Vulkan: Feedback loop detection and barriers (#7226)

* Vulkan: Feedback loop improvements

This PR allows the Vulkan backend to detect attachment feedback loops. These are currently used in the following ways:

- Partial use of VK_EXT_attachment_feedback_loop_layout
  - All renderable textures have AttachmentFeedbackLoopBitExt
  - Compile pipelines with Color/DepthStencil feedback loop flags when present
- Support using FragmentBarrier for feedback loops (fixes regressions from https://github.com/Ryujinx/Ryujinx/pull/7012 )

TODO:
- AMD GPUs may need layout transitions for it to properly allow textures to be used in feedback loops.
- Use dynamic state for feedback loops. The background pipeline will always miss since feedback loop state isn't known on the GPU project.
- How is the barrier dependency flag used? (DXVK just ignores it, there's no vulkan validation...)
- Improve subpass dependencies to fix validation errors

* Mark field readonly

* Add feedback loop dynamic state

* fix: add MoltenVK resolver workaround

fix: add MoltenVK resolver workaround

* Formatting

* Fix more complaints

* RADV dcc workaround

* Use dynamic state properly, cleanup.

* Use aspects flags in more places

Directory.Packages.props

@@ -11,18 +11,18 @@
     <PackageVersion Include="Avalonia.Svg" Version="11.0.0.18" />
     <PackageVersion Include="Avalonia.Svg.Skia" Version="11.0.0.18" />
     <PackageVersion Include="CommandLineParser" Version="2.9.1" />
-    <PackageVersion Include="Concentus" Version="1.1.7" />
+    <PackageVersion Include="Concentus" Version="2.2.0" />
     <PackageVersion Include="DiscordRichPresence" Version="1.2.1.24" />
-    <PackageVersion Include="DynamicData" Version="8.4.1" />
+    <PackageVersion Include="DynamicData" Version="9.0.4" />
     <PackageVersion Include="FluentAvaloniaUI" Version="2.0.5" />
     <PackageVersion Include="GtkSharp.Dependencies" Version="1.1.1" />
     <PackageVersion Include="GtkSharp.Dependencies.osx" Version="0.0.5" />
     <PackageVersion Include="LibHac" Version="0.19.0" />
     <PackageVersion Include="Microsoft.CodeAnalysis.Analyzers" Version="3.3.4" />
     <PackageVersion Include="Microsoft.CodeAnalysis.CSharp" Version="4.9.2" />
-    <PackageVersion Include="Microsoft.IdentityModel.JsonWebTokens" Version="7.5.1" />
+    <PackageVersion Include="Microsoft.IdentityModel.JsonWebTokens" Version="8.0.1" />
     <PackageVersion Include="Microsoft.NET.Test.Sdk" Version="17.9.0" />
-    <PackageVersion Include="Microsoft.IO.RecyclableMemoryStream" Version="3.0.0" />
+    <PackageVersion Include="Microsoft.IO.RecyclableMemoryStream" Version="3.0.1" />
     <PackageVersion Include="MsgPack.Cli" Version="1.0.1" />
     <PackageVersion Include="NetCoreServer" Version="8.0.7" />
     <PackageVersion Include="NUnit" Version="3.13.3" />
@@ -39,14 +39,14 @@
     <PackageVersion Include="securifybv.ShellLink" Version="0.1.0" />
     <PackageVersion Include="shaderc.net" Version="0.1.0" />
     <PackageVersion Include="SharpZipLib" Version="1.4.2" />
-    <PackageVersion Include="Silk.NET.Vulkan" Version="2.16.0" />
+    <PackageVersion Include="Silk.NET.Vulkan" Version="2.21.0" />
-    <PackageVersion Include="Silk.NET.Vulkan.Extensions.EXT" Version="2.16.0" />
+    <PackageVersion Include="Silk.NET.Vulkan.Extensions.EXT" Version="2.21.0" />
-    <PackageVersion Include="Silk.NET.Vulkan.Extensions.KHR" Version="2.16.0" />
+    <PackageVersion Include="Silk.NET.Vulkan.Extensions.KHR" Version="2.21.0" />
-    <PackageVersion Include="SixLabors.ImageSharp" Version="2.1.8" />
+    <PackageVersion Include="SkiaSharp" Version="2.88.7" />
-    <PackageVersion Include="SixLabors.ImageSharp.Drawing" Version="1.0.0" />
+    <PackageVersion Include="SkiaSharp.NativeAssets.Linux" Version="2.88.7" />
     <PackageVersion Include="SPB" Version="0.0.4-build32" />
     <PackageVersion Include="System.IO.Hashing" Version="8.0.0" />
     <PackageVersion Include="System.Management" Version="8.0.0" />
     <PackageVersion Include="UnicornEngine.Unicorn" Version="2.0.2-rc1-fb78016" />
   </ItemGroup>
-</Project>
+</Project>

Ryujinx.sln

@@ -87,6 +87,8 @@ Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Ryujinx.Horizon", "src\Ryuj
 EndProject
 Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Ryujinx.Horizon.Kernel.Generators", "src\Ryujinx.Horizon.Kernel.Generators\Ryujinx.Horizon.Kernel.Generators.csproj", "{7F55A45D-4E1D-4A36-ADD3-87F29A285AA2}"
 EndProject
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "Ryujinx.HLE.Generators", "src\Ryujinx.HLE.Generators\Ryujinx.HLE.Generators.csproj", "{B575BCDE-2FD8-4A5D-8756-31CDD7FE81F0}"
+EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
 		Debug|Any CPU = Debug|Any CPU
@@ -249,6 +251,10 @@ Global
 		{7F55A45D-4E1D-4A36-ADD3-87F29A285AA2}.Debug|Any CPU.Build.0 = Debug|Any CPU
 		{7F55A45D-4E1D-4A36-ADD3-87F29A285AA2}.Release|Any CPU.ActiveCfg = Release|Any CPU
 		{7F55A45D-4E1D-4A36-ADD3-87F29A285AA2}.Release|Any CPU.Build.0 = Release|Any CPU
+		{B575BCDE-2FD8-4A5D-8756-31CDD7FE81F0}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
+		{B575BCDE-2FD8-4A5D-8756-31CDD7FE81F0}.Debug|Any CPU.Build.0 = Debug|Any CPU
+		{B575BCDE-2FD8-4A5D-8756-31CDD7FE81F0}.Release|Any CPU.ActiveCfg = Release|Any CPU
+		{B575BCDE-2FD8-4A5D-8756-31CDD7FE81F0}.Release|Any CPU.Build.0 = Release|Any CPU
 	EndGlobalSection
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE

src/ARMeilleure/CodeGen/Arm64/CodeGenContext.cs

@@ -237,7 +237,7 @@ namespace ARMeilleure.CodeGen.Arm64
             long originalPosition = _stream.Position;
 
             _stream.Seek(0, SeekOrigin.Begin);
-            _stream.Read(code, 0, code.Length);
+            _stream.ReadExactly(code, 0, code.Length);
             _stream.Seek(originalPosition, SeekOrigin.Begin);
 
             RelocInfo relocInfo;

src/ARMeilleure/CodeGen/RegisterAllocators/LinearScanAllocator.cs

@@ -251,7 +251,20 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                 }
             }
 
-            int selectedReg = GetHighestValueIndex(freePositions);
+            // If this is a copy destination variable, we prefer the register used for the copy source.
+            // If the register is available, then the copy can be eliminated later as both source
+            // and destination will use the same register.
+            int selectedReg;
+
+            if (current.TryGetCopySourceRegister(out int preferredReg) && freePositions[preferredReg] >= current.GetEnd())
+            {
+                selectedReg = preferredReg;
+            }
+            else
+            {
+                selectedReg = GetHighestValueIndex(freePositions);
+            }
+
             int selectedNextUse = freePositions[selectedReg];
 
             // Intervals starts and ends at odd positions, unless they span an entire
@@ -431,7 +444,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             }
         }
 
-        private static int GetHighestValueIndex(Span<int> span)
+        private static int GetHighestValueIndex(ReadOnlySpan<int> span)
         {
             int highest = int.MinValue;
 
@@ -798,12 +811,12 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             // The "visited" state is stored in the MSB of the local's value.
             const ulong VisitedMask = 1ul << 63;
 
-            bool IsVisited(Operand local)
+            static bool IsVisited(Operand local)
             {
                 return (local.GetValueUnsafe() & VisitedMask) != 0;
             }
 
-            void SetVisited(Operand local)
+            static void SetVisited(Operand local)
             {
                 local.GetValueUnsafe() |= VisitedMask;
             }
@@ -826,9 +839,25 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
                         {
                             dest.NumberLocal(_intervals.Count);
 
-                            _intervals.Add(new LiveInterval(dest));
+                            LiveInterval interval = new LiveInterval(dest);
+                            _intervals.Add(interval);
 
                             SetVisited(dest);
+
+                            // If this is a copy (or copy-like operation), set the copy source interval as well.
+                            // This is used for register preferencing later on, which allows the copy to be eliminated
+                            // in some cases.
+                            if (node.Instruction == Instruction.Copy || node.Instruction == Instruction.ZeroExtend32)
+                            {
+                                Operand source = node.GetSource(0);
+
+                                if (source.Kind == OperandKind.LocalVariable &&
+                                    source.GetLocalNumber() > 0 &&
+                                    (node.Instruction == Instruction.Copy || source.Type == OperandType.I32))
+                                {
+                                    interval.SetCopySource(_intervals[source.GetLocalNumber()]);
+                                }
+                            }
                         }
                     }
                 }

src/ARMeilleure/CodeGen/RegisterAllocators/LiveInterval.cs

@@ -19,6 +19,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             public LiveRange CurrRange;
 
             public LiveInterval Parent;
+            public LiveInterval CopySource;
 
             public UseList Uses;
             public LiveIntervalList Children;
@@ -37,6 +38,7 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
         private ref LiveRange CurrRange => ref _data->CurrRange;
         private ref LiveRange PrevRange => ref _data->PrevRange;
         private ref LiveInterval Parent => ref _data->Parent;
+        private ref LiveInterval CopySource => ref _data->CopySource;
         private ref UseList Uses => ref _data->Uses;
         private ref LiveIntervalList Children => ref _data->Children;
 
@@ -78,6 +80,25 @@ namespace ARMeilleure.CodeGen.RegisterAllocators
             Register = register;
         }
 
+        public void SetCopySource(LiveInterval copySource)
+        {
+            CopySource = copySource;
+        }
+
+        public bool TryGetCopySourceRegister(out int copySourceRegIndex)
+        {
+            if (CopySource._data != null)
+            {
+                copySourceRegIndex = CopySource.Register.Index;
+
+                return true;
+            }
+
+            copySourceRegIndex = 0;
+
+            return false;
+        }
+
         public void Reset()
         {
             PrevRange = default;

src/ARMeilleure/CodeGen/X86/Assembler.cs

@@ -1444,7 +1444,7 @@ namespace ARMeilleure.CodeGen.X86
 
                 Span<byte> buffer = new byte[jump.JumpPosition - _stream.Position];
 
-                _stream.Read(buffer);
+                _stream.ReadExactly(buffer);
                 _stream.Seek(ReservedBytesForJump, SeekOrigin.Current);
 
                 codeStream.Write(buffer);

src/ARMeilleure/Decoders/OpCodeTable.cs

@@ -822,6 +822,10 @@ namespace ARMeilleure.Decoders
             SetA32("<<<<00000100xxxxxxxxxxxx1001xxxx", InstName.Umaal,   InstEmit32.Umaal,   OpCode32AluUmull.Create);
             SetA32("<<<<0000101xxxxxxxxxxxxx1001xxxx", InstName.Umlal,   InstEmit32.Umlal,   OpCode32AluUmull.Create);
             SetA32("<<<<0000100xxxxxxxxxxxxx1001xxxx", InstName.Umull,   InstEmit32.Umull,   OpCode32AluUmull.Create);
+            SetA32("<<<<01100110xxxxxxxx11110001xxxx", InstName.Uqadd16, InstEmit32.Uqadd16, OpCode32AluReg.Create);
+            SetA32("<<<<01100110xxxxxxxx11111001xxxx", InstName.Uqadd8,  InstEmit32.Uqadd8,  OpCode32AluReg.Create);
+            SetA32("<<<<01100110xxxxxxxx11110111xxxx", InstName.Uqsub16, InstEmit32.Uqsub16, OpCode32AluReg.Create);
+            SetA32("<<<<01100110xxxxxxxx11111111xxxx", InstName.Uqsub8,  InstEmit32.Uqsub8,  OpCode32AluReg.Create);
             SetA32("<<<<0110111xxxxxxxxxxxxxxx01xxxx", InstName.Usat,    InstEmit32.Usat,    OpCode32Sat.Create);
             SetA32("<<<<01101110xxxxxxxx11110011xxxx", InstName.Usat16,  InstEmit32.Usat16,  OpCode32Sat16.Create);
             SetA32("<<<<01100101xxxxxxxx11111111xxxx", InstName.Usub8,   InstEmit32.Usub8,   OpCode32AluReg.Create);
@@ -1007,6 +1011,8 @@ namespace ARMeilleure.Decoders
             SetAsimd("111100100x10xxxxxxxx1011xxx0xxxx", InstName.Vqdmulh,     InstEmit32.Vqdmulh,      OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);
             SetAsimd("111100111x11<<10xxxx00101xx0xxx0", InstName.Vqmovn,      InstEmit32.Vqmovn,       OpCode32SimdMovn.Create,        OpCode32SimdMovn.CreateT32);
             SetAsimd("111100111x11<<10xxxx001001x0xxx0", InstName.Vqmovun,     InstEmit32.Vqmovun,      OpCode32SimdMovn.Create,        OpCode32SimdMovn.CreateT32);
+            SetAsimd("111100110x01xxxxxxxx1011xxx0xxxx", InstName.Vqrdmulh,    InstEmit32.Vqrdmulh,     OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);
+            SetAsimd("111100110x10xxxxxxxx1011xxx0xxxx", InstName.Vqrdmulh,    InstEmit32.Vqrdmulh,     OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);
             SetAsimd("1111001x1x>>>xxxxxxx100101x1xxx0", InstName.Vqrshrn,     InstEmit32.Vqrshrn,      OpCode32SimdShImmNarrow.Create, OpCode32SimdShImmNarrow.CreateT32);
             SetAsimd("111100111x>>>xxxxxxx100001x1xxx0", InstName.Vqrshrun,    InstEmit32.Vqrshrun,     OpCode32SimdShImmNarrow.Create, OpCode32SimdShImmNarrow.CreateT32);
             SetAsimd("1111001x1x>>>xxxxxxx100100x1xxx0", InstName.Vqshrn,      InstEmit32.Vqshrn,       OpCode32SimdShImmNarrow.Create, OpCode32SimdShImmNarrow.CreateT32);
@@ -1030,6 +1036,7 @@ namespace ARMeilleure.Decoders
             SetAsimd("1111001x1x>>>xxxxxxx101000x1xxxx", InstName.Vshll,       InstEmit32.Vshll,        OpCode32SimdShImmLong.Create,   OpCode32SimdShImmLong.CreateT32); // A1 encoding.
             SetAsimd("1111001x1x>>>xxxxxxx0000>xx1xxxx", InstName.Vshr,        InstEmit32.Vshr,         OpCode32SimdShImm.Create,       OpCode32SimdShImm.CreateT32);
             SetAsimd("111100101x>>>xxxxxxx100000x1xxx0", InstName.Vshrn,       InstEmit32.Vshrn,        OpCode32SimdShImmNarrow.Create, OpCode32SimdShImmNarrow.CreateT32);
+            SetAsimd("111100111x>>>xxxxxxx0101>xx1xxxx", InstName.Vsli,        InstEmit32.Vsli_I,       OpCode32SimdShImm.Create,       OpCode32SimdShImm.CreateT32);
             SetAsimd("1111001x1x>>>xxxxxxx0001>xx1xxxx", InstName.Vsra,        InstEmit32.Vsra,         OpCode32SimdShImm.Create,       OpCode32SimdShImm.CreateT32);
             SetAsimd("111101001x00xxxxxxxx0000xxx0xxxx", InstName.Vst1,        InstEmit32.Vst1,         OpCode32SimdMemSingle.Create,   OpCode32SimdMemSingle.CreateT32);
             SetAsimd("111101001x00xxxxxxxx0100xx0xxxxx", InstName.Vst1,        InstEmit32.Vst1,         OpCode32SimdMemSingle.Create,   OpCode32SimdMemSingle.CreateT32);
@@ -1054,6 +1061,7 @@ namespace ARMeilleure.Decoders
             SetAsimd("111100100x10xxxxxxxx1101xxx0xxxx", InstName.Vsub,        InstEmit32.Vsub_V,       OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);
             SetAsimd("1111001x1x<<xxxxxxx00010x0x0xxxx", InstName.Vsubl,       InstEmit32.Vsubl_I,      OpCode32SimdRegLong.Create,     OpCode32SimdRegLong.CreateT32);
             SetAsimd("1111001x1x<<xxxxxxx00011x0x0xxxx", InstName.Vsubw,       InstEmit32.Vsubw_I,      OpCode32SimdRegWide.Create,     OpCode32SimdRegWide.CreateT32);
+            SetAsimd("111100111x110010xxxx00000xx0xxxx", InstName.Vswp,        InstEmit32.Vswp,         OpCode32Simd.Create,            OpCode32Simd.CreateT32);
             SetAsimd("111100111x11xxxxxxxx10xxxxx0xxxx", InstName.Vtbl,        InstEmit32.Vtbl,         OpCode32SimdTbl.Create,         OpCode32SimdTbl.CreateT32);
             SetAsimd("111100111x11<<10xxxx00001xx0xxxx", InstName.Vtrn,        InstEmit32.Vtrn,         OpCode32SimdCmpZ.Create,        OpCode32SimdCmpZ.CreateT32);
             SetAsimd("111100100x<<xxxxxxxx1000xxx1xxxx", InstName.Vtst,        InstEmit32.Vtst,         OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);

src/ARMeilleure/Instructions/InstEmitAlu32.cs

@@ -2,6 +2,8 @@ using ARMeilleure.Decoders;
 using ARMeilleure.IntermediateRepresentation;
 using ARMeilleure.State;
 using ARMeilleure.Translation;
+using System;
+using System.Diagnostics;
 using System.Diagnostics.CodeAnalysis;
 using static ARMeilleure.Instructions.InstEmitAluHelper;
 using static ARMeilleure.Instructions.InstEmitHelper;
@@ -558,6 +560,46 @@ namespace ARMeilleure.Instructions
             EmitHsub8(context, unsigned: true);
         }
 
+        public static void Uqadd16(ArmEmitterContext context)
+        {
+            OpCode32AluReg op = (OpCode32AluReg)context.CurrOp;
+
+            SetIntA32(context, op.Rd, EmitUnsigned16BitPair(context, GetIntA32(context, op.Rn), GetIntA32(context, op.Rm), (d, n, m) =>
+            {
+                EmitSaturateUqadd(context, d, context.Add(n, m), 16);
+            }));
+        }
+
+        public static void Uqadd8(ArmEmitterContext context)
+        {
+            OpCode32AluReg op = (OpCode32AluReg)context.CurrOp;
+
+            SetIntA32(context, op.Rd, EmitUnsigned8BitPair(context, GetIntA32(context, op.Rn), GetIntA32(context, op.Rm), (d, n, m) =>
+            {
+                EmitSaturateUqadd(context, d, context.Add(n, m), 8);
+            }));
+        }
+
+        public static void Uqsub16(ArmEmitterContext context)
+        {
+            OpCode32AluReg op = (OpCode32AluReg)context.CurrOp;
+
+            SetIntA32(context, op.Rd, EmitUnsigned16BitPair(context, GetIntA32(context, op.Rn), GetIntA32(context, op.Rm), (d, n, m) =>
+            {
+                EmitSaturateUqsub(context, d, context.Subtract(n, m), 16);
+            }));
+        }
+
+        public static void Uqsub8(ArmEmitterContext context)
+        {
+            OpCode32AluReg op = (OpCode32AluReg)context.CurrOp;
+
+            SetIntA32(context, op.Rd, EmitUnsigned8BitPair(context, GetIntA32(context, op.Rn), GetIntA32(context, op.Rm), (d, n, m) =>
+            {
+                EmitSaturateUqsub(context, d, context.Subtract(n, m), 8);
+            }));
+        }
+
         public static void Usat(ArmEmitterContext context)
         {
             OpCode32Sat op = (OpCode32Sat)context.CurrOp;
@@ -934,6 +976,148 @@ namespace ARMeilleure.Instructions
             }
         }
 
+        private static void EmitSaturateUqadd(ArmEmitterContext context, Operand result, Operand value, uint saturateTo)
+        {
+            Debug.Assert(saturateTo <= 32);
+
+            if (saturateTo == 32)
+            {
+                // No saturation possible for this case.
+
+                context.Copy(result, value);
+
+                return;
+            }
+            else if (saturateTo == 0)
+            {
+                // Result is always zero if we saturate 0 bits.
+
+                context.Copy(result, Const(0));
+
+                return;
+            }
+
+            // If the result is 0, the values are equal and we don't need saturation.
+            Operand lblNoSat = Label();
+            context.BranchIfFalse(lblNoSat, context.ShiftRightUI(value, Const((int)saturateTo)));
+
+            // Saturate.
+            context.Copy(result, Const(uint.MaxValue >> (32 - (int)saturateTo)));
+
+            Operand lblExit = Label();
+            context.Branch(lblExit);
+
+            context.MarkLabel(lblNoSat);
+
+            context.Copy(result, value);
+
+            context.MarkLabel(lblExit);
+        }
+
+        private static void EmitSaturateUqsub(ArmEmitterContext context, Operand result, Operand value, uint saturateTo)
+        {
+            Debug.Assert(saturateTo <= 32);
+
+            if (saturateTo == 32)
+            {
+                // No saturation possible for this case.
+
+                context.Copy(result, value);
+
+                return;
+            }
+            else if (saturateTo == 0)
+            {
+                // Result is always zero if we saturate 0 bits.
+
+                context.Copy(result, Const(0));
+
+                return;
+            }
+
+            // If the result is 0, the values are equal and we don't need saturation.
+            Operand lblNoSat = Label();
+            context.BranchIf(lblNoSat, value, Const(0), Comparison.GreaterOrEqual);
+
+            // Saturate.
+            // Assumes that the value can only underflow, since this is only used for unsigned subtraction.
+            context.Copy(result, Const(0));
+
+            Operand lblExit = Label();
+            context.Branch(lblExit);
+
+            context.MarkLabel(lblNoSat);
+
+            context.Copy(result, value);
+
+            context.MarkLabel(lblExit);
+        }
+
+        private static Operand EmitUnsigned16BitPair(ArmEmitterContext context, Operand rn, Operand rm, Action<Operand, Operand, Operand> elementAction)
+        {
+            Operand tempD = context.AllocateLocal(OperandType.I32);
+
+            Operand tempN = context.ZeroExtend16(OperandType.I32, rn);
+            Operand tempM = context.ZeroExtend16(OperandType.I32, rm);
+            elementAction(tempD, tempN, tempM);
+            Operand tempD2 = context.ZeroExtend16(OperandType.I32, tempD);
+
+            tempN = context.ShiftRightUI(rn, Const(16));
+            tempM = context.ShiftRightUI(rm, Const(16));
+            elementAction(tempD, tempN, tempM);
+            return context.BitwiseOr(tempD2, context.ShiftLeft(tempD, Const(16)));
+        }
+
+        private static Operand EmitSigned8BitPair(ArmEmitterContext context, Operand rn, Operand rm, Action<Operand, Operand, Operand> elementAction)
+        {
+            return Emit8BitPair(context, rn, rm, elementAction, unsigned: false);
+        }
+
+        private static Operand EmitUnsigned8BitPair(ArmEmitterContext context, Operand rn, Operand rm, Action<Operand, Operand, Operand> elementAction)
+        {
+            return Emit8BitPair(context, rn, rm, elementAction, unsigned: true);
+        }
+
+        private static Operand Emit8BitPair(ArmEmitterContext context, Operand rn, Operand rm, Action<Operand, Operand, Operand> elementAction, bool unsigned)
+        {
+            Operand tempD = context.AllocateLocal(OperandType.I32);
+            Operand result = default;
+
+            for (int b = 0; b < 4; b++)
+            {
+                Operand nByte = b != 0 ? context.ShiftRightUI(rn, Const(b * 8)) : rn;
+                Operand mByte = b != 0 ? context.ShiftRightUI(rm, Const(b * 8)) : rm;
+
+                if (unsigned)
+                {
+                    nByte = context.ZeroExtend8(OperandType.I32, nByte);
+                    mByte = context.ZeroExtend8(OperandType.I32, mByte);
+                }
+                else
+                {
+                    nByte = context.SignExtend8(OperandType.I32, nByte);
+                    mByte = context.SignExtend8(OperandType.I32, mByte);
+                }
+
+                elementAction(tempD, nByte, mByte);
+
+                if (b == 0)
+                {
+                    result = context.ZeroExtend8(OperandType.I32, tempD);
+                }
+                else if (b < 3)
+                {
+                    result = context.BitwiseOr(result, context.ShiftLeft(context.ZeroExtend8(OperandType.I32, tempD), Const(b * 8)));
+                }
+                else
+                {
+                    result = context.BitwiseOr(result, context.ShiftLeft(tempD, Const(24)));
+                }
+            }
+
+            return result;
+        }
+
         private static void EmitAluStore(ArmEmitterContext context, Operand value)
         {
             IOpCode32Alu op = (IOpCode32Alu)context.CurrOp;

src/ARMeilleure/Instructions/InstEmitSimdArithmetic32.cs

@@ -1246,6 +1246,33 @@ namespace ARMeilleure.Instructions
             EmitVectorUnaryNarrowOp32(context, (op1) => EmitSatQ(context, op1, 8 << op.Size, signedSrc: true, signedDst: false), signed: true);
         }
 
+        public static void Vqrdmulh(ArmEmitterContext context)
+        {
+            OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;
+            int eSize = 8 << op.Size;
+
+            EmitVectorBinaryOpI32(context, (op1, op2) =>
+            {
+                if (op.Size == 2)
+                {
+                    op1 = context.SignExtend32(OperandType.I64, op1);
+                    op2 = context.SignExtend32(OperandType.I64, op2);
+                }
+
+                Operand res = context.Multiply(op1, op2);
+                res = context.Add(res, Const(res.Type, 1L << (eSize - 2)));
+                res = context.ShiftRightSI(res, Const(eSize - 1));
+                res = EmitSatQ(context, res, eSize, signedSrc: true, signedDst: true);
+
+                if (op.Size == 2)
+                {
+                    res = context.ConvertI64ToI32(res);
+                }
+
+                return res;
+            }, signed: true);
+        }
+
         public static void Vqsub(ArmEmitterContext context)
         {
             OpCode32SimdReg op = (OpCode32SimdReg)context.CurrOp;

src/ARMeilleure/Instructions/InstEmitSimdMove32.cs

@@ -191,6 +191,26 @@ namespace ARMeilleure.Instructions
             context.Copy(GetVecA32(op.Qd), res);
         }
 
+        public static void Vswp(ArmEmitterContext context)
+        {
+            OpCode32Simd op = (OpCode32Simd)context.CurrOp;
+
+            if (op.Q)
+            {
+                Operand temp = context.Copy(GetVecA32(op.Qd));
+
+                context.Copy(GetVecA32(op.Qd), GetVecA32(op.Qm));
+                context.Copy(GetVecA32(op.Qm), temp);
+            }
+            else
+            {
+                Operand temp = ExtractScalar(context, OperandType.I64, op.Vd);
+
+                InsertScalar(context, op.Vd, ExtractScalar(context, OperandType.I64, op.Vm));
+                InsertScalar(context, op.Vm, temp);
+            }
+        }
+
         public static void Vtbl(ArmEmitterContext context)
         {
             OpCode32SimdTbl op = (OpCode32SimdTbl)context.CurrOp;

src/ARMeilleure/Instructions/InstEmitSimdShift32.cs

@@ -130,6 +130,36 @@ namespace ARMeilleure.Instructions
             EmitVectorUnaryNarrowOp32(context, (op1) => context.ShiftRightUI(op1, Const(shift)));
         }
 
+        public static void Vsli_I(ArmEmitterContext context)
+        {
+            OpCode32SimdShImm op = (OpCode32SimdShImm)context.CurrOp;
+            int shift = op.Shift;
+            int eSize = 8 << op.Size;
+
+            ulong mask = shift != 0 ? ulong.MaxValue >> (64 - shift) : 0UL;
+
+            Operand res = GetVec(op.Qd);
+
+            int elems = op.GetBytesCount() >> op.Size;
+
+            for (int index = 0; index < elems; index++)
+            {
+                Operand me = EmitVectorExtractZx(context, op.Qm, op.Im + index, op.Size);
+
+                Operand neShifted = context.ShiftLeft(me, Const(shift));
+
+                Operand de = EmitVectorExtractZx(context, op.Qd, op.Id + index, op.Size);
+
+                Operand deMasked = context.BitwiseAnd(de, Const(mask));
+
+                Operand e = context.BitwiseOr(neShifted, deMasked);
+
+                res = EmitVectorInsert(context, res, e, op.Id + index, op.Size);
+            }
+
+            context.Copy(GetVec(op.Qd), res);
+        }
+
         public static void Vsra(ArmEmitterContext context)
         {
             OpCode32SimdShImm op = (OpCode32SimdShImm)context.CurrOp;

src/ARMeilleure/Instructions/InstName.cs

@@ -571,6 +571,10 @@ namespace ARMeilleure.Instructions
         Umaal,
         Umlal,
         Umull,
+        Uqadd16,
+        Uqadd8,
+        Uqsub16,
+        Uqsub8,
         Usat,
         Usat16,
         Usub8,
@@ -645,6 +649,7 @@ namespace ARMeilleure.Instructions
         Vqdmulh,
         Vqmovn,
         Vqmovun,
+        Vqrdmulh,
         Vqrshrn,
         Vqrshrun,
         Vqshrn,
@@ -666,6 +671,7 @@ namespace ARMeilleure.Instructions
         Vshll,
         Vshr,
         Vshrn,
+        Vsli,
         Vst1,
         Vst2,
         Vst3,
@@ -682,6 +688,7 @@ namespace ARMeilleure.Instructions
         Vsub,
         Vsubl,
         Vsubw,
+        Vswp,
         Vtbl,
         Vtrn,
         Vtst,

src/ARMeilleure/Translation/ControlFlowGraph.cs

@@ -11,7 +11,7 @@ namespace ARMeilleure.Translation
         private int[] _postOrderMap;
 
         public int LocalsCount { get; private set; }
-        public BasicBlock Entry { get; }
+        public BasicBlock Entry { get; private set; }
         public IntrusiveList<BasicBlock> Blocks { get; }
         public BasicBlock[] PostOrderBlocks => _postOrderBlocks;
         public int[] PostOrderMap => _postOrderMap;
@@ -34,6 +34,15 @@ namespace ARMeilleure.Translation
             return result;
         }
 
+        public void UpdateEntry(BasicBlock newEntry)
+        {
+            newEntry.AddSuccessor(Entry);
+
+            Entry = newEntry;
+            Blocks.AddFirst(newEntry);
+            Update();
+        }
+
         public void Update()
         {
             RemoveUnreachableBlocks(Blocks);

src/ARMeilleure/Translation/PTC/Ptc.cs

@@ -29,7 +29,7 @@ namespace ARMeilleure.Translation.PTC
         private const string OuterHeaderMagicString = "PTCohd\0\0";
         private const string InnerHeaderMagicString = "PTCihd\0\0";
 
-        private const uint InternalVersion = 6634; //! To be incremented manually for each change to the ARMeilleure project.
+        private const uint InternalVersion = 6950; //! To be incremented manually for each change to the ARMeilleure project.
 
         private const string ActualDir = "0";
         private const string BackupDir = "1";

src/ARMeilleure/Translation/RegisterUsage.cs

@@ -89,6 +89,17 @@ namespace ARMeilleure.Translation
 
         public static void RunPass(ControlFlowGraph cfg, ExecutionMode mode)
         {
+            if (cfg.Entry.Predecessors.Count != 0)
+            {
+                // We expect the entry block to have no predecessors.
+                // This is required because we have a implicit context load at the start of the function,
+                // but if there is a jump to the start of the function, the context load would trash the modified values.
+                // Here we insert a new entry block that will jump to the existing entry block.
+                BasicBlock newEntry = new BasicBlock(cfg.Blocks.Count);
+
+                cfg.UpdateEntry(newEntry);
+            }
+
             // Compute local register inputs and outputs used inside blocks.
             RegisterMask[] localInputs = new RegisterMask[cfg.Blocks.Count];
             RegisterMask[] localOutputs = new RegisterMask[cfg.Blocks.Count];
@@ -201,7 +212,7 @@ namespace ARMeilleure.Translation
 
                 // The only block without any predecessor should be the entry block.
                 // It always needs a context load as it is the first block to run.
-                if (block.Predecessors.Count == 0 || hasContextLoad)
+                if (block == cfg.Entry || hasContextLoad)
                 {
                     long vecMask = globalInputs[block.Index].VecMask;
                     long intMask = globalInputs[block.Index].IntMask;

src/ARMeilleure/Translation/TranslatorQueue.cs

@@ -80,7 +80,10 @@ namespace ARMeilleure.Translation
                         return true;
                     }
 
-                    Monitor.Wait(Sync);
+                    if (!_disposed)
+                    {
+                        Monitor.Wait(Sync);
+                    }
                 }
             }
 

src/Ryujinx.Audio.Backends.SDL2/SDL2HardwareDeviceSession.cs

@@ -89,9 +89,9 @@ namespace Ryujinx.Audio.Backends.SDL2
                 return;
             }
 
-            using IMemoryOwner<byte> samplesOwner = ByteMemoryPool.Rent(frameCount * _bytesPerFrame);
+            using SpanOwner<byte> samplesOwner = SpanOwner<byte>.Rent(frameCount * _bytesPerFrame);
 
-            Span<byte> samples = samplesOwner.Memory.Span;
+            Span<byte> samples = samplesOwner.Span;
 
             _ringBuffer.Read(samples, 0, samples.Length);
 

src/Ryujinx.Audio.Backends.SoundIo/SoundIoHardwareDeviceSession.cs

@@ -122,9 +122,9 @@ namespace Ryujinx.Audio.Backends.SoundIo
 
             int channelCount = areas.Length;
 
-            using IMemoryOwner<byte> samplesOwner = ByteMemoryPool.Rent(frameCount * bytesPerFrame);
+            using SpanOwner<byte> samplesOwner = SpanOwner<byte>.Rent(frameCount * bytesPerFrame);
 
-            Span<byte> samples = samplesOwner.Memory.Span;
+            Span<byte> samples = samplesOwner.Span;
 
             _ringBuffer.Read(samples, 0, samples.Length);
 

src/Ryujinx.Audio/Backends/Common/DynamicRingBuffer.cs

@@ -14,7 +14,7 @@ namespace Ryujinx.Audio.Backends.Common
 
         private readonly object _lock = new();
 
-        private IMemoryOwner<byte> _bufferOwner;
+        private MemoryOwner<byte> _bufferOwner;
         private Memory<byte> _buffer;
         private int _size;
         private int _headOffset;
@@ -24,7 +24,7 @@ namespace Ryujinx.Audio.Backends.Common
 
         public DynamicRingBuffer(int initialCapacity = RingBufferAlignment)
         {
-            _bufferOwner = ByteMemoryPool.RentCleared(initialCapacity);
+            _bufferOwner = MemoryOwner<byte>.RentCleared(initialCapacity);
             _buffer = _bufferOwner.Memory;
         }
 
@@ -62,7 +62,7 @@ namespace Ryujinx.Audio.Backends.Common
 
         private void SetCapacityLocked(int capacity)
         {
-            IMemoryOwner<byte> newBufferOwner = ByteMemoryPool.RentCleared(capacity);
+            MemoryOwner<byte> newBufferOwner = MemoryOwner<byte>.RentCleared(capacity);
             Memory<byte> newBuffer = newBufferOwner.Memory;
 
             if (_size > 0)

src/Ryujinx.Audio/Renderer/Server/Performance/PerformanceManager.cs

@@ -18,16 +18,12 @@ namespace Ryujinx.Audio.Renderer.Server.Performance
 
             if (version == 2)
             {
-                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion2,
+                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion2, PerformanceEntryVersion2, PerformanceDetailVersion2>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
-                                                 PerformanceEntryVersion2,
-                                                 PerformanceDetailVersion2>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
             }
 
             if (version == 1)
             {
-                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion1,
+                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion1, PerformanceEntryVersion1, PerformanceDetailVersion1>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
-                    PerformanceEntryVersion1,
-                    PerformanceDetailVersion1>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
             }
 
             throw new NotImplementedException($"Unknown Performance metrics data format version {version}");

src/Ryujinx.Audio/Renderer/Server/Performance/PerformanceManagerGeneric.cs

@@ -234,7 +234,7 @@ namespace Ryujinx.Audio.Renderer.Server.Performance
         {
             performanceEntry = null;
 
-            if (_entryDetailIndex > MaxFrameDetailCount)
+            if (_entryDetailIndex >= MaxFrameDetailCount)
             {
                 return false;
             }
@@ -245,7 +245,7 @@ namespace Ryujinx.Audio.Renderer.Server.Performance
                 EntryCountOffset = (uint)CurrentHeader.GetEntryCountOffset(),
             };
 
-            uint baseEntryOffset = (uint)(Unsafe.SizeOf<THeader>() + GetEntriesSize() + Unsafe.SizeOf<IPerformanceDetailEntry>() * _entryDetailIndex);
+            uint baseEntryOffset = (uint)(Unsafe.SizeOf<THeader>() + GetEntriesSize() + Unsafe.SizeOf<TEntryDetail>() * _entryDetailIndex);
 
             ref TEntryDetail entryDetail = ref EntriesDetail[_entryDetailIndex];
 

src/Ryujinx.Common/GraphicsDriver/DriverUtilities.cs

@@ -1,13 +1,33 @@
+using Ryujinx.Common.Utilities;
 using System;
 
 namespace Ryujinx.Common.GraphicsDriver
 {
     public static class DriverUtilities
     {
+        private static void AddMesaFlags(string envVar, string newFlags)
+        {
+            string existingFlags = Environment.GetEnvironmentVariable(envVar);
+
+            string flags = existingFlags == null ? newFlags : $"{existingFlags},{newFlags}";
+
+            OsUtils.SetEnvironmentVariableNoCaching(envVar, flags);
+        }
+
+        public static void InitDriverConfig(bool oglThreading)
+        {
+            if (OperatingSystem.IsLinux())
+            {
+                AddMesaFlags("RADV_DEBUG", "nodcc");
+            }
+
+            ToggleOGLThreading(oglThreading);
+        }
+
         public static void ToggleOGLThreading(bool enabled)
         {
-            Environment.SetEnvironmentVariable("mesa_glthread", enabled.ToString().ToLower());
+            OsUtils.SetEnvironmentVariableNoCaching("mesa_glthread", enabled.ToString().ToLower());
-            Environment.SetEnvironmentVariable("__GL_THREADED_OPTIMIZATIONS", enabled ? "1" : "0");
+            OsUtils.SetEnvironmentVariableNoCaching("__GL_THREADED_OPTIMIZATIONS", enabled ? "1" : "0");
 
             try
             {

src/Ryujinx.Common/Memory/ByteMemoryPool.ByteMemoryPoolBuffer.cs

@@ -1,51 +0,0 @@
-using System;
-using System.Buffers;
-using System.Threading;
-
-namespace Ryujinx.Common.Memory
-{
-    public partial class ByteMemoryPool
-    {
-        /// <summary>
-        /// Represents a <see cref="IMemoryOwner{Byte}"/> that wraps an array rented from
-        /// <see cref="ArrayPool{Byte}.Shared"/> and exposes it as <see cref="Memory{Byte}"/>
-        /// with a length of the requested size.
-        /// </summary>
-        private sealed class ByteMemoryPoolBuffer : IMemoryOwner<byte>
-        {
-            private byte[] _array;
-            private readonly int _length;
-
-            public ByteMemoryPoolBuffer(int length)
-            {
-                _array = ArrayPool<byte>.Shared.Rent(length);
-                _length = length;
-            }
-
-            /// <summary>
-            /// Returns a <see cref="Memory{Byte}"/> belonging to this owner.
-            /// </summary>
-            public Memory<byte> Memory
-            {
-                get
-                {
-                    byte[] array = _array;
-
-                    ObjectDisposedException.ThrowIf(array is null, this);
-
-                    return new Memory<byte>(array, 0, _length);
-                }
-            }
-
-            public void Dispose()
-            {
-                var array = Interlocked.Exchange(ref _array, null);
-
-                if (array != null)
-                {
-                    ArrayPool<byte>.Shared.Return(array);
-                }
-            }
-        }
-    }
-}

src/Ryujinx.Common/Memory/ByteMemoryPool.cs

@@ -1,106 +0,0 @@
-using System;
-using System.Buffers;
-
-namespace Ryujinx.Common.Memory
-{
-    /// <summary>
-    /// Provides a pool of re-usable byte array instances.
-    /// </summary>
-    public static partial class ByteMemoryPool
-    {
-        /// <summary>
-        /// Returns the maximum buffer size supported by this pool.
-        /// </summary>
-        public static int MaxBufferSize => Array.MaxLength;
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer may contain data from a prior use.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> Rent(long length)
-            => RentImpl(checked((int)length));
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer may contain data from a prior use.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> Rent(ulong length)
-            => RentImpl(checked((int)length));
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer may contain data from a prior use.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> Rent(int length)
-            => RentImpl(length);
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer's contents are cleared (set to all 0s) before returning.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> RentCleared(long length)
-            => RentCleared(checked((int)length));
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer's contents are cleared (set to all 0s) before returning.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> RentCleared(ulong length)
-            => RentCleared(checked((int)length));
-
-        /// <summary>
-        /// Rents a byte memory buffer from <see cref="ArrayPool{Byte}.Shared"/>.
-        /// The buffer's contents are cleared (set to all 0s) before returning.
-        /// </summary>
-        /// <param name="length">The buffer's required length in bytes</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory</returns>
-        /// <exception cref="ArgumentOutOfRangeException"></exception>
-        public static IMemoryOwner<byte> RentCleared(int length)
-        {
-            var buffer = RentImpl(length);
-
-            buffer.Memory.Span.Clear();
-
-            return buffer;
-        }
-
-        /// <summary>
-        /// Copies <paramref name="buffer"/> into a newly rented byte memory buffer.
-        /// </summary>
-        /// <param name="buffer">The byte buffer to copy</param>
-        /// <returns>A <see cref="IMemoryOwner{Byte}"/> wrapping the rented memory with <paramref name="buffer"/> copied to it</returns>
-        public static IMemoryOwner<byte> RentCopy(ReadOnlySpan<byte> buffer)
-        {
-            var copy = RentImpl(buffer.Length);
-
-            buffer.CopyTo(copy.Memory.Span);
-
-            return copy;
-        }
-
-        private static ByteMemoryPoolBuffer RentImpl(int length)
-        {
-            if ((uint)length > Array.MaxLength)
-            {
-                throw new ArgumentOutOfRangeException(nameof(length), length, null);
-            }
-
-            return new ByteMemoryPoolBuffer(length);
-        }
-    }
-}

src/Ryujinx.Common/Memory/MemoryOwner.cs

@@ -0,0 +1,140 @@
+#nullable enable
+using System;
+using System.Buffers;
+using System.Diagnostics.CodeAnalysis;
+using System.Runtime.CompilerServices;
+using System.Runtime.InteropServices;
+using System.Threading;
+
+namespace Ryujinx.Common.Memory
+{
+    /// <summary>
+    /// An <see cref="IMemoryOwner{T}"/> implementation with an embedded length and fast <see cref="Span{T}"/>
+    /// accessor, with memory allocated from <seealso cref="ArrayPool{T}.Shared"/>.
+    /// </summary>
+    /// <typeparam name="T">The type of item to store.</typeparam>
+    public sealed class MemoryOwner<T> : IMemoryOwner<T>
+    {
+        private readonly int _length;
+        private T[]? _array;
+
+        /// <summary>
+        /// Initializes a new instance of the <see cref="MemoryOwner{T}"/> class with the specified parameters.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        private MemoryOwner(int length)
+        {
+            _length = length;
+            _array = ArrayPool<T>.Shared.Rent(length);
+        }
+
+        /// <summary>
+        /// Creates a new <see cref="MemoryOwner{T}"/> instance with the specified length.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        /// <returns>A <see cref="MemoryOwner{T}"/> instance of the requested length</returns>
+        /// <exception cref="ArgumentOutOfRangeException">Thrown when <paramref name="length"/> is not valid</exception>
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static MemoryOwner<T> Rent(int length) => new(length);
+
+        /// <summary>
+        /// Creates a new <see cref="MemoryOwner{T}"/> instance with the specified length and the content cleared.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        /// <returns>A <see cref="MemoryOwner{T}"/> instance of the requested length and the content cleared</returns>
+        /// <exception cref="ArgumentOutOfRangeException">Thrown when <paramref name="length"/> is not valid</exception>
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static MemoryOwner<T> RentCleared(int length)
+        {
+            MemoryOwner<T> result = new(length);
+
+            result._array.AsSpan(0, length).Clear();
+
+            return result;
+        }
+
+        /// <summary>
+        /// Creates a new <see cref="MemoryOwner{T}"/> instance with the content copied from the specified buffer.
+        /// </summary>
+        /// <param name="buffer">The buffer to copy</param>
+        /// <returns>A <see cref="MemoryOwner{T}"/> instance with the same length and content as <paramref name="buffer"/></returns>
+        public static MemoryOwner<T> RentCopy(ReadOnlySpan<T> buffer)
+        {
+            MemoryOwner<T> result = new(buffer.Length);
+
+            buffer.CopyTo(result._array);
+
+            return result;
+        }
+
+        /// <summary>
+        /// Gets the number of items in the current instance.
+        /// </summary>
+        public int Length
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get => _length;
+        }
+
+        /// <inheritdoc/>
+        public Memory<T> Memory
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get
+            {
+                T[]? array = _array;
+
+                if (array is null)
+                {
+                    ThrowObjectDisposedException();
+                }
+
+                return new(array, 0, _length);
+            }
+        }
+
+        /// <summary>
+        /// Gets a <see cref="Span{T}"/> wrapping the memory belonging to the current instance.
+        /// </summary>
+        /// <remarks>
+        /// Uses a trick made possible by the .NET 6+ runtime array layout.
+        /// </remarks>
+        public Span<T> Span
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get
+            {
+                T[]? array = _array;
+
+                if (array is null)
+                {
+                    ThrowObjectDisposedException();
+                }
+
+                ref T firstElementRef = ref MemoryMarshal.GetArrayDataReference(array);
+
+                return MemoryMarshal.CreateSpan(ref firstElementRef, _length);
+            }
+        }
+
+        /// <inheritdoc/>
+        public void Dispose()
+        {
+            T[]? array = Interlocked.Exchange(ref _array, null);
+
+            if (array is not null)
+            {
+                ArrayPool<T>.Shared.Return(array, RuntimeHelpers.IsReferenceOrContainsReferences<T>());
+            }
+        }
+
+        /// <summary>
+        /// Throws an <see cref="ObjectDisposedException"/> when <see cref="_array"/> is <see langword="null"/>.
+        /// </summary>
+        [DoesNotReturn]
+        private static void ThrowObjectDisposedException()
+        {
+            throw new ObjectDisposedException(nameof(MemoryOwner<T>), "The buffer has already been disposed.");
+        }
+    }
+}

src/Ryujinx.Common/Memory/SpanOwner.cs

@@ -0,0 +1,114 @@
+using System;
+using System.Buffers;
+using System.Runtime.CompilerServices;
+using System.Runtime.InteropServices;
+
+namespace Ryujinx.Common.Memory
+{
+    /// <summary>
+    /// A stack-only type that rents a buffer of a specified length from <seealso cref="ArrayPool{T}.Shared"/>.
+    /// It does not implement <see cref="IDisposable"/> to avoid being boxed, but should still be disposed. This
+    /// is easy since C# 8, which allows use of C# `using` constructs on any type that has a public Dispose() method.
+    /// To keep this type simple, fast, and read-only, it does not check or guard against multiple disposals.
+    /// For all these reasons, all usage should be with a `using` block or statement.
+    /// </summary>
+    /// <typeparam name="T">The type of item to store.</typeparam>
+    public readonly ref struct SpanOwner<T>
+    {
+        private readonly int _length;
+        private readonly T[] _array;
+
+        /// <summary>
+        /// Initializes a new instance of the <see cref="SpanOwner{T}"/> struct with the specified parameters.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        private SpanOwner(int length)
+        {
+            _length = length;
+            _array = ArrayPool<T>.Shared.Rent(length);
+        }
+
+        /// <summary>
+        /// Gets an empty <see cref="SpanOwner{T}"/> instance.
+        /// </summary>
+        public static SpanOwner<T> Empty
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get => new(0);
+        }
+
+        /// <summary>
+        /// Creates a new <see cref="SpanOwner{T}"/> instance with the specified length.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        /// <returns>A <see cref="SpanOwner{T}"/> instance of the requested length</returns>
+        /// <exception cref="ArgumentOutOfRangeException">Thrown when <paramref name="length"/> is not valid</exception>
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static SpanOwner<T> Rent(int length) => new(length);
+
+        /// <summary>
+        /// Creates a new <see cref="SpanOwner{T}"/> instance with the length and the content cleared.
+        /// </summary>
+        /// <param name="length">The length of the new memory buffer to use</param>
+        /// <returns>A <see cref="SpanOwner{T}"/> instance of the requested length and the content cleared</returns>
+        /// <exception cref="ArgumentOutOfRangeException">Thrown when <paramref name="length"/> is not valid</exception>
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static SpanOwner<T> RentCleared(int length)
+        {
+            SpanOwner<T> result = new(length);
+
+            result._array.AsSpan(0, length).Clear();
+
+            return result;
+        }
+
+        /// <summary>
+        /// Creates a new <see cref="SpanOwner{T}"/> instance with the content copied from the specified buffer.
+        /// </summary>
+        /// <param name="buffer">The buffer to copy</param>
+        /// <returns>A <see cref="SpanOwner{T}"/> instance with the same length and content as <paramref name="buffer"/></returns>
+        public static SpanOwner<T> RentCopy(ReadOnlySpan<T> buffer)
+        {
+            SpanOwner<T> result = new(buffer.Length);
+
+            buffer.CopyTo(result._array);
+
+            return result;
+        }
+
+        /// <summary>
+        /// Gets the number of items in the current instance
+        /// </summary>
+        public int Length
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get => _length;
+        }
+
+        /// <summary>
+        /// Gets a <see cref="Span{T}"/> wrapping the memory belonging to the current instance.
+        /// </summary>
+        /// <remarks>
+        /// Uses a trick made possible by the .NET 6+ runtime array layout.
+        /// </remarks>
+        public Span<T> Span
+        {
+            [MethodImpl(MethodImplOptions.AggressiveInlining)]
+            get
+            {
+                ref T firstElementRef = ref MemoryMarshal.GetArrayDataReference(_array);
+
+                return MemoryMarshal.CreateSpan(ref firstElementRef, _length);
+            }
+        }
+
+        /// <summary>
+        /// Implements the duck-typed <see cref="IDisposable.Dispose"/> method.
+        /// </summary>
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public void Dispose()
+        {
+            ArrayPool<T>.Shared.Return(_array, RuntimeHelpers.IsReferenceOrContainsReferences<T>());
+        }
+    }
+}

src/Ryujinx.Common/Utilities/EmbeddedResources.cs

@@ -1,6 +1,6 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Common.Utilities;
 using System;
-using System.Buffers;
 using System.IO;
 using System.Linq;
 using System.Reflection;
@@ -42,14 +42,14 @@ namespace Ryujinx.Common
             return StreamUtils.StreamToBytes(stream);
         }
 
-        public static IMemoryOwner<byte> ReadFileToRentedMemory(string filename)
+        public static MemoryOwner<byte> ReadFileToRentedMemory(string filename)
         {
             var (assembly, path) = ResolveManifestPath(filename);
 
             return ReadFileToRentedMemory(assembly, path);
         }
 
-        public static IMemoryOwner<byte> ReadFileToRentedMemory(Assembly assembly, string filename)
+        public static MemoryOwner<byte> ReadFileToRentedMemory(Assembly assembly, string filename)
         {
             using var stream = GetStream(assembly, filename);
 

src/Ryujinx.Common/Utilities/OsUtils.cs

@@ -0,0 +1,24 @@
+using System;
+using System.Diagnostics;
+using System.Runtime.InteropServices;
+
+namespace Ryujinx.Common.Utilities
+{
+    public partial class OsUtils
+    {
+        [LibraryImport("libc", SetLastError = true)]
+        private static partial int setenv([MarshalAs(UnmanagedType.LPStr)] string name, [MarshalAs(UnmanagedType.LPStr)] string value, int overwrite);
+
+        public static void SetEnvironmentVariableNoCaching(string key, string value)
+        {
+            // Set the value in the cached environment variables, too.
+            Environment.SetEnvironmentVariable(key, value);
+
+            if (!OperatingSystem.IsWindows())
+            {
+                int res = setenv(key, value, 1);
+                Debug.Assert(res != -1);
+            }
+        }
+    }
+}

src/Ryujinx.Common/Utilities/StreamUtils.cs

@@ -1,6 +1,5 @@
 using Microsoft.IO;
 using Ryujinx.Common.Memory;
-using System.Buffers;
 using System.IO;
 using System.Threading;
 using System.Threading.Tasks;
@@ -16,7 +15,7 @@ namespace Ryujinx.Common.Utilities
             return output.ToArray();
         }
 
-        public static IMemoryOwner<byte> StreamToRentedMemory(Stream input)
+        public static MemoryOwner<byte> StreamToRentedMemory(Stream input)
         {
             if (input is MemoryStream inputMemoryStream)
             {
@@ -26,9 +25,9 @@ namespace Ryujinx.Common.Utilities
             {
                 long bytesExpected = input.Length;
 
-                IMemoryOwner<byte> ownedMemory = ByteMemoryPool.Rent(bytesExpected);
+                MemoryOwner<byte> ownedMemory = MemoryOwner<byte>.Rent(checked((int)bytesExpected));
 
-                var destSpan = ownedMemory.Memory.Span;
+                var destSpan = ownedMemory.Span;
 
                 int totalBytesRead = 0;
 
@@ -66,14 +65,14 @@ namespace Ryujinx.Common.Utilities
             return stream.ToArray();
         }
 
-        private static IMemoryOwner<byte> MemoryStreamToRentedMemory(MemoryStream input)
+        private static MemoryOwner<byte> MemoryStreamToRentedMemory(MemoryStream input)
         {
             input.Position = 0;
 
-            IMemoryOwner<byte> ownedMemory = ByteMemoryPool.Rent(input.Length);
+            MemoryOwner<byte> ownedMemory = MemoryOwner<byte>.Rent(checked((int)input.Length));
 
             // Discard the return value because we assume reading a MemoryStream always succeeds completely.
-            _ = input.Read(ownedMemory.Memory.Span);
+            _ = input.Read(ownedMemory.Span);
 
             return ownedMemory;
         }

src/Ryujinx.Cpu/Jit/MemoryManagerHostTracked.cs

@@ -303,9 +303,9 @@ namespace Ryujinx.Cpu.Jit
             }
             else
             {
-                IMemoryOwner<byte> memoryOwner = ByteMemoryPool.Rent(size);
+                MemoryOwner<byte> memoryOwner = MemoryOwner<byte>.Rent(size);
 
-                Read(va, memoryOwner.Memory.Span);
+                Read(va, memoryOwner.Span);
 
                 return new WritableRegion(this, va, memoryOwner);
             }

src/Ryujinx.Cpu/LightningJit/Arm32/Target/Arm64/InstEmitMove.cs

@@ -1,6 +1,5 @@
 using Ryujinx.Cpu.LightningJit.CodeGen;
 using Ryujinx.Cpu.LightningJit.CodeGen.Arm64;
-using System.Diagnostics;
 
 namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
 {

src/Ryujinx.Cpu/LightningJit/Arm32/Target/Arm64/InstEmitSaturate.cs

@@ -114,7 +114,7 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
             InstEmitCommon.EmitUnsigned16BitPair(context, rd, rn, rm, (d, n, m) =>
             {
                 context.Arm64Assembler.Add(d, n, m);
-                EmitSaturateUnsignedRange(context, d, 16);
+                EmitSaturateUqadd(context, d, 16);
             });
         }
 
@@ -123,7 +123,7 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
             InstEmitCommon.EmitUnsigned8BitPair(context, rd, rn, rm, (d, n, m) =>
             {
                 context.Arm64Assembler.Add(d, n, m);
-                EmitSaturateUnsignedRange(context, d, 8);
+                EmitSaturateUqadd(context, d, 8);
             });
         }
 
@@ -140,7 +140,7 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
                     context.Arm64Assembler.Add(d, n, m);
                 }
 
-                EmitSaturateUnsignedRange(context, d, 16);
+                EmitSaturateUq(context, d, 16, e == 0);
             });
         }
 
@@ -157,25 +157,25 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
                     context.Arm64Assembler.Sub(d, n, m);
                 }
 
-                EmitSaturateUnsignedRange(context, d, 16);
+                EmitSaturateUq(context, d, 16, e != 0);
             });
         }
 
         public static void Uqsub16(CodeGenContext context, uint rd, uint rn, uint rm)
         {
-            InstEmitCommon.EmitSigned16BitPair(context, rd, rn, rm, (d, n, m) =>
+            InstEmitCommon.EmitUnsigned16BitPair(context, rd, rn, rm, (d, n, m) =>
             {
                 context.Arm64Assembler.Sub(d, n, m);
-                EmitSaturateUnsignedRange(context, d, 16);
+                EmitSaturateUqsub(context, d, 16);
             });
         }
 
         public static void Uqsub8(CodeGenContext context, uint rd, uint rn, uint rm)
         {
-            InstEmitCommon.EmitSigned8BitPair(context, rd, rn, rm, (d, n, m) =>
+            InstEmitCommon.EmitUnsigned8BitPair(context, rd, rn, rm, (d, n, m) =>
             {
                 context.Arm64Assembler.Sub(d, n, m);
-                EmitSaturateUnsignedRange(context, d, 8);
+                EmitSaturateUqsub(context, d, 8);
             });
         }
 
@@ -358,7 +358,17 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
             }
         }
 
-        private static void EmitSaturateUnsignedRange(CodeGenContext context, Operand value, uint saturateTo)
+        private static void EmitSaturateUqadd(CodeGenContext context, Operand value, uint saturateTo)
+        {
+            EmitSaturateUq(context, value, saturateTo, isSub: false);
+        }
+
+        private static void EmitSaturateUqsub(CodeGenContext context, Operand value, uint saturateTo)
+        {
+            EmitSaturateUq(context, value, saturateTo, isSub: true);
+        }
+
+        private static void EmitSaturateUq(CodeGenContext context, Operand value, uint saturateTo, bool isSub)
         {
             Debug.Assert(saturateTo <= 32);
 
@@ -379,7 +389,7 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
                 return;
             }
 
-            context.Arm64Assembler.Lsr(tempRegister.Operand, value, InstEmitCommon.Const(32 - (int)saturateTo));
+            context.Arm64Assembler.Lsr(tempRegister.Operand, value, InstEmitCommon.Const((int)saturateTo));
 
             int branchIndex = context.CodeWriter.InstructionPointer;
 
@@ -387,7 +397,7 @@ namespace Ryujinx.Cpu.LightningJit.Arm32.Target.Arm64
             context.Arm64Assembler.Cbz(tempRegister.Operand, 0);
 
             // Saturate.
-            context.Arm64Assembler.Mov(value, uint.MaxValue >> (32 - (int)saturateTo));
+            context.Arm64Assembler.Mov(value, isSub ? 0u : uint.MaxValue >> (32 - (int)saturateTo));
 
             int delta = context.CodeWriter.InstructionPointer - branchIndex;
             context.CodeWriter.WriteInstructionAt(branchIndex, context.CodeWriter.ReadInstructionAt(branchIndex) | (uint)((delta & 0x7ffff) << 5));

src/Ryujinx.Graphics.Device/DeviceMemoryManager.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common.Memory;
 using Ryujinx.Memory;
 using System;
-using System.Buffers;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
 
@@ -145,9 +144,9 @@ namespace Ryujinx.Graphics.Device
             }
             else
             {
-                IMemoryOwner<byte> memoryOwner = ByteMemoryPool.Rent(size);
+                MemoryOwner<byte> memoryOwner = MemoryOwner<byte>.Rent(size);
 
-                GetSpan(va, size).CopyTo(memoryOwner.Memory.Span);
+                ReadImpl(va, memoryOwner.Span);
 
                 return new WritableRegion(this, va, memoryOwner, tracked: true);
             }

src/Ryujinx.Graphics.Device/DeviceState.cs

@@ -39,7 +39,10 @@ namespace Ryujinx.Graphics.Device
             {
                 var field = fields[fieldIndex];
 
-                int sizeOfField = SizeCalculator.SizeOf(field.FieldType);
+                var currentFieldOffset = (int)Marshal.OffsetOf<TState>(field.Name);
+                var nextFieldOffset = fieldIndex + 1 == fields.Length ? Unsafe.SizeOf<TState>() : (int)Marshal.OffsetOf<TState>(fields[fieldIndex + 1].Name);
+
+                int sizeOfField = nextFieldOffset - currentFieldOffset;
 
                 for (int i = 0; i < ((sizeOfField + 3) & ~3); i += 4)
                 {

src/Ryujinx.Graphics.Device/SizeCalculator.cs

@@ -1,63 +0,0 @@
-using System;
-using System.Reflection;
-
-namespace Ryujinx.Graphics.Device
-{
-    public static class SizeCalculator
-    {
-        public static int SizeOf(Type type)
-        {
-            // Is type a enum type?
-            if (type.IsEnum)
-            {
-                type = type.GetEnumUnderlyingType();
-            }
-
-            // Is type a pointer type?
-            if (type.IsPointer || type == typeof(IntPtr) || type == typeof(UIntPtr))
-            {
-                return IntPtr.Size;
-            }
-
-            // Is type a struct type?
-            if (type.IsValueType && !type.IsPrimitive)
-            {
-                // Check if the struct has a explicit size, if so, return that.
-                if (type.StructLayoutAttribute.Size != 0)
-                {
-                    return type.StructLayoutAttribute.Size;
-                }
-
-                // Otherwise we calculate the sum of the sizes of all fields.
-                int size = 0;
-                var fields = type.GetFields(BindingFlags.Public | BindingFlags.NonPublic | BindingFlags.Instance);
-
-                for (int fieldIndex = 0; fieldIndex < fields.Length; fieldIndex++)
-                {
-                    size += SizeOf(fields[fieldIndex].FieldType);
-                }
-
-                return size;
-            }
-
-            // Primitive types.
-            return (Type.GetTypeCode(type)) switch
-            {
-                TypeCode.SByte => sizeof(sbyte),
-                TypeCode.Byte => sizeof(byte),
-                TypeCode.Int16 => sizeof(short),
-                TypeCode.UInt16 => sizeof(ushort),
-                TypeCode.Int32 => sizeof(int),
-                TypeCode.UInt32 => sizeof(uint),
-                TypeCode.Int64 => sizeof(long),
-                TypeCode.UInt64 => sizeof(ulong),
-                TypeCode.Char => sizeof(char),
-                TypeCode.Single => sizeof(float),
-                TypeCode.Double => sizeof(double),
-                TypeCode.Decimal => sizeof(decimal),
-                TypeCode.Boolean => sizeof(bool),
-                _ => throw new ArgumentException($"Length for type \"{type.Name}\" is unknown."),
-            };
-        }
-    }
-}

src/Ryujinx.Graphics.GAL/BufferAccess.cs

@@ -6,8 +6,13 @@ namespace Ryujinx.Graphics.GAL
     public enum BufferAccess
     {
         Default = 0,
-        FlushPersistent = 1 << 0,
+        HostMemory = 1,
-        Stream = 1 << 1,
+        DeviceMemory = 2,
-        SparseCompatible = 1 << 2,
+        DeviceMemoryMapped = 3,
+
+        MemoryTypeMask = 0xf,
+
+        Stream = 1 << 4,
+        SparseCompatible = 1 << 5,
     }
 }

src/Ryujinx.Graphics.GAL/Capabilities.cs

@@ -6,6 +6,7 @@ namespace Ryujinx.Graphics.GAL
     {
         public readonly TargetApi Api;
         public readonly string VendorName;
+        public readonly SystemMemoryType MemoryType;
 
         public readonly bool HasFrontFacingBug;
         public readonly bool HasVectorIndexingBug;
@@ -50,6 +51,13 @@ namespace Ryujinx.Graphics.GAL
         public readonly bool SupportsIndirectParameters;
         public readonly bool SupportsDepthClipControl;
 
+        public readonly int UniformBufferSetIndex;
+        public readonly int StorageBufferSetIndex;
+        public readonly int TextureSetIndex;
+        public readonly int ImageSetIndex;
+        public readonly int ExtraSetBaseIndex;
+        public readonly int MaximumExtraSets;
+
         public readonly uint MaximumUniformBuffersPerStage;
         public readonly uint MaximumStorageBuffersPerStage;
         public readonly uint MaximumTexturesPerStage;
@@ -66,6 +74,7 @@ namespace Ryujinx.Graphics.GAL
         public Capabilities(
             TargetApi api,
             string vendorName,
+            SystemMemoryType memoryType,
             bool hasFrontFacingBug,
             bool hasVectorIndexingBug,
             bool needsFragmentOutputSpecialization,
@@ -107,6 +116,12 @@ namespace Ryujinx.Graphics.GAL
             bool supportsViewportSwizzle,
             bool supportsIndirectParameters,
             bool supportsDepthClipControl,
+            int uniformBufferSetIndex,
+            int storageBufferSetIndex,
+            int textureSetIndex,
+            int imageSetIndex,
+            int extraSetBaseIndex,
+            int maximumExtraSets,
             uint maximumUniformBuffersPerStage,
             uint maximumStorageBuffersPerStage,
             uint maximumTexturesPerStage,
@@ -120,6 +135,7 @@ namespace Ryujinx.Graphics.GAL
         {
             Api = api;
             VendorName = vendorName;
+            MemoryType = memoryType;
             HasFrontFacingBug = hasFrontFacingBug;
             HasVectorIndexingBug = hasVectorIndexingBug;
             NeedsFragmentOutputSpecialization = needsFragmentOutputSpecialization;
@@ -161,6 +177,12 @@ namespace Ryujinx.Graphics.GAL
             SupportsViewportSwizzle = supportsViewportSwizzle;
             SupportsIndirectParameters = supportsIndirectParameters;
             SupportsDepthClipControl = supportsDepthClipControl;
+            UniformBufferSetIndex = uniformBufferSetIndex;
+            StorageBufferSetIndex = storageBufferSetIndex;
+            TextureSetIndex = textureSetIndex;
+            ImageSetIndex = imageSetIndex;
+            ExtraSetBaseIndex = extraSetBaseIndex;
+            MaximumExtraSets = maximumExtraSets;
             MaximumUniformBuffersPerStage = maximumUniformBuffersPerStage;
             MaximumStorageBuffersPerStage = maximumStorageBuffersPerStage;
             MaximumTexturesPerStage = maximumTexturesPerStage;

src/Ryujinx.Graphics.GAL/Format.cs

@@ -711,5 +711,36 @@ namespace Ryujinx.Graphics.GAL
         {
             return format.IsUint() || format.IsSint();
         }
+
+        /// <summary>
+        /// Checks if the texture format is a float or sRGB color format.
+        /// </summary>
+        /// <remarks>
+        /// Does not include normalized, compressed or depth formats.
+        /// Float and sRGB formats do not participate in logical operations.
+        /// </remarks>
+        /// <param name="format">Texture format</param>
+        /// <returns>True if the format is a float or sRGB color format, false otherwise</returns>
+        public static bool IsFloatOrSrgb(this Format format)
+        {
+            switch (format)
+            {
+                case Format.R8G8B8A8Srgb:
+                case Format.B8G8R8A8Srgb:
+                case Format.R16Float:
+                case Format.R16G16Float:
+                case Format.R16G16B16Float:
+                case Format.R16G16B16A16Float:
+                case Format.R32Float:
+                case Format.R32G32Float:
+                case Format.R32G32B32Float:
+                case Format.R32G32B32A32Float:
+                case Format.R11G11B10Float:
+                case Format.R9G9B9E5Float:
+                    return true;
+            }
+
+            return false;
+        }
     }
 }

src/Ryujinx.Graphics.GAL/IImageArray.cs

@@ -1,6 +1,8 @@
+using System;
+
 namespace Ryujinx.Graphics.GAL
 {
-    public interface IImageArray
+    public interface IImageArray : IDisposable
     {
         void SetFormats(int index, Format[] imageFormats);
         void SetImages(int index, ITexture[] images);

src/Ryujinx.Graphics.GAL/IPipeline.cs

@@ -60,6 +60,7 @@ namespace Ryujinx.Graphics.GAL
 
         void SetImage(ShaderStage stage, int binding, ITexture texture, Format imageFormat);
         void SetImageArray(ShaderStage stage, int binding, IImageArray array);
+        void SetImageArraySeparate(ShaderStage stage, int setIndex, IImageArray array);
 
         void SetLineParameters(float width, bool smooth);
 
@@ -91,6 +92,7 @@ namespace Ryujinx.Graphics.GAL
 
         void SetTextureAndSampler(ShaderStage stage, int binding, ITexture texture, ISampler sampler);
         void SetTextureArray(ShaderStage stage, int binding, ITextureArray array);
+        void SetTextureArraySeparate(ShaderStage stage, int setIndex, ITextureArray array);
 
         void SetTransformFeedbackBuffers(ReadOnlySpan<BufferRange> buffers);
         void SetUniformBuffers(ReadOnlySpan<BufferAssignment> buffers);

src/Ryujinx.Graphics.GAL/IRenderer.cs

@@ -17,7 +17,6 @@ namespace Ryujinx.Graphics.GAL
         void BackgroundContextAction(Action action, bool alwaysBackground = false);
 
         BufferHandle CreateBuffer(int size, BufferAccess access = BufferAccess.Default);
-        BufferHandle CreateBuffer(int size, BufferAccess access, BufferHandle storageHint);
         BufferHandle CreateBuffer(nint pointer, int size);
         BufferHandle CreateBufferSparse(ReadOnlySpan<BufferRange> storageBuffers);
 

src/Ryujinx.Graphics.GAL/ITextureArray.cs

@@ -1,6 +1,8 @@
+using System;
+
 namespace Ryujinx.Graphics.GAL
 {
-    public interface ITextureArray
+    public interface ITextureArray : IDisposable
     {
         void SetSamplers(int index, ISampler[] samplers);
         void SetTextures(int index, ITexture[] textures);

src/Ryujinx.Graphics.GAL/Multithreading/CommandHelper.cs

@@ -44,7 +44,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             }
 
             Register<ActionCommand>(CommandType.Action);
-            Register<CreateBufferCommand>(CommandType.CreateBuffer);
             Register<CreateBufferAccessCommand>(CommandType.CreateBufferAccess);
             Register<CreateBufferSparseCommand>(CommandType.CreateBufferSparse);
             Register<CreateHostBufferCommand>(CommandType.CreateHostBuffer);
@@ -67,6 +66,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             Register<CounterEventDisposeCommand>(CommandType.CounterEventDispose);
             Register<CounterEventFlushCommand>(CommandType.CounterEventFlush);
 
+            Register<ImageArrayDisposeCommand>(CommandType.ImageArrayDispose);
             Register<ImageArraySetFormatsCommand>(CommandType.ImageArraySetFormats);
             Register<ImageArraySetImagesCommand>(CommandType.ImageArraySetImages);
 
@@ -89,6 +89,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             Register<TextureSetDataSliceRegionCommand>(CommandType.TextureSetDataSliceRegion);
             Register<TextureSetStorageCommand>(CommandType.TextureSetStorage);
 
+            Register<TextureArrayDisposeCommand>(CommandType.TextureArrayDispose);
             Register<TextureArraySetSamplersCommand>(CommandType.TextureArraySetSamplers);
             Register<TextureArraySetTexturesCommand>(CommandType.TextureArraySetTextures);
 
@@ -125,6 +126,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             Register<SetUniformBuffersCommand>(CommandType.SetUniformBuffers);
             Register<SetImageCommand>(CommandType.SetImage);
             Register<SetImageArrayCommand>(CommandType.SetImageArray);
+            Register<SetImageArraySeparateCommand>(CommandType.SetImageArraySeparate);
             Register<SetIndexBufferCommand>(CommandType.SetIndexBuffer);
             Register<SetLineParametersCommand>(CommandType.SetLineParameters);
             Register<SetLogicOpStateCommand>(CommandType.SetLogicOpState);
@@ -142,6 +144,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             Register<SetStencilTestCommand>(CommandType.SetStencilTest);
             Register<SetTextureAndSamplerCommand>(CommandType.SetTextureAndSampler);
             Register<SetTextureArrayCommand>(CommandType.SetTextureArray);
+            Register<SetTextureArraySeparateCommand>(CommandType.SetTextureArraySeparate);
             Register<SetUserClipDistanceCommand>(CommandType.SetUserClipDistance);
             Register<SetVertexAttribsCommand>(CommandType.SetVertexAttribs);
             Register<SetVertexBuffersCommand>(CommandType.SetVertexBuffers);

src/Ryujinx.Graphics.GAL/Multithreading/CommandType.cs

@@ -3,7 +3,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading
     enum CommandType : byte
     {
         Action,
-        CreateBuffer,
         CreateBufferAccess,
         CreateBufferSparse,
         CreateHostBuffer,
@@ -27,6 +26,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
         CounterEventDispose,
         CounterEventFlush,
 
+        ImageArrayDispose,
         ImageArraySetFormats,
         ImageArraySetImages,
 
@@ -49,6 +49,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
         TextureSetDataSliceRegion,
         TextureSetStorage,
 
+        TextureArrayDispose,
         TextureArraySetSamplers,
         TextureArraySetTextures,
 
@@ -85,6 +86,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
         SetUniformBuffers,
         SetImage,
         SetImageArray,
+        SetImageArraySeparate,
         SetIndexBuffer,
         SetLineParameters,
         SetLogicOpState,
@@ -102,6 +104,7 @@ namespace Ryujinx.Graphics.GAL.Multithreading
         SetStencilTest,
         SetTextureAndSampler,
         SetTextureArray,
+        SetTextureArraySeparate,
         SetUserClipDistance,
         SetVertexAttribs,
         SetVertexBuffers,

src/Ryujinx.Graphics.GAL/Multithreading/Commands/ImageArray/ImageArrayDisposeCommand.cs

@@ -0,0 +1,21 @@
+using Ryujinx.Graphics.GAL.Multithreading.Model;
+using Ryujinx.Graphics.GAL.Multithreading.Resources;
+
+namespace Ryujinx.Graphics.GAL.Multithreading.Commands.ImageArray
+{
+    struct ImageArrayDisposeCommand : IGALCommand, IGALCommand<ImageArrayDisposeCommand>
+    {
+        public readonly CommandType CommandType => CommandType.ImageArrayDispose;
+        private TableRef<ThreadedImageArray> _imageArray;
+
+        public void Set(TableRef<ThreadedImageArray> imageArray)
+        {
+            _imageArray = imageArray;
+        }
+
+        public static void Run(ref ImageArrayDisposeCommand command, ThreadedRenderer threaded, IRenderer renderer)
+        {
+            command._imageArray.Get(threaded).Base.Dispose();
+        }
+    }
+}

src/Ryujinx.Graphics.GAL/Multithreading/Commands/Renderer/CreateBufferCommand.cs

@@ -1,31 +0,0 @@
-namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Renderer
-{
-    struct CreateBufferCommand : IGALCommand, IGALCommand<CreateBufferCommand>
-    {
-        public readonly CommandType CommandType => CommandType.CreateBuffer;
-        private BufferHandle _threadedHandle;
-        private int _size;
-        private BufferAccess _access;
-        private BufferHandle _storageHint;
-
-        public void Set(BufferHandle threadedHandle, int size, BufferAccess access, BufferHandle storageHint)
-        {
-            _threadedHandle = threadedHandle;
-            _size = size;
-            _access = access;
-            _storageHint = storageHint;
-        }
-
-        public static void Run(ref CreateBufferCommand command, ThreadedRenderer threaded, IRenderer renderer)
-        {
-            BufferHandle hint = BufferHandle.Null;
-
-            if (command._storageHint != BufferHandle.Null)
-            {
-                hint = threaded.Buffers.MapBuffer(command._storageHint);
-            }
-
-            threaded.Buffers.AssignBuffer(command._threadedHandle, renderer.CreateBuffer(command._size, command._access, hint));
-        }
-    }
-}

src/Ryujinx.Graphics.GAL/Multithreading/Commands/SetImageArraySeparateCommand.cs

@@ -0,0 +1,26 @@
+using Ryujinx.Graphics.GAL.Multithreading.Model;
+using Ryujinx.Graphics.GAL.Multithreading.Resources;
+using Ryujinx.Graphics.Shader;
+
+namespace Ryujinx.Graphics.GAL.Multithreading.Commands
+{
+    struct SetImageArraySeparateCommand : IGALCommand, IGALCommand<SetImageArraySeparateCommand>
+    {
+        public readonly CommandType CommandType => CommandType.SetImageArraySeparate;
+        private ShaderStage _stage;
+        private int _setIndex;
+        private TableRef<IImageArray> _array;
+
+        public void Set(ShaderStage stage, int setIndex, TableRef<IImageArray> array)
+        {
+            _stage = stage;
+            _setIndex = setIndex;
+            _array = array;
+        }
+
+        public static void Run(ref SetImageArraySeparateCommand command, ThreadedRenderer threaded, IRenderer renderer)
+        {
+            renderer.Pipeline.SetImageArraySeparate(command._stage, command._setIndex, command._array.GetAs<ThreadedImageArray>(threaded)?.Base);
+        }
+    }
+}

src/Ryujinx.Graphics.GAL/Multithreading/Commands/SetTextureArraySeparateCommand.cs

@@ -0,0 +1,26 @@
+using Ryujinx.Graphics.GAL.Multithreading.Model;
+using Ryujinx.Graphics.GAL.Multithreading.Resources;
+using Ryujinx.Graphics.Shader;
+
+namespace Ryujinx.Graphics.GAL.Multithreading.Commands
+{
+    struct SetTextureArraySeparateCommand : IGALCommand, IGALCommand<SetTextureArraySeparateCommand>
+    {
+        public readonly CommandType CommandType => CommandType.SetTextureArraySeparate;
+        private ShaderStage _stage;
+        private int _setIndex;
+        private TableRef<ITextureArray> _array;
+
+        public void Set(ShaderStage stage, int setIndex, TableRef<ITextureArray> array)
+        {
+            _stage = stage;
+            _setIndex = setIndex;
+            _array = array;
+        }
+
+        public static void Run(ref SetTextureArraySeparateCommand command, ThreadedRenderer threaded, IRenderer renderer)
+        {
+            renderer.Pipeline.SetTextureArraySeparate(command._stage, command._setIndex, command._array.GetAs<ThreadedTextureArray>(threaded)?.Base);
+        }
+    }
+}

src/Ryujinx.Graphics.GAL/Multithreading/Commands/TextureArray/TextureArrayDisposeCommand.cs

@@ -0,0 +1,21 @@
+using Ryujinx.Graphics.GAL.Multithreading.Model;
+using Ryujinx.Graphics.GAL.Multithreading.Resources;
+
+namespace Ryujinx.Graphics.GAL.Multithreading.Commands.TextureArray
+{
+    struct TextureArrayDisposeCommand : IGALCommand, IGALCommand<TextureArrayDisposeCommand>
+    {
+        public readonly CommandType CommandType => CommandType.TextureArrayDispose;
+        private TableRef<ThreadedTextureArray> _textureArray;
+
+        public void Set(TableRef<ThreadedTextureArray> textureArray)
+        {
+            _textureArray = textureArray;
+        }
+
+        public static void Run(ref TextureArrayDisposeCommand command, ThreadedRenderer threaded, IRenderer renderer)
+        {
+            command._textureArray.Get(threaded).Base.Dispose();
+        }
+    }
+}

src/Ryujinx.Graphics.GAL/Multithreading/Resources/ThreadedImageArray.cs

@@ -21,6 +21,12 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Resources
             return new TableRef<T>(_renderer, reference);
         }
 
+        public void Dispose()
+        {
+            _renderer.New<ImageArrayDisposeCommand>().Set(Ref(this));
+            _renderer.QueueCommand();
+        }
+
         public void SetFormats(int index, Format[] imageFormats)
         {
             _renderer.New<ImageArraySetFormatsCommand>().Set(Ref(this), index, Ref(imageFormats));

src/Ryujinx.Graphics.GAL/Multithreading/Resources/ThreadedTextureArray.cs

@@ -22,6 +22,12 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Resources
             return new TableRef<T>(_renderer, reference);
         }
 
+        public void Dispose()
+        {
+            _renderer.New<TextureArrayDisposeCommand>().Set(Ref(this));
+            _renderer.QueueCommand();
+        }
+
         public void SetSamplers(int index, ISampler[] samplers)
         {
             _renderer.New<TextureArraySetSamplersCommand>().Set(Ref(this), index, Ref(samplers.ToArray()));

src/Ryujinx.Graphics.GAL/Multithreading/ThreadedPipeline.cs

@@ -189,6 +189,12 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             _renderer.QueueCommand();
         }
 
+        public void SetImageArraySeparate(ShaderStage stage, int setIndex, IImageArray array)
+        {
+            _renderer.New<SetImageArraySeparateCommand>().Set(stage, setIndex, Ref(array));
+            _renderer.QueueCommand();
+        }
+
         public void SetIndexBuffer(BufferRange buffer, IndexType type)
         {
             _renderer.New<SetIndexBufferCommand>().Set(buffer, type);
@@ -297,6 +303,12 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             _renderer.QueueCommand();
         }
 
+        public void SetTextureArraySeparate(ShaderStage stage, int setIndex, ITextureArray array)
+        {
+            _renderer.New<SetTextureArraySeparateCommand>().Set(stage, setIndex, Ref(array));
+            _renderer.QueueCommand();
+        }
+
         public void SetTransformFeedbackBuffers(ReadOnlySpan<BufferRange> buffers)
         {
             _renderer.New<SetTransformFeedbackBuffersCommand>().Set(_renderer.CopySpan(buffers));

src/Ryujinx.Graphics.GAL/Multithreading/ThreadedRenderer.cs

@@ -272,15 +272,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             return handle;
         }
 
-        public BufferHandle CreateBuffer(int size, BufferAccess access, BufferHandle storageHint)
-        {
-            BufferHandle handle = Buffers.CreateBufferHandle();
-            New<CreateBufferCommand>().Set(handle, size, access, storageHint);
-            QueueCommand();
-
-            return handle;
-        }
-
         public BufferHandle CreateBuffer(nint pointer, int size)
         {
             BufferHandle handle = Buffers.CreateBufferHandle();

src/Ryujinx.Graphics.GAL/ResourceLayout.cs

@@ -74,13 +74,15 @@ namespace Ryujinx.Graphics.GAL
         public int ArrayLength { get; }
         public ResourceType Type { get; }
         public ResourceStages Stages { get; }
+        public bool Write { get; }
 
-        public ResourceUsage(int binding, int arrayLength, ResourceType type, ResourceStages stages)
+        public ResourceUsage(int binding, int arrayLength, ResourceType type, ResourceStages stages, bool write)
         {
             Binding = binding;
             ArrayLength = arrayLength;
             Type = type;
             Stages = stages;
+            Write = write;
         }
 
         public override int GetHashCode()

src/Ryujinx.Graphics.GAL/SystemMemoryType.cs

@@ -0,0 +1,29 @@
+namespace Ryujinx.Graphics.GAL
+{
+    public enum SystemMemoryType
+    {
+        /// <summary>
+        /// The backend manages the ownership of memory. This mode never supports host imported memory.
+        /// </summary>
+        BackendManaged,
+
+        /// <summary>
+        /// Device memory has similar performance to host memory, usually because it's shared between CPU/GPU.
+        /// Use host memory whenever possible.
+        /// </summary>
+        UnifiedMemory,
+
+        /// <summary>
+        /// GPU storage to host memory goes though a slow interconnect, but it would still be preferable to use it if the data is flushed back often.
+        /// Assumes constant buffer access to host memory is rather fast.
+        /// </summary>
+        DedicatedMemory,
+
+        /// <summary>
+        /// GPU storage to host memory goes though a slow interconnect, that is very slow when doing access from storage.
+        /// When frequently accessed, copy buffers to host memory using DMA.
+        /// Assumes constant buffer access to host memory is rather fast.
+        /// </summary>
+        DedicatedMemorySlowStorage
+    }
+}

src/Ryujinx.Graphics.GAL/TextureCreateInfo.cs

@@ -1,6 +1,5 @@
 using Ryujinx.Common;
 using System;
-using System.Numerics;
 
 namespace Ryujinx.Graphics.GAL
 {
@@ -113,25 +112,6 @@ namespace Ryujinx.Graphics.GAL
             return 1;
         }
 
-        public int GetLevelsClamped()
-        {
-            int maxSize = Width;
-
-            if (Target != Target.Texture1D &&
-                Target != Target.Texture1DArray)
-            {
-                maxSize = Math.Max(maxSize, Height);
-            }
-
-            if (Target == Target.Texture3D)
-            {
-                maxSize = Math.Max(maxSize, Depth);
-            }
-
-            int maxLevels = BitOperations.Log2((uint)maxSize) + 1;
-            return Math.Min(Levels, maxLevels);
-        }
-
         private static int GetLevelSize(int size, int level)
         {
             return Math.Max(1, size >> level);

src/Ryujinx.Graphics.Gpu/Engine/InlineToMemory/InlineToMemoryClass.cs

@@ -199,7 +199,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.InlineToMemory
                     if (target != null)
                     {
                         target.SynchronizeMemory();
-                        var dataCopy = ByteMemoryPool.RentCopy(data);
+                        var dataCopy = MemoryOwner<byte>.RentCopy(data);
                         target.SetData(dataCopy, 0, 0, new GAL.Rectangle<int>(_dstX, _dstY, _lineLengthIn / target.Info.FormatInfo.BytesPerPixel, _lineCount));
                         target.SignalModified();
 

src/Ryujinx.Graphics.Gpu/Engine/MME/MacroHLE.cs

@@ -5,6 +5,7 @@ using Ryujinx.Graphics.GAL;
 using Ryujinx.Graphics.Gpu.Engine.GPFifo;
 using Ryujinx.Graphics.Gpu.Engine.Threed;
 using Ryujinx.Graphics.Gpu.Engine.Types;
+using Ryujinx.Graphics.Gpu.Memory;
 using Ryujinx.Memory.Range;
 using System;
 using System.Collections.Generic;
@@ -495,8 +496,8 @@ namespace Ryujinx.Graphics.Gpu.Engine.MME
 
             ulong indirectBufferSize = (ulong)maxDrawCount * (ulong)stride;
 
-            MultiRange indirectBufferRange = bufferCache.TranslateAndCreateMultiBuffers(_processor.MemoryManager, indirectBufferGpuVa, indirectBufferSize);
+            MultiRange indirectBufferRange = bufferCache.TranslateAndCreateMultiBuffers(_processor.MemoryManager, indirectBufferGpuVa, indirectBufferSize, BufferStage.Indirect);
-            MultiRange parameterBufferRange = bufferCache.TranslateAndCreateMultiBuffers(_processor.MemoryManager, parameterBufferGpuVa, 4);
+            MultiRange parameterBufferRange = bufferCache.TranslateAndCreateMultiBuffers(_processor.MemoryManager, parameterBufferGpuVa, 4, BufferStage.Indirect);
 
             _processor.ThreedClass.DrawIndirect(
                 topology,

src/Ryujinx.Graphics.Gpu/Engine/Threed/ComputeDraw/VtgAsComputeContext.cs

@@ -438,7 +438,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
 
             ReadOnlySpan<byte> dataBytes = MemoryMarshal.Cast<int, byte>(data);
 
-            BufferHandle buffer = _context.Renderer.CreateBuffer(dataBytes.Length);
+            BufferHandle buffer = _context.Renderer.CreateBuffer(dataBytes.Length, BufferAccess.DeviceMemory);
             _context.Renderer.SetBufferData(buffer, 0, dataBytes);
 
             return new IndexBuffer(buffer, count, dataBytes.Length);
@@ -529,7 +529,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
         {
             if (_dummyBuffer == BufferHandle.Null)
             {
-                _dummyBuffer = _context.Renderer.CreateBuffer(DummyBufferSize);
+                _dummyBuffer = _context.Renderer.CreateBuffer(DummyBufferSize, BufferAccess.DeviceMemory);
                 _context.Renderer.Pipeline.ClearBuffer(_dummyBuffer, 0, DummyBufferSize, 0);
             }
 
@@ -550,7 +550,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
                     _context.Renderer.DeleteBuffer(_sequentialIndexBuffer);
                 }
 
-                _sequentialIndexBuffer = _context.Renderer.CreateBuffer(count * sizeof(uint));
+                _sequentialIndexBuffer = _context.Renderer.CreateBuffer(count * sizeof(uint), BufferAccess.DeviceMemory);
                 _sequentialIndexBufferCount = count;
 
                 Span<int> data = new int[count];
@@ -583,7 +583,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
                     _context.Renderer.DeleteBuffer(buffer.Handle);
                 }
 
-                buffer.Handle = _context.Renderer.CreateBuffer(newSize);
+                buffer.Handle = _context.Renderer.CreateBuffer(newSize, BufferAccess.DeviceMemory);
                 buffer.Size = newSize;
             }
 

src/Ryujinx.Graphics.Gpu/Engine/Threed/ComputeDraw/VtgAsComputeState.cs

@@ -3,6 +3,7 @@ using Ryujinx.Common.Logging;
 using Ryujinx.Graphics.GAL;
 using Ryujinx.Graphics.Gpu.Engine.Types;
 using Ryujinx.Graphics.Gpu.Image;
+using Ryujinx.Graphics.Gpu.Memory;
 using Ryujinx.Graphics.Gpu.Shader;
 using Ryujinx.Graphics.Shader;
 using Ryujinx.Graphics.Shader.Translation;
@@ -370,7 +371,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
         {
             var memoryManager = _channel.MemoryManager;
 
-            BufferRange range = memoryManager.Physical.BufferCache.GetBufferRange(memoryManager.GetPhysicalRegions(address, size));
+            BufferRange range = memoryManager.Physical.BufferCache.GetBufferRange(memoryManager.GetPhysicalRegions(address, size), BufferStage.VertexBuffer);
 
             ITexture bufferTexture = _vacContext.EnsureBufferTexture(index + 2, format);
             bufferTexture.SetStorage(range);
@@ -412,7 +413,9 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed.ComputeDraw
             var memoryManager = _channel.MemoryManager;
 
             ulong misalign = address & ((ulong)_context.Capabilities.TextureBufferOffsetAlignment - 1);
-            BufferRange range = memoryManager.Physical.BufferCache.GetBufferRange(memoryManager.GetPhysicalRegions(address + indexOffset - misalign, size + misalign));
+            BufferRange range = memoryManager.Physical.BufferCache.GetBufferRange(
+                memoryManager.GetPhysicalRegions(address + indexOffset - misalign, size + misalign),
+                BufferStage.IndexBuffer);
             misalignedOffset = (int)misalign >> shift;
 
             SetIndexBufferTexture(reservations, range, format);

src/Ryujinx.Graphics.Gpu/Engine/Threed/DrawManager.cs

@@ -684,8 +684,8 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed
 
             if (hasCount)
             {
-                var indirectBuffer = memory.BufferCache.GetBufferRange(indirectBufferRange);
+                var indirectBuffer = memory.BufferCache.GetBufferRange(indirectBufferRange, BufferStage.Indirect);
-                var parameterBuffer = memory.BufferCache.GetBufferRange(parameterBufferRange);
+                var parameterBuffer = memory.BufferCache.GetBufferRange(parameterBufferRange, BufferStage.Indirect);
 
                 if (indexed)
                 {
@@ -698,7 +698,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed
             }
             else
             {
-                var indirectBuffer = memory.BufferCache.GetBufferRange(indirectBufferRange);
+                var indirectBuffer = memory.BufferCache.GetBufferRange(indirectBufferRange, BufferStage.Indirect);
 
                 if (indexed)
                 {

src/Ryujinx.Graphics.Gpu/Engine/Threed/StateUpdateTracker.cs

@@ -79,7 +79,10 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed
             {
                 var field = fields[fieldIndex];
 
-                int sizeOfField = SizeCalculator.SizeOf(field.FieldType);
+                var currentFieldOffset = (int)Marshal.OffsetOf<TState>(field.Name);
+                var nextFieldOffset = fieldIndex + 1 == fields.Length ? Unsafe.SizeOf<TState>() : (int)Marshal.OffsetOf<TState>(fields[fieldIndex + 1].Name);
+
+                int sizeOfField = nextFieldOffset - currentFieldOffset;
 
                 if (fieldToDelegate.TryGetValue(field.Name, out int entryIndex))
                 {

src/Ryujinx.Graphics.Gpu/Engine/Threed/ThreedClassState.cs

@@ -415,7 +415,13 @@ namespace Ryujinx.Graphics.Gpu.Engine.Threed
 #pragma warning disable CS0649 // Field is never assigned to
         public int Width;
         public int Height;
-        public int Depth;
+        public ushort Depth;
+        public ushort Flags;
+
+        public readonly bool UnpackIsLayered()
+        {
+            return (Flags & 1) == 0;
+        }
 #pragma warning restore CS0649
     }
 

src/Ryujinx.Graphics.Gpu/GpuContext.cs

@@ -393,17 +393,18 @@ namespace Ryujinx.Graphics.Gpu
 
             if (force || _pendingSync || (syncpoint && SyncpointActions.Count > 0))
             {
-                Renderer.CreateSync(SyncNumber, strict);
-
                 foreach (var action in SyncActions)
                 {
                     action.SyncPreAction(syncpoint);
                 }
+
                 foreach (var action in SyncpointActions)
                 {
                     action.SyncPreAction(syncpoint);
                 }
 
+                Renderer.CreateSync(SyncNumber, strict);
+
                 SyncNumber++;
 
                 SyncActions.RemoveAll(action => action.SyncAction(syncpoint));

src/Ryujinx.Graphics.Gpu/Image/Texture.cs

@@ -1,4 +1,5 @@
 using Ryujinx.Common.Logging;
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL;
 using Ryujinx.Graphics.Gpu.Memory;
 using Ryujinx.Graphics.Texture;
@@ -805,7 +806,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                         sliceDepth,
                         levels,
                         layers,
-                        out IMemoryOwner<byte> decoded))
+                        out MemoryOwner<byte> decoded))
                     {
                         string texInfo = $"{Info.Target} {Info.FormatInfo.Format} {Info.Width}x{Info.Height}x{Info.DepthOrLayers} levels {Info.Levels}";
 

src/Ryujinx.Graphics.Gpu/Image/TextureBindingInfo.cs

@@ -19,6 +19,11 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// </summary>
         public Format Format { get; }
 
+        /// <summary>
+        /// Shader texture host set index.
+        /// </summary>
+        public int Set { get; }
+
         /// <summary>
         /// Shader texture host binding point.
         /// </summary>
@@ -54,15 +59,17 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// </summary>
         /// <param name="target">The shader sampler target type</param>
         /// <param name="format">Format of the image as declared on the shader</param>
+        /// <param name="set">Shader texture host set index</param>
         /// <param name="binding">The shader texture binding point</param>
         /// <param name="arrayLength">For array of textures, this indicates the length of the array. A value of one indicates it is not an array</param>
         /// <param name="cbufSlot">Constant buffer slot where the texture handle is located</param>
         /// <param name="handle">The shader texture handle (read index into the texture constant buffer)</param>
         /// <param name="flags">The texture's usage flags, indicating how it is used in the shader</param>
-        public TextureBindingInfo(Target target, Format format, int binding, int arrayLength, int cbufSlot, int handle, TextureUsageFlags flags)
+        public TextureBindingInfo(Target target, Format format, int set, int binding, int arrayLength, int cbufSlot, int handle, TextureUsageFlags flags)
         {
             Target = target;
             Format = format;
+            Set = set;
             Binding = binding;
             ArrayLength = arrayLength;
             CbufSlot = cbufSlot;
@@ -74,6 +81,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// Constructs the texture binding information structure.
         /// </summary>
         /// <param name="target">The shader sampler target type</param>
+        /// <param name="set">Shader texture host set index</param>
         /// <param name="binding">The shader texture binding point</param>
         /// <param name="arrayLength">For array of textures, this indicates the length of the array. A value of one indicates it is not an array</param>
         /// <param name="cbufSlot">Constant buffer slot where the texture handle is located</param>
@@ -82,12 +90,13 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="isSamplerOnly">Indicates that the binding is for a sampler</param>
         public TextureBindingInfo(
             Target target,
+            int set,
             int binding,
             int arrayLength,
             int cbufSlot,
             int handle,
             TextureUsageFlags flags,
-            bool isSamplerOnly) : this(target, 0, binding, arrayLength, cbufSlot, handle, flags)
+            bool isSamplerOnly) : this(target, 0, set, binding, arrayLength, cbufSlot, handle, flags)
         {
             IsSamplerOnly = isSamplerOnly;
         }

src/Ryujinx.Graphics.Gpu/Image/TextureBindingsArrayCache.cs

@@ -340,7 +340,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             /// <returns>True if any used entries of the pool might have been modified, false otherwise</returns>
             public bool SamplerPoolModified()
             {
-                return SamplerPool.WasModified(ref _samplerPoolSequence);
+                return SamplerPool != null && SamplerPool.WasModified(ref _samplerPoolSequence);
             }
         }
 
@@ -516,12 +516,15 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
 
                 // Check if any of our cached samplers changed on the pool.
-                foreach ((int samplerId, (Sampler sampler, SamplerDescriptor descriptor)) in SamplerIds)
+                if (SamplerPool != null)
                 {
-                    if (SamplerPool.GetCachedItem(samplerId) != sampler ||
+                    foreach ((int samplerId, (Sampler sampler, SamplerDescriptor descriptor)) in SamplerIds)
-                        (sampler == null && SamplerPool.IsValidId(samplerId) && !SamplerPool.GetDescriptorRef(samplerId).Equals(descriptor)))
                     {
-                        return true;
+                        if (SamplerPool.GetCachedItem(samplerId) != sampler ||
+                            (sampler == null && SamplerPool.IsValidId(samplerId) && !SamplerPool.GetDescriptorRef(samplerId).Equals(descriptor)))
+                        {
+                            return true;
+                        }
                     }
                 }
 
@@ -566,7 +569,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             int stageIndex,
             int textureBufferIndex,
             SamplerIndex samplerIndex,
-            TextureBindingInfo bindingInfo)
+            in TextureBindingInfo bindingInfo)
         {
             Update(texturePool, samplerPool, stage, stageIndex, textureBufferIndex, isImage: false, samplerIndex, bindingInfo);
         }
@@ -579,7 +582,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="stageIndex">Shader stage index where the array is used</param>
         /// <param name="textureBufferIndex">Texture constant buffer index</param>
         /// <param name="bindingInfo">Array binding information</param>
-        public void UpdateImageArray(TexturePool texturePool, ShaderStage stage, int stageIndex, int textureBufferIndex, TextureBindingInfo bindingInfo)
+        public void UpdateImageArray(TexturePool texturePool, ShaderStage stage, int stageIndex, int textureBufferIndex, in TextureBindingInfo bindingInfo)
         {
             Update(texturePool, null, stage, stageIndex, textureBufferIndex, isImage: true, SamplerIndex.ViaHeaderIndex, bindingInfo);
         }
@@ -603,7 +606,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             int textureBufferIndex,
             bool isImage,
             SamplerIndex samplerIndex,
-            TextureBindingInfo bindingInfo)
+            in TextureBindingInfo bindingInfo)
         {
             if (IsDirectHandleType(bindingInfo.Handle))
             {
@@ -623,7 +626,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="stage">Shader stage where the array is used</param>
         /// <param name="isImage">Whether the array is a image or texture array</param>
         /// <param name="bindingInfo">Array binding information</param>
-        private void UpdateFromPool(TexturePool texturePool, SamplerPool samplerPool, ShaderStage stage, bool isImage, TextureBindingInfo bindingInfo)
+        private void UpdateFromPool(TexturePool texturePool, SamplerPool samplerPool, ShaderStage stage, bool isImage, in TextureBindingInfo bindingInfo)
         {
             CacheEntry entry = GetOrAddEntry(texturePool, samplerPool, bindingInfo, isImage, out bool isNewEntry);
 
@@ -638,11 +641,11 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                 if (isImage)
                 {
-                    _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, entry.ImageArray);
+                    SetImageArray(stage, bindingInfo, entry.ImageArray);
                 }
                 else
                 {
-                    _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, entry.TextureArray);
+                    SetTextureArray(stage, bindingInfo, entry.TextureArray);
                 }
 
                 return;
@@ -708,11 +711,11 @@ namespace Ryujinx.Graphics.Gpu.Image
                             format = texture.Format;
                         }
 
-                        _channel.BufferManager.SetBufferTextureStorage(entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
                     }
                     else
                     {
-                        _channel.BufferManager.SetBufferTextureStorage(entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
                     }
                 }
                 else if (isImage)
@@ -737,14 +740,14 @@ namespace Ryujinx.Graphics.Gpu.Image
                 entry.ImageArray.SetFormats(0, formats);
                 entry.ImageArray.SetImages(0, textures);
 
-                _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, entry.ImageArray);
+                SetImageArray(stage, bindingInfo, entry.ImageArray);
             }
             else
             {
                 entry.TextureArray.SetSamplers(0, samplers);
                 entry.TextureArray.SetTextures(0, textures);
 
-                _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, entry.TextureArray);
+                SetTextureArray(stage, bindingInfo, entry.TextureArray);
             }
         }
 
@@ -767,7 +770,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             int textureBufferIndex,
             bool isImage,
             SamplerIndex samplerIndex,
-            TextureBindingInfo bindingInfo)
+            in TextureBindingInfo bindingInfo)
         {
             (textureBufferIndex, int samplerBufferIndex) = TextureHandle.UnpackSlots(bindingInfo.CbufSlot, textureBufferIndex);
 
@@ -800,11 +803,11 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                     if (isImage)
                     {
-                        _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, entry.ImageArray);
+                        SetImageArray(stage, bindingInfo, entry.ImageArray);
                     }
                     else
                     {
-                        _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, entry.TextureArray);
+                        SetTextureArray(stage, bindingInfo, entry.TextureArray);
                     }
 
                     return;
@@ -829,11 +832,11 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                     if (isImage)
                     {
-                        _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, entry.ImageArray);
+                        SetImageArray(stage, bindingInfo, entry.ImageArray);
                     }
                     else
                     {
-                        _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, entry.TextureArray);
+                        SetTextureArray(stage, bindingInfo, entry.TextureArray);
                     }
 
                     return;
@@ -899,13 +902,19 @@ namespace Ryujinx.Graphics.Gpu.Image
                     }
                 }
 
-                Sampler sampler = samplerPool?.Get(samplerId);
-
                 entry.TextureIds[textureId] = (texture, descriptor);
-                entry.SamplerIds[samplerId] = (sampler, samplerPool?.GetDescriptorRef(samplerId) ?? default);
 
                 ITexture hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
-                ISampler hostSampler = sampler?.GetHostSampler(texture);
+                ISampler hostSampler = null;
+
+                if (!isImage && bindingInfo.Target != Target.TextureBuffer)
+                {
+                    Sampler sampler = samplerPool?.Get(samplerId);
+
+                    entry.SamplerIds[samplerId] = (sampler, samplerPool?.GetDescriptorRef(samplerId) ?? default);
+
+                    hostSampler = sampler?.GetHostSampler(texture);
+                }
 
                 Format format = bindingInfo.Format;
 
@@ -921,11 +930,11 @@ namespace Ryujinx.Graphics.Gpu.Image
                             format = texture.Format;
                         }
 
-                        _channel.BufferManager.SetBufferTextureStorage(entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
                     }
                     else
                     {
-                        _channel.BufferManager.SetBufferTextureStorage(entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
                     }
                 }
                 else if (isImage)
@@ -950,14 +959,50 @@ namespace Ryujinx.Graphics.Gpu.Image
                 entry.ImageArray.SetFormats(0, formats);
                 entry.ImageArray.SetImages(0, textures);
 
-                _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, entry.ImageArray);
+                SetImageArray(stage, bindingInfo, entry.ImageArray);
             }
             else
             {
                 entry.TextureArray.SetSamplers(0, samplers);
                 entry.TextureArray.SetTextures(0, textures);
 
-                _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, entry.TextureArray);
+                SetTextureArray(stage, bindingInfo, entry.TextureArray);
+            }
+        }
+
+        /// <summary>
+        /// Updates a texture array binding on the host.
+        /// </summary>
+        /// <param name="stage">Shader stage where the array is used</param>
+        /// <param name="bindingInfo">Array binding information</param>
+        /// <param name="array">Texture array</param>
+        private void SetTextureArray(ShaderStage stage, in TextureBindingInfo bindingInfo, ITextureArray array)
+        {
+            if (bindingInfo.Set >= _context.Capabilities.ExtraSetBaseIndex && _context.Capabilities.MaximumExtraSets != 0)
+            {
+                _context.Renderer.Pipeline.SetTextureArraySeparate(stage, bindingInfo.Set, array);
+            }
+            else
+            {
+                _context.Renderer.Pipeline.SetTextureArray(stage, bindingInfo.Binding, array);
+            }
+        }
+
+        /// <summary>
+        /// Updates a image array binding on the host.
+        /// </summary>
+        /// <param name="stage">Shader stage where the array is used</param>
+        /// <param name="bindingInfo">Array binding information</param>
+        /// <param name="array">Image array</param>
+        private void SetImageArray(ShaderStage stage, in TextureBindingInfo bindingInfo, IImageArray array)
+        {
+            if (bindingInfo.Set >= _context.Capabilities.ExtraSetBaseIndex && _context.Capabilities.MaximumExtraSets != 0)
+            {
+                _context.Renderer.Pipeline.SetImageArraySeparate(stage, bindingInfo.Set, array);
+            }
+            else
+            {
+                _context.Renderer.Pipeline.SetImageArray(stage, bindingInfo.Binding, array);
             }
         }
 
@@ -973,7 +1018,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         private CacheEntry GetOrAddEntry(
             TexturePool texturePool,
             SamplerPool samplerPool,
-            TextureBindingInfo bindingInfo,
+            in TextureBindingInfo bindingInfo,
             bool isImage,
             out bool isNew)
         {
@@ -1015,7 +1060,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         private CacheEntryFromBuffer GetOrAddEntry(
             TexturePool texturePool,
             SamplerPool samplerPool,
-            TextureBindingInfo bindingInfo,
+            in TextureBindingInfo bindingInfo,
             bool isImage,
             ref BufferBounds textureBufferBounds,
             out bool isNew)
@@ -1077,6 +1122,15 @@ namespace Ryujinx.Graphics.Gpu.Image
                 nextNode = nextNode.Next;
                 _cacheFromBuffer.Remove(toRemove.Value.Key);
                 _lruCache.Remove(toRemove);
+
+                if (toRemove.Value.Key.IsImage)
+                {
+                    toRemove.Value.ImageArray.Dispose();
+                }
+                else
+                {
+                    toRemove.Value.TextureArray.Dispose();
+                }
             }
         }
 
@@ -1088,11 +1142,20 @@ namespace Ryujinx.Graphics.Gpu.Image
         {
             List<CacheEntryFromPoolKey> keysToRemove = null;
 
-            foreach (CacheEntryFromPoolKey key in _cacheFromPool.Keys)
+            foreach ((CacheEntryFromPoolKey key, CacheEntry entry) in _cacheFromPool)
             {
                 if (key.MatchesPool(pool))
                 {
                     (keysToRemove ??= new()).Add(key);
+
+                    if (key.IsImage)
+                    {
+                        entry.ImageArray.Dispose();
+                    }
+                    else
+                    {
+                        entry.TextureArray.Dispose();
+                    }
                 }
             }
 

src/Ryujinx.Graphics.Gpu/Image/TextureCache.cs

@@ -468,13 +468,11 @@ namespace Ryujinx.Graphics.Gpu.Image
             int gobBlocksInY = dsState.MemoryLayout.UnpackGobBlocksInY();
             int gobBlocksInZ = dsState.MemoryLayout.UnpackGobBlocksInZ();
 
+            layered &= size.UnpackIsLayered();
+
             Target target;
 
-            if (dsState.MemoryLayout.UnpackIsTarget3D())
+            if ((samplesInX | samplesInY) != 1)
-            {
-                target = Target.Texture3D;
-            }
-            else if ((samplesInX | samplesInY) != 1)
             {
                 target = size.Depth > 1 && layered
                     ? Target.Texture2DMultisampleArray

src/Ryujinx.Graphics.Gpu/Image/TextureGroup.cs

@@ -645,7 +645,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
                 else
                 {
-                    _flushBuffer = _context.Renderer.CreateBuffer((int)Storage.Size, BufferAccess.FlushPersistent);
+                    _flushBuffer = _context.Renderer.CreateBuffer((int)Storage.Size, BufferAccess.HostMemory);
                     _flushBufferImported = false;
                 }
 

src/Ryujinx.Graphics.Gpu/Image/TexturePool.cs

@@ -6,6 +6,7 @@ using Ryujinx.Memory.Range;
 using System;
 using System.Collections.Concurrent;
 using System.Collections.Generic;
+using System.Numerics;
 using System.Threading;
 
 namespace Ryujinx.Graphics.Gpu.Image
@@ -490,6 +491,8 @@ namespace Ryujinx.Graphics.Gpu.Image
                 levels = (maxLod - minLod) + 1;
             }
 
+            levels = ClampLevels(target, width, height, depthOrLayers, levels);
+
             SwizzleComponent swizzleR = descriptor.UnpackSwizzleR().Convert();
             SwizzleComponent swizzleG = descriptor.UnpackSwizzleG().Convert();
             SwizzleComponent swizzleB = descriptor.UnpackSwizzleB().Convert();
@@ -540,6 +543,34 @@ namespace Ryujinx.Graphics.Gpu.Image
                 swizzleA);
         }
 
+        /// <summary>
+        /// Clamps the amount of mipmap levels to the maximum allowed for the given texture dimensions.
+        /// </summary>
+        /// <param name="target">Number of texture dimensions (1D, 2D, 3D, Cube, etc)</param>
+        /// <param name="width">Width of the texture</param>
+        /// <param name="height">Height of the texture, ignored for 1D textures</param>
+        /// <param name="depthOrLayers">Depth of the texture for 3D textures, otherwise ignored</param>
+        /// <param name="levels">Original amount of mipmap levels</param>
+        /// <returns>Clamped mipmap levels</returns>
+        private static int ClampLevels(Target target, int width, int height, int depthOrLayers, int levels)
+        {
+            int maxSize = width;
+
+            if (target != Target.Texture1D &&
+                target != Target.Texture1DArray)
+            {
+                maxSize = Math.Max(maxSize, height);
+            }
+
+            if (target == Target.Texture3D)
+            {
+                maxSize = Math.Max(maxSize, depthOrLayers);
+            }
+
+            int maxLevels = BitOperations.Log2((uint)maxSize) + 1;
+            return Math.Min(levels, maxLevels);
+        }
+
         /// <summary>
         /// Gets the texture depth-stencil mode, based on the swizzle components of each color channel.
         /// The depth-stencil mode is determined based on how the driver sets those parameters.

src/Ryujinx.Graphics.Gpu/Memory/Buffer.cs

@@ -10,6 +10,8 @@ using System.Threading;
 
 namespace Ryujinx.Graphics.Gpu.Memory
 {
+    delegate void BufferFlushAction(ulong address, ulong size, ulong syncNumber);
+
     /// <summary>
     /// Buffer, used to store vertex and index data, uniform and storage buffers, and others.
     /// </summary>
@@ -23,7 +25,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <summary>
         /// Host buffer handle.
         /// </summary>
-        public BufferHandle Handle { get; }
+        public BufferHandle Handle { get; private set; }
 
         /// <summary>
         /// Start address of the buffer in guest memory.
@@ -60,6 +62,17 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </remarks>
         private BufferModifiedRangeList _modifiedRanges = null;
 
+        /// <summary>
+        /// A structure that is used to flush buffer data back to a host mapped buffer for cached readback.
+        /// Only used if the buffer data is explicitly owned by device local memory.
+        /// </summary>
+        private BufferPreFlush _preFlush = null;
+
+        /// <summary>
+        /// Usage tracking state that determines what type of backing the buffer should use.
+        /// </summary>
+        public BufferBackingState BackingState;
+
         private readonly MultiRegionHandle _memoryTrackingGranular;
         private readonly RegionHandle _memoryTracking;
 
@@ -87,6 +100,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="physicalMemory">Physical memory where the buffer is mapped</param>
         /// <param name="address">Start address of the buffer</param>
         /// <param name="size">Size of the buffer in bytes</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <param name="sparseCompatible">Indicates if the buffer can be used in a sparse buffer mapping</param>
         /// <param name="baseBuffers">Buffers which this buffer contains, and will inherit tracking handles from</param>
         public Buffer(
@@ -94,6 +108,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             PhysicalMemory physicalMemory,
             ulong address,
             ulong size,
+            BufferStage stage,
             bool sparseCompatible,
             IEnumerable<Buffer> baseBuffers = null)
         {
@@ -103,9 +118,11 @@ namespace Ryujinx.Graphics.Gpu.Memory
             Size = size;
             SparseCompatible = sparseCompatible;
 
-            BufferAccess access = sparseCompatible ? BufferAccess.SparseCompatible : BufferAccess.Default;
+            BackingState = new BufferBackingState(_context, this, stage, baseBuffers);
 
-            Handle = context.Renderer.CreateBuffer((int)size, access, baseBuffers?.MaxBy(x => x.Size).Handle ?? BufferHandle.Null);
+            BufferAccess access = BackingState.SwitchAccess(this);
+
+            Handle = context.Renderer.CreateBuffer((int)size, access);
 
             _useGranular = size > GranularBufferThreshold;
 
@@ -161,6 +178,29 @@ namespace Ryujinx.Graphics.Gpu.Memory
             _virtualDependenciesLock = new ReaderWriterLockSlim();
         }
 
+        /// <summary>
+        /// Recreates the backing buffer based on the desired access type
+        /// reported by the backing state struct.
+        /// </summary>
+        private void ChangeBacking()
+        {
+            BufferAccess access = BackingState.SwitchAccess(this);
+
+            BufferHandle newHandle = _context.Renderer.CreateBuffer((int)Size, access);
+
+            _context.Renderer.Pipeline.CopyBuffer(Handle, newHandle, 0, 0, (int)Size);
+
+            _modifiedRanges?.SelfMigration();
+
+            // If swtiching from device local to host mapped, pre-flushing data no longer makes sense.
+            // This is set to null and disposed when the migration fully completes.
+            _preFlush = null;
+
+            Handle = newHandle;
+
+            _physicalMemory.BufferCache.BufferBackingChanged(this);
+        }
+
         /// <summary>
         /// Gets a sub-range from the buffer, from a start address til a page boundary after the given size.
         /// </summary>
@@ -246,6 +286,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                     }
                     else
                     {
+                        BackingState.RecordSet();
                         _context.Renderer.SetBufferData(Handle, 0, _physicalMemory.GetSpan(Address, (int)Size));
                         CopyToDependantVirtualBuffers();
                     }
@@ -283,15 +324,35 @@ namespace Ryujinx.Graphics.Gpu.Memory
             _modifiedRanges ??= new BufferModifiedRangeList(_context, this, Flush);
         }
 
+        /// <summary>
+        /// Checks if a backing change is deemed necessary from the given usage.
+        /// If it is, queues a backing change to happen on the next sync action.
+        /// </summary>
+        /// <param name="stage">Buffer stage that can change backing type</param>
+        private void TryQueueBackingChange(BufferStage stage)
+        {
+            if (BackingState.ShouldChangeBacking(stage))
+            {
+                if (!_syncActionRegistered)
+                {
+                    _context.RegisterSyncAction(this);
+                    _syncActionRegistered = true;
+                }
+            }
+        }
+
         /// <summary>
         /// Signal that the given region of the buffer has been modified.
         /// </summary>
         /// <param name="address">The start address of the modified region</param>
         /// <param name="size">The size of the modified region</param>
-        public void SignalModified(ulong address, ulong size)
+        /// <param name="stage">Buffer stage that triggered the modification</param>
+        public void SignalModified(ulong address, ulong size, BufferStage stage)
         {
             EnsureRangeList();
 
+            TryQueueBackingChange(stage);
+
             _modifiedRanges.SignalModified(address, size);
 
             if (!_syncActionRegistered)
@@ -311,6 +372,37 @@ namespace Ryujinx.Graphics.Gpu.Memory
             _modifiedRanges?.Clear(address, size);
         }
 
+        /// <summary>
+        /// Action to be performed immediately before sync is created.
+        /// This will copy any buffer ranges designated for pre-flushing.
+        /// </summary>
+        /// <param name="syncpoint">True if the action is a guest syncpoint</param>
+        public void SyncPreAction(bool syncpoint)
+        {
+            if (_referenceCount == 0)
+            {
+                return;
+            }
+
+            if (BackingState.ShouldChangeBacking())
+            {
+                ChangeBacking();
+            }
+
+            if (BackingState.IsDeviceLocal)
+            {
+                _preFlush ??= new BufferPreFlush(_context, this, FlushImpl);
+
+                if (_preFlush.ShouldCopy)
+                {
+                    _modifiedRanges?.GetRangesAtSync(Address, Size, _context.SyncNumber, (address, size) =>
+                    {
+                        _preFlush.CopyModified(address, size);
+                    });
+                }
+            }
+        }
+
         /// <summary>
         /// Action to be performed when a syncpoint is reached after modification.
         /// This will register read/write tracking to flush the buffer from GPU when its memory is used.
@@ -466,6 +558,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="mSize">Size of the modified region</param>
         private void LoadRegion(ulong mAddress, ulong mSize)
         {
+            BackingState.RecordSet();
+
             int offset = (int)(mAddress - Address);
 
             _context.Renderer.SetBufferData(Handle, offset, _physicalMemory.GetSpan(mAddress, (int)mSize));
@@ -539,18 +633,84 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// Flushes a range of the buffer.
         /// This writes the range data back into guest memory.
         /// </summary>
+        /// <param name="handle">Buffer handle to flush data from</param>
         /// <param name="address">Start address of the range</param>
         /// <param name="size">Size in bytes of the range</param>
-        public void Flush(ulong address, ulong size)
+        private void FlushImpl(BufferHandle handle, ulong address, ulong size)
         {
             int offset = (int)(address - Address);
 
-            using PinnedSpan<byte> data = _context.Renderer.GetBufferData(Handle, offset, (int)size);
+            using PinnedSpan<byte> data = _context.Renderer.GetBufferData(handle, offset, (int)size);
 
             // TODO: When write tracking shaders, they will need to be aware of changes in overlapping buffers.
             _physicalMemory.WriteUntracked(address, CopyFromDependantVirtualBuffers(data.Get(), address, size));
         }
 
+        /// <summary>
+        /// Flushes a range of the buffer.
+        /// This writes the range data back into guest memory.
+        /// </summary>
+        /// <param name="address">Start address of the range</param>
+        /// <param name="size">Size in bytes of the range</param>
+        private void FlushImpl(ulong address, ulong size)
+        {
+            FlushImpl(Handle, address, size);
+        }
+
+        /// <summary>
+        /// Flushes a range of the buffer from the most optimal source.
+        /// This writes the range data back into guest memory.
+        /// </summary>
+        /// <param name="address">Start address of the range</param>
+        /// <param name="size">Size in bytes of the range</param>
+        /// <param name="syncNumber">Sync number waited for before flushing the data</param>
+        public void Flush(ulong address, ulong size, ulong syncNumber)
+        {
+            BackingState.RecordFlush();
+
+            BufferPreFlush preFlush = _preFlush;
+
+            if (preFlush != null)
+            {
+                preFlush.FlushWithAction(address, size, syncNumber);
+            }
+            else
+            {
+                FlushImpl(address, size);
+            }
+        }
+        /// <summary>
+        /// Gets an action that disposes the backing buffer using its current handle.
+        /// Useful for deleting an old copy of the buffer after the handle changes.
+        /// </summary>
+        /// <returns>An action that flushes data from the specified range, using the buffer handle at the time the method is generated</returns>
+        public Action GetSnapshotDisposeAction()
+        {
+            BufferHandle handle = Handle;
+            BufferPreFlush preFlush = _preFlush;
+
+            return () =>
+            {
+                _context.Renderer.DeleteBuffer(handle);
+                preFlush?.Dispose();
+            };
+        }
+
+        /// <summary>
+        /// Gets an action that flushes a range of the buffer using its current handle.
+        /// Useful for flushing data from old copies of the buffer after the handle changes.
+        /// </summary>
+        /// <returns>An action that flushes data from the specified range, using the buffer handle at the time the method is generated</returns>
+        public BufferFlushAction GetSnapshotFlushAction()
+        {
+            BufferHandle handle = Handle;
+
+            return (ulong address, ulong size, ulong _) =>
+            {
+                FlushImpl(handle, address, size);
+            };
+        }
+
         /// <summary>
         /// Align a given address and size region to page boundaries.
         /// </summary>
@@ -857,6 +1017,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
             _modifiedRanges?.Clear();
 
             _context.Renderer.DeleteBuffer(Handle);
+            _preFlush?.Dispose();
+            _preFlush = null;
 
             UnmappedSequence++;
         }

src/Ryujinx.Graphics.Gpu/Memory/BufferBackingState.cs

@@ -0,0 +1,294 @@
+using Ryujinx.Graphics.GAL;
+using System;
+using System.Collections.Generic;
+
+namespace Ryujinx.Graphics.Gpu.Memory
+{
+    /// <summary>
+    /// Type of backing memory.
+    /// In ascending order of priority when merging multiple buffer backing states.
+    /// </summary>
+    internal enum BufferBackingType
+    {
+        HostMemory,
+        DeviceMemory,
+        DeviceMemoryWithFlush
+    }
+
+    /// <summary>
+    /// Keeps track of buffer usage to decide what memory heap that buffer memory is placed on.
+    /// Dedicated GPUs prefer certain types of resources to be device local,
+    /// and if we need data to be read back, we might prefer that they're in host memory.
+    /// 
+    /// The measurements recorded here compare to a set of heruristics (thresholds and conditions)
+    /// that appear to produce good performance in most software.
+    /// </summary>
+    internal struct BufferBackingState
+    {
+        private const int DeviceLocalSizeThreshold = 256 * 1024; // 256kb
+
+        private const int SetCountThreshold = 100;
+        private const int WriteCountThreshold = 50;
+        private const int FlushCountThreshold = 5;
+        private const int DeviceLocalForceExpiry = 100;
+
+        public readonly bool IsDeviceLocal => _activeType != BufferBackingType.HostMemory;
+
+        private readonly SystemMemoryType _systemMemoryType;
+        private BufferBackingType _activeType;
+        private BufferBackingType _desiredType;
+
+        private bool _canSwap;
+
+        private int _setCount;
+        private int _writeCount;
+        private int _flushCount;
+        private int _flushTemp;
+        private int _lastFlushWrite;
+        private int _deviceLocalForceCount;
+
+        private readonly int _size;
+
+        /// <summary>
+        /// Initialize the buffer backing state for a given parent buffer.
+        /// </summary>
+        /// <param name="context">GPU context</param>
+        /// <param name="parent">Parent buffer</param>
+        /// <param name="stage">Initial buffer stage</param>
+        /// <param name="baseBuffers">Buffers to inherit state from</param>
+        public BufferBackingState(GpuContext context, Buffer parent, BufferStage stage, IEnumerable<Buffer> baseBuffers = null)
+        {
+            _size = (int)parent.Size;
+            _systemMemoryType = context.Capabilities.MemoryType;
+
+            // Backend managed is always auto, unified memory is always host.
+            _desiredType = BufferBackingType.HostMemory;
+            _canSwap = _systemMemoryType != SystemMemoryType.BackendManaged && _systemMemoryType != SystemMemoryType.UnifiedMemory;
+
+            if (_canSwap)
+            {
+                // Might want to start certain buffers as being device local,
+                // and the usage might also lock those buffers into being device local.
+
+                BufferStage storageFlags = stage & BufferStage.StorageMask;
+
+                if (parent.Size > DeviceLocalSizeThreshold && baseBuffers == null)
+                {
+                    _desiredType = BufferBackingType.DeviceMemory;
+                }
+
+                if (storageFlags != 0)
+                {
+                    // Storage buffer bindings may require special treatment.
+
+                    var rawStage = stage & BufferStage.StageMask;
+
+                    if (rawStage == BufferStage.Fragment)
+                    {
+                        // Fragment read should start device local.
+
+                        _desiredType = BufferBackingType.DeviceMemory;
+
+                        if (storageFlags != BufferStage.StorageRead)
+                        {
+                            // Fragment write should stay device local until the use doesn't happen anymore.
+
+                            _deviceLocalForceCount = DeviceLocalForceExpiry;
+                        }
+                    }
+
+                    // TODO: Might be nice to force atomic access to be device local for any stage.
+                }
+
+                if (baseBuffers != null)
+                {
+                    foreach (Buffer buffer in baseBuffers)
+                    {
+                        CombineState(buffer.BackingState);
+                    }
+                }
+            }
+        }
+
+        /// <summary>
+        /// Combine buffer backing types, selecting the one with highest priority.
+        /// </summary>
+        /// <param name="left">First buffer backing type</param>
+        /// <param name="right">Second buffer backing type</param>
+        /// <returns>Combined buffer backing type</returns>
+        private static BufferBackingType CombineTypes(BufferBackingType left, BufferBackingType right)
+        {
+            return (BufferBackingType)Math.Max((int)left, (int)right);
+        }
+
+        /// <summary>
+        /// Combine the state from the given buffer backing state with this one,
+        /// so that the state isn't lost when migrating buffers.
+        /// </summary>
+        /// <param name="oldState">Buffer state to combine into this state</param>
+        private void CombineState(BufferBackingState oldState)
+        {
+            _setCount += oldState._setCount;
+            _writeCount += oldState._writeCount;
+            _flushCount += oldState._flushCount;
+            _flushTemp += oldState._flushTemp;
+            _lastFlushWrite = -1;
+            _deviceLocalForceCount = Math.Max(_deviceLocalForceCount, oldState._deviceLocalForceCount);
+
+            _canSwap &= oldState._canSwap;
+
+            _desiredType = CombineTypes(_desiredType, oldState._desiredType);
+        }
+
+        /// <summary>
+        /// Get the buffer access for the desired backing type, and record that type as now being active.
+        /// </summary>
+        /// <param name="parent">Parent buffer</param>
+        /// <returns>Buffer access</returns>
+        public BufferAccess SwitchAccess(Buffer parent)
+        {
+            BufferAccess access = parent.SparseCompatible ? BufferAccess.SparseCompatible : BufferAccess.Default;
+
+            bool isBackendManaged = _systemMemoryType == SystemMemoryType.BackendManaged;
+
+            if (!isBackendManaged)
+            {
+                switch (_desiredType)
+                {
+                    case BufferBackingType.HostMemory:
+                        access |= BufferAccess.HostMemory;
+                        break;
+                    case BufferBackingType.DeviceMemory:
+                        access |= BufferAccess.DeviceMemory;
+                        break;
+                    case BufferBackingType.DeviceMemoryWithFlush:
+                        access |= BufferAccess.DeviceMemoryMapped;
+                        break;
+                }
+            }
+
+            _activeType = _desiredType;
+
+            return access;
+        }
+
+        /// <summary>
+        /// Record when data has been uploaded to the buffer.
+        /// </summary>
+        public void RecordSet()
+        {
+            _setCount++;
+
+            ConsiderUseCounts();
+        }
+
+        /// <summary>
+        /// Record when data has been flushed from the buffer.
+        /// </summary>
+        public void RecordFlush()
+        {
+            if (_lastFlushWrite != _writeCount)
+            {
+                // If it's on the same page as the last flush, ignore it.
+                _lastFlushWrite = _writeCount;
+                _flushCount++;
+            }
+        }
+
+        /// <summary>
+        /// Determine if the buffer backing should be changed.
+        /// </summary>
+        /// <returns>True if the desired backing type is different from the current type</returns>
+        public readonly bool ShouldChangeBacking()
+        {
+            return _desiredType != _activeType;
+        }
+
+        /// <summary>
+        /// Determine if the buffer backing should be changed, considering a new use with the given buffer stage.
+        /// </summary>
+        /// <param name="stage">Buffer stage for the use</param>
+        /// <returns>True if the desired backing type is different from the current type</returns>
+        public bool ShouldChangeBacking(BufferStage stage)
+        {
+            if (!_canSwap)
+            {
+                return false;
+            }
+
+            BufferStage storageFlags = stage & BufferStage.StorageMask;
+
+            if (storageFlags != 0)
+            {
+                if (storageFlags != BufferStage.StorageRead)
+                {
+                    // Storage write.
+                    _writeCount++;
+
+                    var rawStage = stage & BufferStage.StageMask;
+
+                    if (rawStage == BufferStage.Fragment)
+                    {
+                        // Switch to device memory, swap back only if this use disappears.
+
+                        _desiredType = CombineTypes(_desiredType, BufferBackingType.DeviceMemory);
+                        _deviceLocalForceCount = DeviceLocalForceExpiry;
+
+                        // TODO: Might be nice to force atomic access to be device local for any stage.
+                    }
+                }
+
+                ConsiderUseCounts();
+            }
+
+            return _desiredType != _activeType;
+        }
+
+        /// <summary>
+        /// Evaluate the current counts to determine what the buffer's desired backing type is.
+        /// This method depends on heuristics devised by testing a variety of software.
+        /// </summary>
+        private void ConsiderUseCounts()
+        {
+            if (_canSwap)
+            {
+                if (_writeCount >= WriteCountThreshold || _setCount >= SetCountThreshold || _flushCount >= FlushCountThreshold)
+                {
+                    if (_deviceLocalForceCount > 0 && --_deviceLocalForceCount != 0)
+                    {
+                        // Some buffer usage demanded that the buffer stay device local.
+                        // The desired type was selected when this counter was set.
+                    }
+                    else if (_flushCount > 0 || _flushTemp-- > 0)
+                    {
+                        // Buffers that flush should ideally be mapped in host address space for easy copies.
+                        // If the buffer is large it will do better on GPU memory, as there will be more writes than data flushes (typically individual pages).
+                        // If it is small, then it's likely most of the buffer will be flushed so we want it on host memory, as access is cached.
+                        _desiredType = _size > DeviceLocalSizeThreshold ? BufferBackingType.DeviceMemoryWithFlush : BufferBackingType.HostMemory;
+                    }
+                    else if (_writeCount >= WriteCountThreshold)
+                    {
+                        // Buffers that are written often should ideally be in the device local heap. (Storage buffers)
+                        _desiredType = BufferBackingType.DeviceMemory;
+                    }
+                    else if (_setCount > SetCountThreshold)
+                    {
+                        // Buffers that have their data set often should ideally be host mapped. (Constant buffers)
+                        _desiredType = BufferBackingType.HostMemory;
+                    }
+
+                    // It's harder for a buffer that is flushed to revert to another type of mapping.
+                    if (_flushCount > 0)
+                    {
+                        _flushTemp = 1000;
+                    }
+
+                    _lastFlushWrite = -1;
+                    _flushCount = 0;
+                    _writeCount = 0;
+                    _setCount = 0;
+                }
+            }
+        }
+    }
+}

src/Ryujinx.Graphics.Gpu/Memory/BufferCache.cs

@@ -107,8 +107,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="memoryManager">GPU memory manager where the buffer is mapped</param>
         /// <param name="gpuVa">Start GPU virtual address of the buffer</param>
         /// <param name="size">Size in bytes of the buffer</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <returns>Contiguous physical range of the buffer, after address translation</returns>
-        public MultiRange TranslateAndCreateBuffer(MemoryManager memoryManager, ulong gpuVa, ulong size)
+        public MultiRange TranslateAndCreateBuffer(MemoryManager memoryManager, ulong gpuVa, ulong size, BufferStage stage)
         {
             if (gpuVa == 0)
             {
@@ -119,7 +120,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             if (address != MemoryManager.PteUnmapped)
             {
-                CreateBuffer(address, size);
+                CreateBuffer(address, size, stage);
             }
 
             return new MultiRange(address, size);
@@ -132,8 +133,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="memoryManager">GPU memory manager where the buffer is mapped</param>
         /// <param name="gpuVa">Start GPU virtual address of the buffer</param>
         /// <param name="size">Size in bytes of the buffer</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <returns>Physical ranges of the buffer, after address translation</returns>
-        public MultiRange TranslateAndCreateMultiBuffers(MemoryManager memoryManager, ulong gpuVa, ulong size)
+        public MultiRange TranslateAndCreateMultiBuffers(MemoryManager memoryManager, ulong gpuVa, ulong size, BufferStage stage)
         {
             if (gpuVa == 0)
             {
@@ -149,7 +151,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 return range;
             }
 
-            CreateBuffer(range);
+            CreateBuffer(range, stage);
 
             return range;
         }
@@ -161,8 +163,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="memoryManager">GPU memory manager where the buffer is mapped</param>
         /// <param name="gpuVa">Start GPU virtual address of the buffer</param>
         /// <param name="size">Size in bytes of the buffer</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <returns>Physical ranges of the buffer, after address translation</returns>
-        public MultiRange TranslateAndCreateMultiBuffersPhysicalOnly(MemoryManager memoryManager, ulong gpuVa, ulong size)
+        public MultiRange TranslateAndCreateMultiBuffersPhysicalOnly(MemoryManager memoryManager, ulong gpuVa, ulong size, BufferStage stage)
         {
             if (gpuVa == 0)
             {
@@ -186,11 +189,11 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 {
                     if (range.Count > 1)
                     {
-                        CreateBuffer(subRange.Address, subRange.Size, SparseBufferAlignmentSize);
+                        CreateBuffer(subRange.Address, subRange.Size, stage, SparseBufferAlignmentSize);
                     }
                     else
                     {
-                        CreateBuffer(subRange.Address, subRange.Size);
+                        CreateBuffer(subRange.Address, subRange.Size, stage);
                     }
                 }
             }
@@ -203,11 +206,12 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// This can be used to ensure the existance of a buffer.
         /// </summary>
         /// <param name="range">Physical ranges of memory where the buffer data is located</param>
-        public void CreateBuffer(MultiRange range)
+        /// <param name="stage">The type of usage that created the buffer</param>
+        public void CreateBuffer(MultiRange range, BufferStage stage)
         {
             if (range.Count > 1)
             {
-                CreateMultiRangeBuffer(range);
+                CreateMultiRangeBuffer(range, stage);
             }
             else
             {
@@ -215,7 +219,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                 if (subRange.Address != MemoryManager.PteUnmapped)
                 {
-                    CreateBuffer(subRange.Address, subRange.Size);
+                    CreateBuffer(subRange.Address, subRange.Size, stage);
                 }
             }
         }
@@ -226,7 +230,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Address of the buffer in memory</param>
         /// <param name="size">Size of the buffer in bytes</param>
-        public void CreateBuffer(ulong address, ulong size)
+        /// <param name="stage">The type of usage that created the buffer</param>
+        public void CreateBuffer(ulong address, ulong size, BufferStage stage)
         {
             ulong endAddress = address + size;
 
@@ -239,7 +244,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 alignedEndAddress += BufferAlignmentSize;
             }
 
-            CreateBufferAligned(alignedAddress, alignedEndAddress - alignedAddress);
+            CreateBufferAligned(alignedAddress, alignedEndAddress - alignedAddress, stage);
         }
 
         /// <summary>
@@ -248,8 +253,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Address of the buffer in memory</param>
         /// <param name="size">Size of the buffer in bytes</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <param name="alignment">Alignment of the start address of the buffer in bytes</param>
-        public void CreateBuffer(ulong address, ulong size, ulong alignment)
+        public void CreateBuffer(ulong address, ulong size, BufferStage stage, ulong alignment)
         {
             ulong alignmentMask = alignment - 1;
             ulong pageAlignmentMask = BufferAlignmentMask;
@@ -264,7 +270,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 alignedEndAddress += pageAlignmentMask;
             }
 
-            CreateBufferAligned(alignedAddress, alignedEndAddress - alignedAddress, alignment);
+            CreateBufferAligned(alignedAddress, alignedEndAddress - alignedAddress, stage, alignment);
         }
 
         /// <summary>
@@ -272,7 +278,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// if it does not exist yet.
         /// </summary>
         /// <param name="range">Physical ranges of memory</param>
-        private void CreateMultiRangeBuffer(MultiRange range)
+        /// <param name="stage">The type of usage that created the buffer</param>
+        private void CreateMultiRangeBuffer(MultiRange range, BufferStage stage)
         {
             // Ensure all non-contiguous buffer we might use are sparse aligned.
             for (int i = 0; i < range.Count; i++)
@@ -281,7 +288,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                 if (subRange.Address != MemoryManager.PteUnmapped)
                 {
-                    CreateBuffer(subRange.Address, subRange.Size, SparseBufferAlignmentSize);
+                    CreateBuffer(subRange.Address, subRange.Size, stage, SparseBufferAlignmentSize);
                 }
             }
 
@@ -431,9 +438,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 result.EndGpuAddress < gpuVa + size ||
                 result.UnmappedSequence != result.Buffer.UnmappedSequence)
             {
-                MultiRange range = TranslateAndCreateBuffer(memoryManager, gpuVa, size);
+                MultiRange range = TranslateAndCreateBuffer(memoryManager, gpuVa, size, BufferStage.Internal);
                 ulong address = range.GetSubRange(0).Address;
-                result = new BufferCacheEntry(address, gpuVa, GetBuffer(address, size));
+                result = new BufferCacheEntry(address, gpuVa, GetBuffer(address, size, BufferStage.Internal));
 
                 _dirtyCache[gpuVa] = result;
             }
@@ -466,9 +473,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 result.EndGpuAddress < alignedEndGpuVa ||
                 result.UnmappedSequence != result.Buffer.UnmappedSequence)
             {
-                MultiRange range = TranslateAndCreateBuffer(memoryManager, alignedGpuVa, size);
+                MultiRange range = TranslateAndCreateBuffer(memoryManager, alignedGpuVa, size, BufferStage.None);
                 ulong address = range.GetSubRange(0).Address;
-                result = new BufferCacheEntry(address, alignedGpuVa, GetBuffer(address, size));
+                result = new BufferCacheEntry(address, alignedGpuVa, GetBuffer(address, size, BufferStage.None));
 
                 _modifiedCache[alignedGpuVa] = result;
             }
@@ -485,7 +492,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Address of the buffer in guest memory</param>
         /// <param name="size">Size in bytes of the buffer</param>
-        private void CreateBufferAligned(ulong address, ulong size)
+        /// <param name="stage">The type of usage that created the buffer</param>
+        private void CreateBufferAligned(ulong address, ulong size, BufferStage stage)
         {
             Buffer[] overlaps = _bufferOverlaps;
             int overlapsCount = _buffers.FindOverlapsNonOverlapping(address, size, ref overlaps);
@@ -546,13 +554,13 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                     ulong newSize = endAddress - address;
 
-                    CreateBufferAligned(address, newSize, anySparseCompatible, overlaps, overlapsCount);
+                    CreateBufferAligned(address, newSize, stage, anySparseCompatible, overlaps, overlapsCount);
                 }
             }
             else
             {
                 // No overlap, just create a new buffer.
-                Buffer buffer = new(_context, _physicalMemory, address, size, sparseCompatible: false);
+                Buffer buffer = new(_context, _physicalMemory, address, size, stage, sparseCompatible: false);
 
                 lock (_buffers)
                 {
@@ -570,8 +578,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Address of the buffer in guest memory</param>
         /// <param name="size">Size in bytes of the buffer</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <param name="alignment">Alignment of the start address of the buffer</param>
-        private void CreateBufferAligned(ulong address, ulong size, ulong alignment)
+        private void CreateBufferAligned(ulong address, ulong size, BufferStage stage, ulong alignment)
         {
             Buffer[] overlaps = _bufferOverlaps;
             int overlapsCount = _buffers.FindOverlapsNonOverlapping(address, size, ref overlaps);
@@ -624,13 +633,13 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                     ulong newSize = endAddress - address;
 
-                    CreateBufferAligned(address, newSize, sparseAligned, overlaps, overlapsCount);
+                    CreateBufferAligned(address, newSize, stage, sparseAligned, overlaps, overlapsCount);
                 }
             }
             else
             {
                 // No overlap, just create a new buffer.
-                Buffer buffer = new(_context, _physicalMemory, address, size, sparseAligned);
+                Buffer buffer = new(_context, _physicalMemory, address, size, stage, sparseAligned);
 
                 lock (_buffers)
                 {
@@ -648,12 +657,13 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Address of the buffer in guest memory</param>
         /// <param name="size">Size in bytes of the buffer</param>
+        /// <param name="stage">The type of usage that created the buffer</param>
         /// <param name="sparseCompatible">Indicates if the buffer can be used in a sparse buffer mapping</param>
         /// <param name="overlaps">Buffers overlapping the range</param>
         /// <param name="overlapsCount">Total of overlaps</param>
-        private void CreateBufferAligned(ulong address, ulong size, bool sparseCompatible, Buffer[] overlaps, int overlapsCount)
+        private void CreateBufferAligned(ulong address, ulong size, BufferStage stage, bool sparseCompatible, Buffer[] overlaps, int overlapsCount)
         {
-            Buffer newBuffer = new Buffer(_context, _physicalMemory, address, size, sparseCompatible, overlaps.Take(overlapsCount));
+            Buffer newBuffer = new Buffer(_context, _physicalMemory, address, size, stage, sparseCompatible, overlaps.Take(overlapsCount));
 
             lock (_buffers)
             {
@@ -704,7 +714,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             for (int index = 0; index < overlapCount; index++)
             {
-                CreateMultiRangeBuffer(overlaps[index].Range);
+                CreateMultiRangeBuffer(overlaps[index].Range, BufferStage.None);
             }
         }
 
@@ -731,8 +741,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="size">Size in bytes of the copy</param>
         public void CopyBuffer(MemoryManager memoryManager, ulong srcVa, ulong dstVa, ulong size)
         {
-            MultiRange srcRange = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, srcVa, size);
+            MultiRange srcRange = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, srcVa, size, BufferStage.Copy);
-            MultiRange dstRange = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, dstVa, size);
+            MultiRange dstRange = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, dstVa, size, BufferStage.Copy);
 
             if (srcRange.Count == 1 && dstRange.Count == 1)
             {
@@ -788,8 +798,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="size">Size in bytes of the copy</param>
         private void CopyBufferSingleRange(MemoryManager memoryManager, ulong srcAddress, ulong dstAddress, ulong size)
         {
-            Buffer srcBuffer = GetBuffer(srcAddress, size);
+            Buffer srcBuffer = GetBuffer(srcAddress, size, BufferStage.Copy);
-            Buffer dstBuffer = GetBuffer(dstAddress, size);
+            Buffer dstBuffer = GetBuffer(dstAddress, size, BufferStage.Copy);
 
             int srcOffset = (int)(srcAddress - srcBuffer.Address);
             int dstOffset = (int)(dstAddress - dstBuffer.Address);
@@ -803,7 +813,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             if (srcBuffer.IsModified(srcAddress, size))
             {
-                dstBuffer.SignalModified(dstAddress, size);
+                dstBuffer.SignalModified(dstAddress, size, BufferStage.Copy);
             }
             else
             {
@@ -828,12 +838,12 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="value">Value to be written into the buffer</param>
         public void ClearBuffer(MemoryManager memoryManager, ulong gpuVa, ulong size, uint value)
         {
-            MultiRange range = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, gpuVa, size);
+            MultiRange range = TranslateAndCreateMultiBuffersPhysicalOnly(memoryManager, gpuVa, size, BufferStage.Copy);
 
             for (int index = 0; index < range.Count; index++)
             {
                 MemoryRange subRange = range.GetSubRange(index);
-                Buffer buffer = GetBuffer(subRange.Address, subRange.Size);
+                Buffer buffer = GetBuffer(subRange.Address, subRange.Size, BufferStage.Copy);
 
                 int offset = (int)(subRange.Address - buffer.Address);
 
@@ -849,18 +859,19 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// Gets a buffer sub-range starting at a given memory address, aligned to the next page boundary.
         /// </summary>
         /// <param name="range">Physical regions of memory where the buffer is mapped</param>
+        /// <param name="stage">Buffer stage that triggered the access</param>
         /// <param name="write">Whether the buffer will be written to by this use</param>
         /// <returns>The buffer sub-range starting at the given memory address</returns>
-        public BufferRange GetBufferRangeAligned(MultiRange range, bool write = false)
+        public BufferRange GetBufferRangeAligned(MultiRange range, BufferStage stage, bool write = false)
         {
             if (range.Count > 1)
             {
-                return GetBuffer(range, write).GetRange(range);
+                return GetBuffer(range, stage, write).GetRange(range);
             }
             else
             {
                 MemoryRange subRange = range.GetSubRange(0);
-                return GetBuffer(subRange.Address, subRange.Size, write).GetRangeAligned(subRange.Address, subRange.Size, write);
+                return GetBuffer(subRange.Address, subRange.Size, stage, write).GetRangeAligned(subRange.Address, subRange.Size, write);
             }
         }
 
@@ -868,18 +879,19 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// Gets a buffer sub-range for a given memory range.
         /// </summary>
         /// <param name="range">Physical regions of memory where the buffer is mapped</param>
+        /// <param name="stage">Buffer stage that triggered the access</param>
         /// <param name="write">Whether the buffer will be written to by this use</param>
         /// <returns>The buffer sub-range for the given range</returns>
-        public BufferRange GetBufferRange(MultiRange range, bool write = false)
+        public BufferRange GetBufferRange(MultiRange range, BufferStage stage, bool write = false)
         {
             if (range.Count > 1)
             {
-                return GetBuffer(range, write).GetRange(range);
+                return GetBuffer(range, stage, write).GetRange(range);
             }
             else
             {
                 MemoryRange subRange = range.GetSubRange(0);
-                return GetBuffer(subRange.Address, subRange.Size, write).GetRange(subRange.Address, subRange.Size, write);
+                return GetBuffer(subRange.Address, subRange.Size, stage, write).GetRange(subRange.Address, subRange.Size, write);
             }
         }
 
@@ -888,9 +900,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// A buffer overlapping with the specified range is assumed to already exist on the cache.
         /// </summary>
         /// <param name="range">Physical regions of memory where the buffer is mapped</param>
+        /// <param name="stage">Buffer stage that triggered the access</param>
         /// <param name="write">Whether the buffer will be written to by this use</param>
         /// <returns>The buffer where the range is fully contained</returns>
-        private MultiRangeBuffer GetBuffer(MultiRange range, bool write = false)
+        private MultiRangeBuffer GetBuffer(MultiRange range, BufferStage stage, bool write = false)
         {
             for (int i = 0; i < range.Count; i++)
             {
@@ -902,7 +915,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                 if (write)
                 {
-                    subBuffer.SignalModified(subRange.Address, subRange.Size);
+                    subBuffer.SignalModified(subRange.Address, subRange.Size, stage);
                 }
             }
 
@@ -935,9 +948,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         /// <param name="address">Start address of the memory range</param>
         /// <param name="size">Size in bytes of the memory range</param>
+        /// <param name="stage">Buffer stage that triggered the access</param>
         /// <param name="write">Whether the buffer will be written to by this use</param>
         /// <returns>The buffer where the range is fully contained</returns>
-        private Buffer GetBuffer(ulong address, ulong size, bool write = false)
+        private Buffer GetBuffer(ulong address, ulong size, BufferStage stage, bool write = false)
         {
             Buffer buffer;
 
@@ -950,7 +964,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                 if (write)
                 {
-                    buffer.SignalModified(address, size);
+                    buffer.SignalModified(address, size, stage);
                 }
             }
             else
@@ -1004,6 +1018,18 @@ namespace Ryujinx.Graphics.Gpu.Memory
             }
         }
 
+        /// <summary>
+        /// Signal that the given buffer's handle has changed,
+        /// forcing rebind and any overlapping multi-range buffers to be recreated.
+        /// </summary>
+        /// <param name="buffer">The buffer that has changed handle</param>
+        public void BufferBackingChanged(Buffer buffer)
+        {
+            NotifyBuffersModified?.Invoke();
+
+            RecreateMultiRangeBuffers(buffer.Address, buffer.Size);
+        }
+
         /// <summary>
         /// Prune any invalid entries from a quick access dictionary.
         /// </summary>

src/Ryujinx.Graphics.Gpu/Memory/BufferManager.cs

@@ -156,7 +156,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="type">Type of each index buffer element</param>
         public void SetIndexBuffer(ulong gpuVa, ulong size, IndexType type)
         {
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size, BufferStage.IndexBuffer);
 
             _indexBuffer.Range = range;
             _indexBuffer.Type = type;
@@ -186,7 +186,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="divisor">Vertex divisor of the buffer, for instanced draws</param>
         public void SetVertexBuffer(int index, ulong gpuVa, ulong size, int stride, int divisor)
         {
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size, BufferStage.VertexBuffer);
 
             _vertexBuffers[index].Range = range;
             _vertexBuffers[index].Stride = stride;
@@ -213,7 +213,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="size">Size in bytes of the transform feedback buffer</param>
         public void SetTransformFeedbackBuffer(int index, ulong gpuVa, ulong size)
         {
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size, BufferStage.TransformFeedback);
 
             _transformFeedbackBuffers[index] = new BufferBounds(range);
             _transformFeedbackBuffersDirty = true;
@@ -260,7 +260,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             gpuVa = BitUtils.AlignDown<ulong>(gpuVa, (ulong)_context.Capabilities.StorageBufferOffsetAlignment);
 
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size, BufferStageUtils.ComputeStorage(flags));
 
             _cpStorageBuffers.SetBounds(index, range, flags);
         }
@@ -284,7 +284,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             gpuVa = BitUtils.AlignDown<ulong>(gpuVa, (ulong)_context.Capabilities.StorageBufferOffsetAlignment);
 
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateMultiBuffers(_channel.MemoryManager, gpuVa, size, BufferStageUtils.GraphicsStorage(stage, flags));
 
             if (!buffers.Buffers[index].Range.Equals(range))
             {
@@ -303,7 +303,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="size">Size in bytes of the storage buffer</param>
         public void SetComputeUniformBuffer(int index, ulong gpuVa, ulong size)
         {
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size, BufferStage.Compute);
 
             _cpUniformBuffers.SetBounds(index, range);
         }
@@ -318,7 +318,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="size">Size in bytes of the storage buffer</param>
         public void SetGraphicsUniformBuffer(int stage, int index, ulong gpuVa, ulong size)
         {
-            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size);
+            MultiRange range = _channel.MemoryManager.Physical.BufferCache.TranslateAndCreateBuffer(_channel.MemoryManager, gpuVa, size, BufferStageUtils.FromShaderStage(stage));
 
             _gpUniformBuffers[stage].SetBounds(index, range);
             _gpUniformBuffersDirty = true;
@@ -502,7 +502,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 foreach (var binding in _bufferTextures)
                 {
                     var isStore = binding.BindingInfo.Flags.HasFlag(TextureUsageFlags.ImageStore);
-                    var range = bufferCache.GetBufferRange(binding.Range, isStore);
+                    var range = bufferCache.GetBufferRange(binding.Range, BufferStageUtils.TextureBuffer(binding.Stage, binding.BindingInfo.Flags), isStore);
                     binding.Texture.SetStorage(range);
 
                     // The texture must be rebound to use the new storage if it was updated.
@@ -526,7 +526,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                 foreach (var binding in _bufferTextureArrays)
                 {
-                    var range = bufferCache.GetBufferRange(binding.Range);
+                    var range = bufferCache.GetBufferRange(binding.Range, BufferStage.None);
                     binding.Texture.SetStorage(range);
 
                     textureArray[0] = binding.Texture;
@@ -536,7 +536,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 foreach (var binding in _bufferImageArrays)
                 {
                     var isStore = binding.BindingInfo.Flags.HasFlag(TextureUsageFlags.ImageStore);
-                    var range = bufferCache.GetBufferRange(binding.Range, isStore);
+                    var range = bufferCache.GetBufferRange(binding.Range, BufferStage.None, isStore);
                     binding.Texture.SetStorage(range);
 
                     textureArray[0] = binding.Texture;
@@ -565,7 +565,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                     if (!_indexBuffer.Range.IsUnmapped)
                     {
-                        BufferRange buffer = bufferCache.GetBufferRange(_indexBuffer.Range);
+                        BufferRange buffer = bufferCache.GetBufferRange(_indexBuffer.Range, BufferStage.IndexBuffer);
 
                         _context.Renderer.Pipeline.SetIndexBuffer(buffer, _indexBuffer.Type);
                     }
@@ -597,7 +597,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                         continue;
                     }
 
-                    BufferRange buffer = bufferCache.GetBufferRange(vb.Range);
+                    BufferRange buffer = bufferCache.GetBufferRange(vb.Range, BufferStage.VertexBuffer);
 
                     vertexBuffers[index] = new VertexBufferDescriptor(buffer, vb.Stride, vb.Divisor);
                 }
@@ -637,7 +637,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                             continue;
                         }
 
-                        tfbs[index] = bufferCache.GetBufferRange(tfb.Range, write: true);
+                        tfbs[index] = bufferCache.GetBufferRange(tfb.Range, BufferStage.TransformFeedback, write: true);
                     }
 
                     _context.Renderer.Pipeline.SetTransformFeedbackBuffers(tfbs);
@@ -684,7 +684,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                             _context.SupportBufferUpdater.SetTfeOffset(index, tfeOffset);
 
-                            buffers[index] = new BufferAssignment(index, bufferCache.GetBufferRange(range, write: true));
+                            buffers[index] = new BufferAssignment(index, bufferCache.GetBufferRange(range, BufferStage.TransformFeedback, write: true));
                         }
                     }
 
@@ -751,6 +751,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             for (ShaderStage stage = ShaderStage.Vertex; stage <= ShaderStage.Fragment; stage++)
             {
                 ref var buffers = ref bindings[(int)stage - 1];
+                BufferStage bufferStage = BufferStageUtils.FromShaderStage(stage);
 
                 for (int index = 0; index < buffers.Count; index++)
                 {
@@ -762,8 +763,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
                     {
                         var isWrite = bounds.Flags.HasFlag(BufferUsageFlags.Write);
                         var range = isStorage
-                            ? bufferCache.GetBufferRangeAligned(bounds.Range, isWrite)
+                            ? bufferCache.GetBufferRangeAligned(bounds.Range, bufferStage | BufferStageUtils.FromUsage(bounds.Flags), isWrite)
-                            : bufferCache.GetBufferRange(bounds.Range);
+                            : bufferCache.GetBufferRange(bounds.Range, bufferStage);
 
                         ranges[rangesCount++] = new BufferAssignment(bindingInfo.Binding, range);
                     }
@@ -799,8 +800,8 @@ namespace Ryujinx.Graphics.Gpu.Memory
                 {
                     var isWrite = bounds.Flags.HasFlag(BufferUsageFlags.Write);
                     var range = isStorage
-                        ? bufferCache.GetBufferRangeAligned(bounds.Range, isWrite)
+                        ? bufferCache.GetBufferRangeAligned(bounds.Range, BufferStageUtils.ComputeStorage(bounds.Flags), isWrite)
-                        : bufferCache.GetBufferRange(bounds.Range);
+                        : bufferCache.GetBufferRange(bounds.Range, BufferStage.Compute);
 
                     ranges[rangesCount++] = new BufferAssignment(bindingInfo.Binding, range);
                 }
@@ -875,7 +876,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             Format format,
             bool isImage)
         {
-            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range);
+            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
             _bufferTextures.Add(new BufferTextureBinding(stage, texture, range, bindingInfo, format, isImage));
         }
@@ -883,6 +884,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <summary>
         /// Sets the buffer storage of a buffer texture array element. This will be bound when the buffer manager commits bindings.
         /// </summary>
+        /// <param name="stage">Shader stage accessing the texture</param>
         /// <param name="array">Texture array where the element will be inserted</param>
         /// <param name="texture">Buffer texture</param>
         /// <param name="range">Physical ranges of memory where the buffer texture data is located</param>
@@ -890,6 +892,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="index">Index of the binding on the array</param>
         /// <param name="format">Format of the buffer texture</param>
         public void SetBufferTextureStorage(
+            ShaderStage stage,
             ITextureArray array,
             ITexture texture,
             MultiRange range,
@@ -897,7 +900,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             int index,
             Format format)
         {
-            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range);
+            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
             _bufferTextureArrays.Add(new BufferTextureArrayBinding<ITextureArray>(array, texture, range, bindingInfo, index, format));
         }
@@ -905,6 +908,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <summary>
         /// Sets the buffer storage of a buffer image array element. This will be bound when the buffer manager commits bindings.
         /// </summary>
+        /// <param name="stage">Shader stage accessing the texture</param>
         /// <param name="array">Image array where the element will be inserted</param>
         /// <param name="texture">Buffer texture</param>
         /// <param name="range">Physical ranges of memory where the buffer texture data is located</param>
@@ -912,6 +916,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="index">Index of the binding on the array</param>
         /// <param name="format">Format of the buffer texture</param>
         public void SetBufferTextureStorage(
+            ShaderStage stage,
             IImageArray array,
             ITexture texture,
             MultiRange range,
@@ -919,7 +924,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             int index,
             Format format)
         {
-            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range);
+            _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
             _bufferImageArrays.Add(new BufferTextureArrayBinding<IImageArray>(array, texture, range, bindingInfo, index, format));
         }

src/Ryujinx.Graphics.Gpu/Memory/BufferMigration.cs

@@ -1,37 +1,21 @@
 using System;
+using System.Threading;
 
 namespace Ryujinx.Graphics.Gpu.Memory
 {
     /// <summary>
-    /// A record of when buffer data was copied from one buffer to another, along with the SyncNumber when the migration will be complete.
+    /// A record of when buffer data was copied from multiple buffers to one migration target,
-    /// Keeps the source buffer alive for data flushes until the migration is complete.
+    /// along with the SyncNumber when the migration will be complete.
+    /// Keeps the source buffers alive for data flushes until the migration is complete.
+    /// All spans cover the full range of the "destination" buffer.
     /// </summary>
     internal class BufferMigration : IDisposable
     {
         /// <summary>
-        /// The offset for the migrated region.
+        /// Ranges from source buffers that were copied as part of this migration.
+        /// Ordered by increasing base address.
         /// </summary>
-        private readonly ulong _offset;
+        public BufferMigrationSpan[] Spans { get; private set; }
-
-        /// <summary>
-        /// The size for the migrated region.
-        /// </summary>
-        private readonly ulong _size;
-
-        /// <summary>
-        /// The buffer that was migrated from.
-        /// </summary>
-        private readonly Buffer _buffer;
-
-        /// <summary>
-        /// The source range action, to be called on overlap with an unreached sync number.
-        /// </summary>
-        private readonly Action<ulong, ulong> _sourceRangeAction;
-
-        /// <summary>
-        /// The source range list.
-        /// </summary>
-        private readonly BufferModifiedRangeList _source;
 
         /// <summary>
         /// The destination range list. This range list must be updated when flushing the source.
@@ -43,55 +27,193 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         public readonly ulong SyncNumber;
 
+        /// <summary>
+        /// Number of active users there are traversing this migration's spans.
+        /// </summary>
+        private int _refCount;
+
+        /// <summary>
+        /// Create a new buffer migration.
+        /// </summary>
+        /// <param name="spans">Source spans for the migration</param>
+        /// <param name="destination">Destination buffer range list</param>
+        /// <param name="syncNumber">Sync number where this migration will be complete</param>
+        public BufferMigration(BufferMigrationSpan[] spans, BufferModifiedRangeList destination, ulong syncNumber)
+        {
+            Spans = spans;
+            Destination = destination;
+            SyncNumber = syncNumber;
+        }
+
+        /// <summary>
+        /// Add a span to the migration. Allocates a new array with the target size, and replaces it.
+        /// </summary>
+        /// <remarks>
+        /// The base address for the span is assumed to be higher than all other spans in the migration,
+        /// to keep the span array ordered.
+        /// </remarks>
+        public void AddSpanToEnd(BufferMigrationSpan span)
+        {
+            BufferMigrationSpan[] oldSpans = Spans;
+
+            BufferMigrationSpan[] newSpans = new BufferMigrationSpan[oldSpans.Length + 1];
+
+            oldSpans.CopyTo(newSpans, 0);
+
+            newSpans[oldSpans.Length] = span;
+
+            Spans = newSpans;
+        }
+
+        /// <summary>
+        /// Performs the given range action, or one from a migration that overlaps and has not synced yet.
+        /// </summary>
+        /// <param name="offset">The offset to pass to the action</param>
+        /// <param name="size">The size to pass to the action</param>
+        /// <param name="syncNumber">The sync number that has been reached</param>
+        /// <param name="rangeAction">The action to perform</param>
+        public void RangeActionWithMigration(ulong offset, ulong size, ulong syncNumber, BufferFlushAction rangeAction)
+        {
+            long syncDiff = (long)(syncNumber - SyncNumber);
+
+            if (syncDiff >= 0)
+            {
+                // The migration has completed. Run the parent action.
+                rangeAction(offset, size, syncNumber);
+            }
+            else
+            {
+                Interlocked.Increment(ref _refCount);
+
+                ulong prevAddress = offset;
+                ulong endAddress = offset + size;
+
+                foreach (BufferMigrationSpan span in Spans)
+                {
+                    if (!span.Overlaps(offset, size))
+                    {
+                        continue;
+                    }
+
+                    if (span.Address > prevAddress)
+                    {
+                        // There's a gap between this span and the last (or the start address). Flush the range using the parent action.
+
+                        rangeAction(prevAddress, span.Address - prevAddress, syncNumber);
+                    }
+
+                    span.RangeActionWithMigration(offset, size, syncNumber);
+
+                    prevAddress = span.Address + span.Size;
+                }
+
+                if (endAddress > prevAddress)
+                {
+                    // There's a gap at the end of the range with no migration. Flush the range using the parent action.
+                    rangeAction(prevAddress, endAddress - prevAddress, syncNumber);
+                }
+
+                Interlocked.Decrement(ref _refCount);
+            }
+        }
+
+        /// <summary>
+        /// Dispose the buffer migration. This removes the reference from the destination range list,
+        /// and runs all the dispose buffers for the migration spans. (typically disposes the source buffer)
+        /// </summary>
+        public void Dispose()
+        {
+            while (Volatile.Read(ref _refCount) > 0)
+            {
+                // Coming into this method, the sync for the migration will be met, so nothing can increment the ref count.
+                // However, an existing traversal of the spans for data flush could still be in progress.
+                // Spin if this is ever the case, so they don't get disposed before the operation is complete.
+            }
+
+            Destination.RemoveMigration(this);
+
+            foreach (BufferMigrationSpan span in Spans)
+            {
+                span.Dispose();
+            }
+        }
+    }
+
+    /// <summary>
+    /// A record of when buffer data was copied from one buffer to another, for a specific range in a source buffer.
+    /// Keeps the source buffer alive for data flushes until the migration is complete.
+    /// </summary>
+    internal readonly struct BufferMigrationSpan : IDisposable
+    {
+        /// <summary>
+        /// The offset for the migrated region.
+        /// </summary>
+        public readonly ulong Address;
+
+        /// <summary>
+        /// The size for the migrated region.
+        /// </summary>
+        public readonly ulong Size;
+
+        /// <summary>
+        /// The action to perform when the migration isn't needed anymore.
+        /// </summary>
+        private readonly Action _disposeAction;
+
+        /// <summary>
+        /// The source range action, to be called on overlap with an unreached sync number.
+        /// </summary>
+        private readonly BufferFlushAction _sourceRangeAction;
+
+        /// <summary>
+        /// Optional migration for the source data. Can chain together if many migrations happen in a short time.
+        /// If this is null, then _sourceRangeAction will always provide up to date data.
+        /// </summary>
+        private readonly BufferMigration _source;
+
         /// <summary>
         /// Creates a record for a buffer migration.
         /// </summary>
         /// <param name="buffer">The source buffer for this migration</param>
+        /// <param name="disposeAction">The action to perform when the migration isn't needed anymore</param>
         /// <param name="sourceRangeAction">The flush action for the source buffer</param>
-        /// <param name="source">The modified range list for the source buffer</param>
+        /// <param name="source">Pending migration for the source buffer</param>
-        /// <param name="dest">The modified range list for the destination buffer</param>
+        public BufferMigrationSpan(
-        /// <param name="syncNumber">The sync number for when the migration is complete</param>
-        public BufferMigration(
             Buffer buffer,
-            Action<ulong, ulong> sourceRangeAction,
+            Action disposeAction,
-            BufferModifiedRangeList source,
+            BufferFlushAction sourceRangeAction,
-            BufferModifiedRangeList dest,
+            BufferMigration source)
-            ulong syncNumber)
         {
-            _offset = buffer.Address;
+            Address = buffer.Address;
-            _size = buffer.Size;
+            Size = buffer.Size;
-            _buffer = buffer;
+            _disposeAction = disposeAction;
             _sourceRangeAction = sourceRangeAction;
             _source = source;
-            Destination = dest;
-            SyncNumber = syncNumber;
         }
 
+        /// <summary>
+        /// Creates a record for a buffer migration, using the default buffer dispose action.
+        /// </summary>
+        /// <param name="buffer">The source buffer for this migration</param>
+        /// <param name="sourceRangeAction">The flush action for the source buffer</param>
+        /// <param name="source">Pending migration for the source buffer</param>
+        public BufferMigrationSpan(
+            Buffer buffer,
+            BufferFlushAction sourceRangeAction,
+            BufferMigration source) : this(buffer, buffer.DecrementReferenceCount, sourceRangeAction, source) { }
+
         /// <summary>
         /// Determine if the given range overlaps this migration, and has not been completed yet.
         /// </summary>
         /// <param name="offset">Start offset</param>
         /// <param name="size">Range size</param>
-        /// <param name="syncNumber">The sync number that was waited on</param>
         /// <returns>True if overlapping and in progress, false otherwise</returns>
-        public bool Overlaps(ulong offset, ulong size, ulong syncNumber)
+        public bool Overlaps(ulong offset, ulong size)
         {
             ulong end = offset + size;
-            ulong destEnd = _offset + _size;
+            ulong destEnd = Address + Size;
-            long syncDiff = (long)(syncNumber - SyncNumber); // syncNumber is less if the copy has not completed.
 
-            return !(end <= _offset || offset >= destEnd) && syncDiff < 0;
+            return !(end <= Address || offset >= destEnd);
-        }
-
-        /// <summary>
-        /// Determine if the given range matches this migration.
-        /// </summary>
-        /// <param name="offset">Start offset</param>
-        /// <param name="size">Range size</param>
-        /// <returns>True if the range exactly matches, false otherwise</returns>
-        public bool FullyMatches(ulong offset, ulong size)
-        {
-            return _offset == offset && _size == size;
         }
 
         /// <summary>
@@ -100,26 +222,30 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="offset">Start offset</param>
         /// <param name="size">Range size</param>
         /// <param name="syncNumber">Current sync number</param>
-        /// <param name="parent">The modified range list that originally owned this range</param>
+        public void RangeActionWithMigration(ulong offset, ulong size, ulong syncNumber)
-        public void RangeActionWithMigration(ulong offset, ulong size, ulong syncNumber, BufferModifiedRangeList parent)
         {
             ulong end = offset + size;
-            end = Math.Min(_offset + _size, end);
+            end = Math.Min(Address + Size, end);
-            offset = Math.Max(_offset, offset);
+            offset = Math.Max(Address, offset);
 
             size = end - offset;
 
-            _source.RangeActionWithMigration(offset, size, syncNumber, parent, _sourceRangeAction);
+            if (_source != null)
+            {
+                _source.RangeActionWithMigration(offset, size, syncNumber, _sourceRangeAction);
+            }
+            else
+            {
+                _sourceRangeAction(offset, size, syncNumber);
+            }
         }
 
         /// <summary>
-        /// Removes this reference to the range list, potentially allowing for the source buffer to be disposed.
+        /// Removes this migration span, potentially allowing for the source buffer to be disposed.
         /// </summary>
         public void Dispose()
         {
-            Destination.RemoveMigration(this);
+            _disposeAction();
-
-            _buffer.DecrementReferenceCount();
         }
     }
 }

src/Ryujinx.Graphics.Gpu/Memory/BufferModifiedRangeList.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common.Pools;
 using Ryujinx.Memory.Range;
 using System;
-using System.Collections.Generic;
 using System.Linq;
 
 namespace Ryujinx.Graphics.Gpu.Memory
@@ -72,10 +71,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
         private readonly GpuContext _context;
         private readonly Buffer _parent;
-        private readonly Action<ulong, ulong> _flushAction;
+        private readonly BufferFlushAction _flushAction;
 
-        private List<BufferMigration> _sources;
+        private BufferMigration _source;
-        private BufferMigration _migrationTarget;
+        private BufferModifiedRangeList _migrationTarget;
 
         private readonly object _lock = new();
 
@@ -99,7 +98,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="context">GPU context that the buffer range list belongs to</param>
         /// <param name="parent">The parent buffer that owns this range list</param>
         /// <param name="flushAction">The flush action for the parent buffer</param>
-        public BufferModifiedRangeList(GpuContext context, Buffer parent, Action<ulong, ulong> flushAction) : base(BackingInitialSize)
+        public BufferModifiedRangeList(GpuContext context, Buffer parent, BufferFlushAction flushAction) : base(BackingInitialSize)
         {
             _context = context;
             _parent = parent;
@@ -199,6 +198,36 @@ namespace Ryujinx.Graphics.Gpu.Memory
             }
         }
 
+        /// <summary>
+        /// Gets modified ranges within the specified region, and then fires the given action for each range individually.
+        /// </summary>
+        /// <param name="address">Start address to query</param>
+        /// <param name="size">Size to query</param>
+        /// <param name="syncNumber">Sync number required for a range to be signalled</param>
+        /// <param name="rangeAction">The action to call for each modified range</param>
+        public void GetRangesAtSync(ulong address, ulong size, ulong syncNumber, Action<ulong, ulong> rangeAction)
+        {
+            int count = 0;
+
+            ref var overlaps = ref ThreadStaticArray<BufferModifiedRange>.Get();
+
+            // Range list must be consistent for this operation.
+            lock (_lock)
+            {
+                count = FindOverlapsNonOverlapping(address, size, ref overlaps);
+            }
+
+            for (int i = 0; i < count; i++)
+            {
+                BufferModifiedRange overlap = overlaps[i];
+
+                if (overlap.SyncNumber == syncNumber)
+                {
+                    rangeAction(overlap.Address, overlap.Size);
+                }
+            }
+        }
+
         /// <summary>
         /// Gets modified ranges within the specified region, and then fires the given action for each range individually.
         /// </summary>
@@ -245,41 +274,16 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="offset">The offset to pass to the action</param>
         /// <param name="size">The size to pass to the action</param>
         /// <param name="syncNumber">The sync number that has been reached</param>
-        /// <param name="parent">The modified range list that originally owned this range</param>
         /// <param name="rangeAction">The action to perform</param>
-        public void RangeActionWithMigration(ulong offset, ulong size, ulong syncNumber, BufferModifiedRangeList parent, Action<ulong, ulong> rangeAction)
+        public void RangeActionWithMigration(ulong offset, ulong size, ulong syncNumber, BufferFlushAction rangeAction)
         {
-            bool firstSource = true;
+            if (_source != null)
-
-            if (parent != this)
             {
-                lock (_lock)
+                _source.RangeActionWithMigration(offset, size, syncNumber, rangeAction);
-                {
-                    if (_sources != null)
-                    {
-                        foreach (BufferMigration source in _sources)
-                        {
-                            if (source.Overlaps(offset, size, syncNumber))
-                            {
-                                if (firstSource && !source.FullyMatches(offset, size))
-                                {
-                                    // Perform this buffer's action first. The migrations will run after.
-                                    rangeAction(offset, size);
-                                }
-
-                                source.RangeActionWithMigration(offset, size, syncNumber, parent);
-
-                                firstSource = false;
-                            }
-                        }
-                    }
-                }
             }
-
+            else
-            if (firstSource)
             {
-                // No overlapping migrations, or they are not meant for this range, flush the data using the given action.
+                rangeAction(offset, size, syncNumber);
-                rangeAction(offset, size);
             }
         }
 
@@ -319,7 +323,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                             ClearPart(overlap, clampAddress, clampEnd);
 
-                            RangeActionWithMigration(clampAddress, clampEnd - clampAddress, waitSync, overlap.Parent, _flushAction);
+                            RangeActionWithMigration(clampAddress, clampEnd - clampAddress, waitSync, _flushAction);
                         }
                     }
 
@@ -329,7 +333,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             // There is a migration target to call instead. This can't be changed after set so accessing it outside the lock is fine.
 
-            _migrationTarget.Destination.RemoveRangesAndFlush(overlaps, rangeCount, highestDiff, currentSync, address, endAddress);
+            _migrationTarget.RemoveRangesAndFlush(overlaps, rangeCount, highestDiff, currentSync, address, endAddress);
         }
 
         /// <summary>
@@ -367,7 +371,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             if (rangeCount == -1)
             {
-                _migrationTarget.Destination.WaitForAndFlushRanges(address, size);
+                _migrationTarget.WaitForAndFlushRanges(address, size);
 
                 return;
             }
@@ -407,6 +411,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <summary>
         /// Inherit ranges from another modified range list.
         /// </summary>
+        /// <remarks>
+        /// Assumes that ranges will be inherited in address ascending order.
+        /// </remarks>
         /// <param name="ranges">The range list to inherit from</param>
         /// <param name="registerRangeAction">The action to call for each modified range</param>
         public void InheritRanges(BufferModifiedRangeList ranges, Action<ulong, ulong> registerRangeAction)
@@ -415,18 +422,31 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
             lock (ranges._lock)
             {
-                BufferMigration migration = new(ranges._parent, ranges._flushAction, ranges, this, _context.SyncNumber);
-
-                ranges._parent.IncrementReferenceCount();
-                ranges._migrationTarget = migration;
-
-                _context.RegisterBufferMigration(migration);
-
                 inheritRanges = ranges.ToArray();
 
                 lock (_lock)
                 {
-                    (_sources ??= new List<BufferMigration>()).Add(migration);
+                    // Copy over the migration from the previous range list
+
+                    BufferMigration oldMigration = ranges._source;
+
+                    BufferMigrationSpan span = new BufferMigrationSpan(ranges._parent, ranges._flushAction, oldMigration);
+                    ranges._parent.IncrementReferenceCount();
+
+                    if (_source == null)
+                    {
+                        // Create a new migration. 
+                        _source = new BufferMigration(new BufferMigrationSpan[] { span }, this, _context.SyncNumber);
+
+                        _context.RegisterBufferMigration(_source);
+                    }
+                    else
+                    {
+                        // Extend the migration
+                        _source.AddSpanToEnd(span);
+                    }
+
+                    ranges._migrationTarget = this;
 
                     foreach (BufferModifiedRange range in inheritRanges)
                     {
@@ -445,6 +465,27 @@ namespace Ryujinx.Graphics.Gpu.Memory
             }
         }
 
+        /// <summary>
+        /// Register a migration from previous buffer storage. This migration is from a snapshot of the buffer's
+        /// current handle to its handle in the future, and is assumed to be complete when the sync action completes.
+        /// When the migration completes, the handle is disposed.
+        /// </summary>
+        public void SelfMigration()
+        {
+            lock (_lock)
+            {
+                BufferMigrationSpan span = new(_parent, _parent.GetSnapshotDisposeAction(), _parent.GetSnapshotFlushAction(), _source);
+                BufferMigration migration = new(new BufferMigrationSpan[] { span }, this, _context.SyncNumber);
+
+                // Migration target is used to redirect flush actions to the latest range list,
+                // so we don't need to set it here. (this range list is still the latest)
+
+                _context.RegisterBufferMigration(migration);
+
+                _source = migration;
+            }
+        }
+
         /// <summary>
         /// Removes a source buffer migration, indicating its copy has completed.
         /// </summary>
@@ -453,7 +494,10 @@ namespace Ryujinx.Graphics.Gpu.Memory
         {
             lock (_lock)
             {
-                _sources.Remove(migration);
+                if (_source == migration)
+                {
+                    _source = null;
+                }
             }
         }
 

src/Ryujinx.Graphics.Gpu/Memory/BufferPreFlush.cs

@@ -0,0 +1,295 @@
+using Ryujinx.Common;
+using Ryujinx.Graphics.GAL;
+using System;
+
+namespace Ryujinx.Graphics.Gpu.Memory
+{
+    /// <summary>
+    /// Manages flushing ranges from buffers in advance for easy access, if they are flushed often.
+    /// Typically, from device local memory to a host mapped target for cached access.
+    /// </summary>
+    internal class BufferPreFlush : IDisposable
+    {
+        private const ulong PageSize = MemoryManager.PageSize;
+
+        /// <summary>
+        /// Threshold for the number of copies without a flush required to disable preflush on a page.
+        /// </summary>
+        private const int DeactivateCopyThreshold = 200;
+
+        /// <summary>
+        /// Value that indicates whether a page has been flushed or copied before.
+        /// </summary>
+        private enum PreFlushState
+        {
+            None,
+            HasFlushed,
+            HasCopied
+        }
+
+        /// <summary>
+        /// Flush state for each page of the buffer.
+        /// Controls whether data should be copied to the flush buffer, what sync is expected
+        /// and unflushed copy counting for stopping copies that are no longer needed.
+        /// </summary>
+        private struct PreFlushPage
+        {
+            public PreFlushState State;
+            public ulong FirstActivatedSync;
+            public ulong LastCopiedSync;
+            public int CopyCount;
+        }
+
+        /// <summary>
+        /// True if there are ranges that should copy to the flush buffer, false otherwise.
+        /// </summary>
+        public bool ShouldCopy { get; private set; }
+
+        private readonly GpuContext _context;
+        private readonly Buffer _buffer;
+        private readonly PreFlushPage[] _pages;
+        private readonly ulong _address;
+        private readonly ulong _size;
+        private readonly ulong _misalignment;
+        private readonly Action<BufferHandle, ulong, ulong> _flushAction;
+
+        private BufferHandle _flushBuffer;
+
+        public BufferPreFlush(GpuContext context, Buffer parent, Action<BufferHandle, ulong, ulong> flushAction)
+        {
+            _context = context;
+            _buffer = parent;
+            _address = parent.Address;
+            _size = parent.Size;
+            _pages = new PreFlushPage[BitUtils.DivRoundUp(_size, PageSize)];
+            _misalignment = _address & (PageSize - 1);
+
+            _flushAction = flushAction;
+        }
+
+        /// <summary>
+        /// Ensure that the flush buffer exists.
+        /// </summary>
+        private void EnsureFlushBuffer()
+        {
+            if (_flushBuffer == BufferHandle.Null)
+            {
+                _flushBuffer = _context.Renderer.CreateBuffer((int)_size, BufferAccess.HostMemory);
+            }
+        }
+
+        /// <summary>
+        /// Gets a page range from an address and size byte range.
+        /// </summary>
+        /// <param name="address">Range address</param>
+        /// <param name="size">Range size</param>
+        /// <returns>A page index and count</returns>
+        private (int index, int count) GetPageRange(ulong address, ulong size)
+        {
+            ulong offset = address - _address;
+            ulong endOffset = offset + size;
+
+            int basePage = (int)(offset / PageSize);
+            int endPage = (int)((endOffset - 1) / PageSize);
+
+            return (basePage, 1 + endPage - basePage);
+        }
+
+        /// <summary>
+        /// Gets an offset and size range in the parent buffer from a page index and count.
+        /// </summary>
+        /// <param name="startPage">Range start page</param>
+        /// <param name="count">Range page count</param>
+        /// <returns>Offset and size range</returns>
+        private (int offset, int size) GetOffset(int startPage, int count)
+        {
+            int offset = (int)((ulong)startPage * PageSize - _misalignment);
+            int endOffset = (int)((ulong)(startPage + count) * PageSize - _misalignment);
+
+            offset = Math.Max(0, offset);
+            endOffset = Math.Min((int)_size, endOffset);
+
+            return (offset, endOffset - offset);
+        }
+
+        /// <summary>
+        /// Copy a range of pages from the parent buffer into the flush buffer.
+        /// </summary>
+        /// <param name="startPage">Range start page</param>
+        /// <param name="count">Range page count</param>
+        private void CopyPageRange(int startPage, int count)
+        {
+            (int offset, int size) = GetOffset(startPage, count);
+
+            EnsureFlushBuffer();
+
+            _context.Renderer.Pipeline.CopyBuffer(_buffer.Handle, _flushBuffer, offset, offset, size);
+        }
+
+        /// <summary>
+        /// Copy a modified range into the flush buffer if it's marked as flushed.
+        /// Any pages the range overlaps are copied, and copies aren't repeated in the same sync number.
+        /// </summary>
+        /// <param name="address">Range address</param>
+        /// <param name="size">Range size</param>
+        public void CopyModified(ulong address, ulong size)
+        {
+            (int baseIndex, int count) = GetPageRange(address, size);
+            ulong syncNumber = _context.SyncNumber;
+
+            int startPage = -1;
+
+            for (int i = 0; i < count; i++)
+            {
+                int pageIndex = baseIndex + i;
+                ref PreFlushPage page = ref _pages[pageIndex];
+
+                if (page.State > PreFlushState.None)
+                {
+                    // Perform the copy, and update the state of each page.
+                    if (startPage == -1)
+                    {
+                        startPage = pageIndex;
+                    }
+
+                    if (page.State != PreFlushState.HasCopied)
+                    {
+                        page.FirstActivatedSync = syncNumber;
+                        page.State = PreFlushState.HasCopied;
+                    }
+                    else if (page.CopyCount++ >= DeactivateCopyThreshold)
+                    {
+                        page.CopyCount = 0;
+                        page.State = PreFlushState.None;
+                    }
+
+                    if (page.LastCopiedSync != syncNumber)
+                    {
+                        page.LastCopiedSync = syncNumber;
+                    }
+                }
+                else if (startPage != -1)
+                {
+                    CopyPageRange(startPage, pageIndex - startPage);
+
+                    startPage = -1;
+                }
+            }
+
+            if (startPage != -1)
+            {
+                CopyPageRange(startPage, (baseIndex + count) - startPage);
+            }
+        }
+
+        /// <summary>
+        /// Flush the given page range back into guest memory, optionally using data from the flush buffer.
+        /// The actual flushed range is an intersection of the page range and the address range.
+        /// </summary>
+        /// <param name="address">Address range start</param>
+        /// <param name="size">Address range size</param>
+        /// <param name="startPage">Page range start</param>
+        /// <param name="count">Page range count</param>
+        /// <param name="preFlush">True if the data should come from the flush buffer</param>
+        private void FlushPageRange(ulong address, ulong size, int startPage, int count, bool preFlush)
+        {
+            (int pageOffset, int pageSize) = GetOffset(startPage, count);
+
+            int offset = (int)(address - _address);
+            int end = offset + (int)size;
+
+            offset = Math.Max(offset, pageOffset);
+            end = Math.Min(end, pageOffset + pageSize);
+
+            if (end >= offset)
+            {
+                BufferHandle handle = preFlush ? _flushBuffer : _buffer.Handle;
+                _flushAction(handle, _address + (ulong)offset, (ulong)(end - offset));
+            }
+        }
+
+        /// <summary>
+        /// Flush the given address range back into guest memory, optionally using data from the flush buffer.
+        /// When a copy has been performed on or before the waited sync number, the data can come from the flush buffer.
+        /// Otherwise, it flushes the parent buffer directly.
+        /// </summary>
+        /// <param name="address">Range address</param>
+        /// <param name="size">Range size</param>
+        /// <param name="syncNumber">Sync number that has been waited for</param>
+        public void FlushWithAction(ulong address, ulong size, ulong syncNumber)
+        {
+            // Copy the parts of the range that have pre-flush copies that have been completed.
+            // Run the flush action for ranges that don't have pre-flush copies.
+
+            // If a range doesn't have a pre-flush copy, consider adding one.
+
+            (int baseIndex, int count) = GetPageRange(address, size);
+
+            bool rangePreFlushed = false;
+            int startPage = -1;
+
+            for (int i = 0; i < count; i++)
+            {
+                int pageIndex = baseIndex + i;
+                ref PreFlushPage page = ref _pages[pageIndex];
+
+                bool flushPage = false;
+                page.CopyCount = 0;
+
+                if (page.State == PreFlushState.HasCopied)
+                {
+                    if (syncNumber >= page.FirstActivatedSync)
+                    {
+                        // After the range is first activated, its data will always be copied to the preflush buffer on each sync.
+                        flushPage = true;
+                    }
+                }
+                else if (page.State == PreFlushState.None)
+                {
+                    page.State = PreFlushState.HasFlushed;
+                    ShouldCopy = true;
+                }
+
+                if (flushPage)
+                {
+                    if (!rangePreFlushed || startPage == -1)
+                    {
+                        if (startPage != -1)
+                        {
+                            FlushPageRange(address, size, startPage, pageIndex - startPage, false);
+                        }
+
+                        rangePreFlushed = true;
+                        startPage = pageIndex;
+                    }
+                }
+                else if (rangePreFlushed || startPage == -1)
+                {
+                    if (startPage != -1)
+                    {
+                        FlushPageRange(address, size, startPage, pageIndex - startPage, true);
+                    }
+
+                    rangePreFlushed = false;
+                    startPage = pageIndex;
+                }
+            }
+
+            if (startPage != -1)
+            {
+                FlushPageRange(address, size, startPage, (baseIndex + count) - startPage, rangePreFlushed);
+            }
+        }
+
+        /// <summary>
+        /// Dispose the flush buffer, if present.
+        /// </summary>
+        public void Dispose()
+        {
+            if (_flushBuffer != BufferHandle.Null)
+            {
+                _context.Renderer.DeleteBuffer(_flushBuffer);
+            }
+        }
+    }
+}

src/Ryujinx.Graphics.Gpu/Memory/BufferStage.cs

@@ -0,0 +1,99 @@
+using Ryujinx.Graphics.Shader;
+using System.Runtime.CompilerServices;
+
+namespace Ryujinx.Graphics.Gpu.Memory
+{
+    /// <summary>
+    /// Pipeline stages that can modify buffer data, as well as flags indicating storage usage.
+    /// Must match ShaderStage for the shader stages, though anything after that can be in any order.
+    /// </summary>
+    internal enum BufferStage : byte
+    {
+        Compute,
+        Vertex,
+        TessellationControl,
+        TessellationEvaluation,
+        Geometry,
+        Fragment,
+
+        Indirect,
+        VertexBuffer,
+        IndexBuffer,
+        Copy,
+        TransformFeedback,
+        Internal,
+        None,
+
+        StageMask = 0x3f,
+        StorageMask = 0xc0,
+
+        StorageRead = 0x40,
+        StorageWrite = 0x80,
+
+#pragma warning disable CA1069 // Enums values should not be duplicated
+        StorageAtomic = 0xc0
+#pragma warning restore CA1069 // Enums values should not be duplicated
+    }
+
+    /// <summary>
+    /// Utility methods to convert shader stages and binding flags into buffer stages.
+    /// </summary>
+    internal static class BufferStageUtils
+    {
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage FromShaderStage(ShaderStage stage)
+        {
+            return (BufferStage)stage;
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage FromShaderStage(int stageIndex)
+        {
+            return (BufferStage)(stageIndex + 1);
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage FromUsage(BufferUsageFlags flags)
+        {
+            if (flags.HasFlag(BufferUsageFlags.Write))
+            {
+                return BufferStage.StorageWrite;
+            }
+            else
+            {
+                return BufferStage.StorageRead;
+            }
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage FromUsage(TextureUsageFlags flags)
+        {
+            if (flags.HasFlag(TextureUsageFlags.ImageStore))
+            {
+                return BufferStage.StorageWrite;
+            }
+            else
+            {
+                return BufferStage.StorageRead;
+            }
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage TextureBuffer(ShaderStage shaderStage, TextureUsageFlags flags)
+        {
+            return FromShaderStage(shaderStage) | FromUsage(flags);
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage GraphicsStorage(int stageIndex, BufferUsageFlags flags)
+        {
+            return FromShaderStage(stageIndex) | FromUsage(flags);
+        }
+
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public static BufferStage ComputeStorage(BufferUsageFlags flags)
+        {
+            return BufferStage.Compute | FromUsage(flags);
+        }
+    }
+}

src/Ryujinx.Graphics.Gpu/Memory/MemoryManager.cs

@@ -2,7 +2,6 @@ using Ryujinx.Common.Memory;
 using Ryujinx.Memory;
 using Ryujinx.Memory.Range;
 using System;
-using System.Buffers;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
@@ -242,9 +241,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
             }
             else
             {
-                IMemoryOwner<byte> memoryOwner = ByteMemoryPool.Rent(size);
+                MemoryOwner<byte> memoryOwner = MemoryOwner<byte>.Rent(size);
 
-                GetSpan(va, size).CopyTo(memoryOwner.Memory.Span);
+                ReadImpl(va, memoryOwner.Span, tracked);
 
                 return new WritableRegion(this, va, memoryOwner, tracked);
             }

src/Ryujinx.Graphics.Gpu/Memory/PhysicalMemory.cs

@@ -192,9 +192,9 @@ namespace Ryujinx.Graphics.Gpu.Memory
             }
             else
             {
-                IMemoryOwner<byte> memoryOwner = ByteMemoryPool.Rent(range.GetSize());
+                MemoryOwner<byte> memoryOwner = MemoryOwner<byte>.Rent(checked((int)range.GetSize()));
 
-                Memory<byte> memory = memoryOwner.Memory;
+                Span<byte> memorySpan = memoryOwner.Span;
 
                 int offset = 0;
                 for (int i = 0; i < range.Count; i++)
@@ -203,7 +203,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
                     int size = (int)currentRange.Size;
                     if (currentRange.Address != MemoryManager.PteUnmapped)
                     {
-                        GetSpan(currentRange.Address, size).CopyTo(memory.Span.Slice(offset, size));
+                        GetSpan(currentRange.Address, size).CopyTo(memorySpan.Slice(offset, size));
                     }
                     offset += size;
                 }

src/Ryujinx.Graphics.Gpu/Shader/CachedShaderBindings.cs

@@ -62,6 +62,7 @@ namespace Ryujinx.Graphics.Gpu.Shader
 
                     var result = new TextureBindingInfo(
                         target,
+                        descriptor.Set,
                         descriptor.Binding,
                         descriptor.ArrayLength,
                         descriptor.CbufSlot,
@@ -90,6 +91,7 @@ namespace Ryujinx.Graphics.Gpu.Shader
                     var result = new TextureBindingInfo(
                         target,
                         format,
+                        descriptor.Set,
                         descriptor.Binding,
                         descriptor.ArrayLength,
                         descriptor.CbufSlot,

src/Ryujinx.Graphics.Gpu/Shader/DiskCache/BinarySerializer.cs

@@ -125,9 +125,18 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
             CompressionAlgorithm algorithm = CompressionAlgorithm.None;
             Read(ref algorithm);
 
-            if (algorithm == CompressionAlgorithm.Deflate)
+            switch (algorithm)
             {
-                _activeStream = new DeflateStream(_stream, CompressionMode.Decompress, true);
+                case CompressionAlgorithm.None:
+                    break;
+                case CompressionAlgorithm.Deflate:
+                    _activeStream = new DeflateStream(_stream, CompressionMode.Decompress, true);
+                    break;
+                case CompressionAlgorithm.Brotli:
+                    _activeStream = new BrotliStream(_stream, CompressionMode.Decompress, true);
+                    break;
+                default:
+                    throw new ArgumentException($"Invalid compression algorithm \"{algorithm}\"");
             }
         }
 
@@ -139,9 +148,18 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
         {
             Write(ref algorithm);
 
-            if (algorithm == CompressionAlgorithm.Deflate)
+            switch (algorithm)
             {
-                _activeStream = new DeflateStream(_stream, CompressionLevel.Fastest, true);
+                case CompressionAlgorithm.None:
+                    break;
+                case CompressionAlgorithm.Deflate:
+                    _activeStream = new DeflateStream(_stream, CompressionLevel.Fastest, true);
+                    break;
+                case CompressionAlgorithm.Brotli:
+                    _activeStream = new BrotliStream(_stream, CompressionLevel.Fastest, true);
+                    break;
+                default:
+                    throw new ArgumentException($"Invalid compression algorithm \"{algorithm}\"");
             }
         }
 
@@ -177,7 +195,7 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
             switch (algorithm)
             {
                 case CompressionAlgorithm.None:
-                    stream.Read(data);
+                    stream.ReadExactly(data);
                     break;
                 case CompressionAlgorithm.Deflate:
                     stream = new DeflateStream(stream, CompressionMode.Decompress, true);
@@ -187,6 +205,14 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
                     }
                     stream.Dispose();
                     break;
+                case CompressionAlgorithm.Brotli:
+                    stream = new BrotliStream(stream, CompressionMode.Decompress, true);
+                    for (int offset = 0; offset < data.Length;)
+                    {
+                        offset += stream.Read(data[offset..]);
+                    }
+                    stream.Dispose();
+                    break;
             }
         }
 
@@ -210,6 +236,11 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
                     stream.Write(data);
                     stream.Dispose();
                     break;
+                case CompressionAlgorithm.Brotli:
+                    stream = new BrotliStream(stream, CompressionLevel.Fastest, true);
+                    stream.Write(data);
+                    stream.Dispose();
+                    break;
             }
         }
     }

src/Ryujinx.Graphics.Gpu/Shader/DiskCache/CompressionAlgorithm.cs

@@ -14,5 +14,10 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
         /// Deflate compression (RFC 1951).
         /// </summary>
         Deflate,
+
+        /// <summary>
+        /// Brotli compression (RFC 7932).
+        /// </summary>
+        Brotli,
     }
 }

src/Ryujinx.Graphics.Gpu/Shader/DiskCache/DiskCacheCommon.cs

@@ -51,7 +51,7 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
         /// <returns>Compression algorithm</returns>
         public static CompressionAlgorithm GetCompressionAlgorithm()
         {
-            return CompressionAlgorithm.Deflate;
+            return CompressionAlgorithm.Brotli;
         }
     }
 }

src/Ryujinx.Graphics.Gpu/Shader/DiskCache/DiskCacheGuestStorage.cs

@@ -220,7 +220,7 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
                 }
 
                 dataFileStream.Seek((long)entry.Offset, SeekOrigin.Begin);
-                dataFileStream.Read(cb1Data);
+                dataFileStream.ReadExactly(cb1Data);
                 BinarySerializer.ReadCompressed(dataFileStream, guestCode);
 
                 _cache[index] = (guestCode, cb1Data);
@@ -279,7 +279,7 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
                     dataFileStream.Seek((long)entry.Offset, SeekOrigin.Begin);
                     byte[] cachedCode = new byte[entry.CodeSize];
                     byte[] cachedCb1Data = new byte[entry.Cb1DataSize];
-                    dataFileStream.Read(cachedCb1Data);
+                    dataFileStream.ReadExactly(cachedCb1Data);
                     BinarySerializer.ReadCompressed(dataFileStream, cachedCode);
 
                     if (data.SequenceEqual(cachedCode) && cb1Data.SequenceEqual(cachedCb1Data))

src/Ryujinx.Graphics.Gpu/Shader/DiskCache/DiskCacheHostStorage.cs

@@ -22,7 +22,7 @@ namespace Ryujinx.Graphics.Gpu.Shader.DiskCache
         private const ushort FileFormatVersionMajor = 1;
         private const ushort FileFormatVersionMinor = 2;
         private const uint FileFormatVersionPacked = ((uint)FileFormatVersionMajor << 16) | FileFormatVersionMinor;
-        private const uint CodeGenVersion = 5936;
+        private const uint CodeGenVersion = 7131;
 
         private const string SharedTocFileName = "shared.toc";
         private const string SharedDataFileName = "shared.data";

src/Ryujinx.Graphics.Gpu/Shader/GpuAccessorBase.cs

@@ -51,7 +51,7 @@ namespace Ryujinx.Graphics.Gpu.Shader
             _reservedImages = rrc.ReservedImages;
         }
 
-        public int CreateConstantBufferBinding(int index)
+        public SetBindingPair CreateConstantBufferBinding(int index)
         {
             int binding;
 
@@ -64,10 +64,10 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 binding = _resourceCounts.UniformBuffersCount++;
             }
 
-            return binding + _reservedConstantBuffers;
+            return new SetBindingPair(_context.Capabilities.UniformBufferSetIndex, binding + _reservedConstantBuffers);
         }
 
-        public int CreateImageBinding(int count, bool isBuffer)
+        public SetBindingPair CreateImageBinding(int count, bool isBuffer)
         {
             int binding;
 
@@ -96,10 +96,10 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 _resourceCounts.ImagesCount += count;
             }
 
-            return binding + _reservedImages;
+            return new SetBindingPair(_context.Capabilities.ImageSetIndex, binding + _reservedImages);
         }
 
-        public int CreateStorageBufferBinding(int index)
+        public SetBindingPair CreateStorageBufferBinding(int index)
         {
             int binding;
 
@@ -112,10 +112,10 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 binding = _resourceCounts.StorageBuffersCount++;
             }
 
-            return binding + _reservedStorageBuffers;
+            return new SetBindingPair(_context.Capabilities.StorageBufferSetIndex, binding + _reservedStorageBuffers);
         }
 
-        public int CreateTextureBinding(int count, bool isBuffer)
+        public SetBindingPair CreateTextureBinding(int count, bool isBuffer)
         {
             int binding;
 
@@ -144,7 +144,7 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 _resourceCounts.TexturesCount += count;
             }
 
-            return binding + _reservedTextures;
+            return new SetBindingPair(_context.Capabilities.TextureSetIndex, binding + _reservedTextures);
         }
 
         private int GetBindingFromIndex(int index, uint maxPerStage, string resourceName)
@@ -183,6 +183,16 @@ namespace Ryujinx.Graphics.Gpu.Shader
             return maxPerStage * Constants.ShaderStages;
         }
 
+        public int CreateExtraSet()
+        {
+            if (_resourceCounts.SetsCount >= _context.Capabilities.MaximumExtraSets)
+            {
+                return -1;
+            }
+
+            return _context.Capabilities.ExtraSetBaseIndex + _resourceCounts.SetsCount++;
+        }
+
         public int QueryHostGatherBiasPrecision() => _context.Capabilities.GatherBiasPrecision;
 
         public bool QueryHostReducedPrecision() => _context.Capabilities.ReduceShaderPrecision;

src/Ryujinx.Graphics.Gpu/Shader/ResourceCounts.cs

@@ -24,5 +24,10 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// Total of images used by the shaders.
         /// </summary>
         public int ImagesCount;
+
+        /// <summary>
+        /// Total of extra sets used by the shaders.
+        /// </summary>
+        public int SetsCount;
     }
 }

src/Ryujinx.Graphics.Gpu/Shader/ShaderInfoBuilder.cs

@@ -1,5 +1,6 @@
 using Ryujinx.Graphics.GAL;
 using Ryujinx.Graphics.Shader;
+using System;
 using System.Collections.Generic;
 
 namespace Ryujinx.Graphics.Gpu.Shader
@@ -9,13 +10,6 @@ namespace Ryujinx.Graphics.Gpu.Shader
     /// </summary>
     class ShaderInfoBuilder
     {
-        private const int TotalSets = 4;
-
-        private const int UniformSetIndex = 0;
-        private const int StorageSetIndex = 1;
-        private const int TextureSetIndex = 2;
-        private const int ImageSetIndex = 3;
-
         private const ResourceStages SupportBufferStages =
             ResourceStages.Compute |
             ResourceStages.Vertex |
@@ -36,8 +30,8 @@ namespace Ryujinx.Graphics.Gpu.Shader
         private readonly int _reservedTextures;
         private readonly int _reservedImages;
 
-        private readonly List<ResourceDescriptor>[] _resourceDescriptors;
+        private List<ResourceDescriptor>[] _resourceDescriptors;
-        private readonly List<ResourceUsage>[] _resourceUsages;
+        private List<ResourceUsage>[] _resourceUsages;
 
         /// <summary>
         /// Creates a new shader info builder.
@@ -51,17 +45,27 @@ namespace Ryujinx.Graphics.Gpu.Shader
 
             _fragmentOutputMap = -1;
 
-            _resourceDescriptors = new List<ResourceDescriptor>[TotalSets];
+            int uniformSetIndex = context.Capabilities.UniformBufferSetIndex;
-            _resourceUsages = new List<ResourceUsage>[TotalSets];
+            int storageSetIndex = context.Capabilities.StorageBufferSetIndex;
+            int textureSetIndex = context.Capabilities.TextureSetIndex;
+            int imageSetIndex = context.Capabilities.ImageSetIndex;
 
-            for (int index = 0; index < TotalSets; index++)
+            int totalSets = Math.Max(uniformSetIndex, storageSetIndex);
+            totalSets = Math.Max(totalSets, textureSetIndex);
+            totalSets = Math.Max(totalSets, imageSetIndex);
+            totalSets++;
+
+            _resourceDescriptors = new List<ResourceDescriptor>[totalSets];
+            _resourceUsages = new List<ResourceUsage>[totalSets];
+
+            for (int index = 0; index < totalSets; index++)
             {
                 _resourceDescriptors[index] = new();
                 _resourceUsages[index] = new();
             }
 
-            AddDescriptor(SupportBufferStages, ResourceType.UniformBuffer, UniformSetIndex, 0, 1);
+            AddDescriptor(SupportBufferStages, ResourceType.UniformBuffer, uniformSetIndex, 0, 1);
-            AddUsage(SupportBufferStages, ResourceType.UniformBuffer, UniformSetIndex, 0, 1);
+            AddUsage(SupportBufferStages, ResourceType.UniformBuffer, uniformSetIndex, 0, 1);
 
             ResourceReservationCounts rrc = new(!context.Capabilities.SupportsTransformFeedback && tfEnabled, vertexAsCompute);
 
@@ -73,16 +77,25 @@ namespace Ryujinx.Graphics.Gpu.Shader
             // TODO: Handle that better? Maybe we should only set the binding that are really needed on each shader.
             ResourceStages stages = vertexAsCompute ? ResourceStages.Compute | ResourceStages.Vertex : VtgStages;
 
-            PopulateDescriptorAndUsages(stages, ResourceType.UniformBuffer, UniformSetIndex, 1, rrc.ReservedConstantBuffers - 1);
+            PopulateDescriptorAndUsages(stages, ResourceType.UniformBuffer, uniformSetIndex, 1, rrc.ReservedConstantBuffers - 1);
-            PopulateDescriptorAndUsages(stages, ResourceType.StorageBuffer, StorageSetIndex, 0, rrc.ReservedStorageBuffers);
+            PopulateDescriptorAndUsages(stages, ResourceType.StorageBuffer, storageSetIndex, 0, rrc.ReservedStorageBuffers, true);
-            PopulateDescriptorAndUsages(stages, ResourceType.BufferTexture, TextureSetIndex, 0, rrc.ReservedTextures);
+            PopulateDescriptorAndUsages(stages, ResourceType.BufferTexture, textureSetIndex, 0, rrc.ReservedTextures);
-            PopulateDescriptorAndUsages(stages, ResourceType.BufferImage, ImageSetIndex, 0, rrc.ReservedImages);
+            PopulateDescriptorAndUsages(stages, ResourceType.BufferImage, imageSetIndex, 0, rrc.ReservedImages, true);
         }
 
-        private void PopulateDescriptorAndUsages(ResourceStages stages, ResourceType type, int setIndex, int start, int count)
+        /// <summary>
+        /// Populates descriptors and usages for vertex as compute and transform feedback emulation reserved resources.
+        /// </summary>
+        /// <param name="stages">Shader stages where the resources are used</param>
+        /// <param name="type">Resource type</param>
+        /// <param name="setIndex">Resource set index where the resources are used</param>
+        /// <param name="start">First binding number</param>
+        /// <param name="count">Amount of bindings</param>
+        /// <param name="write">True if the binding is written from the shader, false otherwise</param>
+        private void PopulateDescriptorAndUsages(ResourceStages stages, ResourceType type, int setIndex, int start, int count, bool write = false)
         {
             AddDescriptor(stages, type, setIndex, start, count);
-            AddUsage(stages, type, setIndex, start, count);
+            AddUsage(stages, type, setIndex, start, count, write);
         }
 
         /// <summary>
@@ -127,18 +140,23 @@ namespace Ryujinx.Graphics.Gpu.Shader
             int textureBinding = _reservedTextures + stageIndex * texturesPerStage * 2;
             int imageBinding = _reservedImages + stageIndex * imagesPerStage * 2;
 
-            AddDescriptor(stages, ResourceType.UniformBuffer, UniformSetIndex, uniformBinding, uniformsPerStage);
+            int uniformSetIndex = _context.Capabilities.UniformBufferSetIndex;
-            AddDescriptor(stages, ResourceType.StorageBuffer, StorageSetIndex, storageBinding, storagesPerStage);
+            int storageSetIndex = _context.Capabilities.StorageBufferSetIndex;
-            AddDualDescriptor(stages, ResourceType.TextureAndSampler, ResourceType.BufferTexture, TextureSetIndex, textureBinding, texturesPerStage);
+            int textureSetIndex = _context.Capabilities.TextureSetIndex;
-            AddDualDescriptor(stages, ResourceType.Image, ResourceType.BufferImage, ImageSetIndex, imageBinding, imagesPerStage);
+            int imageSetIndex = _context.Capabilities.ImageSetIndex;
 
-            AddArrayDescriptors(info.Textures, stages, TextureSetIndex, isImage: false);
+            AddDescriptor(stages, ResourceType.UniformBuffer, uniformSetIndex, uniformBinding, uniformsPerStage);
-            AddArrayDescriptors(info.Images, stages, TextureSetIndex, isImage: true);
+            AddDescriptor(stages, ResourceType.StorageBuffer, storageSetIndex, storageBinding, storagesPerStage);
+            AddDualDescriptor(stages, ResourceType.TextureAndSampler, ResourceType.BufferTexture, textureSetIndex, textureBinding, texturesPerStage);
+            AddDualDescriptor(stages, ResourceType.Image, ResourceType.BufferImage, imageSetIndex, imageBinding, imagesPerStage);
 
-            AddUsage(info.CBuffers, stages, UniformSetIndex, isStorage: false);
+            AddArrayDescriptors(info.Textures, stages, isImage: false);
-            AddUsage(info.SBuffers, stages, StorageSetIndex, isStorage: true);
+            AddArrayDescriptors(info.Images, stages, isImage: true);
-            AddUsage(info.Textures, stages, TextureSetIndex, isImage: false);
+
-            AddUsage(info.Images, stages, ImageSetIndex, isImage: true);
+            AddUsage(info.CBuffers, stages, isStorage: false);
+            AddUsage(info.SBuffers, stages, isStorage: true);
+            AddUsage(info.Textures, stages, isImage: false);
+            AddUsage(info.Images, stages, isImage: true);
         }
 
         /// <summary>
@@ -177,9 +195,8 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// </summary>
         /// <param name="textures">Textures to be added</param>
         /// <param name="stages">Stages where the textures are used</param>
-        /// <param name="setIndex">Descriptor set index where the textures will be bound</param>
         /// <param name="isImage">True for images, false for textures</param>
-        private void AddArrayDescriptors(IEnumerable<TextureDescriptor> textures, ResourceStages stages, int setIndex, bool isImage)
+        private void AddArrayDescriptors(IEnumerable<TextureDescriptor> textures, ResourceStages stages, bool isImage)
         {
             foreach (TextureDescriptor texture in textures)
             {
@@ -187,7 +204,7 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 {
                     ResourceType type = GetTextureResourceType(texture, isImage);
 
-                    _resourceDescriptors[setIndex].Add(new ResourceDescriptor(texture.Binding, texture.ArrayLength, type, stages));
+                    GetDescriptors(texture.Set).Add(new ResourceDescriptor(texture.Binding, texture.ArrayLength, type, stages));
                 }
             }
         }
@@ -200,11 +217,12 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// <param name="setIndex">Descriptor set number where the resource will be bound</param>
         /// <param name="binding">Binding number where the resource will be bound</param>
         /// <param name="count">Number of resources bound at the binding location</param>
-        private void AddUsage(ResourceStages stages, ResourceType type, int setIndex, int binding, int count)
+        /// <param name="write">True if the binding is written from the shader, false otherwise</param>
+        private void AddUsage(ResourceStages stages, ResourceType type, int setIndex, int binding, int count, bool write = false)
         {
             for (int index = 0; index < count; index++)
             {
-                _resourceUsages[setIndex].Add(new ResourceUsage(binding + index, 1, type, stages));
+                _resourceUsages[setIndex].Add(new ResourceUsage(binding + index, 1, type, stages, write));
             }
         }
 
@@ -213,17 +231,17 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// </summary>
         /// <param name="buffers">Buffers to be added</param>
         /// <param name="stages">Stages where the buffers are used</param>
-        /// <param name="setIndex">Descriptor set index where the buffers will be bound</param>
         /// <param name="isStorage">True for storage buffers, false for uniform buffers</param>
-        private void AddUsage(IEnumerable<BufferDescriptor> buffers, ResourceStages stages, int setIndex, bool isStorage)
+        private void AddUsage(IEnumerable<BufferDescriptor> buffers, ResourceStages stages, bool isStorage)
         {
             foreach (BufferDescriptor buffer in buffers)
             {
-                _resourceUsages[setIndex].Add(new ResourceUsage(
+                GetUsages(buffer.Set).Add(new ResourceUsage(
                     buffer.Binding,
                     1,
                     isStorage ? ResourceType.StorageBuffer : ResourceType.UniformBuffer,
-                    stages));
+                    stages,
+                    buffer.Flags.HasFlag(BufferUsageFlags.Write)));
             }
         }
 
@@ -232,18 +250,70 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// </summary>
         /// <param name="textures">Textures to be added</param>
         /// <param name="stages">Stages where the textures are used</param>
-        /// <param name="setIndex">Descriptor set index where the textures will be bound</param>
         /// <param name="isImage">True for images, false for textures</param>
-        private void AddUsage(IEnumerable<TextureDescriptor> textures, ResourceStages stages, int setIndex, bool isImage)
+        private void AddUsage(IEnumerable<TextureDescriptor> textures, ResourceStages stages, bool isImage)
         {
             foreach (TextureDescriptor texture in textures)
             {
                 ResourceType type = GetTextureResourceType(texture, isImage);
 
-                _resourceUsages[setIndex].Add(new ResourceUsage(texture.Binding, texture.ArrayLength, type, stages));
+                GetUsages(texture.Set).Add(new ResourceUsage(
+                    texture.Binding,
+                    texture.ArrayLength,
+                    type,
+                    stages,
+                    texture.Flags.HasFlag(TextureUsageFlags.ImageStore)));
             }
         }
 
+        /// <summary>
+        /// Gets the list of resource descriptors for a given set index. A new list will be created if needed.
+        /// </summary>
+        /// <param name="setIndex">Resource set index</param>
+        /// <returns>List of resource descriptors</returns>
+        private List<ResourceDescriptor> GetDescriptors(int setIndex)
+        {
+            if (_resourceDescriptors.Length <= setIndex)
+            {
+                int oldLength = _resourceDescriptors.Length;
+                Array.Resize(ref _resourceDescriptors, setIndex + 1);
+
+                for (int index = oldLength; index <= setIndex; index++)
+                {
+                    _resourceDescriptors[index] = new();
+                }
+            }
+
+            return _resourceDescriptors[setIndex];
+        }
+
+        /// <summary>
+        /// Gets the list of resource usages for a given set index. A new list will be created if needed.
+        /// </summary>
+        /// <param name="setIndex">Resource set index</param>
+        /// <returns>List of resource usages</returns>
+        private List<ResourceUsage> GetUsages(int setIndex)
+        {
+            if (_resourceUsages.Length <= setIndex)
+            {
+                int oldLength = _resourceUsages.Length;
+                Array.Resize(ref _resourceUsages, setIndex + 1);
+
+                for (int index = oldLength; index <= setIndex; index++)
+                {
+                    _resourceUsages[index] = new();
+                }
+            }
+
+            return _resourceUsages[setIndex];
+        }
+
+        /// <summary>
+        /// Gets a resource type from a texture descriptor.
+        /// </summary>
+        /// <param name="texture">Texture descriptor</param>
+        /// <param name="isImage">Whether the texture is a image texture (writable) or not (sampled)</param>
+        /// <returns>Resource type</returns>
         private static ResourceType GetTextureResourceType(TextureDescriptor texture, bool isImage)
         {
             bool isBuffer = (texture.Type & SamplerType.Mask) == SamplerType.TextureBuffer;
@@ -278,10 +348,12 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// <returns>Shader information</returns>
         public ShaderInfo Build(ProgramPipelineState? pipeline, bool fromCache = false)
         {
-            var descriptors = new ResourceDescriptorCollection[TotalSets];
+            int totalSets = _resourceDescriptors.Length;
-            var usages = new ResourceUsageCollection[TotalSets];
 
-            for (int index = 0; index < TotalSets; index++)
+            var descriptors = new ResourceDescriptorCollection[totalSets];
+            var usages = new ResourceUsageCollection[totalSets];
+
+            for (int index = 0; index < totalSets; index++)
             {
                 descriptors[index] = new ResourceDescriptorCollection(_resourceDescriptors[index].ToArray().AsReadOnly());
                 usages[index] = new ResourceUsageCollection(_resourceUsages[index].ToArray().AsReadOnly());

src/Ryujinx.Graphics.OpenGL/Image/FormatConverter.cs

@@ -1,6 +1,5 @@
 using Ryujinx.Common.Memory;
 using System;
-using System.Buffers;
 using System.Numerics;
 using System.Runtime.InteropServices;
 using System.Runtime.Intrinsics;
@@ -10,11 +9,11 @@ namespace Ryujinx.Graphics.OpenGL.Image
 {
     static class FormatConverter
     {
-        public unsafe static IMemoryOwner<byte> ConvertS8D24ToD24S8(ReadOnlySpan<byte> data)
+        public unsafe static MemoryOwner<byte> ConvertS8D24ToD24S8(ReadOnlySpan<byte> data)
         {
-            IMemoryOwner<byte> outputMemory = ByteMemoryPool.Rent(data.Length);
+            MemoryOwner<byte> outputMemory = MemoryOwner<byte>.Rent(data.Length);
 
-            Span<byte> output = outputMemory.Memory.Span;
+            Span<byte> output = outputMemory.Span;
 
             int start = 0;
 

src/Ryujinx.Graphics.OpenGL/Image/ImageArray.cs

@@ -63,5 +63,9 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 }
             }
         }
+
+        public void Dispose()
+        {
+        }
     }
 }

src/Ryujinx.Graphics.OpenGL/Image/TextureArray.cs

@@ -48,5 +48,9 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 }
             }
         }
+
+        public void Dispose()
+        {
+        }
     }
 }

src/Ryujinx.Graphics.OpenGL/Image/TextureStorage.cs

@@ -48,7 +48,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 internalFormat = (SizedInternalFormat)format.PixelInternalFormat;
             }
 
-            int levels = Info.GetLevelsClamped();
+            int levels = Info.Levels;
 
             switch (Info.Target)
             {

src/Ryujinx.Graphics.OpenGL/Image/TextureView.cs

@@ -51,7 +51,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 pixelInternalFormat = format.PixelInternalFormat;
             }
 
-            int levels = Info.GetLevelsClamped();
+            int levels = Info.Levels;
 
             GL.TextureView(
                 Handle,
@@ -267,7 +267,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
         public unsafe PinnedSpan<byte> GetData()
         {
             int size = 0;
-            int levels = Info.GetLevelsClamped();
+            int levels = Info.Levels;
 
             for (int level = 0; level < levels; level++)
             {
@@ -426,7 +426,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 faces = 6;
             }
 
-            int levels = Info.GetLevelsClamped();
+            int levels = Info.Levels;
 
             for (int level = 0; level < levels; level++)
             {
@@ -716,7 +716,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
             int width = Info.Width;
             int height = Info.Height;
             int depth = Info.Depth;
-            int levels = Info.GetLevelsClamped();
+            int levels = Info.Levels;
 
             int offset = 0;
 

src/Ryujinx.Graphics.OpenGL/OpenGLRenderer.cs

@@ -61,7 +61,9 @@ namespace Ryujinx.Graphics.OpenGL
         {
             BufferCount++;
 
-            if (access.HasFlag(GAL.BufferAccess.FlushPersistent))
+            var memType = access & GAL.BufferAccess.MemoryTypeMask;
+
+            if (memType == GAL.BufferAccess.HostMemory)
             {
                 BufferHandle handle = Buffer.CreatePersistent(size);
 
@@ -75,11 +77,6 @@ namespace Ryujinx.Graphics.OpenGL
             }
         }
 
-        public BufferHandle CreateBuffer(int size, GAL.BufferAccess access, BufferHandle storageHint)
-        {
-            return CreateBuffer(size, access);
-        }
-
         public BufferHandle CreateBuffer(nint pointer, int size)
         {
             throw new NotSupportedException();
@@ -148,6 +145,7 @@ namespace Ryujinx.Graphics.OpenGL
             return new Capabilities(
                 api: TargetApi.OpenGL,
                 vendorName: GpuVendor,
+                memoryType: SystemMemoryType.BackendManaged,
                 hasFrontFacingBug: intelWindows,
                 hasVectorIndexingBug: amdWindows,
                 needsFragmentOutputSpecialization: false,
@@ -189,6 +187,12 @@ namespace Ryujinx.Graphics.OpenGL
                 supportsViewportSwizzle: HwCapabilities.SupportsViewportSwizzle,
                 supportsIndirectParameters: HwCapabilities.SupportsIndirectParameters,
                 supportsDepthClipControl: true,
+                uniformBufferSetIndex: 0,
+                storageBufferSetIndex: 1,
+                textureSetIndex: 2,
+                imageSetIndex: 3,
+                extraSetBaseIndex: 0,
+                maximumExtraSets: 0,
                 maximumUniformBuffersPerStage: 13, // TODO: Avoid hardcoding those limits here and get from driver?
                 maximumStorageBuffersPerStage: 16,
                 maximumTexturesPerStage: 32,

src/Ryujinx.Graphics.OpenGL/Pipeline.cs

@@ -963,6 +963,11 @@ namespace Ryujinx.Graphics.OpenGL
             (array as ImageArray).Bind(binding);
         }
 
+        public void SetImageArraySeparate(ShaderStage stage, int setIndex, IImageArray array)
+        {
+            throw new NotSupportedException("OpenGL does not support descriptor sets.");
+        }
+
         public void SetIndexBuffer(BufferRange buffer, IndexType type)
         {
             _elementsType = type.Convert();
@@ -1312,6 +1317,11 @@ namespace Ryujinx.Graphics.OpenGL
             (array as TextureArray).Bind(binding);
         }
 
+        public void SetTextureArraySeparate(ShaderStage stage, int setIndex, ITextureArray array)
+        {
+            throw new NotSupportedException("OpenGL does not support descriptor sets.");
+        }
+
         public void SetTransformFeedbackBuffers(ReadOnlySpan<BufferRange> buffers)
         {
             if (_tfEnabled)

src/Ryujinx.Graphics.Shader/BufferDescriptor.cs

@@ -4,14 +4,16 @@ namespace Ryujinx.Graphics.Shader
     {
         // New fields should be added to the end of the struct to keep disk shader cache compatibility.
 
+        public readonly int Set;
         public readonly int Binding;
         public readonly byte Slot;
         public readonly byte SbCbSlot;
         public readonly ushort SbCbOffset;
         public readonly BufferUsageFlags Flags;
 
-        public BufferDescriptor(int binding, int slot)
+        public BufferDescriptor(int set, int binding, int slot)
         {
+            Set = set;
             Binding = binding;
             Slot = (byte)slot;
             SbCbSlot = 0;
@@ -19,8 +21,9 @@ namespace Ryujinx.Graphics.Shader
             Flags = BufferUsageFlags.None;
         }
 
-        public BufferDescriptor(int binding, int slot, int sbCbSlot, int sbCbOffset, BufferUsageFlags flags)
+        public BufferDescriptor(int set, int binding, int slot, int sbCbSlot, int sbCbOffset, BufferUsageFlags flags)
         {
+            Set = set;
             Binding = binding;
             Slot = (byte)slot;
             SbCbSlot = (byte)sbCbSlot;

src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Instructions/InstGenMemory.cs

@@ -462,7 +462,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
             }
             else
             {
-                context.Properties.Textures.TryGetValue(texOp.Binding, out TextureDefinition definition);
+                context.Properties.Textures.TryGetValue(texOp.GetTextureSetAndBinding(), out TextureDefinition definition);
                 bool hasLod = !definition.Type.HasFlag(SamplerType.Multisample) && (definition.Type & SamplerType.Mask) != SamplerType.TextureBuffer;
                 string texCall;
 
@@ -639,7 +639,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
 
         private static string GetSamplerName(CodeGenContext context, AstTextureOperation texOp, ref int srcIndex)
         {
-            TextureDefinition textureDefinition = context.Properties.Textures[texOp.Binding];
+            TextureDefinition textureDefinition = context.Properties.Textures[texOp.GetTextureSetAndBinding()];
             string name = textureDefinition.Name;
 
             if (textureDefinition.ArrayLength != 1)
@@ -649,7 +649,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
 
             if (texOp.IsSeparate)
             {
-                TextureDefinition samplerDefinition = context.Properties.Textures[texOp.SamplerBinding];
+                TextureDefinition samplerDefinition = context.Properties.Textures[texOp.GetSamplerSetAndBinding()];
                 string samplerName = samplerDefinition.Name;
 
                 if (samplerDefinition.ArrayLength != 1)
@@ -665,7 +665,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
 
         private static string GetImageName(CodeGenContext context, AstTextureOperation texOp, ref int srcIndex)
         {
-            TextureDefinition definition = context.Properties.Images[texOp.Binding];
+            TextureDefinition definition = context.Properties.Images[texOp.GetTextureSetAndBinding()];
             string name = definition.Name;
 
             if (definition.ArrayLength != 1)