrays() {

    const bool is_indexed{regs.index_array.count && !regs.vertex_buffer.count};
    if (ShouldExecute()) {
-        rasterizer.DrawBatch(is_indexed);
+        rasterizer.Draw(is_indexed, false);
    }

    // TODO(bunnei): Below, we reset vertex count so that we can use these registers to determine if
@@ -542,7 +542,7 @@ public:
                BitField<12, 1, InvMemoryLayout> type;
            } memory_layout;
            union {
-                BitField<0, 16, u32> array_mode;
+                BitField<0, 16, u32> layers;
                BitField<16, 1, u32> volume;
            };
            u32 layer_stride;
@@ -800,8 +800,12 @@ public:

                u32 zeta_width;
                u32 zeta_height;
+                union {
+                    BitField<0, 16, u32> zeta_layers;
+                    BitField<16, 1, u32> zeta_volume;
+                };

-                INSERT_UNION_PADDING_WORDS(0x27);
+                INSERT_UNION_PADDING_WORDS(0x26);

                u32 depth_test_enable;

@@ -1507,6 +1511,7 @@ ASSERT_REG_POSITION(vertex_attrib_format, 0x458);
 ASSERT_REG_POSITION(rt_control, 0x487);
 ASSERT_REG_POSITION(zeta_width, 0x48a);
 ASSERT_REG_POSITION(zeta_height, 0x48b);
+ASSERT_REG_POSITION(zeta_layers, 0x48c);
 ASSERT_REG_POSITION(depth_test_enable, 0x4B3);
 ASSERT_REG_POSITION(independent_blend_enable, 0x4B9);
 ASSERT_REG_POSITION(depth_write_enabled, 0x4BA);
@@ -1677,11 +1677,11 @@ union Instruction {
    } xmad;

    union {
-        BitField<20, 14, u64> offset;
+        BitField<20, 14, u64> shifted_offset;
        BitField<34, 5, u64> index;

        u64 GetOffset() const {
-            return offset * 4;
+            return shifted_offset * 4;
        }
    } cbuf34;

@@ -24,7 +24,7 @@ MICROPROFILE_DEFINE(GPU_wait, "GPU", "Wait for the GPU", MP_RGB(128, 128, 192));
 GPU::GPU(Core::System& system, VideoCore::RendererBase& renderer, bool is_async)
    : system{system}, renderer{renderer}, is_async{is_async} {
    auto& rasterizer{renderer.Rasterizer()};
-    memory_manager = std::make_unique<Tegra::MemoryManager>(system);
+    memory_manager = std::make_unique<Tegra::MemoryManager>(system, rasterizer);
    dma_pusher = std::make_unique<Tegra::DmaPusher>(*this);
    maxwell_3d = std::make_unique<Engines::Maxwell3D>(system, rasterizer, *memory_manager);
    fermi_2d = std::make_unique<Engines::Fermi2D>(rasterizer);
@@ -140,71 +140,6 @@ void GPU::FlushCommands() {
    renderer.Rasterizer().FlushCommands();
 }

-u32 RenderTargetBytesPerPixel(RenderTargetFormat format) {
-    ASSERT(format != RenderTargetFormat::NONE);
-
-    switch (format) {
-    case RenderTargetFormat::RGBA32_FLOAT:
-    case RenderTargetFormat::RGBA32_UINT:
-        return 16;
-    case RenderTargetFormat::RGBA16_UINT:
-    case RenderTargetFormat::RGBA16_UNORM:
-    case RenderTargetFormat::RGBA16_FLOAT:
-    case RenderTargetFormat::RGBX16_FLOAT:
-    case RenderTargetFormat::RG32_FLOAT:
-    case RenderTargetFormat::RG32_UINT:
-        return 8;
-    case RenderTargetFormat::RGBA8_UNORM:
-    case RenderTargetFormat::RGBA8_SNORM:
-    case RenderTargetFormat::RGBA8_SRGB:
-    case RenderTargetFormat::RGBA8_UINT:
-    case RenderTargetFormat::RGB10_A2_UNORM:
-    case RenderTargetFormat::BGRA8_UNORM:
-    case RenderTargetFormat::BGRA8_SRGB:
-    case RenderTargetFormat::RG16_UNORM:
-    case RenderTargetFormat::RG16_SNORM:
-    case RenderTargetFormat::RG16_UINT:
-    case RenderTargetFormat::RG16_SINT:
-    case RenderTargetFormat::RG16_FLOAT:
-    case RenderTargetFormat::R32_FLOAT:
-    case RenderTargetFormat::R11G11B10_FLOAT:
-    case RenderTargetFormat::R32_UINT:
-        return 4;
-    case RenderTargetFormat::R16_UNORM:
-    case RenderTargetFormat::R16_SNORM:
-    case RenderTargetFormat::R16_UINT:
-    case RenderTargetFormat::R16_SINT:
-    case RenderTargetFormat::R16_FLOAT:
-    case RenderTargetFormat::RG8_UNORM:
-    case RenderTargetFormat::RG8_SNORM:
-        return 2;
-    case RenderTargetFormat::R8_UNORM:
-    case RenderTargetFormat::R8_UINT:
-        return 1;
-    default:
-        UNIMPLEMENTED_MSG("Unimplemented render target format {}", static_cast<u32>(format));
-        return 1;
-    }
-}
-
-u32 DepthFormatBytesPerPixel(DepthFormat format) {
-    switch (format) {
-    case DepthFormat::Z32_S8_X24_FLOAT:
-        return 8;
-    case DepthFormat::Z32_FLOAT:
-    case DepthFormat::S8_Z24_UNORM:
-    case DepthFormat::Z24_X8_UNORM:
-    case DepthFormat::Z24_S8_UNORM:
-    case DepthFormat::Z24_C8_UNORM:
-        return 4;
-    case DepthFormat::Z16_UNORM:
-        return 2;
-    default:
-        UNIMPLEMENTED_MSG("Unimplemented Depth format {}", static_cast<u32>(format));
-        return 1;
-    }
-}
-
 // Note that, traditionally, methods are treated as 4-byte addressable locations, and hence
 // their numbers are written down multiplied by 4 in Docs. Here we are not multiply by 4.
 // So the values you see in docs might be multiplied by 4.
@@ -82,12 +82,6 @@ enum class DepthFormat : u32 {
    Z32_S8_X24_FLOAT = 0x19,
 };

-/// Returns the number of bytes per pixel of each rendertarget format.
-u32 RenderTargetBytesPerPixel(RenderTargetFormat format);
-
-/// Returns the number of bytes per pixel of each depth format.
-u32 DepthFormatBytesPerPixel(DepthFormat format);
-
 struct CommandListHeader;
 class DebugContext;

@@ -11,10 +11,12 @@
 #include "core/memory.h"
 #include "video_core/gpu.h"
 #include "video_core/memory_manager.h"
+#include "video_core/rasterizer_interface.h"

 namespace Tegra {

-MemoryManager::MemoryManager(Core::System& system) : system{system} {
+MemoryManager::MemoryManager(Core::System& system, VideoCore::RasterizerInterface& rasterizer)
+    : rasterizer{rasterizer}, system{system} {
    std::fill(page_table.pointers.begin(), page_table.pointers.end(), nullptr);
    std::fill(page_table.attributes.begin(), page_table.attributes.end(),
              Common::PageType::Unmapped);
@@ -83,6 +85,7 @@ GPUVAddr MemoryManager::UnmapBuffer(GPUVAddr gpu_addr, u64 size) {
    const auto cpu_addr = GpuToCpuAddress(gpu_addr);
    ASSERT(cpu_addr);

+    // Flush and invalidate through the GPU interface, to be asynchronous if possible.
    system.GPU().FlushAndInvalidateRegion(cache_addr, aligned_size);

    UnmapRange(gpu_addr, aligned_size);
@@ -242,7 +245,9 @@ void MemoryManager::ReadBlock(GPUVAddr src_addr, void* dest_buffer, const std::s
        switch (page_table.attributes[page_index]) {
        case Common::PageType::Memory: {
            const u8* src_ptr{page_table.pointers[page_index] + page_offset};
-            system.GPU().FlushRegion(ToCacheAddr(src_ptr), copy_amount);
+            // Flush must happen on the rasterizer interface, such that memory is always synchronous
+            // when it is read (even when in asynchronous GPU mode). Fixes Dead Cells title menu.
+            rasterizer.FlushRegion(ToCacheAddr(src_ptr), copy_amount);
            std::memcpy(dest_buffer, src_ptr, copy_amount);
            break;
        }
@@ -292,7 +297,9 @@ void MemoryManager::WriteBlock(GPUVAddr dest_addr, const void* src_buffer, const
        switch (page_table.attributes[page_index]) {
        case Common::PageType::Memory: {
            u8* dest_ptr{page_table.pointers[page_index] + page_offset};
-            system.GPU().InvalidateRegion(ToCacheAddr(dest_ptr), copy_amount);
+            // Invalidate must happen on the rasterizer interface, such that memory is always
+            // synchronous when it is written (even when in asynchronous GPU mode).
+            rasterizer.InvalidateRegion(ToCacheAddr(dest_ptr), copy_amount);
            std::memcpy(dest_ptr, src_buffer, copy_amount);
            break;
        }
@@ -339,8 +346,10 @@ void MemoryManager::CopyBlock(GPUVAddr dest_addr, GPUVAddr src_addr, const std::

        switch (page_table.attributes[page_index]) {
        case Common::PageType::Memory: {
+            // Flush must happen on the rasterizer interface, such that memory is always synchronous
+            // when it is copied (even when in asynchronous GPU mode).
            const u8* src_ptr{page_table.pointers[page_index] + page_offset};
-            system.GPU().FlushRegion(ToCacheAddr(src_ptr), copy_amount);
+            rasterizer.FlushRegion(ToCacheAddr(src_ptr), copy_amount);
            WriteBlock(dest_addr, src_ptr, copy_amount);
            break;
        }
@@ -10,6 +10,10 @@
 #include "common/common_types.h"
 #include "common/page_table.h"

+namespace VideoCore {
+class RasterizerInterface;
+}
+
 namespace Core {
 class System;
 }
@@ -47,7 +51,7 @@ struct VirtualMemoryArea {

 class MemoryManager final {
 public:
-    explicit MemoryManager(Core::System& system);
+    explicit MemoryManager(Core::System& system, VideoCore::RasterizerInterface& rasterizer);
    ~MemoryManager();

    GPUVAddr AllocateSpace(u64 size, u64 align);
@@ -172,6 +176,7 @@ private:

    Common::PageTable page_table{page_bits};
    VMAMap vma_map;
+    VideoCore::RasterizerInterface& rasterizer;

    Core::System& system;
 };
@@ -35,11 +35,8 @@ class RasterizerInterface {
 public:
    virtual ~RasterizerInterface() {}

-    /// Draw the current batch of vertex arrays
-    virtual bool DrawBatch(bool is_indexed) = 0;
-
-    /// Draw the current batch of multiple instances of vertex arrays
-    virtual bool DrawMultiBatch(bool is_indexed) = 0;
+    /// Dispatches a draw invocation
+    virtual void Draw(bool is_indexed, bool is_instanced) = 0;

    /// Clear the current framebuffer
    virtual void Clear() = 0;
@@ -617,7 +617,7 @@ void RasterizerOpenGL::Draw(bool is_indexed, bool is_instanced) {

    // Setup shaders and their used resources.
    texture_cache.GuardSamplers(true);
-    const auto primitive_mode = MaxwellToGL::PrimitiveTopology(gpu.regs.draw.topology);
+    const GLenum primitive_mode = MaxwellToGL::PrimitiveTopology(gpu.regs.draw.topology);
    SetupShaders(primitive_mode);
    texture_cache.GuardSamplers(false);

@@ -650,31 +650,41 @@ void RasterizerOpenGL::Draw(bool is_indexed, bool is_instanced) {
    const GLsizei num_instances =
        static_cast<GLsizei>(is_instanced ? gpu.mme_draw.instance_count : 1);
    if (is_indexed) {
-        const GLenum index_format = MaxwellToGL::IndexFormat(gpu.regs.index_array.format);
        const GLint base_vertex = static_cast<GLint>(gpu.regs.vb_element_base);
        const GLsizei num_vertices = static_cast<GLsizei>(gpu.regs.index_array.count);
-        glDrawElementsInstancedBaseVertexBaseInstance(
-            primitive_mode, num_vertices, index_format,
-            reinterpret_cast<const void*>(index_buffer_offset), num_instances, base_vertex,
-            base_instance);
+        const GLvoid* offset = reinterpret_cast<const GLvoid*>(index_buffer_offset);
+        const GLenum format = MaxwellToGL::IndexFormat(gpu.regs.index_array.format);
+        if (num_instances == 1 && base_instance == 0 && base_vertex == 0) {
+            glDrawElements(primitive_mode, num_vertices, format, offset);
+        } else if (num_instances == 1 && base_instance == 0) {
+            glDrawElementsBaseVertex(primitive_mode, num_vertices, format, offset, base_vertex);
+        } else if (base_vertex == 0 && base_instance == 0) {
+            glDrawElementsInstanced(primitive_mode, num_vertices, format, offset, num_instances);
+        } else if (base_vertex == 0) {
+            glDrawElementsInstancedBaseInstance(primitive_mode, num_vertices, format, offset,
+                                                num_instances, base_instance);
+        } else if (base_instance == 0) {
+            glDrawElementsInstancedBaseVertex(primitive_mode, num_vertices, format, offset,
+                                              num_instances, base_vertex);
+        } else {
+            glDrawElementsInstancedBaseVertexBaseInstance(primitive_mode, num_vertices, format,
+                                                          offset, num_instances, base_vertex,
+                                                          base_instance);
+        }
    } else {
        const GLint base_vertex = static_cast<GLint>(gpu.regs.vertex_buffer.first);
        const GLsizei num_vertices = static_cast<GLsizei>(gpu.regs.vertex_buffer.count);
-        glDrawArraysInstancedBaseInstance(primitive_mode, base_vertex, num_vertices, num_instances,
-                                          base_instance);
+        if (num_instances == 1 && base_instance == 0) {
+            glDrawArrays(primitive_mode, base_vertex, num_vertices);
+        } else if (base_instance == 0) {
+            glDrawArraysInstanced(primitive_mode, base_vertex, num_vertices, num_instances);
+        } else {
+            glDrawArraysInstancedBaseInstance(primitive_mode, base_vertex, num_vertices,
+                                              num_instances, base_instance);
+        }
    }
 }

-bool RasterizerOpenGL::DrawBatch(bool is_indexed) {
-    Draw(is_indexed, false);
-    return true;
-}
-
-bool RasterizerOpenGL::DrawMultiBatch(bool is_indexed) {
-    Draw(is_indexed, true);
-    return true;
-}
-
 void RasterizerOpenGL::DispatchCompute(GPUVAddr code_addr) {
    if (device.HasBrokenCompute()) {
        return;
@@ -58,8 +58,7 @@ public:
                              ScreenInfo& info);
    ~RasterizerOpenGL() override;

-    bool DrawBatch(bool is_indexed) override;
-    bool DrawMultiBatch(bool is_indexed) override;
+    void Draw(bool is_indexed, bool is_instanced) override;
    void Clear() override;
    void DispatchCompute(GPUVAddr code_addr) override;
    void ResetCounter(VideoCore::QueryType type) override;
@@ -110,9 +109,6 @@ private:
    void SetupGlobalMemory(u32 binding, const GLShader::GlobalMemoryEntry& entry, GPUVAddr gpu_addr,
                           std::size_t size);

-    /// Syncs all the state, shaders, render targets and textures setting before a draw call.
-    void Draw(bool is_indexed, bool is_instanced);
-
    /// Configures the current textures to use for the draw command.
    void SetupDrawTextures(std::size_t stage_index, const Shader& shader);

@@ -260,6 +260,13 @@ CachedSurface::~CachedSurface() = default;
 void CachedSurface::DownloadTexture(std::vector<u8>& staging_buffer) {
    MICROPROFILE_SCOPE(OpenGL_Texture_Download);

+    if (params.IsBuffer()) {
+        glGetNamedBufferSubData(texture_buffer.handle, 0,
+                                static_cast<GLsizeiptr>(params.GetHostSizeInBytes()),
+                                staging_buffer.data());
+        return;
+    }
+
    SCOPE_EXIT({ glPixelStorei(GL_PACK_ROW_LENGTH, 0); });

    for (u32 level = 0; level < params.emulated_levels; ++level) {
@@ -398,24 +405,36 @@ CachedSurfaceView::CachedSurfaceView(CachedSurface& surface, const ViewParams& p
 CachedSurfaceView::~CachedSurfaceView() = default;

 void CachedSurfaceView::Attach(GLenum attachment, GLenum target) const {
-    ASSERT(params.num_layers == 1 && params.num_levels == 1);
+    ASSERT(params.num_levels == 1);

-    const auto& owner_params = surface.GetSurfaceParams();
+    const GLuint texture = surface.GetTexture();
+    if (params.num_layers > 1) {
+        // Layered framebuffer attachments
+        UNIMPLEMENTED_IF(params.base_layer != 0);

-    switch (owner_params.target) {
+        switch (params.target) {
+        case SurfaceTarget::Texture2DArray:
+            glFramebufferTexture(target, attachment, texture, params.base_level);
+            break;
+        default:
+            UNIMPLEMENTED();
+        }
+        return;
+    }
+
+    const GLenum view_target = surface.GetTarget();
+    switch (surface.GetSurfaceParams().target) {
    case SurfaceTarget::Texture1D:
-        glFramebufferTexture1D(target, attachment, surface.GetTarget(), surface.GetTexture(),
-                               params.base_level);
+        glFramebufferTexture1D(target, attachment, view_target, texture, params.base_level);
        break;
    case SurfaceTarget::Texture2D:
-        glFramebufferTexture2D(target, attachment, surface.GetTarget(), surface.GetTexture(),
-                               params.base_level);
+        glFramebufferTexture2D(target, attachment, view_target, texture, params.base_level);
        break;
    case SurfaceTarget::Texture1DArray:
    case SurfaceTarget::Texture2DArray:
    case SurfaceTarget::TextureCubemap:
    case SurfaceTarget::TextureCubeArray:
-        glFramebufferTextureLayer(target, attachment, surface.GetTexture(), params.base_level,
+        glFramebufferTextureLayer(target, attachment, texture, params.base_level,
                                  params.base_layer);
        break;
    default:
@@ -164,7 +164,7 @@ struct FormatTuple {
    {vk::Format::eUndefined, {}},                                // ASTC_2D_5X4
    {vk::Format::eUndefined, {}},                                // BGRA8_SRGB
    {vk::Format::eBc1RgbaSrgbBlock, {}},                         // DXT1_SRGB
-    {vk::Format::eUndefined, {}},                                // DXT23_SRGB
+    {vk::Format::eBc2SrgbBlock, {}},                             // DXT23_SRGB
    {vk::Format::eBc3SrgbBlock, {}},                             // DXT45_SRGB
    {vk::Format::eBc7SrgbBlock, {}},                             // BC7U_SRGB
    {vk::Format::eR4G4B4A4UnormPack16, Attachable},              // R4G4B4A4U
@@ -363,6 +363,8 @@ vk::Format VertexFormat(Maxwell::VertexAttribute::Type type, Maxwell::VertexAttr
            return vk::Format::eR8G8B8A8Uint;
        case Maxwell::VertexAttribute::Size::Size_32:
            return vk::Format::eR32Uint;
+        case Maxwell::VertexAttribute::Size::Size_32_32_32_32:
+            return vk::Format::eR32G32B32A32Uint;
        default:
            break;
        }
@@ -107,6 +107,8 @@ bool VKDevice::Create(const vk::DispatchLoaderDynamic& dldi, vk::Instance instan
    features.occlusionQueryPrecise = true;
    features.fragmentStoresAndAtomics = true;
    features.shaderImageGatherExtended = true;
+    features.shaderStorageImageReadWithoutFormat =
+        is_shader_storage_img_read_without_format_supported;
    features.shaderStorageImageWriteWithoutFormat = true;
    features.textureCompressionASTC_LDR = is_optimal_astc_supported;

@@ -465,6 +467,8 @@ void VKDevice::SetupFamilies(const vk::DispatchLoaderDynamic& dldi, vk::SurfaceK

 void VKDevice::SetupFeatures(const vk::DispatchLoaderDynamic& dldi) {
    const auto supported_features{physical.getFeatures(dldi)};
+    is_shader_storage_img_read_without_format_supported =
+        supported_features.shaderStorageImageReadWithoutFormat;
    is_optimal_astc_supported = IsOptimalAstcSupported(supported_features, dldi);
 }

@@ -538,6 +542,7 @@ std::unordered_map<vk::Format, vk::FormatProperties> VKDevice::GetFormatProperti
                                        vk::Format::eBc6HUfloatBlock,
                                        vk::Format::eBc6HSfloatBlock,
                                        vk::Format::eBc1RgbaSrgbBlock,
+                                        vk::Format::eBc2SrgbBlock,
                                        vk::Format::eBc3SrgbBlock,
                                        vk::Format::eBc7SrgbBlock,
                                        vk::Format::eAstc4x4SrgbBlock,
@@ -122,6 +122,11 @@ public:
        return properties.limits.maxPushConstantsSize;
    }

+    /// Returns true if Shader storage Image Read Without Format supported.
+    bool IsShaderStorageImageReadWithoutFormatSupported() const {
+        return is_shader_storage_img_read_without_format_supported;
+    }
+
    /// Returns true if ASTC is natively supported.
    bool IsOptimalAstcSupported() const {
        return is_optimal_astc_supported;
@@ -227,6 +232,8 @@ private:
    bool ext_depth_range_unrestricted{};       ///< Support for VK_EXT_depth_range_unrestricted.
    bool ext_shader_viewport_index_layer{};    ///< Support for VK_EXT_shader_viewport_index_layer.
    bool nv_device_diagnostic_checkpoints{};   ///< Support for VK_NV_device_diagnostic_checkpoints.
+    bool is_shader_storage_img_read_without_format_supported{}; ///< Support for shader storage
+                                                                ///< image read without format

    // Telemetry parameters
    std::string vendor_name;                      ///< Device's driver name.
@@ -295,16 +295,6 @@ RasterizerVulkan::RasterizerVulkan(Core::System& system, Core::Frontend::EmuWind

 RasterizerVulkan::~RasterizerVulkan() = default;

-bool RasterizerVulkan::DrawBatch(bool is_indexed) {
-    Draw(is_indexed, false);
-    return true;
-}
-
-bool RasterizerVulkan::DrawMultiBatch(bool is_indexed) {
-    Draw(is_indexed, true);
-    return true;
-}
-
 void RasterizerVulkan::Draw(bool is_indexed, bool is_instanced) {
    MICROPROFILE_SCOPE(Vulkan_Drawing);

@@ -621,33 +611,34 @@ bool RasterizerVulkan::WalkAttachmentOverlaps(const CachedSurfaceView& attachmen
 std::tuple<vk::Framebuffer, vk::Extent2D> RasterizerVulkan::ConfigureFramebuffers(
    vk::RenderPass renderpass) {
    FramebufferCacheKey key{renderpass, std::numeric_limits<u32>::max(),
-                            std::numeric_limits<u32>::max()};
+                            std::numeric_limits<u32>::max(), std::numeric_limits<u32>::max()};

-    const auto MarkAsModifiedAndPush = [&](const View& view) {
-        if (view == nullptr) {
+    const auto try_push = [&](const View& view) {
+        if (!view) {
            return false;
        }
        key.views.push_back(view->GetHandle());
        key.width = std::min(key.width, view->GetWidth());
        key.height = std::min(key.height, view->GetHeight());
+        key.layers = std::min(key.layers, view->GetNumLayers());
        return true;
    };

    for (std::size_t index = 0; index < std::size(color_attachments); ++index) {
-        if (MarkAsModifiedAndPush(color_attachments[index])) {
+        if (try_push(color_attachments[index])) {
            texture_cache.MarkColorBufferInUse(index);
        }
    }
-    if (MarkAsModifiedAndPush(zeta_attachment)) {
+    if (try_push(zeta_attachment)) {
        texture_cache.MarkDepthBufferInUse();
    }

    const auto [fbentry, is_cache_miss] = framebuffer_cache.try_emplace(key);
    auto& framebuffer = fbentry->second;
    if (is_cache_miss) {
-        const vk::FramebufferCreateInfo framebuffer_ci({}, key.renderpass,
-                                                       static_cast<u32>(key.views.size()),
-                                                       key.views.data(), key.width, key.height, 1);
+        const vk::FramebufferCreateInfo framebuffer_ci(
+            {}, key.renderpass, static_cast<u32>(key.views.size()), key.views.data(), key.width,
+            key.height, key.layers);
        const auto dev = device.GetLogical();
        const auto& dld = device.GetDispatchLoader();
        framebuffer = dev.createFramebufferUnique(framebuffer_ci, nullptr, dld);
@@ -56,6 +56,7 @@ struct FramebufferCacheKey {
    vk::RenderPass renderpass{};
    u32 width = 0;
    u32 height = 0;
+    u32 layers = 0;
    ImageViewsPack views;

    std::size_t Hash() const noexcept {
@@ -66,12 +67,17 @@ struct FramebufferCacheKey {
        }
        boost::hash_combine(hash, width);
        boost::hash_combine(hash, height);
+        boost::hash_combine(hash, layers);
        return hash;
    }

    bool operator==(const FramebufferCacheKey& rhs) const noexcept {
-        return std::tie(renderpass, views, width, height) ==
-               std::tie(rhs.renderpass, rhs.views, rhs.width, rhs.height);
+        return std::tie(renderpass, views, width, height, layers) ==
+               std::tie(rhs.renderpass, rhs.views, rhs.width, rhs.height, rhs.layers);
+    }
+
+    bool operator!=(const FramebufferCacheKey& rhs) const noexcept {
+        return !operator==(rhs);
    }
 };

@@ -105,8 +111,7 @@ public:
                              VKScheduler& scheduler);
    ~RasterizerVulkan() override;

-    bool DrawBatch(bool is_indexed) override;
-    bool DrawMultiBatch(bool is_indexed) override;
+    void Draw(bool is_indexed, bool is_instanced) override;
    void Clear() override;
    void DispatchCompute(GPUVAddr code_addr) override;
    void ResetCounter(VideoCore::QueryType type) override;
@@ -143,8 +148,6 @@ private:

    static constexpr std::size_t ZETA_TEXCEPTION_INDEX = 8;

-    void Draw(bool is_indexed, bool is_instanced);
-
    void FlushWork();

    Texceptions UpdateAttachments();
@@ -23,7 +23,14 @@ static std::optional<vk::BorderColor> TryConvertBorderColor(std::array<float, 4>
    } else if (color == std::array<float, 4>{1, 1, 1, 1}) {
        return vk::BorderColor::eFloatOpaqueWhite;
    } else {
-        return {};
+        if (color[0] + color[1] + color[2] > 1.35f) {
+            // If color elements are brighter than roughly 0.5 average, use white border
+            return vk::BorderColor::eFloatOpaqueWhite;
+        }
+        if (color[3] > 0.5f) {
+            return vk::BorderColor::eFloatOpaqueBlack;
+        }
+        return vk::BorderColor::eFloatTransparentBlack;
    }
 }

@@ -37,8 +44,6 @@ UniqueSampler VKSamplerCache::CreateSampler(const Tegra::Texture::TSCEntry& tsc)

    const auto border_color{tsc.GetBorderColor()};
    const auto vk_border_color{TryConvertBorderColor(border_color)};
-    UNIMPLEMENTED_IF_MSG(!vk_border_color, "Unimplemented border color {} {} {} {}",
-                         border_color[0], border_color[1], border_color[2], border_color[3]);

    constexpr bool unnormalized_coords{false};

@@ -86,6 +86,7 @@ struct AttributeType {

 struct VertexIndices {
    std::optional<u32> position;
+    std::optional<u32> layer;
    std::optional<u32> viewport;
    std::optional<u32> point_size;
    std::optional<u32> clip_distances;
@@ -275,21 +276,29 @@ public:
        AddCapability(spv::Capability::ImageGatherExtended);
        AddCapability(spv::Capability::SampledBuffer);
        AddCapability(spv::Capability::StorageImageWriteWithoutFormat);
+        AddCapability(spv::Capability::DrawParameters);
        AddCapability(spv::Capability::SubgroupBallotKHR);
        AddCapability(spv::Capability::SubgroupVoteKHR);
        AddExtension("SPV_KHR_shader_ballot");
        AddExtension("SPV_KHR_subgroup_vote");
        AddExtension("SPV_KHR_storage_buffer_storage_class");
        AddExtension("SPV_KHR_variable_pointers");
+        AddExtension("SPV_KHR_shader_draw_parameters");

-        if (ir.UsesViewportIndex()) {
-            AddCapability(spv::Capability::MultiViewport);
-            if (device.IsExtShaderViewportIndexLayerSupported()) {
+        if (ir.UsesLayer() || ir.UsesViewportIndex()) {
+            if (ir.UsesViewportIndex()) {
+                AddCapability(spv::Capability::MultiViewport);
+            }
+            if (stage != ShaderType::Geometry && device.IsExtShaderViewportIndexLayerSupported()) {
                AddExtension("SPV_EXT_shader_viewport_index_layer");
                AddCapability(spv::Capability::ShaderViewportIndexLayerEXT);
            }
        }

+        if (device.IsShaderStorageImageReadWithoutFormatSupported()) {
+            AddCapability(spv::Capability::StorageImageReadWithoutFormat);
+        }
+
        if (device.IsFloat16Supported()) {
            AddCapability(spv::Capability::Float16);
        }
@@ -492,9 +501,11 @@ private:
        interfaces.push_back(AddGlobalVariable(Name(out_vertex, "out_vertex")));

        // Declare input attributes
-        vertex_index = DeclareInputBuiltIn(spv::BuiltIn::VertexIndex, t_in_uint, "vertex_index");
+        vertex_index = DeclareInputBuiltIn(spv::BuiltIn::VertexIndex, t_in_int, "vertex_index");
        instance_index =
-            DeclareInputBuiltIn(spv::BuiltIn::InstanceIndex, t_in_uint, "instance_index");
+            DeclareInputBuiltIn(spv::BuiltIn::InstanceIndex, t_in_int, "instance_index");
+        base_vertex = DeclareInputBuiltIn(spv::BuiltIn::BaseVertex, t_in_int, "base_vertex");
+        base_instance = DeclareInputBuiltIn(spv::BuiltIn::BaseInstance, t_in_int, "base_instance");
    }

    void DeclareTessControl() {
@@ -920,13 +931,22 @@ private:
        VertexIndices indices;
        indices.position = AddBuiltIn(t_float4, spv::BuiltIn::Position, "position");

+        if (ir.UsesLayer()) {
+            if (stage != ShaderType::Vertex || device.IsExtShaderViewportIndexLayerSupported()) {
+                indices.layer = AddBuiltIn(t_int, spv::BuiltIn::Layer, "layer");
+            } else {
+                LOG_ERROR(
+                    Render_Vulkan,
+                    "Shader requires Layer but it's not supported on this stage with this device.");
+            }
+        }
+
        if (ir.UsesViewportIndex()) {
            if (stage != ShaderType::Vertex || device.IsExtShaderViewportIndexLayerSupported()) {
                indices.viewport = AddBuiltIn(t_int, spv::BuiltIn::ViewportIndex, "viewport_index");
            } else {
-                LOG_ERROR(Render_Vulkan,
-                          "Shader requires ViewportIndex but it's not supported on this "
-                          "stage with this device.");
+                LOG_ERROR(Render_Vulkan, "Shader requires ViewportIndex but it's not supported on "
+                                         "this stage with this device.");
            }
        }

@@ -1068,9 +1088,12 @@ private:
                    return {OpLoad(t_float, AccessElement(t_in_float, tess_coord, element)),
                            Type::Float};
                case 2:
-                    return {OpLoad(t_uint, instance_index), Type::Uint};
+                    return {
+                        OpISub(t_int, OpLoad(t_int, instance_index), OpLoad(t_int, base_instance)),
+                        Type::Int};
                case 3:
-                    return {OpLoad(t_uint, vertex_index), Type::Uint};
+                    return {OpISub(t_int, OpLoad(t_int, vertex_index), OpLoad(t_int, base_vertex)),
+                            Type::Int};
                }
                UNIMPLEMENTED_MSG("Unmanaged TessCoordInstanceIDVertexID element={}", element);
                return {Constant(t_uint, 0U), Type::Uint};
@@ -1285,6 +1308,13 @@ private:
                }
                case Attribute::Index::LayerViewportPointSize:
                    switch (element) {
+                    case 1: {
+                        if (!out_indices.layer) {
+                            return {};
+                        }
+                        const u32 index = out_indices.layer.value();
+                        return {AccessElement(t_out_int, out_vertex, index), Type::Int};
+                    }
                    case 2: {
                        if (!out_indices.viewport) {
                            return {};
@@ -1355,6 +1385,11 @@ private:
            UNIMPLEMENTED();
        }

+        if (!target.id) {
+            // On failure we return a nullptr target.id, skip these stores.
+            return {};
+        }
+
        OpStore(target.id, As(Visit(src), target.type));
        return {};
    }
@@ -1748,8 +1783,16 @@ private:
    }

    Expression ImageLoad(Operation operation) {
-        UNIMPLEMENTED();
-        return {};
+        if (!device.IsShaderStorageImageReadWithoutFormatSupported()) {
+            return {v_float_zero, Type::Float};
+        }
+
+        const auto& meta{std::get<MetaImage>(operation.GetMeta())};
+
+        const Id coords = GetCoordinates(operation, Type::Int);
+        const Id texel = OpImageRead(t_uint4, GetImage(operation), coords);
+
+        return {OpCompositeExtract(t_uint, texel, meta.element), Type::Uint};
    }

    Expression ImageStore(Operation operation) {
@@ -2542,6 +2585,8 @@ private:

    Id instance_index{};
    Id vertex_index{};
+    Id base_instance{};
+    Id base_vertex{};
    std::array<Id, Maxwell::NumRenderTargets> frag_colors{};
    Id frag_depth{};
    Id frag_coord{};
@@ -151,6 +151,10 @@ public:
        return params.GetMipHeight(base_level);
    }

+    u32 GetNumLayers() const {
+        return num_layers;
+    }
+
    bool IsBufferView() const {
        return buffer_view;
    }
@@ -166,13 +166,13 @@ u32 ShaderIR::DecodeArithmeticInteger(NodeBlock& bb, u32 pc) {
        const auto [op_rhs, test] = [&]() -> std::pair<Node, Node> {
            switch (opcode->get().GetId()) {
            case OpCode::Id::ICMP_CR:
-                return {GetConstBuffer(instr.cbuf34.index, instr.cbuf34.offset),
+                return {GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset()),
                        GetRegister(instr.gpr39)};
            case OpCode::Id::ICMP_R:
                return {GetRegister(instr.gpr20), GetRegister(instr.gpr39)};
            case OpCode::Id::ICMP_RC:
                return {GetRegister(instr.gpr39),
-                        GetConstBuffer(instr.cbuf34.index, instr.cbuf34.offset)};
+                        GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
            case OpCode::Id::ICMP_IMM:
                return {Immediate(instr.alu.GetSignedImm20_20()), GetRegister(instr.gpr39)};
            default:
@@ -21,7 +21,7 @@ u32 ShaderIR::DecodeBfi(NodeBlock& bb, u32 pc) {
        switch (opcode->get().GetId()) {
        case OpCode::Id::BFI_RC:
            return {GetRegister(instr.gpr39),
-                    GetConstBuffer(instr.cbuf34.index, instr.cbuf34.offset)};
+                    GetConstBuffer(instr.cbuf34.index, instr.cbuf34.GetOffset())};
        case OpCode::Id::BFI_IMM_R:
            return {Immediate(instr.alu.GetSignedImm20_20()), GetRegister(instr.gpr39)};
        default:
@@ -83,14 +83,14 @@ u32 ShaderIR::DecodeConversion(NodeBlock& bb, u32 pc) {

        const bool input_signed = instr.conversion.is_input_signed;

-        if (instr.conversion.src_size == Register::Size::Byte) {
-            const u32 offset = static_cast<u32>(instr.conversion.int_src.selector) * 8;
-            if (offset > 0) {
-                value = SignedOperation(OperationCode::ILogicalShiftRight, input_signed,
-                                        std::move(value), Immediate(offset));
+        if (const u32 offset = static_cast<u32>(instr.conversion.int_src.selector); offset > 0) {
+            ASSERT(instr.conversion.src_size == Register::Size::Byte ||
+                   instr.conversion.src_size == Register::Size::Short);
+            if (instr.conversion.src_size == Register::Size::Short) {
+                ASSERT(offset == 0 || offset == 2);
            }
-        } else {
-            UNIMPLEMENTED_IF(instr.conversion.int_src.selector != 0);
+            value = SignedOperation(OperationCode::ILogicalShiftRight, input_signed,
+                                    std::move(value), Immediate(offset * 8));
        }

        value = ConvertIntegerSize(value, instr.conversion.src_size, input_signed);
@@ -522,68 +522,53 @@ Node4 ShaderIR::GetTextureCode(Instruction instr, TextureType texture_type,
                               Node array, Node depth_compare, u32 bias_offset,
                               std::vector<Node> aoffi,
                               std::optional<Tegra::Shader::Register> bindless_reg) {
-    const auto is_array = static_cast<bool>(array);
-    const auto is_shadow = static_cast<bool>(depth_compare);
+    const bool is_array = array != nullptr;
+    const bool is_shadow = depth_compare != nullptr;
    const bool is_bindless = bindless_reg.has_value();

-    UNIMPLEMENTED_IF_MSG((texture_type == TextureType::Texture3D && (is_array || is_shadow)) ||
-                             (texture_type == TextureType::TextureCube && is_array && is_shadow),
-                         "This method is not supported.");
+    UNIMPLEMENTED_IF(texture_type == TextureType::TextureCube && is_array && is_shadow);
+    ASSERT_MSG(texture_type != TextureType::Texture3D || !is_array || !is_shadow,
+               "Illegal texture type");

    const SamplerInfo info{texture_type, is_array, is_shadow, false};
-    Node index_var{};
+    Node index_var;
    const Sampler* sampler = is_bindless ? GetBindlessSampler(*bindless_reg, index_var, info)
                                         : GetSampler(instr.sampler, info);
-    Node4 values;
-    if (sampler == nullptr) {
-        for (u32 element = 0; element < values.size(); ++element) {
-            values[element] = Immediate(0);
-        }
-        return values;
+    if (!sampler) {
+        return {Immediate(0), Immediate(0), Immediate(0), Immediate(0)};
    }

    const bool lod_needed = process_mode == TextureProcessMode::LZ ||
                            process_mode == TextureProcessMode::LL ||
                            process_mode == TextureProcessMode::LLA;
-
-    // LOD selection (either via bias or explicit textureLod) not supported in GL for
-    // sampler2DArrayShadow and samplerCubeArrayShadow.
-    const bool gl_lod_supported =
-        !((texture_type == Tegra::Shader::TextureType::Texture2D && is_array && is_shadow) ||
-          (texture_type == Tegra::Shader::TextureType::TextureCube && is_array && is_shadow));
-
-    const OperationCode read_method =
-        (lod_needed && gl_lod_supported) ? OperationCode::TextureLod : OperationCode::Texture;
-
-    UNIMPLEMENTED_IF(process_mode != TextureProcessMode::None && !gl_lod_supported);
+    const OperationCode opcode = lod_needed ? OperationCode::TextureLod : OperationCode::Texture;

    Node bias;
    Node lod;
-    if (process_mode != TextureProcessMode::None && gl_lod_supported) {
-        switch (process_mode) {
-        case TextureProcessMode::LZ:
-            lod = Immediate(0.0f);
-            break;
-        case TextureProcessMode::LB:
-            // If present, lod or bias are always stored in the register
-            // indexed by the gpr20 field with an offset depending on the
-            // usage of the other registers
-            bias = GetRegister(instr.gpr20.Value() + bias_offset);
-            break;
-        case TextureProcessMode::LL:
-            lod = GetRegister(instr.gpr20.Value() + bias_offset);
-            break;
-        default:
-            UNIMPLEMENTED_MSG("Unimplemented process mode={}", static_cast<u32>(process_mode));
-            break;
-        }
+    switch (process_mode) {
+    case TextureProcessMode::None:
+        break;
+    case TextureProcessMode::LZ:
+        lod = Immediate(0.0f);
+        break;
+    case TextureProcessMode::LB:
+        // If present, lod or bias are always stored in the register indexed by the gpr20 field with
+        // an offset depending on the usage of the other registers.
+        bias = GetRegister(instr.gpr20.Value() + bias_offset);
+        break;
+    case TextureProcessMode::LL:
+        lod = GetRegister(instr.gpr20.Value() + bias_offset);
+        break;
+    default:
+        UNIMPLEMENTED_MSG("Unimplemented process mode={}", static_cast<u32>(process_mode));
+        break;
    }

+    Node4 values;
    for (u32 element = 0; element < values.size(); ++element) {
-        auto copy_coords = coords;
        MetaTexture meta{*sampler, array, depth_compare, aoffi,    {}, {}, bias,
                         lod,      {},    element,       index_var};
-        values[element] = Operation(read_method, meta, std::move(copy_coords));
+        values[element] = Operation(opcode, meta, coords);
    }

    return values;
@@ -277,6 +277,10 @@ void SurfaceBaseImpl::FlushBuffer(Tegra::MemoryManager& memory_manager,
            SwizzleFunc(MortonSwizzleMode::LinearToMorton, host_ptr, params,
                        staging_buffer.data() + host_offset, level);
        }
+    } else if (params.IsBuffer()) {
+        // Buffers don't have pitch or any fancy layout property. We can just memcpy them to guest
+        // memory.
+        std::memcpy(host_ptr, staging_buffer.data(), guest_memory_size);
    } else {
        ASSERT(params.target == SurfaceTarget::Texture2D);
        ASSERT(params.num_levels == 1);
@@ -84,19 +84,16 @@ SurfaceParams SurfaceParams::CreateForTexture(const FormatLookupTable& lookup_ta
    if (entry.IsShadow() && params.type == SurfaceType::ColorTexture) {
        switch (params.pixel_format) {
        case PixelFormat::R16U:
-        case PixelFormat::R16F: {
+        case PixelFormat::R16F:
            params.pixel_format = PixelFormat::Z16;
            break;
-        }
-        case PixelFormat::R32F: {
+        case PixelFormat::R32F:
            params.pixel_format = PixelFormat::Z32F;
            break;
-        }
-        default: {
+        default:
            UNIMPLEMENTED_MSG("Unimplemented shadow convert format: {}",
                              static_cast<u32>(params.pixel_format));
        }
-        }
        params.type = GetFormatType(params.pixel_format);
    }
    params.type = GetFormatType(params.pixel_format);
@@ -168,27 +165,29 @@ SurfaceParams SurfaceParams::CreateForImage(const FormatLookupTable& lookup_tabl
    return params;
 }

-SurfaceParams SurfaceParams::CreateForDepthBuffer(
-    Core::System& system, u32 zeta_width, u32 zeta_height, Tegra::DepthFormat format,
-    u32 block_width, u32 block_height, u32 block_depth,
-    Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout type) {
+SurfaceParams SurfaceParams::CreateForDepthBuffer(Core::System& system) {
+    const auto& regs = system.GPU().Maxwell3D().regs;
+    regs.zeta_width, regs.zeta_height, regs.zeta.format, regs.zeta.memory_layout.type;
    SurfaceParams params;
-    params.is_tiled = type == Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear;
+    params.is_tiled = regs.zeta.memory_layout.type ==
+                      Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout::BlockLinear;
    params.srgb_conversion = false;
-    params.block_width = std::min(block_width, 5U);
-    params.block_height = std::min(block_height, 5U);
-    params.block_depth = std::min(block_depth, 5U);
+    params.block_width = std::min(regs.zeta.memory_layout.block_width.Value(), 5U);
+    params.block_height = std::min(regs.zeta.memory_layout.block_height.Value(), 5U);
+    params.block_depth = std::min(regs.zeta.memory_layout.block_depth.Value(), 5U);
    params.tile_width_spacing = 1;
-    params.pixel_format = PixelFormatFromDepthFormat(format);
+    params.pixel_format = PixelFormatFromDepthFormat(regs.zeta.format);
    params.type = GetFormatType(params.pixel_format);
-    params.width = zeta_width;
-    params.height = zeta_height;
-    params.target = SurfaceTarget::Texture2D;
-    params.depth = 1;
+    params.width = regs.zeta_width;
+    params.height = regs.zeta_height;
    params.pitch = 0;
    params.num_levels = 1;
    params.emulated_levels = 1;
-    params.is_layered = false;
+
+    const bool is_layered = regs.zeta_layers > 1 && params.block_depth == 0;
+    params.is_layered = is_layered;
+    params.target = is_layered ? SurfaceTarget::Texture2DArray : SurfaceTarget::Texture2D;
+    params.depth = is_layered ? regs.zeta_layers.Value() : 1U;
    return params;
 }

@@ -214,11 +213,13 @@ SurfaceParams SurfaceParams::CreateForFramebuffer(Core::System& system, std::siz
        params.width = params.pitch / bpp;
    }
    params.height = config.height;
-    params.depth = 1;
-    params.target = SurfaceTarget::Texture2D;
    params.num_levels = 1;
    params.emulated_levels = 1;
-    params.is_layered = false;
+
+    const bool is_layered = config.layers > 1 && params.block_depth == 0;
+    params.is_layered = is_layered;
+    params.depth = is_layered ? config.layers.Value() : 1;
+    params.target = is_layered ? SurfaceTarget::Texture2DArray : SurfaceTarget::Texture2D;
    return params;
 }

@@ -35,10 +35,7 @@ public:
                                        const VideoCommon::Shader::Image& entry);

    /// Creates SurfaceCachedParams for a depth buffer configuration.
-    static SurfaceParams CreateForDepthBuffer(
-        Core::System& system, u32 zeta_width, u32 zeta_height, Tegra::DepthFormat format,
-        u32 block_width, u32 block_height, u32 block_depth,
-        Tegra::Engines::Maxwell3D::Regs::InvMemoryLayout type);
+    static SurfaceParams CreateForDepthBuffer(Core::System& system);

    /// Creates SurfaceCachedParams from a framebuffer configuration.
    static SurfaceParams CreateForFramebuffer(Core::System& system, std::size_t index);
@@ -160,10 +160,7 @@ public:
            SetEmptyDepthBuffer();
            return {};
        }
-        const auto depth_params{SurfaceParams::CreateForDepthBuffer(
-            system, regs.zeta_width, regs.zeta_height, regs.zeta.format,
-            regs.zeta.memory_layout.block_width, regs.zeta.memory_layout.block_height,
-            regs.zeta.memory_layout.block_depth, regs.zeta.memory_layout.type)};
+        const auto depth_params{SurfaceParams::CreateForDepthBuffer(system)};
        auto surface_view = GetSurface(gpu_addr, cache_addr, depth_params, preserve_contents, true);
        if (depth_buffer.target)
            depth_buffer.target->MarkAsRenderTarget(false, NO_RT);
@@ -721,7 +718,6 @@ private:
    std::pair<TSurface, TView> GetSurface(const GPUVAddr gpu_addr, const CacheAddr cache_addr,
                                          const SurfaceParams& params, bool preserve_contents,
                                          bool is_render) {
-
        // Step 1
        // Check Level 1 Cache for a fast structural match. If candidate surface
        // matches at certain level we are pretty much done.
@@ -733,14 +729,18 @@ private:
                return RecycleSurface(overlaps, params, gpu_addr, preserve_contents,
                                      topological_result);
            }
+
            const auto struct_result = current_surface->MatchesStructure(params);
-            if (struct_result != MatchStructureResult::None &&
-                (params.target != SurfaceTarget::Texture3D ||
-                 current_surface->MatchTarget(params.target))) {
-                if (struct_result == MatchStructureResult::FullMatch) {
-                    return ManageStructuralMatch(current_surface, params, is_render);
-                } else {
-                    return RebuildSurface(current_surface, params, is_render);
+            if (struct_result != MatchStructureResult::None) {
+                const auto& old_params = current_surface->GetSurfaceParams();
+                const bool not_3d = params.target != SurfaceTarget::Texture3D &&
+                                    old_params.target != SurfaceTarget::Texture3D;
+                if (not_3d || current_surface->MatchTarget(params.target)) {
+                    if (struct_result == MatchStructureResult::FullMatch) {
+                        return ManageStructuralMatch(current_surface, params, is_render);
+                    } else {
+                        return RebuildSurface(current_surface, params, is_render);
+                    }
                }
            }
        }
@@ -73,14 +73,12 @@ struct Client::Impl {
                if (!parsedUrl.GetPort(&port)) {
                    port = HTTP_PORT;
                }
-                cli = std::make_unique<httplib::Client>(parsedUrl.m_Host.c_str(), port,
-                                                        TIMEOUT_SECONDS);
+                cli = std::make_unique<httplib::Client>(parsedUrl.m_Host.c_str(), port);
            } else if (parsedUrl.m_Scheme == "https") {
                if (!parsedUrl.GetPort(&port)) {
                    port = HTTPS_PORT;
                }
-                cli = std::make_unique<httplib::SSLClient>(parsedUrl.m_Host.c_str(), port,
-                                                           TIMEOUT_SECONDS);
+                cli = std::make_unique<httplib::SSLClient>(parsedUrl.m_Host.c_str(), port);
            } else {
                LOG_ERROR(WebService, "Bad URL scheme {}", parsedUrl.m_Scheme);
                return Common::WebResult{Common::WebResult::Code::InvalidURL, "Bad URL scheme"};
@@ -90,6 +88,7 @@ struct Client::Impl {
            LOG_ERROR(WebService, "Invalid URL {}", host + path);
            return Common::WebResult{Common::WebResult::Code::InvalidURL, "Invalid URL"};
        }
+        cli->set_timeout_sec(TIMEOUT_SECONDS);

        httplib::Headers params;
        if (!jwt.empty()) {
@@ -630,6 +630,7 @@ void Config::ReadRendererValues() {
    Settings::values.vulkan_device = ReadSetting(QStringLiteral("vulkan_device"), 0).toInt();
    Settings::values.resolution_factor =
        ReadSetting(QStringLiteral("resolution_factor"), 1.0).toFloat();
+    Settings::values.aspect_ratio = ReadSetting(QStringLiteral("aspect_ratio"), 0).toInt();
    Settings::values.use_frame_limit =
        ReadSetting(QStringLiteral("use_frame_limit"), true).toBool();
    Settings::values.frame_limit = ReadSetting(QStringLiteral("frame_limit"), 100).toInt();
@@ -1064,6 +1065,7 @@ void Config::SaveRendererValues() {
    WriteSetting(QStringLiteral("vulkan_device"), Settings::values.vulkan_device, 0);
    WriteSetting(QStringLiteral("resolution_factor"),
                 static_cast<double>(Settings::values.resolution_factor), 1.0);
+    WriteSetting(QStringLiteral("aspect_ratio"), Settings::values.aspect_ratio, 0);
    WriteSetting(QStringLiteral("use_frame_limit"), Settings::values.use_frame_limit, true);
    WriteSetting(QStringLiteral("frame_limit"), Settings::values.frame_limit, 100);
    WriteSetting(QStringLiteral("use_disk_shader_cache"), Settings::values.use_disk_shader_cache,
@@ -97,6 +97,7 @@ void ConfigureGraphics::SetConfiguration() {
    ui->api->setCurrentIndex(static_cast<int>(Settings::values.renderer_backend));
    ui->resolution_factor_combobox->setCurrentIndex(
        static_cast<int>(FromResolutionFactor(Settings::values.resolution_factor)));
+    ui->aspect_ratio_combobox->setCurrentIndex(Settings::values.aspect_ratio);
    ui->use_disk_shader_cache->setEnabled(runtime_lock);
    ui->use_disk_shader_cache->setChecked(Settings::values.use_disk_shader_cache);
    ui->use_accurate_gpu_emulation->setChecked(Settings::values.use_accurate_gpu_emulation);
@@ -114,6 +115,7 @@ void ConfigureGraphics::ApplyConfiguration() {
    Settings::values.vulkan_device = vulkan_device;
    Settings::values.resolution_factor =
        ToResolutionFactor(static_cast<Resolution>(ui->resolution_factor_combobox->currentIndex()));
+    Settings::values.aspect_ratio = ui->aspect_ratio_combobox->currentIndex();
    Settings::values.use_disk_shader_cache = ui->use_disk_shader_cache->isChecked();
    Settings::values.use_accurate_gpu_emulation = ui->use_accurate_gpu_emulation->isChecked();
    Settings::values.use_asynchronous_gpu_emulation =
@@ -138,6 +138,41 @@
          </item>
         </layout>
        </item>
+        <item>
+         <layout class="QHBoxLayout" name="horizontalLayout_6">
+          <item>
+           <widget class="QLabel" name="ar_label">
+            <property name="text">
+             <string>Aspect Ratio:</string>
+            </property>
+           </widget>
+          </item>
+          <item>
+           <widget class="QComboBox" name="aspect_ratio_combobox">
+            <item>
+             <property name="text">
+              <string>Default (16:9)</string>
+             </property>
+            </item>
+            <item>
+             <property name="text">
+              <string>Force 4:3</string>
+             </property>
+            </item>
+            <item>
+             <property name="text">
+              <string>Force 21:9</string>
+             </property>
+            </item>
+            <item>
+             <property name="text">
+              <string>Stretch to Window</string>
+             </property>
+            </item>
+           </widget>
+          </item>
+         </layout>
+        </item>
        <item>
         <layout class="QHBoxLayout" name="horizontalLayout_3">
          <item>
@@ -12,8 +12,8 @@
 #include "core/hle/kernel/process.h"
 #include "core/hle/kernel/readable_event.h"
 #include "core/hle/kernel/scheduler.h"
+#include "core/hle/kernel/synchronization_object.h"
 #include "core/hle/kernel/thread.h"
-#include "core/hle/kernel/wait_object.h"
 #include "core/memory.h"

 WaitTreeItem::WaitTreeItem() = default;
@@ -133,8 +133,9 @@ std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeCallstack::GetChildren() cons
    return list;
 }

-WaitTreeWaitObject::WaitTreeWaitObject(const Kernel::WaitObject& o) : object(o) {}
-WaitTreeWaitObject::~WaitTreeWaitObject() = default;
+WaitTreeSynchronizationObject::WaitTreeSynchronizationObject(const Kernel::SynchronizationObject& o)
+    : object(o) {}
+WaitTreeSynchronizationObject::~WaitTreeSynchronizationObject() = default;

 WaitTreeExpandableItem::WaitTreeExpandableItem() = default;
 WaitTreeExpandableItem::~WaitTreeExpandableItem() = default;
@@ -143,25 +144,26 @@ bool WaitTreeExpandableItem::IsExpandable() const {
    return true;
 }

-QString WaitTreeWaitObject::GetText() const {
+QString WaitTreeSynchronizationObject::GetText() const {
    return tr("[%1]%2 %3")
        .arg(object.GetObjectId())
        .arg(QString::fromStdString(object.GetTypeName()),
             QString::fromStdString(object.GetName()));
 }

-std::unique_ptr<WaitTreeWaitObject> WaitTreeWaitObject::make(const Kernel::WaitObject& object) {
+std::unique_ptr<WaitTreeSynchronizationObject> WaitTreeSynchronizationObject::make(
+    const Kernel::SynchronizationObject& object) {
    switch (object.GetHandleType()) {
    case Kernel::HandleType::ReadableEvent:
        return std::make_unique<WaitTreeEvent>(static_cast<const Kernel::ReadableEvent&>(object));
    case Kernel::HandleType::Thread:
        return std::make_unique<WaitTreeThread>(static_cast<const Kernel::Thread&>(object));
    default:
-        return std::make_unique<WaitTreeWaitObject>(object);
+        return std::make_unique<WaitTreeSynchronizationObject>(object);
    }
 }

-std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeWaitObject::GetChildren() const {
+std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeSynchronizationObject::GetChildren() const {
    std::vector<std::unique_ptr<WaitTreeItem>> list;

    const auto& threads = object.GetWaitingThreads();
@@ -173,8 +175,8 @@ std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeWaitObject::GetChildren() con
    return list;
 }

-WaitTreeObjectList::WaitTreeObjectList(const std::vector<std::shared_ptr<Kernel::WaitObject>>& list,
-                                       bool w_all)
+WaitTreeObjectList::WaitTreeObjectList(
+    const std::vector<std::shared_ptr<Kernel::SynchronizationObject>>& list, bool w_all)
    : object_list(list), wait_all(w_all) {}

 WaitTreeObjectList::~WaitTreeObjectList() = default;
@@ -188,11 +190,12 @@ QString WaitTreeObjectList::GetText() const {
 std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeObjectList::GetChildren() const {
    std::vector<std::unique_ptr<WaitTreeItem>> list(object_list.size());
    std::transform(object_list.begin(), object_list.end(), list.begin(),
-                   [](const auto& t) { return WaitTreeWaitObject::make(*t); });
+                   [](const auto& t) { return WaitTreeSynchronizationObject::make(*t); });
    return list;
 }

-WaitTreeThread::WaitTreeThread(const Kernel::Thread& thread) : WaitTreeWaitObject(thread) {}
+WaitTreeThread::WaitTreeThread(const Kernel::Thread& thread)
+    : WaitTreeSynchronizationObject(thread) {}
 WaitTreeThread::~WaitTreeThread() = default;

 QString WaitTreeThread::GetText() const {
@@ -241,7 +244,8 @@ QString WaitTreeThread::GetText() const {
    const QString pc_info = tr(" PC = 0x%1 LR = 0x%2")
                                .arg(context.pc, 8, 16, QLatin1Char{'0'})
                                .arg(context.cpu_registers[30], 8, 16, QLatin1Char{'0'});
-    return QStringLiteral("%1%2 (%3) ").arg(WaitTreeWaitObject::GetText(), pc_info, status);
+    return QStringLiteral("%1%2 (%3) ")
+        .arg(WaitTreeSynchronizationObject::GetText(), pc_info, status);
 }

 QColor WaitTreeThread::GetColor() const {
@@ -273,7 +277,7 @@ QColor WaitTreeThread::GetColor() const {
 }

 std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeThread::GetChildren() const {
-    std::vector<std::unique_ptr<WaitTreeItem>> list(WaitTreeWaitObject::GetChildren());
+    std::vector<std::unique_ptr<WaitTreeItem>> list(WaitTreeSynchronizationObject::GetChildren());

    const auto& thread = static_cast<const Kernel::Thread&>(object);

@@ -314,7 +318,7 @@ std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeThread::GetChildren() const {
    }

    if (thread.GetStatus() == Kernel::ThreadStatus::WaitSynch) {
-        list.push_back(std::make_unique<WaitTreeObjectList>(thread.GetWaitObjects(),
+        list.push_back(std::make_unique<WaitTreeObjectList>(thread.GetSynchronizationObjects(),
                                                            thread.IsSleepingOnWait()));
    }

@@ -323,7 +327,8 @@ std::vector<std::unique_ptr<WaitTreeItem>> WaitTreeThread::GetChildren() const {
    return list;
 }

-WaitTreeEvent::WaitTreeEvent(const Kernel::ReadableEvent& object) : WaitTreeWaitObject(object) {}
+WaitTreeEvent::WaitTreeEvent(const Kernel::ReadableEvent& object)
+    : WaitTreeSynchronizationObject(object) {}
 WaitTreeEvent::~WaitTreeEvent() = default;

 WaitTreeThreadList::WaitTreeThreadList(const std::vector<std::shared_ptr<Kernel::Thread>>& list)
@@ -19,7 +19,7 @@ class EmuThread;
 namespace Kernel {
 class HandleTable;
 class ReadableEvent;
-class WaitObject;
+class SynchronizationObject;
 class Thread;
 } // namespace Kernel

@@ -99,35 +99,37 @@ private:
    const Kernel::Thread& thread;
 };

-class WaitTreeWaitObject : public WaitTreeExpandableItem {
+class WaitTreeSynchronizationObject : public WaitTreeExpandableItem {
    Q_OBJECT
 public:
-    explicit WaitTreeWaitObject(const Kernel::WaitObject& object);
-    ~WaitTreeWaitObject() override;
+    explicit WaitTreeSynchronizationObject(const Kernel::SynchronizationObject& object);
+    ~WaitTreeSynchronizationObject() override;

-    static std::unique_ptr<WaitTreeWaitObject> make(const Kernel::WaitObject& object);
+    static std::unique_ptr<WaitTreeSynchronizationObject> make(
+        const Kernel::SynchronizationObject& object);
    QString GetText() const override;
    std::vector<std::unique_ptr<WaitTreeItem>> GetChildren() const override;

 protected:
-    const Kernel::WaitObject& object;
+    const Kernel::SynchronizationObject& object;
 };

 class WaitTreeObjectList : public WaitTreeExpandableItem {
    Q_OBJECT
 public:
-    WaitTreeObjectList(const std::vector<std::shared_ptr<Kernel::WaitObject>>& list, bool wait_all);
+    WaitTreeObjectList(const std::vector<std::shared_ptr<Kernel::SynchronizationObject>>& list,
+                       bool wait_all);
    ~WaitTreeObjectList() override;

    QString GetText() const override;
    std::vector<std::unique_ptr<WaitTreeItem>> GetChildren() const override;

 private:
-    const std::vector<std::shared_ptr<Kernel::WaitObject>>& object_list;
+    const std::vector<std::shared_ptr<Kernel::SynchronizationObject>>& object_list;
    bool wait_all;
 };

-class WaitTreeThread : public WaitTreeWaitObject {
+class WaitTreeThread : public WaitTreeSynchronizationObject {
    Q_OBJECT
 public:
    explicit WaitTreeThread(const Kernel::Thread& thread);
@@ -138,7 +140,7 @@ public:
    std::vector<std::unique_ptr<WaitTreeItem>> GetChildren() const override;
 };

-class WaitTreeEvent : public WaitTreeWaitObject {
+class WaitTreeEvent : public WaitTreeSynchronizationObject {
    Q_OBJECT
 public:
    explicit WaitTreeEvent(const Kernel::ReadableEvent& object);
@@ -379,6 +379,8 @@ void Config::ReadValues() {

    Settings::values.resolution_factor =
        static_cast<float>(sdl2_config->GetReal("Renderer", "resolution_factor", 1.0));
+    Settings::values.aspect_ratio =
+        static_cast<int>(sdl2_config->GetInteger("Renderer", "aspect_ratio", 0));
    Settings::values.use_frame_limit = sdl2_config->GetBoolean("Renderer", "use_frame_limit", true);
    Settings::values.frame_limit =
        static_cast<u16>(sdl2_config->GetInteger("Renderer", "frame_limit", 100));
@@ -122,6 +122,10 @@ use_shader_jit =
 # factor for the Switch resolution
 resolution_factor =

+# Aspect ratio
+# 0: Default (16:9), 1: Force 4:3, 2: Force 21:9, 3: Stretch to Window
+aspect_ratio =
+
 # Whether to enable V-Sync (caps the framerate at 60FPS) or not.
 # 0 (default): Off, 1: On
 use_vsync =
@@ -118,6 +118,8 @@ void Config::ReadValues() {
    // Renderer
    Settings::values.resolution_factor =
        static_cast<float>(sdl2_config->GetReal("Renderer", "resolution_factor", 1.0));
+    Settings::values.aspect_ratio =
+        static_cast<int>(sdl2_config->GetInteger("Renderer", "aspect_ratio", 0));
    Settings::values.use_frame_limit = false;
    Settings::values.frame_limit = 100;
    Settings::values.use_disk_shader_cache =
@@ -26,6 +26,10 @@ use_shader_jit =
 # factor for the Switch resolution
 resolution_factor =

+# Aspect ratio
+# 0: Default (16:9), 1: Force 4:3, 2: Force 21:9, 3: Stretch to Window
+aspect_ratio =
+
 # Whether to enable V-Sync (caps the framerate at 60FPS) or not.
 # 0 (default): Off, 1: On
 use_vsync =
Author	SHA1	Message	Date
ReinUsesLisp	3c648e3e2d	video_core/gpu: Remove unused functions	2020-02-25 16:53:47 -03:00
bunnei	e22ad52cdb	Merge pull request #3425 from ReinUsesLisp/layered-framebuffer texture_cache: Implement layered framebuffer attachments	2020-02-24 10:14:50 -05:00
bunnei	2b4cdb73b6	Merge pull request #3424 from ReinUsesLisp/spirv-layer vk_shader_decompiler: Implement Layer output attribute	2020-02-22 23:45:16 -05:00
bunnei	754aac331f	Merge pull request #3422 from ReinUsesLisp/buffer-flush surface_base: Implement texture buffer flushes	2020-02-22 23:09:50 -05:00
bunnei	3ef5f2017d	Merge pull request #3416 from FernandoS27/schedule Kernel: Refactors and Implement a TimeManager and SchedulerLocks	2020-02-22 22:32:21 -05:00
Fernando Sahmkow	3d0a2375ca	Scheduler: Inline global scheduler in Scheduler Lock.	2020-02-22 12:39:17 -04:00
Fernando Sahmkow	a1bf353780	Kernel: Correct pending feedback.	2020-02-22 11:51:03 -04:00
Fernando Sahmkow	b9472eae44	System: Expose Host thread registering routines from kernel.	2020-02-22 11:18:07 -04:00
Fernando Sahmkow	d219a96cc8	Kernel: Address Feedback.	2020-02-22 11:18:07 -04:00
Fernando Sahmkow	ea956c823e	Kernel: Implement Scheduler locks	2020-02-22 11:18:07 -04:00
Fernando Sahmkow	5c90d22f3d	Kernel: Implement Time Manager.	2020-02-22 11:18:07 -04:00
Fernando Sahmkow	179bafa7cb	Kernel: Rename ThreadCallbackHandleTable and Setup Thread Ids on Kernel.	2020-02-22 11:18:06 -04:00
Fernando Sahmkow	0728dfef84	Kernel: Make global scheduler depend on KernelCore	2020-02-22 11:18:06 -04:00
bunnei	d4da52bbd9	Merge pull request #3444 from bunnei/linux-audio-fix audio_core: interpolate: Fix include for climits (Linux build break).	2020-02-22 03:08:05 -05:00
bunnei	f5cf67140b	audio_core: interpolate: Fix include for climits (Linux build break).	2020-02-22 02:29:41 -05:00
bunnei	19bce3685a	Merge pull request #3310 from FearlessTobi/fast-resample audio_core: Switch to a faster interpolation technique	2020-02-22 01:54:40 -05:00
bunnei	27d57e0c4a	Merge pull request #3442 from ReinUsesLisp/fix-3d-assert shader/texture: Fix illegal 3D texture assert	2020-02-21 22:08:57 -05:00
ReinUsesLisp	7dc488a375	shader/texture: Fix illegal 3D texture assert Fix typo in the illegal 3D texture assert logic. We care about catching arrayed 3D textures or 3D shadow textures, not regular 3D textures.	2020-02-21 15:57:27 -03:00
Rodrigo Locatti	4a6a1aeab4	Merge pull request #3433 from namkazt/patch-1 renderer_vulkan: Add the rest of case for TryConvertBorderColor	2020-02-21 15:56:09 -03:00
Rodrigo Locatti	ef27b4b7b5	Merge pull request #3434 from namkazt/patch-2 vk_shader: Implement ImageLoad	2020-02-21 15:55:05 -03:00
Rodrigo Locatti	6b2719c0bb	Merge pull request #3435 from namkazt/patch-3 vulkan: add DXT23_SRGB	2020-02-21 15:48:19 -03:00
bunnei	dc7ebc2d01	Merge pull request #3423 from ReinUsesLisp/no-match-3d texture_cache: Avoid matches in 3D textures	2020-02-21 12:16:51 -05:00
Nguyen Dac Nam	c0c4da27d9	vk_device: remove left over from other branch	2020-02-21 08:56:18 +07:00
bunnei	fe8e5d8ae4	Merge pull request #3438 from bunnei/gpu-mem-manager-fix video_core: memory_manager: Flush/invalidate asynchronously when possible.	2020-02-20 20:04:05 -05:00
Nguyen Dac Nam	ecf275887b	clang-format	2020-02-20 09:39:30 +07:00
Nguyen Dac Nam	fbbad95845	shader_decompiler: only add StorageImageReadWithoutFormat when available	2020-02-20 09:28:13 +07:00
bunnei	2342c0d50e	Merge pull request #3432 from brianclinkenbeard/update-httplib Update httplib to 0.5.5	2020-02-19 21:15:06 -05:00
bunnei	bf0c929d4c	Merge pull request #3415 from ReinUsesLisp/texture-code shader/texture: Allow 2D shadow arrays and simplify code	2020-02-19 20:06:14 -05:00
bunnei	d65fa7d65c	video_core: memory_manager: Flush/invalidate asynchronously on Unmap. - Minor perf improvement.	2020-02-19 20:03:52 -05:00
Brian Clinkenbeard	d31156931d	fix issue with windows getnameinfo()	2020-02-19 16:16:49 -08:00
bunnei	b2bc7682b4	Merge pull request #3414 from ReinUsesLisp/maxwell-3d-draw maxwell_3d: Unify draw methods	2020-02-19 16:13:50 -05:00
bunnei	c8261a1a57	Merge pull request #3411 from ReinUsesLisp/specific-funcs gl_rasterizer: Use the least generic OpenGL draw function possible	2020-02-19 15:37:41 -05:00
bunnei	fd4c5463e8	Merge pull request #3437 from namkazt/patch-5 shader_conversion: add conversion I2F for Short	2020-02-19 11:27:28 -05:00
Nguyen Dac Nam	88cb05e6e7	shader_decompiler: add check in case of device not support ShaderStorageImageReadWithoutFormat	2020-02-19 12:57:22 +07:00
Nguyen Dac Nam	e61c7e9310	vk_device: setup shaderStorageImageReadWithoutFormat	2020-02-19 12:56:36 +07:00
Nguyen Dac Nam	47106ab152	vk_device: add check for shaderStorageImageReadWithoutFormat	2020-02-19 12:55:56 +07:00
Nguyen Dac Nam	1b6308727c	shader_conversion: I2F : add Assert for case src_size is Short	2020-02-19 11:40:35 +07:00
Nguyen Dac Nam	a2c2c5768f	fix warning	2020-02-19 11:10:26 +07:00
Nguyen Dac Nam	a8508f2bc0	clang-format fix	2020-02-19 11:02:59 +07:00
Nguyen Dac Nam	556f3a6e9a	shader_conversion: add conversion I2F for Short	2020-02-19 10:54:37 +07:00
bunnei	e545c2322c	Merge pull request #3410 from ReinUsesLisp/vk-draw-index vk_shader_decompiler: Fix vertex id and instance id	2020-02-18 22:37:33 -05:00
Nguyen Dac Nam	2ef8af93aa	vk_shader: add Capability StorageImageReadWithoutFormat	2020-02-19 10:16:51 +07:00
Brian Clinkenbeard	ad4e5c15fb	httplib compatibility	2020-02-18 18:04:33 -08:00
Nguyen Dac Nam	f6f0762e81	vk_shader: Implement function ImageLoad (Used by Kirby Start Allies) Please enter the commit message for your changes. Lines starting	2020-02-19 08:39:01 +07:00
Brian Clinkenbeard	7f6c686d55	update httplib to latest commit	2020-02-18 17:11:40 -08:00
Nguyen Dac Nam	ec206f7f95	fixups mistake auto commit.	2020-02-19 01:24:32 +07:00
Nguyen Dac Nam	eaf60ca5d8	Update code structure Co-Authored-By: Mat M. <mathew1800@gmail.com>	2020-02-19 01:23:08 +07:00
Fernando Sahmkow	93acfbd3a5	Merge pull request #3409 from ReinUsesLisp/host-queries query_cache: Implement a query cache and query 21 (samples passed)	2020-02-18 11:31:06 -04:00
Nguyen Dac Nam	9295966d26	add vertex UnsignedInt size RGBA	2020-02-18 21:52:51 +07:00
Nguyen Dac Nam	9fc42fffd9	add eBc2SrgbBlock to formats	2020-02-18 21:44:09 +07:00
Nguyen Dac Nam	493f0ad904	vulkan: add DXT23_SRGB	2020-02-18 21:39:50 +07:00
Nguyen Dac Nam	ba84f0988f	renderer_vulkan: Add the rest of case for TryConvertBorderColor	2020-02-18 16:52:54 +07:00
Brian Clinkenbeard	9e42025e5b	update httplib README	2020-02-17 22:54:09 -08:00
Brian Clinkenbeard	76b55c3624	0.4.2 works too	2020-02-17 22:53:25 -08:00
Brian Clinkenbeard	293d4d553a	update httplib to 0.2.6	2020-02-17 20:13:24 -08:00
bunnei	72d4c6fee0	Merge pull request #3412 from Morph1984/aspect-ratio GUI: Add aspect ratio dropdown	2020-02-17 22:02:18 -05:00
bunnei	7f380f4ffa	Merge pull request #3429 from brianclinkenbeard/fix-cmake-sdl2-arch Fix CMake build errors for certain SDL2 installations	2020-02-17 18:33:20 -05:00
Brian Clinkenbeard	13b02a1414	fix CMake build errors for certain SDL2 installations	2020-02-17 13:01:40 -08:00
bunnei	26006cbd2c	Merge pull request #3420 from namkazt/master2 nvhost_gpu: implement ChannelSetTimeslice	2020-02-17 00:31:11 -05:00
bunnei	af29e9d98e	Merge pull request #3421 from namkazt/patch-1 IUserLocalCommunicationService: stub function Initialize2	2020-02-16 04:01:42 -05:00
ReinUsesLisp	6a0220b2e1	texture_cache: Implement layered framebuffer attachments Layered framebuffer attachments is a feature that allows applications to write attach layered textures to a single attachment. What layer the fragments are written to is decided from the shader using gl_Layer.	2020-02-16 04:19:32 -03:00
ReinUsesLisp	1caf3f11c8	vk_shader_decompiler: Implement Layer output attribute SPIR-V's Layer is GLSL's gl_Layer. It lets the application choose from a shader stage (vertex, tessellation or geometry) which framebuffer layer write the output fragments to.	2020-02-16 04:17:37 -03:00
ReinUsesLisp	bfda5ff3f6	texture_cache: Avoid matches in 3D textures Code before this commit was trying to match 3D textures with another target. Fix that.	2020-02-16 04:15:42 -03:00
ReinUsesLisp	fd62bdf377	surface_base: Implement texture buffer flushes Implement downloads to guest memory from texture buffers on the generic cache and OpenGL.	2020-02-16 04:13:27 -03:00
Nguyen Dac Nam	5257a83ebe	IUserLocalCommunicationService: add function Initialize2	2020-02-16 13:24:34 +07:00
Nguyen Dac Nam	6c0eb6026b	HLE: correct function name of IUserLocalCommunicationService 402: function name should be Initialize2 (7.0.0+) not SetOperationMode Follow by: https://switchbrew.org/wiki/LDN_services#IUserLocalCommunicationService	2020-02-16 13:14:06 +07:00
namkazy	7fadc9c180	nvhost_gpu: implement ChannelSetTimeslice	2020-02-16 11:53:03 +07:00
bunnei	619f64d7f4	Merge pull request #3419 from yuzu-emu/revert-3386-gpu-mem-interface Revert "video_core: memory_manager: Use GPU interface for cache functions."	2020-02-15 22:37:29 -05:00
bunnei	0f70f68fb3	Revert "video_core: memory_manager: Use GPU interface for cache functions."	2020-02-15 17:47:15 -05:00
ReinUsesLisp	6910ade146	shader/texture: Allow 2D shadow arrays and simplify code Shadow sampler 2D arrays are supported on OpenGL, so there's no reason to forbid these. Enable textureLod usage on these. Minor style changes.	2020-02-15 02:36:28 -03:00
ReinUsesLisp	91aa58e410	maxwell_3d: Unify draw methods Pass instanced state of a draw invocation as an argument instead of having two separate virtual methods.	2020-02-14 18:09:40 -03:00
bunnei	f552d553ba	Merge pull request #3401 from FernandoS27/synchronization Set of refactors for Kernel Synchronization and Hardware Constants	2020-02-14 14:40:20 -05:00
Morph	c3d0a0d627	Add 4:3 aspect ratio and address feedback	2020-02-14 14:39:04 -05:00
bunnei	63a59b9935	Merge pull request #3379 from ReinUsesLisp/cbuf-offset shader/decode: Fix constant buffer offsets	2020-02-14 13:22:53 -05:00
Zach Hilman	4501bd8ca9	Merge pull request #3398 from brianclinkenbeard/fix-cmake-sdl2 Use config mode for finding SDL2 with CMake	2020-02-14 09:11:47 -05:00
Fernando Sahmkow	829d8c0d6b	Core: Correct compilition in GCC	2020-02-14 05:53:30 -04:00
Morph	20dc2e3622	Address feedback	2020-02-14 00:06:26 -05:00
Morph	22f58cca5e	Use enumeration instead of magic numbers	2020-02-13 23:13:23 -05:00
Morph	27e19f87c6	Add following aspect ratios: 16:9, 21:9, Stretch to Window Available as a drop down within the configure graphics tab.	2020-02-13 22:17:28 -05:00
bunnei	74feed372c	Merge pull request #3400 from makigumo/patch-1 update hwopus DecodeInterleaved for FW 7.0.0+	2020-02-13 21:26:13 -05:00
ReinUsesLisp	336a4f8e99	gl_rasterizer: Use the least generic OpenGL draw function possible This may help some implementations.	2020-02-13 21:55:21 -03:00
ReinUsesLisp	cbea8c74de	vk_shader_decompiler: Fix vertex id and instance id Vulkan's VertexIndex and InstanceIndex don't match with hardware. This is because Nvidia implements gl_VertexID and gl_InstanceID. The math that relates these is: gl_VertexIndex = gl_BaseVertex + gl_VertexID gl_InstanceIndex = gl_InstanceIndex + gl_InstanceID To emulate it using what Vulkan's SPIR-V offers (the Index variants) this commit substracts gl_Base from gl_*Index to obtain the OpenGL and hardware's equivalent.	2020-02-13 20:25:28 -03:00
Fernando Sahmkow	2bc949628d	Core: Address Feedback	2020-02-13 19:10:33 -04:00
Brian Clinkenbeard	0d85b6bfe1	Merge branch 'master' into fix-cmake-sdl2	2020-02-12 16:07:07 -08:00
Fernando Sahmkow	1e6f8aba04	Core: Set all hardware emulation constants in a single file.	2020-02-11 20:19:11 -04:00
Fernando Sahmkow	d23d504d77	Kernel: Refactor synchronization to better match RE	2020-02-11 18:47:31 -04:00
makigumo	926ea5a16d	update hwopus DecodeInterleaved for FW 7.0.0+ trivial change, see https://switchbrew.org/wiki/Audio_services#IHardwareOpusDecoder	2020-02-11 18:41:04 +01:00
Fernando Sahmkow	c5aefe42aa	Kernel: Change WaitObject to Synchronization object. In order to better reflect RE.	2020-02-11 10:46:25 -04:00
Brian Clinkenbeard	68043dd233	use config mode for finding SDL2 with CMake	2020-02-10 19:56:33 -08:00
ReinUsesLisp	bf9a822b87	shader/decode: Fix constant buffer offsets Some instances were using cbuf34.offset instead of cbuf34.GetOffset(). This returned the an invalid offset. Address those instances and rename offset to "shifted_offset" to avoid future bugs.	2020-02-05 12:19:09 -03:00
FearlessTobi	e3cad7d49e	audio_core: Switch to a faster interpolation technique	2020-01-24 00:38:22 +01:00