sdl: set app name (#7370)

Ryujinx was not hinting application name, so on some platforms (e.g.
Linux) volume control shows Ryujinx as 'SDL Application'. This can cause
confusion.

This commit fixes name in volume control applets on some platforms.

see: https://wiki.libsdl.org/SDL2/SDL_HINT_APP_NAME

.github/ISSUE_TEMPLATE/bug_report.yml

@@ -23,7 +23,7 @@ body:
     attributes:
       label: Log file
       description: A log file will help our developers to better diagnose and fix the issue.
-      placeholder: Logs files can be found under "Logs" folder in Ryujinx program folder. You can drag and drop the log on to the text area
+      placeholder: Logs files can be found under "Logs" folder in Ryujinx program folder. They can also be accessed by opening Ryujinx, then going to File > Open Logs Folder. You can drag and drop the log on to the text area (do not copy paste).
     validations:
       required: true
   - type: input
@@ -83,4 +83,4 @@ body:
         - Additional info about your environment:
         - Any other information relevant to your issue.
     validations:
-      required: false
+      required: false

Directory.Packages.props

@@ -13,14 +13,14 @@
     <PackageVersion Include="CommandLineParser" Version="2.9.1" />
     <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="7.6.2" />
+    <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="3.0.1" />
     <PackageVersion Include="MsgPack.Cli" Version="1.0.1" />
@@ -39,11 +39,11 @@
     <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.Extensions.EXT" Version="2.16.0" />
-    <PackageVersion Include="Silk.NET.Vulkan.Extensions.KHR" Version="2.16.0" />
-    <PackageVersion Include="SixLabors.ImageSharp" Version="2.1.8" />
-    <PackageVersion Include="SixLabors.ImageSharp.Drawing" Version="1.0.0" />
+    <PackageVersion Include="Silk.NET.Vulkan" Version="2.21.0" />
+    <PackageVersion Include="Silk.NET.Vulkan.Extensions.EXT" Version="2.21.0" />
+    <PackageVersion Include="Silk.NET.Vulkan.Extensions.KHR" Version="2.21.0" />
+    <PackageVersion Include="SkiaSharp" Version="2.88.7" />
+    <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" />

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/Decoders/OpCodeTable.cs

@@ -746,6 +746,7 @@ namespace ARMeilleure.Decoders
             SetA32("<<<<01101000xxxxxxxxxxxxxx01xxxx", InstName.Pkh,     InstEmit32.Pkh,     OpCode32AluRsImm.Create);
             SetA32("11110101xx01xxxx1111xxxxxxxxxxxx", InstName.Pld,     InstEmit32.Nop,     OpCode32.Create);
             SetA32("11110111xx01xxxx1111xxxxxxx0xxxx", InstName.Pld,     InstEmit32.Nop,     OpCode32.Create);
+            SetA32("<<<<01100010xxxxxxxx11110001xxxx", InstName.Qadd16,  InstEmit32.Qadd16,  OpCode32AluReg.Create);
             SetA32("<<<<011011111111xxxx11110011xxxx", InstName.Rbit,    InstEmit32.Rbit,    OpCode32AluReg.Create);
             SetA32("<<<<011010111111xxxx11110011xxxx", InstName.Rev,     InstEmit32.Rev,     OpCode32AluReg.Create);
             SetA32("<<<<011010111111xxxx11111011xxxx", InstName.Rev16,   InstEmit32.Rev16,   OpCode32AluReg.Create);
@@ -822,6 +823,10 @@ 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 +1012,8 @@ 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);
@@ -1028,8 +1035,10 @@ namespace ARMeilleure.Decoders
             SetAsimd("111100101x>>>xxxxxxx0101>xx1xxxx", InstName.Vshl,        InstEmit32.Vshl,         OpCode32SimdShImm.Create,       OpCode32SimdShImm.CreateT32);
             SetAsimd("1111001x0xxxxxxxxxxx0100xxx0xxxx", InstName.Vshl,        InstEmit32.Vshl_I,       OpCode32SimdReg.Create,         OpCode32SimdReg.CreateT32);
             SetAsimd("1111001x1x>>>xxxxxxx101000x1xxxx", InstName.Vshll,       InstEmit32.Vshll,        OpCode32SimdShImmLong.Create,   OpCode32SimdShImmLong.CreateT32); // A1 encoding.
+            SetAsimd("111100111x11<<10xxxx001100x0xxxx", InstName.Vshll,       InstEmit32.Vshll2,       OpCode32SimdMovn.Create,        OpCode32SimdMovn.CreateT32); // A2 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 +1063,7 @@ 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;
@@ -290,6 +292,16 @@ namespace ARMeilleure.Instructions
             EmitAluStore(context, res);
         }
 
+        public static void Qadd16(ArmEmitterContext context)
+        {
+            OpCode32AluReg op = (OpCode32AluReg)context.CurrOp;
+
+            SetIntA32(context, op.Rd, EmitSigned16BitPair(context, GetIntA32(context, op.Rn), GetIntA32(context, op.Rm), (d, n, m) =>
+            {
+                EmitSaturateRange(context, d, context.Add(n, m), 16, unsigned: false, setQ: false);
+            }));
+        }
+
         public static void Rbit(ArmEmitterContext context)
         {
             Operand m = GetAluM(context);
@@ -558,6 +570,46 @@ 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 +986,251 @@ namespace ARMeilleure.Instructions
             }
         }
 
+        private static void EmitSaturateRange(ArmEmitterContext context, Operand result, Operand value, uint saturateTo, bool unsigned, bool setQ = true)
+        {
+            Debug.Assert(saturateTo <= 32);
+            Debug.Assert(!unsigned || saturateTo < 32);
+
+            if (!unsigned && 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;
+            }
+
+            Operand satValue;
+
+            if (unsigned)
+            {
+                // Negative values always saturate (to zero).
+                // So we must always ignore the sign bit when masking, so that the truncated value will differ from the original one.
+
+                satValue = context.BitwiseAnd(value, Const((int)(uint.MaxValue >> (32 - (int)saturateTo))));
+            }
+            else
+            {
+                satValue = context.ShiftLeft(value, Const(32 - (int)saturateTo));
+                satValue = context.ShiftRightSI(satValue, Const(32 - (int)saturateTo));
+            }
+
+            // If the result is 0, the values are equal and we don't need saturation.
+            Operand lblNoSat = Label();
+            context.BranchIfFalse(lblNoSat, context.Subtract(value, satValue));
+
+            // Saturate and set Q flag.
+            if (unsigned)
+            {
+                if (saturateTo == 31)
+                {
+                    // Only saturation case possible when going from 32 bits signed to 32 or 31 bits unsigned
+                    // is when the signed input is negative, as all positive values are representable on a 31 bits range.
+
+                    satValue = Const(0);
+                }
+                else
+                {
+                    satValue = context.ShiftRightSI(value, Const(31));
+                    satValue = context.BitwiseNot(satValue);
+                    satValue = context.ShiftRightUI(satValue, Const(32 - (int)saturateTo));
+                }
+            }
+            else
+            {
+                if (saturateTo == 1)
+                {
+                    satValue = context.ShiftRightSI(value, Const(31));
+                }
+                else
+                {
+                    satValue = Const(uint.MaxValue >> (33 - (int)saturateTo));
+                    satValue = context.BitwiseExclusiveOr(satValue, context.ShiftRightSI(value, Const(31)));
+                }
+            }
+
+            if (setQ)
+            {
+                SetFlag(context, PState.QFlag, Const(1));
+            }
+
+            context.Copy(result, satValue);
+
+            Operand lblExit = Label();
+            context.Branch(lblExit);
+
+            context.MarkLabel(lblNoSat);
+
+            context.Copy(result, value);
+
+            context.MarkLabel(lblExit);
+        }
+
+        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 EmitSigned16BitPair(ArmEmitterContext context, Operand rn, Operand rm, Action<Operand, Operand, Operand> elementAction)
+        {
+            Operand tempD = context.AllocateLocal(OperandType.I32);
+
+            Operand tempN = context.SignExtend16(OperandType.I32, rn);
+            Operand tempM = context.SignExtend16(OperandType.I32, rm);
+            elementAction(tempD, tempN, tempM);
+            Operand tempD2 = context.ZeroExtend16(OperandType.I32, tempD);
+
+            tempN = context.ShiftRightSI(rn, Const(16));
+            tempM = context.ShiftRightSI(rm, Const(16));
+            elementAction(tempD, tempN, tempM);
+            return context.BitwiseOr(tempD2, context.ShiftLeft(tempD, Const(16)));
+        }
+
+        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

@@ -106,6 +106,38 @@ namespace ARMeilleure.Instructions
             context.Copy(GetVecA32(op.Qd), res);
         }
 
+        public static void Vshll2(ArmEmitterContext context)
+        {
+            OpCode32Simd op = (OpCode32Simd)context.CurrOp;
+
+            Operand res = context.VectorZero();
+
+            int elems = op.GetBytesCount() >> op.Size;
+
+            for (int index = 0; index < elems; index++)
+            {
+                Operand me = EmitVectorExtract32(context, op.Qm, op.Im + index, op.Size, !op.U);
+
+                if (op.Size == 2)
+                {
+                    if (op.U)
+                    {
+                        me = context.ZeroExtend32(OperandType.I64, me);
+                    }
+                    else
+                    {
+                        me = context.SignExtend32(OperandType.I64, me);
+                    }
+                }
+
+                me = context.ShiftLeft(me, Const(8 << op.Size));
+
+                res = EmitVectorInsert(context, res, me, index, op.Size + 1);
+            }
+
+            context.Copy(GetVecA32(op.Qd), res);
+        }
+
         public static void Vshr(ArmEmitterContext context)
         {
             OpCode32SimdShImm op = (OpCode32SimdShImm)context.CurrOp;
@@ -130,6 +162,36 @@ 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

@@ -527,6 +527,7 @@ namespace ARMeilleure.Instructions
         Pld,
         Pop,
         Push,
+        Qadd16,
         Rev,
         Revsh,
         Rsb,
@@ -571,6 +572,10 @@ namespace ARMeilleure.Instructions
         Umaal,
         Umlal,
         Umull,
+        Uqadd16,
+        Uqadd8,
+        Uqsub16,
+        Uqsub8,
         Usat,
         Usat16,
         Usub8,
@@ -645,6 +650,7 @@ namespace ARMeilleure.Instructions
         Vqdmulh,
         Vqmovn,
         Vqmovun,
+        Vqrdmulh,
         Vqrshrn,
         Vqrshrun,
         Vqshrn,
@@ -666,6 +672,7 @@ namespace ARMeilleure.Instructions
         Vshll,
         Vshr,
         Vshrn,
+        Vsli,
         Vst1,
         Vst2,
         Vst3,
@@ -682,6 +689,7 @@ namespace ARMeilleure.Instructions
         Vsub,
         Vsubl,
         Vsubw,
+        Vswp,
         Vtbl,
         Vtrn,
         Vtst,

src/ARMeilleure/Translation/DelegateInfo.cs

@@ -1,5 +1,4 @@
 using System;
-using System.Runtime.InteropServices;
 
 namespace ARMeilleure.Translation
 {
@@ -11,11 +10,10 @@ namespace ARMeilleure.Translation
 
         public IntPtr FuncPtr { get; }
 
-        public DelegateInfo(Delegate dlg)
+        public DelegateInfo(Delegate dlg, IntPtr funcPtr)
         {
             _dlg = dlg;
-
-            FuncPtr = Marshal.GetFunctionPointerForDelegate<Delegate>(dlg);
+            FuncPtr = funcPtr;
         }
     }
 }

src/ARMeilleure/Translation/Delegates.cs

@@ -3,6 +3,7 @@ using ARMeilleure.State;
 using System;
 using System.Collections.Generic;
 using System.Reflection;
+using System.Runtime.InteropServices;
 
 namespace ARMeilleure.Translation
 {
@@ -64,11 +65,11 @@ namespace ARMeilleure.Translation
             return index;
         }
 
-        private static void SetDelegateInfo(Delegate dlg)
+        private static void SetDelegateInfo(Delegate dlg, IntPtr funcPtr)
         {
             string key = GetKey(dlg.Method);
 
-            _delegates.Add(key, new DelegateInfo(dlg)); // ArgumentException (key).
+            _delegates.Add(key, new DelegateInfo(dlg, funcPtr)); // ArgumentException (key).
         }
 
         private static string GetKey(MethodInfo info)
@@ -82,179 +83,353 @@ namespace ARMeilleure.Translation
         {
             _delegates = new SortedList<string, DelegateInfo>();
 
-            SetDelegateInfo(new MathAbs(Math.Abs));
-            SetDelegateInfo(new MathCeiling(Math.Ceiling));
-            SetDelegateInfo(new MathFloor(Math.Floor));
-            SetDelegateInfo(new MathRound(Math.Round));
-            SetDelegateInfo(new MathTruncate(Math.Truncate));
+            var dlgMathAbs = new MathAbs(Math.Abs);
+            var dlgMathCeiling = new MathCeiling(Math.Ceiling);
+            var dlgMathFloor = new MathFloor(Math.Floor);
+            var dlgMathRound = new MathRound(Math.Round);
+            var dlgMathTruncate = new MathTruncate(Math.Truncate);
 
-            SetDelegateInfo(new MathFAbs(MathF.Abs));
-            SetDelegateInfo(new MathFCeiling(MathF.Ceiling));
-            SetDelegateInfo(new MathFFloor(MathF.Floor));
-            SetDelegateInfo(new MathFRound(MathF.Round));
-            SetDelegateInfo(new MathFTruncate(MathF.Truncate));
+            var dlgMathFAbs = new MathFAbs(MathF.Abs);
+            var dlgMathFCeiling = new MathFCeiling(MathF.Ceiling);
+            var dlgMathFFloor = new MathFFloor(MathF.Floor);
+            var dlgMathFRound = new MathFRound(MathF.Round);
+            var dlgMathFTruncate = new MathFTruncate(MathF.Truncate);
 
-            SetDelegateInfo(new NativeInterfaceBreak(NativeInterface.Break));
-            SetDelegateInfo(new NativeInterfaceCheckSynchronization(NativeInterface.CheckSynchronization));
-            SetDelegateInfo(new NativeInterfaceEnqueueForRejit(NativeInterface.EnqueueForRejit));
-            SetDelegateInfo(new NativeInterfaceGetCntfrqEl0(NativeInterface.GetCntfrqEl0));
-            SetDelegateInfo(new NativeInterfaceGetCntpctEl0(NativeInterface.GetCntpctEl0));
-            SetDelegateInfo(new NativeInterfaceGetCntvctEl0(NativeInterface.GetCntvctEl0));
-            SetDelegateInfo(new NativeInterfaceGetCtrEl0(NativeInterface.GetCtrEl0));
-            SetDelegateInfo(new NativeInterfaceGetDczidEl0(NativeInterface.GetDczidEl0));
-            SetDelegateInfo(new NativeInterfaceGetFunctionAddress(NativeInterface.GetFunctionAddress));
-            SetDelegateInfo(new NativeInterfaceInvalidateCacheLine(NativeInterface.InvalidateCacheLine));
-            SetDelegateInfo(new NativeInterfaceReadByte(NativeInterface.ReadByte));
-            SetDelegateInfo(new NativeInterfaceReadUInt16(NativeInterface.ReadUInt16));
-            SetDelegateInfo(new NativeInterfaceReadUInt32(NativeInterface.ReadUInt32));
-            SetDelegateInfo(new NativeInterfaceReadUInt64(NativeInterface.ReadUInt64));
-            SetDelegateInfo(new NativeInterfaceReadVector128(NativeInterface.ReadVector128));
-            SetDelegateInfo(new NativeInterfaceSignalMemoryTracking(NativeInterface.SignalMemoryTracking));
-            SetDelegateInfo(new NativeInterfaceSupervisorCall(NativeInterface.SupervisorCall));
-            SetDelegateInfo(new NativeInterfaceThrowInvalidMemoryAccess(NativeInterface.ThrowInvalidMemoryAccess));
-            SetDelegateInfo(new NativeInterfaceUndefined(NativeInterface.Undefined));
-            SetDelegateInfo(new NativeInterfaceWriteByte(NativeInterface.WriteByte));
-            SetDelegateInfo(new NativeInterfaceWriteUInt16(NativeInterface.WriteUInt16));
-            SetDelegateInfo(new NativeInterfaceWriteUInt32(NativeInterface.WriteUInt32));
-            SetDelegateInfo(new NativeInterfaceWriteUInt64(NativeInterface.WriteUInt64));
-            SetDelegateInfo(new NativeInterfaceWriteVector128(NativeInterface.WriteVector128));
+            var dlgNativeInterfaceBreak = new NativeInterfaceBreak(NativeInterface.Break);
+            var dlgNativeInterfaceCheckSynchronization = new NativeInterfaceCheckSynchronization(NativeInterface.CheckSynchronization);
+            var dlgNativeInterfaceEnqueueForRejit = new NativeInterfaceEnqueueForRejit(NativeInterface.EnqueueForRejit);
+            var dlgNativeInterfaceGetCntfrqEl0 = new NativeInterfaceGetCntfrqEl0(NativeInterface.GetCntfrqEl0);
+            var dlgNativeInterfaceGetCntpctEl0 = new NativeInterfaceGetCntpctEl0(NativeInterface.GetCntpctEl0);
+            var dlgNativeInterfaceGetCntvctEl0 = new NativeInterfaceGetCntvctEl0(NativeInterface.GetCntvctEl0);
+            var dlgNativeInterfaceGetCtrEl0 = new NativeInterfaceGetCtrEl0(NativeInterface.GetCtrEl0);
+            var dlgNativeInterfaceGetDczidEl0 = new NativeInterfaceGetDczidEl0(NativeInterface.GetDczidEl0);
+            var dlgNativeInterfaceGetFunctionAddress = new NativeInterfaceGetFunctionAddress(NativeInterface.GetFunctionAddress);
+            var dlgNativeInterfaceInvalidateCacheLine = new NativeInterfaceInvalidateCacheLine(NativeInterface.InvalidateCacheLine);
+            var dlgNativeInterfaceReadByte = new NativeInterfaceReadByte(NativeInterface.ReadByte);
+            var dlgNativeInterfaceReadUInt16 = new NativeInterfaceReadUInt16(NativeInterface.ReadUInt16);
+            var dlgNativeInterfaceReadUInt32 = new NativeInterfaceReadUInt32(NativeInterface.ReadUInt32);
+            var dlgNativeInterfaceReadUInt64 = new NativeInterfaceReadUInt64(NativeInterface.ReadUInt64);
+            var dlgNativeInterfaceReadVector128 = new NativeInterfaceReadVector128(NativeInterface.ReadVector128);
+            var dlgNativeInterfaceSignalMemoryTracking = new NativeInterfaceSignalMemoryTracking(NativeInterface.SignalMemoryTracking);
+            var dlgNativeInterfaceSupervisorCall = new NativeInterfaceSupervisorCall(NativeInterface.SupervisorCall);
+            var dlgNativeInterfaceThrowInvalidMemoryAccess = new NativeInterfaceThrowInvalidMemoryAccess(NativeInterface.ThrowInvalidMemoryAccess);
+            var dlgNativeInterfaceUndefined = new NativeInterfaceUndefined(NativeInterface.Undefined);
+            var dlgNativeInterfaceWriteByte = new NativeInterfaceWriteByte(NativeInterface.WriteByte);
+            var dlgNativeInterfaceWriteUInt16 = new NativeInterfaceWriteUInt16(NativeInterface.WriteUInt16);
+            var dlgNativeInterfaceWriteUInt32 = new NativeInterfaceWriteUInt32(NativeInterface.WriteUInt32);
+            var dlgNativeInterfaceWriteUInt64 = new NativeInterfaceWriteUInt64(NativeInterface.WriteUInt64);
+            var dlgNativeInterfaceWriteVector128 = new NativeInterfaceWriteVector128(NativeInterface.WriteVector128);
 
-            SetDelegateInfo(new SoftFallbackCountLeadingSigns(SoftFallback.CountLeadingSigns));
-            SetDelegateInfo(new SoftFallbackCountLeadingZeros(SoftFallback.CountLeadingZeros));
-            SetDelegateInfo(new SoftFallbackCrc32b(SoftFallback.Crc32b));
-            SetDelegateInfo(new SoftFallbackCrc32cb(SoftFallback.Crc32cb));
-            SetDelegateInfo(new SoftFallbackCrc32ch(SoftFallback.Crc32ch));
-            SetDelegateInfo(new SoftFallbackCrc32cw(SoftFallback.Crc32cw));
-            SetDelegateInfo(new SoftFallbackCrc32cx(SoftFallback.Crc32cx));
-            SetDelegateInfo(new SoftFallbackCrc32h(SoftFallback.Crc32h));
-            SetDelegateInfo(new SoftFallbackCrc32w(SoftFallback.Crc32w));
-            SetDelegateInfo(new SoftFallbackCrc32x(SoftFallback.Crc32x));
-            SetDelegateInfo(new SoftFallbackDecrypt(SoftFallback.Decrypt));
-            SetDelegateInfo(new SoftFallbackEncrypt(SoftFallback.Encrypt));
-            SetDelegateInfo(new SoftFallbackFixedRotate(SoftFallback.FixedRotate));
-            SetDelegateInfo(new SoftFallbackHashChoose(SoftFallback.HashChoose));
-            SetDelegateInfo(new SoftFallbackHashLower(SoftFallback.HashLower));
-            SetDelegateInfo(new SoftFallbackHashMajority(SoftFallback.HashMajority));
-            SetDelegateInfo(new SoftFallbackHashParity(SoftFallback.HashParity));
-            SetDelegateInfo(new SoftFallbackHashUpper(SoftFallback.HashUpper));
-            SetDelegateInfo(new SoftFallbackInverseMixColumns(SoftFallback.InverseMixColumns));
-            SetDelegateInfo(new SoftFallbackMixColumns(SoftFallback.MixColumns));
-            SetDelegateInfo(new SoftFallbackPolynomialMult64_128(SoftFallback.PolynomialMult64_128));
-            SetDelegateInfo(new SoftFallbackSatF32ToS32(SoftFallback.SatF32ToS32));
-            SetDelegateInfo(new SoftFallbackSatF32ToS64(SoftFallback.SatF32ToS64));
-            SetDelegateInfo(new SoftFallbackSatF32ToU32(SoftFallback.SatF32ToU32));
-            SetDelegateInfo(new SoftFallbackSatF32ToU64(SoftFallback.SatF32ToU64));
-            SetDelegateInfo(new SoftFallbackSatF64ToS32(SoftFallback.SatF64ToS32));
-            SetDelegateInfo(new SoftFallbackSatF64ToS64(SoftFallback.SatF64ToS64));
-            SetDelegateInfo(new SoftFallbackSatF64ToU32(SoftFallback.SatF64ToU32));
-            SetDelegateInfo(new SoftFallbackSatF64ToU64(SoftFallback.SatF64ToU64));
-            SetDelegateInfo(new SoftFallbackSha1SchedulePart1(SoftFallback.Sha1SchedulePart1));
-            SetDelegateInfo(new SoftFallbackSha1SchedulePart2(SoftFallback.Sha1SchedulePart2));
-            SetDelegateInfo(new SoftFallbackSha256SchedulePart1(SoftFallback.Sha256SchedulePart1));
-            SetDelegateInfo(new SoftFallbackSha256SchedulePart2(SoftFallback.Sha256SchedulePart2));
-            SetDelegateInfo(new SoftFallbackSignedShrImm64(SoftFallback.SignedShrImm64));
-            SetDelegateInfo(new SoftFallbackTbl1(SoftFallback.Tbl1));
-            SetDelegateInfo(new SoftFallbackTbl2(SoftFallback.Tbl2));
-            SetDelegateInfo(new SoftFallbackTbl3(SoftFallback.Tbl3));
-            SetDelegateInfo(new SoftFallbackTbl4(SoftFallback.Tbl4));
-            SetDelegateInfo(new SoftFallbackTbx1(SoftFallback.Tbx1));
-            SetDelegateInfo(new SoftFallbackTbx2(SoftFallback.Tbx2));
-            SetDelegateInfo(new SoftFallbackTbx3(SoftFallback.Tbx3));
-            SetDelegateInfo(new SoftFallbackTbx4(SoftFallback.Tbx4));
-            SetDelegateInfo(new SoftFallbackUnsignedShrImm64(SoftFallback.UnsignedShrImm64));
+            var dlgSoftFallbackCountLeadingSigns = new SoftFallbackCountLeadingSigns(SoftFallback.CountLeadingSigns);
+            var dlgSoftFallbackCountLeadingZeros = new SoftFallbackCountLeadingZeros(SoftFallback.CountLeadingZeros);
+            var dlgSoftFallbackCrc32b = new SoftFallbackCrc32b(SoftFallback.Crc32b);
+            var dlgSoftFallbackCrc32cb = new SoftFallbackCrc32cb(SoftFallback.Crc32cb);
+            var dlgSoftFallbackCrc32ch = new SoftFallbackCrc32ch(SoftFallback.Crc32ch);
+            var dlgSoftFallbackCrc32cw = new SoftFallbackCrc32cw(SoftFallback.Crc32cw);
+            var dlgSoftFallbackCrc32cx = new SoftFallbackCrc32cx(SoftFallback.Crc32cx);
+            var dlgSoftFallbackCrc32h = new SoftFallbackCrc32h(SoftFallback.Crc32h);
+            var dlgSoftFallbackCrc32w = new SoftFallbackCrc32w(SoftFallback.Crc32w);
+            var dlgSoftFallbackCrc32x = new SoftFallbackCrc32x(SoftFallback.Crc32x);
+            var dlgSoftFallbackDecrypt = new SoftFallbackDecrypt(SoftFallback.Decrypt);
+            var dlgSoftFallbackEncrypt = new SoftFallbackEncrypt(SoftFallback.Encrypt);
+            var dlgSoftFallbackFixedRotate = new SoftFallbackFixedRotate(SoftFallback.FixedRotate);
+            var dlgSoftFallbackHashChoose = new SoftFallbackHashChoose(SoftFallback.HashChoose);
+            var dlgSoftFallbackHashLower = new SoftFallbackHashLower(SoftFallback.HashLower);
+            var dlgSoftFallbackHashMajority = new SoftFallbackHashMajority(SoftFallback.HashMajority);
+            var dlgSoftFallbackHashParity = new SoftFallbackHashParity(SoftFallback.HashParity);
+            var dlgSoftFallbackHashUpper = new SoftFallbackHashUpper(SoftFallback.HashUpper);
+            var dlgSoftFallbackInverseMixColumns = new SoftFallbackInverseMixColumns(SoftFallback.InverseMixColumns);
+            var dlgSoftFallbackMixColumns = new SoftFallbackMixColumns(SoftFallback.MixColumns);
+            var dlgSoftFallbackPolynomialMult64_128 = new SoftFallbackPolynomialMult64_128(SoftFallback.PolynomialMult64_128);
+            var dlgSoftFallbackSatF32ToS32 = new SoftFallbackSatF32ToS32(SoftFallback.SatF32ToS32);
+            var dlgSoftFallbackSatF32ToS64 = new SoftFallbackSatF32ToS64(SoftFallback.SatF32ToS64);
+            var dlgSoftFallbackSatF32ToU32 = new SoftFallbackSatF32ToU32(SoftFallback.SatF32ToU32);
+            var dlgSoftFallbackSatF32ToU64 = new SoftFallbackSatF32ToU64(SoftFallback.SatF32ToU64);
+            var dlgSoftFallbackSatF64ToS32 = new SoftFallbackSatF64ToS32(SoftFallback.SatF64ToS32);
+            var dlgSoftFallbackSatF64ToS64 = new SoftFallbackSatF64ToS64(SoftFallback.SatF64ToS64);
+            var dlgSoftFallbackSatF64ToU32 = new SoftFallbackSatF64ToU32(SoftFallback.SatF64ToU32);
+            var dlgSoftFallbackSatF64ToU64 = new SoftFallbackSatF64ToU64(SoftFallback.SatF64ToU64);
+            var dlgSoftFallbackSha1SchedulePart1 = new SoftFallbackSha1SchedulePart1(SoftFallback.Sha1SchedulePart1);
+            var dlgSoftFallbackSha1SchedulePart2 = new SoftFallbackSha1SchedulePart2(SoftFallback.Sha1SchedulePart2);
+            var dlgSoftFallbackSha256SchedulePart1 = new SoftFallbackSha256SchedulePart1(SoftFallback.Sha256SchedulePart1);
+            var dlgSoftFallbackSha256SchedulePart2 = new SoftFallbackSha256SchedulePart2(SoftFallback.Sha256SchedulePart2);
+            var dlgSoftFallbackSignedShrImm64 = new SoftFallbackSignedShrImm64(SoftFallback.SignedShrImm64);
+            var dlgSoftFallbackTbl1 = new SoftFallbackTbl1(SoftFallback.Tbl1);
+            var dlgSoftFallbackTbl2 = new SoftFallbackTbl2(SoftFallback.Tbl2);
+            var dlgSoftFallbackTbl3 = new SoftFallbackTbl3(SoftFallback.Tbl3);
+            var dlgSoftFallbackTbl4 = new SoftFallbackTbl4(SoftFallback.Tbl4);
+            var dlgSoftFallbackTbx1 = new SoftFallbackTbx1(SoftFallback.Tbx1);
+            var dlgSoftFallbackTbx2 = new SoftFallbackTbx2(SoftFallback.Tbx2);
+            var dlgSoftFallbackTbx3 = new SoftFallbackTbx3(SoftFallback.Tbx3);
+            var dlgSoftFallbackTbx4 = new SoftFallbackTbx4(SoftFallback.Tbx4);
+            var dlgSoftFallbackUnsignedShrImm64 = new SoftFallbackUnsignedShrImm64(SoftFallback.UnsignedShrImm64);
 
-            SetDelegateInfo(new SoftFloat16_32FPConvert(SoftFloat16_32.FPConvert));
-            SetDelegateInfo(new SoftFloat16_64FPConvert(SoftFloat16_64.FPConvert));
+            var dlgSoftFloat16_32FPConvert = new SoftFloat16_32FPConvert(SoftFloat16_32.FPConvert);
+            var dlgSoftFloat16_64FPConvert = new SoftFloat16_64FPConvert(SoftFloat16_64.FPConvert);
 
-            SetDelegateInfo(new SoftFloat32FPAdd(SoftFloat32.FPAdd));
-            SetDelegateInfo(new SoftFloat32FPAddFpscr(SoftFloat32.FPAddFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPCompare(SoftFloat32.FPCompare));
-            SetDelegateInfo(new SoftFloat32FPCompareEQ(SoftFloat32.FPCompareEQ));
-            SetDelegateInfo(new SoftFloat32FPCompareEQFpscr(SoftFloat32.FPCompareEQFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPCompareGE(SoftFloat32.FPCompareGE));
-            SetDelegateInfo(new SoftFloat32FPCompareGEFpscr(SoftFloat32.FPCompareGEFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPCompareGT(SoftFloat32.FPCompareGT));
-            SetDelegateInfo(new SoftFloat32FPCompareGTFpscr(SoftFloat32.FPCompareGTFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPCompareLE(SoftFloat32.FPCompareLE));
-            SetDelegateInfo(new SoftFloat32FPCompareLEFpscr(SoftFloat32.FPCompareLEFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPCompareLT(SoftFloat32.FPCompareLT));
-            SetDelegateInfo(new SoftFloat32FPCompareLTFpscr(SoftFloat32.FPCompareLTFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPDiv(SoftFloat32.FPDiv));
-            SetDelegateInfo(new SoftFloat32FPMax(SoftFloat32.FPMax));
-            SetDelegateInfo(new SoftFloat32FPMaxFpscr(SoftFloat32.FPMaxFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMaxNum(SoftFloat32.FPMaxNum));
-            SetDelegateInfo(new SoftFloat32FPMaxNumFpscr(SoftFloat32.FPMaxNumFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMin(SoftFloat32.FPMin));
-            SetDelegateInfo(new SoftFloat32FPMinFpscr(SoftFloat32.FPMinFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMinNum(SoftFloat32.FPMinNum));
-            SetDelegateInfo(new SoftFloat32FPMinNumFpscr(SoftFloat32.FPMinNumFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMul(SoftFloat32.FPMul));
-            SetDelegateInfo(new SoftFloat32FPMulFpscr(SoftFloat32.FPMulFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMulAdd(SoftFloat32.FPMulAdd));
-            SetDelegateInfo(new SoftFloat32FPMulAddFpscr(SoftFloat32.FPMulAddFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMulSub(SoftFloat32.FPMulSub));
-            SetDelegateInfo(new SoftFloat32FPMulSubFpscr(SoftFloat32.FPMulSubFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPMulX(SoftFloat32.FPMulX));
-            SetDelegateInfo(new SoftFloat32FPNegMulAdd(SoftFloat32.FPNegMulAdd));
-            SetDelegateInfo(new SoftFloat32FPNegMulSub(SoftFloat32.FPNegMulSub));
-            SetDelegateInfo(new SoftFloat32FPRecipEstimate(SoftFloat32.FPRecipEstimate));
-            SetDelegateInfo(new SoftFloat32FPRecipEstimateFpscr(SoftFloat32.FPRecipEstimateFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPRecipStep(SoftFloat32.FPRecipStep)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPRecipStepFused(SoftFloat32.FPRecipStepFused));
-            SetDelegateInfo(new SoftFloat32FPRecpX(SoftFloat32.FPRecpX));
-            SetDelegateInfo(new SoftFloat32FPRSqrtEstimate(SoftFloat32.FPRSqrtEstimate));
-            SetDelegateInfo(new SoftFloat32FPRSqrtEstimateFpscr(SoftFloat32.FPRSqrtEstimateFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPRSqrtStep(SoftFloat32.FPRSqrtStep)); // A32 only.
-            SetDelegateInfo(new SoftFloat32FPRSqrtStepFused(SoftFloat32.FPRSqrtStepFused));
-            SetDelegateInfo(new SoftFloat32FPSqrt(SoftFloat32.FPSqrt));
-            SetDelegateInfo(new SoftFloat32FPSub(SoftFloat32.FPSub));
+            var dlgSoftFloat32FPAdd = new SoftFloat32FPAdd(SoftFloat32.FPAdd);
+            var dlgSoftFloat32FPAddFpscr = new SoftFloat32FPAddFpscr(SoftFloat32.FPAddFpscr); // A32 only.
+            var dlgSoftFloat32FPCompare = new SoftFloat32FPCompare(SoftFloat32.FPCompare);
+            var dlgSoftFloat32FPCompareEQ = new SoftFloat32FPCompareEQ(SoftFloat32.FPCompareEQ);
+            var dlgSoftFloat32FPCompareEQFpscr = new SoftFloat32FPCompareEQFpscr(SoftFloat32.FPCompareEQFpscr); // A32 only.
+            var dlgSoftFloat32FPCompareGE = new SoftFloat32FPCompareGE(SoftFloat32.FPCompareGE);
+            var dlgSoftFloat32FPCompareGEFpscr = new SoftFloat32FPCompareGEFpscr(SoftFloat32.FPCompareGEFpscr); // A32 only.
+            var dlgSoftFloat32FPCompareGT = new SoftFloat32FPCompareGT(SoftFloat32.FPCompareGT);
+            var dlgSoftFloat32FPCompareGTFpscr = new SoftFloat32FPCompareGTFpscr(SoftFloat32.FPCompareGTFpscr); // A32 only.
+            var dlgSoftFloat32FPCompareLE = new SoftFloat32FPCompareLE(SoftFloat32.FPCompareLE);
+            var dlgSoftFloat32FPCompareLEFpscr = new SoftFloat32FPCompareLEFpscr(SoftFloat32.FPCompareLEFpscr); // A32 only.
+            var dlgSoftFloat32FPCompareLT = new SoftFloat32FPCompareLT(SoftFloat32.FPCompareLT);
+            var dlgSoftFloat32FPCompareLTFpscr = new SoftFloat32FPCompareLTFpscr(SoftFloat32.FPCompareLTFpscr); // A32 only.
+            var dlgSoftFloat32FPDiv = new SoftFloat32FPDiv(SoftFloat32.FPDiv);
+            var dlgSoftFloat32FPMax = new SoftFloat32FPMax(SoftFloat32.FPMax);
+            var dlgSoftFloat32FPMaxFpscr = new SoftFloat32FPMaxFpscr(SoftFloat32.FPMaxFpscr); // A32 only.
+            var dlgSoftFloat32FPMaxNum = new SoftFloat32FPMaxNum(SoftFloat32.FPMaxNum);
+            var dlgSoftFloat32FPMaxNumFpscr = new SoftFloat32FPMaxNumFpscr(SoftFloat32.FPMaxNumFpscr); // A32 only.
+            var dlgSoftFloat32FPMin = new SoftFloat32FPMin(SoftFloat32.FPMin);
+            var dlgSoftFloat32FPMinFpscr = new SoftFloat32FPMinFpscr(SoftFloat32.FPMinFpscr); // A32 only.
+            var dlgSoftFloat32FPMinNum = new SoftFloat32FPMinNum(SoftFloat32.FPMinNum);
+            var dlgSoftFloat32FPMinNumFpscr = new SoftFloat32FPMinNumFpscr(SoftFloat32.FPMinNumFpscr); // A32 only.
+            var dlgSoftFloat32FPMul = new SoftFloat32FPMul(SoftFloat32.FPMul);
+            var dlgSoftFloat32FPMulFpscr = new SoftFloat32FPMulFpscr(SoftFloat32.FPMulFpscr); // A32 only.
+            var dlgSoftFloat32FPMulAdd = new SoftFloat32FPMulAdd(SoftFloat32.FPMulAdd);
+            var dlgSoftFloat32FPMulAddFpscr = new SoftFloat32FPMulAddFpscr(SoftFloat32.FPMulAddFpscr); // A32 only.
+            var dlgSoftFloat32FPMulSub = new SoftFloat32FPMulSub(SoftFloat32.FPMulSub);
+            var dlgSoftFloat32FPMulSubFpscr = new SoftFloat32FPMulSubFpscr(SoftFloat32.FPMulSubFpscr); // A32 only.
+            var dlgSoftFloat32FPMulX = new SoftFloat32FPMulX(SoftFloat32.FPMulX);
+            var dlgSoftFloat32FPNegMulAdd = new SoftFloat32FPNegMulAdd(SoftFloat32.FPNegMulAdd);
+            var dlgSoftFloat32FPNegMulSub = new SoftFloat32FPNegMulSub(SoftFloat32.FPNegMulSub);
+            var dlgSoftFloat32FPRecipEstimate = new SoftFloat32FPRecipEstimate(SoftFloat32.FPRecipEstimate);
+            var dlgSoftFloat32FPRecipEstimateFpscr = new SoftFloat32FPRecipEstimateFpscr(SoftFloat32.FPRecipEstimateFpscr); // A32 only.
+            var dlgSoftFloat32FPRecipStep = new SoftFloat32FPRecipStep(SoftFloat32.FPRecipStep); // A32 only.
+            var dlgSoftFloat32FPRecipStepFused = new SoftFloat32FPRecipStepFused(SoftFloat32.FPRecipStepFused);
+            var dlgSoftFloat32FPRecpX = new SoftFloat32FPRecpX(SoftFloat32.FPRecpX);
+            var dlgSoftFloat32FPRSqrtEstimate = new SoftFloat32FPRSqrtEstimate(SoftFloat32.FPRSqrtEstimate);
+            var dlgSoftFloat32FPRSqrtEstimateFpscr = new SoftFloat32FPRSqrtEstimateFpscr(SoftFloat32.FPRSqrtEstimateFpscr); // A32 only.
+            var dlgSoftFloat32FPRSqrtStep = new SoftFloat32FPRSqrtStep(SoftFloat32.FPRSqrtStep); // A32 only.
+            var dlgSoftFloat32FPRSqrtStepFused = new SoftFloat32FPRSqrtStepFused(SoftFloat32.FPRSqrtStepFused);
+            var dlgSoftFloat32FPSqrt = new SoftFloat32FPSqrt(SoftFloat32.FPSqrt);
+            var dlgSoftFloat32FPSub = new SoftFloat32FPSub(SoftFloat32.FPSub);
 
-            SetDelegateInfo(new SoftFloat32_16FPConvert(SoftFloat32_16.FPConvert));
+            var dlgSoftFloat32_16FPConvert = new SoftFloat32_16FPConvert(SoftFloat32_16.FPConvert);
 
-            SetDelegateInfo(new SoftFloat64FPAdd(SoftFloat64.FPAdd));
-            SetDelegateInfo(new SoftFloat64FPAddFpscr(SoftFloat64.FPAddFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPCompare(SoftFloat64.FPCompare));
-            SetDelegateInfo(new SoftFloat64FPCompareEQ(SoftFloat64.FPCompareEQ));
-            SetDelegateInfo(new SoftFloat64FPCompareEQFpscr(SoftFloat64.FPCompareEQFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPCompareGE(SoftFloat64.FPCompareGE));
-            SetDelegateInfo(new SoftFloat64FPCompareGEFpscr(SoftFloat64.FPCompareGEFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPCompareGT(SoftFloat64.FPCompareGT));
-            SetDelegateInfo(new SoftFloat64FPCompareGTFpscr(SoftFloat64.FPCompareGTFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPCompareLE(SoftFloat64.FPCompareLE));
-            SetDelegateInfo(new SoftFloat64FPCompareLEFpscr(SoftFloat64.FPCompareLEFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPCompareLT(SoftFloat64.FPCompareLT));
-            SetDelegateInfo(new SoftFloat64FPCompareLTFpscr(SoftFloat64.FPCompareLTFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPDiv(SoftFloat64.FPDiv));
-            SetDelegateInfo(new SoftFloat64FPMax(SoftFloat64.FPMax));
-            SetDelegateInfo(new SoftFloat64FPMaxFpscr(SoftFloat64.FPMaxFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMaxNum(SoftFloat64.FPMaxNum));
-            SetDelegateInfo(new SoftFloat64FPMaxNumFpscr(SoftFloat64.FPMaxNumFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMin(SoftFloat64.FPMin));
-            SetDelegateInfo(new SoftFloat64FPMinFpscr(SoftFloat64.FPMinFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMinNum(SoftFloat64.FPMinNum));
-            SetDelegateInfo(new SoftFloat64FPMinNumFpscr(SoftFloat64.FPMinNumFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMul(SoftFloat64.FPMul));
-            SetDelegateInfo(new SoftFloat64FPMulFpscr(SoftFloat64.FPMulFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMulAdd(SoftFloat64.FPMulAdd));
-            SetDelegateInfo(new SoftFloat64FPMulAddFpscr(SoftFloat64.FPMulAddFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMulSub(SoftFloat64.FPMulSub));
-            SetDelegateInfo(new SoftFloat64FPMulSubFpscr(SoftFloat64.FPMulSubFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPMulX(SoftFloat64.FPMulX));
-            SetDelegateInfo(new SoftFloat64FPNegMulAdd(SoftFloat64.FPNegMulAdd));
-            SetDelegateInfo(new SoftFloat64FPNegMulSub(SoftFloat64.FPNegMulSub));
-            SetDelegateInfo(new SoftFloat64FPRecipEstimate(SoftFloat64.FPRecipEstimate));
-            SetDelegateInfo(new SoftFloat64FPRecipEstimateFpscr(SoftFloat64.FPRecipEstimateFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPRecipStep(SoftFloat64.FPRecipStep)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPRecipStepFused(SoftFloat64.FPRecipStepFused));
-            SetDelegateInfo(new SoftFloat64FPRecpX(SoftFloat64.FPRecpX));
-            SetDelegateInfo(new SoftFloat64FPRSqrtEstimate(SoftFloat64.FPRSqrtEstimate));
-            SetDelegateInfo(new SoftFloat64FPRSqrtEstimateFpscr(SoftFloat64.FPRSqrtEstimateFpscr)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPRSqrtStep(SoftFloat64.FPRSqrtStep)); // A32 only.
-            SetDelegateInfo(new SoftFloat64FPRSqrtStepFused(SoftFloat64.FPRSqrtStepFused));
-            SetDelegateInfo(new SoftFloat64FPSqrt(SoftFloat64.FPSqrt));
-            SetDelegateInfo(new SoftFloat64FPSub(SoftFloat64.FPSub));
+            var dlgSoftFloat64FPAdd = new SoftFloat64FPAdd(SoftFloat64.FPAdd);
+            var dlgSoftFloat64FPAddFpscr = new SoftFloat64FPAddFpscr(SoftFloat64.FPAddFpscr); // A32 only.
+            var dlgSoftFloat64FPCompare = new SoftFloat64FPCompare(SoftFloat64.FPCompare);
+            var dlgSoftFloat64FPCompareEQ = new SoftFloat64FPCompareEQ(SoftFloat64.FPCompareEQ);
+            var dlgSoftFloat64FPCompareEQFpscr = new SoftFloat64FPCompareEQFpscr(SoftFloat64.FPCompareEQFpscr); // A32 only.
+            var dlgSoftFloat64FPCompareGE = new SoftFloat64FPCompareGE(SoftFloat64.FPCompareGE);
+            var dlgSoftFloat64FPCompareGEFpscr = new SoftFloat64FPCompareGEFpscr(SoftFloat64.FPCompareGEFpscr); // A32 only.
+            var dlgSoftFloat64FPCompareGT = new SoftFloat64FPCompareGT(SoftFloat64.FPCompareGT);
+            var dlgSoftFloat64FPCompareGTFpscr = new SoftFloat64FPCompareGTFpscr(SoftFloat64.FPCompareGTFpscr); // A32 only.
+            var dlgSoftFloat64FPCompareLE = new SoftFloat64FPCompareLE(SoftFloat64.FPCompareLE);
+            var dlgSoftFloat64FPCompareLEFpscr = new SoftFloat64FPCompareLEFpscr(SoftFloat64.FPCompareLEFpscr); // A32 only.
+            var dlgSoftFloat64FPCompareLT = new SoftFloat64FPCompareLT(SoftFloat64.FPCompareLT);
+            var dlgSoftFloat64FPCompareLTFpscr = new SoftFloat64FPCompareLTFpscr(SoftFloat64.FPCompareLTFpscr); // A32 only.
+            var dlgSoftFloat64FPDiv = new SoftFloat64FPDiv(SoftFloat64.FPDiv);
+            var dlgSoftFloat64FPMax = new SoftFloat64FPMax(SoftFloat64.FPMax);
+            var dlgSoftFloat64FPMaxFpscr = new SoftFloat64FPMaxFpscr(SoftFloat64.FPMaxFpscr); // A32 only.
+            var dlgSoftFloat64FPMaxNum = new SoftFloat64FPMaxNum(SoftFloat64.FPMaxNum);
+            var dlgSoftFloat64FPMaxNumFpscr = new SoftFloat64FPMaxNumFpscr(SoftFloat64.FPMaxNumFpscr); // A32 only.
+            var dlgSoftFloat64FPMin = new SoftFloat64FPMin(SoftFloat64.FPMin);
+            var dlgSoftFloat64FPMinFpscr = new SoftFloat64FPMinFpscr(SoftFloat64.FPMinFpscr); // A32 only.
+            var dlgSoftFloat64FPMinNum = new SoftFloat64FPMinNum(SoftFloat64.FPMinNum);
+            var dlgSoftFloat64FPMinNumFpscr = new SoftFloat64FPMinNumFpscr(SoftFloat64.FPMinNumFpscr); // A32 only.
+            var dlgSoftFloat64FPMul = new SoftFloat64FPMul(SoftFloat64.FPMul);
+            var dlgSoftFloat64FPMulFpscr = new SoftFloat64FPMulFpscr(SoftFloat64.FPMulFpscr); // A32 only.
+            var dlgSoftFloat64FPMulAdd = new SoftFloat64FPMulAdd(SoftFloat64.FPMulAdd);
+            var dlgSoftFloat64FPMulAddFpscr = new SoftFloat64FPMulAddFpscr(SoftFloat64.FPMulAddFpscr); // A32 only.
+            var dlgSoftFloat64FPMulSub = new SoftFloat64FPMulSub(SoftFloat64.FPMulSub);
+            var dlgSoftFloat64FPMulSubFpscr = new SoftFloat64FPMulSubFpscr(SoftFloat64.FPMulSubFpscr); // A32 only.
+            var dlgSoftFloat64FPMulX = new SoftFloat64FPMulX(SoftFloat64.FPMulX);
+            var dlgSoftFloat64FPNegMulAdd = new SoftFloat64FPNegMulAdd(SoftFloat64.FPNegMulAdd);
+            var dlgSoftFloat64FPNegMulSub = new SoftFloat64FPNegMulSub(SoftFloat64.FPNegMulSub);
+            var dlgSoftFloat64FPRecipEstimate = new SoftFloat64FPRecipEstimate(SoftFloat64.FPRecipEstimate);
+            var dlgSoftFloat64FPRecipEstimateFpscr = new SoftFloat64FPRecipEstimateFpscr(SoftFloat64.FPRecipEstimateFpscr); // A32 only.
+            var dlgSoftFloat64FPRecipStep = new SoftFloat64FPRecipStep(SoftFloat64.FPRecipStep); // A32 only.
+            var dlgSoftFloat64FPRecipStepFused = new SoftFloat64FPRecipStepFused(SoftFloat64.FPRecipStepFused);
+            var dlgSoftFloat64FPRecpX = new SoftFloat64FPRecpX(SoftFloat64.FPRecpX);
+            var dlgSoftFloat64FPRSqrtEstimate = new SoftFloat64FPRSqrtEstimate(SoftFloat64.FPRSqrtEstimate);
+            var dlgSoftFloat64FPRSqrtEstimateFpscr = new SoftFloat64FPRSqrtEstimateFpscr(SoftFloat64.FPRSqrtEstimateFpscr); // A32 only.
+            var dlgSoftFloat64FPRSqrtStep = new SoftFloat64FPRSqrtStep(SoftFloat64.FPRSqrtStep); // A32 only.
+            var dlgSoftFloat64FPRSqrtStepFused = new SoftFloat64FPRSqrtStepFused(SoftFloat64.FPRSqrtStepFused);
+            var dlgSoftFloat64FPSqrt = new SoftFloat64FPSqrt(SoftFloat64.FPSqrt);
+            var dlgSoftFloat64FPSub = new SoftFloat64FPSub(SoftFloat64.FPSub);
 
-            SetDelegateInfo(new SoftFloat64_16FPConvert(SoftFloat64_16.FPConvert));
+            var dlgSoftFloat64_16FPConvert = new SoftFloat64_16FPConvert(SoftFloat64_16.FPConvert);
+
+            SetDelegateInfo(dlgMathAbs, Marshal.GetFunctionPointerForDelegate<MathAbs>(dlgMathAbs));
+            SetDelegateInfo(dlgMathCeiling, Marshal.GetFunctionPointerForDelegate<MathCeiling>(dlgMathCeiling));
+            SetDelegateInfo(dlgMathFloor, Marshal.GetFunctionPointerForDelegate<MathFloor>(dlgMathFloor));
+            SetDelegateInfo(dlgMathRound, Marshal.GetFunctionPointerForDelegate<MathRound>(dlgMathRound));
+            SetDelegateInfo(dlgMathTruncate, Marshal.GetFunctionPointerForDelegate<MathTruncate>(dlgMathTruncate));
+
+            SetDelegateInfo(dlgMathFAbs, Marshal.GetFunctionPointerForDelegate<MathFAbs>(dlgMathFAbs));
+            SetDelegateInfo(dlgMathFCeiling, Marshal.GetFunctionPointerForDelegate<MathFCeiling>(dlgMathFCeiling));
+            SetDelegateInfo(dlgMathFFloor, Marshal.GetFunctionPointerForDelegate<MathFFloor>(dlgMathFFloor));
+            SetDelegateInfo(dlgMathFRound, Marshal.GetFunctionPointerForDelegate<MathFRound>(dlgMathFRound));
+            SetDelegateInfo(dlgMathFTruncate, Marshal.GetFunctionPointerForDelegate<MathFTruncate>(dlgMathFTruncate));
+
+            SetDelegateInfo(dlgNativeInterfaceBreak, Marshal.GetFunctionPointerForDelegate<NativeInterfaceBreak>(dlgNativeInterfaceBreak));
+            SetDelegateInfo(dlgNativeInterfaceCheckSynchronization, Marshal.GetFunctionPointerForDelegate<NativeInterfaceCheckSynchronization>(dlgNativeInterfaceCheckSynchronization));
+            SetDelegateInfo(dlgNativeInterfaceEnqueueForRejit, Marshal.GetFunctionPointerForDelegate<NativeInterfaceEnqueueForRejit>(dlgNativeInterfaceEnqueueForRejit));
+            SetDelegateInfo(dlgNativeInterfaceGetCntfrqEl0, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetCntfrqEl0>(dlgNativeInterfaceGetCntfrqEl0));
+            SetDelegateInfo(dlgNativeInterfaceGetCntpctEl0, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetCntpctEl0>(dlgNativeInterfaceGetCntpctEl0));
+            SetDelegateInfo(dlgNativeInterfaceGetCntvctEl0, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetCntvctEl0>(dlgNativeInterfaceGetCntvctEl0));
+            SetDelegateInfo(dlgNativeInterfaceGetCtrEl0, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetCtrEl0>(dlgNativeInterfaceGetCtrEl0));
+            SetDelegateInfo(dlgNativeInterfaceGetDczidEl0, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetDczidEl0>(dlgNativeInterfaceGetDczidEl0));
+            SetDelegateInfo(dlgNativeInterfaceGetFunctionAddress, Marshal.GetFunctionPointerForDelegate<NativeInterfaceGetFunctionAddress>(dlgNativeInterfaceGetFunctionAddress));
+            SetDelegateInfo(dlgNativeInterfaceInvalidateCacheLine, Marshal.GetFunctionPointerForDelegate<NativeInterfaceInvalidateCacheLine>(dlgNativeInterfaceInvalidateCacheLine));
+            SetDelegateInfo(dlgNativeInterfaceReadByte, Marshal.GetFunctionPointerForDelegate<NativeInterfaceReadByte>(dlgNativeInterfaceReadByte));
+            SetDelegateInfo(dlgNativeInterfaceReadUInt16, Marshal.GetFunctionPointerForDelegate<NativeInterfaceReadUInt16>(dlgNativeInterfaceReadUInt16));
+            SetDelegateInfo(dlgNativeInterfaceReadUInt32, Marshal.GetFunctionPointerForDelegate<NativeInterfaceReadUInt32>(dlgNativeInterfaceReadUInt32));
+            SetDelegateInfo(dlgNativeInterfaceReadUInt64, Marshal.GetFunctionPointerForDelegate<NativeInterfaceReadUInt64>(dlgNativeInterfaceReadUInt64));
+            SetDelegateInfo(dlgNativeInterfaceReadVector128, Marshal.GetFunctionPointerForDelegate<NativeInterfaceReadVector128>(dlgNativeInterfaceReadVector128));
+            SetDelegateInfo(dlgNativeInterfaceSignalMemoryTracking, Marshal.GetFunctionPointerForDelegate<NativeInterfaceSignalMemoryTracking>(dlgNativeInterfaceSignalMemoryTracking));
+            SetDelegateInfo(dlgNativeInterfaceSupervisorCall, Marshal.GetFunctionPointerForDelegate<NativeInterfaceSupervisorCall>(dlgNativeInterfaceSupervisorCall));
+            SetDelegateInfo(dlgNativeInterfaceThrowInvalidMemoryAccess, Marshal.GetFunctionPointerForDelegate<NativeInterfaceThrowInvalidMemoryAccess>(dlgNativeInterfaceThrowInvalidMemoryAccess));
+            SetDelegateInfo(dlgNativeInterfaceUndefined, Marshal.GetFunctionPointerForDelegate<NativeInterfaceUndefined>(dlgNativeInterfaceUndefined));
+            SetDelegateInfo(dlgNativeInterfaceWriteByte, Marshal.GetFunctionPointerForDelegate<NativeInterfaceWriteByte>(dlgNativeInterfaceWriteByte));
+            SetDelegateInfo(dlgNativeInterfaceWriteUInt16, Marshal.GetFunctionPointerForDelegate<NativeInterfaceWriteUInt16>(dlgNativeInterfaceWriteUInt16));
+            SetDelegateInfo(dlgNativeInterfaceWriteUInt32, Marshal.GetFunctionPointerForDelegate<NativeInterfaceWriteUInt32>(dlgNativeInterfaceWriteUInt32));
+            SetDelegateInfo(dlgNativeInterfaceWriteUInt64, Marshal.GetFunctionPointerForDelegate<NativeInterfaceWriteUInt64>(dlgNativeInterfaceWriteUInt64));
+            SetDelegateInfo(dlgNativeInterfaceWriteVector128, Marshal.GetFunctionPointerForDelegate<NativeInterfaceWriteVector128>(dlgNativeInterfaceWriteVector128));
+
+            SetDelegateInfo(dlgSoftFallbackCountLeadingSigns, Marshal.GetFunctionPointerForDelegate<SoftFallbackCountLeadingSigns>(dlgSoftFallbackCountLeadingSigns));
+            SetDelegateInfo(dlgSoftFallbackCountLeadingZeros, Marshal.GetFunctionPointerForDelegate<SoftFallbackCountLeadingZeros>(dlgSoftFallbackCountLeadingZeros));
+            SetDelegateInfo(dlgSoftFallbackCrc32b, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32b>(dlgSoftFallbackCrc32b));
+            SetDelegateInfo(dlgSoftFallbackCrc32cb, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32cb>(dlgSoftFallbackCrc32cb));
+            SetDelegateInfo(dlgSoftFallbackCrc32ch, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32ch>(dlgSoftFallbackCrc32ch));
+            SetDelegateInfo(dlgSoftFallbackCrc32cw, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32cw>(dlgSoftFallbackCrc32cw));
+            SetDelegateInfo(dlgSoftFallbackCrc32cx, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32cx>(dlgSoftFallbackCrc32cx));
+            SetDelegateInfo(dlgSoftFallbackCrc32h, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32h>(dlgSoftFallbackCrc32h));
+            SetDelegateInfo(dlgSoftFallbackCrc32w, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32w>(dlgSoftFallbackCrc32w));
+            SetDelegateInfo(dlgSoftFallbackCrc32x, Marshal.GetFunctionPointerForDelegate<SoftFallbackCrc32x>(dlgSoftFallbackCrc32x));
+            SetDelegateInfo(dlgSoftFallbackDecrypt, Marshal.GetFunctionPointerForDelegate<SoftFallbackDecrypt>(dlgSoftFallbackDecrypt));
+            SetDelegateInfo(dlgSoftFallbackEncrypt, Marshal.GetFunctionPointerForDelegate<SoftFallbackEncrypt>(dlgSoftFallbackEncrypt));
+            SetDelegateInfo(dlgSoftFallbackFixedRotate, Marshal.GetFunctionPointerForDelegate<SoftFallbackFixedRotate>(dlgSoftFallbackFixedRotate));
+            SetDelegateInfo(dlgSoftFallbackHashChoose, Marshal.GetFunctionPointerForDelegate<SoftFallbackHashChoose>(dlgSoftFallbackHashChoose));
+            SetDelegateInfo(dlgSoftFallbackHashLower, Marshal.GetFunctionPointerForDelegate<SoftFallbackHashLower>(dlgSoftFallbackHashLower));
+            SetDelegateInfo(dlgSoftFallbackHashMajority, Marshal.GetFunctionPointerForDelegate<SoftFallbackHashMajority>(dlgSoftFallbackHashMajority));
+            SetDelegateInfo(dlgSoftFallbackHashParity, Marshal.GetFunctionPointerForDelegate<SoftFallbackHashParity>(dlgSoftFallbackHashParity));
+            SetDelegateInfo(dlgSoftFallbackHashUpper, Marshal.GetFunctionPointerForDelegate<SoftFallbackHashUpper>(dlgSoftFallbackHashUpper));
+            SetDelegateInfo(dlgSoftFallbackInverseMixColumns, Marshal.GetFunctionPointerForDelegate<SoftFallbackInverseMixColumns>(dlgSoftFallbackInverseMixColumns));
+            SetDelegateInfo(dlgSoftFallbackMixColumns, Marshal.GetFunctionPointerForDelegate<SoftFallbackMixColumns>(dlgSoftFallbackMixColumns));
+            SetDelegateInfo(dlgSoftFallbackPolynomialMult64_128, Marshal.GetFunctionPointerForDelegate<SoftFallbackPolynomialMult64_128>(dlgSoftFallbackPolynomialMult64_128));
+            SetDelegateInfo(dlgSoftFallbackSatF32ToS32, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF32ToS32>(dlgSoftFallbackSatF32ToS32));
+            SetDelegateInfo(dlgSoftFallbackSatF32ToS64, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF32ToS64>(dlgSoftFallbackSatF32ToS64));
+            SetDelegateInfo(dlgSoftFallbackSatF32ToU32, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF32ToU32>(dlgSoftFallbackSatF32ToU32));
+            SetDelegateInfo(dlgSoftFallbackSatF32ToU64, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF32ToU64>(dlgSoftFallbackSatF32ToU64));
+            SetDelegateInfo(dlgSoftFallbackSatF64ToS32, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF64ToS32>(dlgSoftFallbackSatF64ToS32));
+            SetDelegateInfo(dlgSoftFallbackSatF64ToS64, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF64ToS64>(dlgSoftFallbackSatF64ToS64));
+            SetDelegateInfo(dlgSoftFallbackSatF64ToU32, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF64ToU32>(dlgSoftFallbackSatF64ToU32));
+            SetDelegateInfo(dlgSoftFallbackSatF64ToU64, Marshal.GetFunctionPointerForDelegate<SoftFallbackSatF64ToU64>(dlgSoftFallbackSatF64ToU64));
+            SetDelegateInfo(dlgSoftFallbackSha1SchedulePart1, Marshal.GetFunctionPointerForDelegate<SoftFallbackSha1SchedulePart1>(dlgSoftFallbackSha1SchedulePart1));
+            SetDelegateInfo(dlgSoftFallbackSha1SchedulePart2, Marshal.GetFunctionPointerForDelegate<SoftFallbackSha1SchedulePart2>(dlgSoftFallbackSha1SchedulePart2));
+            SetDelegateInfo(dlgSoftFallbackSha256SchedulePart1, Marshal.GetFunctionPointerForDelegate<SoftFallbackSha256SchedulePart1>(dlgSoftFallbackSha256SchedulePart1));
+            SetDelegateInfo(dlgSoftFallbackSha256SchedulePart2, Marshal.GetFunctionPointerForDelegate<SoftFallbackSha256SchedulePart2>(dlgSoftFallbackSha256SchedulePart2));
+            SetDelegateInfo(dlgSoftFallbackSignedShrImm64, Marshal.GetFunctionPointerForDelegate<SoftFallbackSignedShrImm64>(dlgSoftFallbackSignedShrImm64));
+            SetDelegateInfo(dlgSoftFallbackTbl1, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbl1>(dlgSoftFallbackTbl1));
+            SetDelegateInfo(dlgSoftFallbackTbl2, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbl2>(dlgSoftFallbackTbl2));
+            SetDelegateInfo(dlgSoftFallbackTbl3, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbl3>(dlgSoftFallbackTbl3));
+            SetDelegateInfo(dlgSoftFallbackTbl4, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbl4>(dlgSoftFallbackTbl4));
+            SetDelegateInfo(dlgSoftFallbackTbx1, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbx1>(dlgSoftFallbackTbx1));
+            SetDelegateInfo(dlgSoftFallbackTbx2, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbx2>(dlgSoftFallbackTbx2));
+            SetDelegateInfo(dlgSoftFallbackTbx3, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbx3>(dlgSoftFallbackTbx3));
+            SetDelegateInfo(dlgSoftFallbackTbx4, Marshal.GetFunctionPointerForDelegate<SoftFallbackTbx4>(dlgSoftFallbackTbx4));
+            SetDelegateInfo(dlgSoftFallbackUnsignedShrImm64, Marshal.GetFunctionPointerForDelegate<SoftFallbackUnsignedShrImm64>(dlgSoftFallbackUnsignedShrImm64));
+
+            SetDelegateInfo(dlgSoftFloat16_32FPConvert, Marshal.GetFunctionPointerForDelegate<SoftFloat16_32FPConvert>(dlgSoftFloat16_32FPConvert));
+            SetDelegateInfo(dlgSoftFloat16_64FPConvert, Marshal.GetFunctionPointerForDelegate<SoftFloat16_64FPConvert>(dlgSoftFloat16_64FPConvert));
+
+            SetDelegateInfo(dlgSoftFloat32FPAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPAdd>(dlgSoftFloat32FPAdd));
+            SetDelegateInfo(dlgSoftFloat32FPAddFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPAddFpscr>(dlgSoftFloat32FPAddFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPCompare, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompare>(dlgSoftFloat32FPCompare));
+            SetDelegateInfo(dlgSoftFloat32FPCompareEQ, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareEQ>(dlgSoftFloat32FPCompareEQ));
+            SetDelegateInfo(dlgSoftFloat32FPCompareEQFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareEQFpscr>(dlgSoftFloat32FPCompareEQFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPCompareGE, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareGE>(dlgSoftFloat32FPCompareGE));
+            SetDelegateInfo(dlgSoftFloat32FPCompareGEFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareGEFpscr>(dlgSoftFloat32FPCompareGEFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPCompareGT, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareGT>(dlgSoftFloat32FPCompareGT));
+            SetDelegateInfo(dlgSoftFloat32FPCompareGTFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareGTFpscr>(dlgSoftFloat32FPCompareGTFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPCompareLE, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareLE>(dlgSoftFloat32FPCompareLE));
+            SetDelegateInfo(dlgSoftFloat32FPCompareLEFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareLEFpscr>(dlgSoftFloat32FPCompareLEFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPCompareLT, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareLT>(dlgSoftFloat32FPCompareLT));
+            SetDelegateInfo(dlgSoftFloat32FPCompareLTFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPCompareLTFpscr>(dlgSoftFloat32FPCompareLTFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPDiv, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPDiv>(dlgSoftFloat32FPDiv));
+            SetDelegateInfo(dlgSoftFloat32FPMax, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMax>(dlgSoftFloat32FPMax));
+            SetDelegateInfo(dlgSoftFloat32FPMaxFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMaxFpscr>(dlgSoftFloat32FPMaxFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMaxNum, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMaxNum>(dlgSoftFloat32FPMaxNum));
+            SetDelegateInfo(dlgSoftFloat32FPMaxNumFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMaxNumFpscr>(dlgSoftFloat32FPMaxNumFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMin, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMin>(dlgSoftFloat32FPMin));
+            SetDelegateInfo(dlgSoftFloat32FPMinFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMinFpscr>(dlgSoftFloat32FPMinFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMinNum, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMinNum>(dlgSoftFloat32FPMinNum));
+            SetDelegateInfo(dlgSoftFloat32FPMinNumFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMinNumFpscr>(dlgSoftFloat32FPMinNumFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMul, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMul>(dlgSoftFloat32FPMul));
+            SetDelegateInfo(dlgSoftFloat32FPMulFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulFpscr>(dlgSoftFloat32FPMulFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMulAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulAdd>(dlgSoftFloat32FPMulAdd));
+            SetDelegateInfo(dlgSoftFloat32FPMulAddFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulAddFpscr>(dlgSoftFloat32FPMulAddFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMulSub, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulSub>(dlgSoftFloat32FPMulSub));
+            SetDelegateInfo(dlgSoftFloat32FPMulSubFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulSubFpscr>(dlgSoftFloat32FPMulSubFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPMulX, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPMulX>(dlgSoftFloat32FPMulX));
+            SetDelegateInfo(dlgSoftFloat32FPNegMulAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPNegMulAdd>(dlgSoftFloat32FPNegMulAdd));
+            SetDelegateInfo(dlgSoftFloat32FPNegMulSub, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPNegMulSub>(dlgSoftFloat32FPNegMulSub));
+            SetDelegateInfo(dlgSoftFloat32FPRecipEstimate, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRecipEstimate>(dlgSoftFloat32FPRecipEstimate));
+            SetDelegateInfo(dlgSoftFloat32FPRecipEstimateFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRecipEstimateFpscr>(dlgSoftFloat32FPRecipEstimateFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPRecipStep, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRecipStep>(dlgSoftFloat32FPRecipStep)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPRecipStepFused, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRecipStepFused>(dlgSoftFloat32FPRecipStepFused));
+            SetDelegateInfo(dlgSoftFloat32FPRecpX, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRecpX>(dlgSoftFloat32FPRecpX));
+            SetDelegateInfo(dlgSoftFloat32FPRSqrtEstimate, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRSqrtEstimate>(dlgSoftFloat32FPRSqrtEstimate));
+            SetDelegateInfo(dlgSoftFloat32FPRSqrtEstimateFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRSqrtEstimateFpscr>(dlgSoftFloat32FPRSqrtEstimateFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPRSqrtStep, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRSqrtStep>(dlgSoftFloat32FPRSqrtStep)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat32FPRSqrtStepFused, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPRSqrtStepFused>(dlgSoftFloat32FPRSqrtStepFused));
+            SetDelegateInfo(dlgSoftFloat32FPSqrt, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPSqrt>(dlgSoftFloat32FPSqrt));
+            SetDelegateInfo(dlgSoftFloat32FPSub, Marshal.GetFunctionPointerForDelegate<SoftFloat32FPSub>(dlgSoftFloat32FPSub));
+
+            SetDelegateInfo(dlgSoftFloat32_16FPConvert, Marshal.GetFunctionPointerForDelegate<SoftFloat32_16FPConvert>(dlgSoftFloat32_16FPConvert));
+
+            SetDelegateInfo(dlgSoftFloat64FPAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPAdd>(dlgSoftFloat64FPAdd));
+            SetDelegateInfo(dlgSoftFloat64FPAddFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPAddFpscr>(dlgSoftFloat64FPAddFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPCompare, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompare>(dlgSoftFloat64FPCompare));
+            SetDelegateInfo(dlgSoftFloat64FPCompareEQ, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareEQ>(dlgSoftFloat64FPCompareEQ));
+            SetDelegateInfo(dlgSoftFloat64FPCompareEQFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareEQFpscr>(dlgSoftFloat64FPCompareEQFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPCompareGE, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareGE>(dlgSoftFloat64FPCompareGE));
+            SetDelegateInfo(dlgSoftFloat64FPCompareGEFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareGEFpscr>(dlgSoftFloat64FPCompareGEFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPCompareGT, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareGT>(dlgSoftFloat64FPCompareGT));
+            SetDelegateInfo(dlgSoftFloat64FPCompareGTFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareGTFpscr>(dlgSoftFloat64FPCompareGTFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPCompareLE, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareLE>(dlgSoftFloat64FPCompareLE));
+            SetDelegateInfo(dlgSoftFloat64FPCompareLEFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareLEFpscr>(dlgSoftFloat64FPCompareLEFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPCompareLT, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareLT>(dlgSoftFloat64FPCompareLT));
+            SetDelegateInfo(dlgSoftFloat64FPCompareLTFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPCompareLTFpscr>(dlgSoftFloat64FPCompareLTFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPDiv, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPDiv>(dlgSoftFloat64FPDiv));
+            SetDelegateInfo(dlgSoftFloat64FPMax, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMax>(dlgSoftFloat64FPMax));
+            SetDelegateInfo(dlgSoftFloat64FPMaxFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMaxFpscr>(dlgSoftFloat64FPMaxFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMaxNum, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMaxNum>(dlgSoftFloat64FPMaxNum));
+            SetDelegateInfo(dlgSoftFloat64FPMaxNumFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMaxNumFpscr>(dlgSoftFloat64FPMaxNumFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMin, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMin>(dlgSoftFloat64FPMin));
+            SetDelegateInfo(dlgSoftFloat64FPMinFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMinFpscr>(dlgSoftFloat64FPMinFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMinNum, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMinNum>(dlgSoftFloat64FPMinNum));
+            SetDelegateInfo(dlgSoftFloat64FPMinNumFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMinNumFpscr>(dlgSoftFloat64FPMinNumFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMul, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMul>(dlgSoftFloat64FPMul));
+            SetDelegateInfo(dlgSoftFloat64FPMulFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulFpscr>(dlgSoftFloat64FPMulFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMulAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulAdd>(dlgSoftFloat64FPMulAdd));
+            SetDelegateInfo(dlgSoftFloat64FPMulAddFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulAddFpscr>(dlgSoftFloat64FPMulAddFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMulSub, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulSub>(dlgSoftFloat64FPMulSub));
+            SetDelegateInfo(dlgSoftFloat64FPMulSubFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulSubFpscr>(dlgSoftFloat64FPMulSubFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPMulX, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPMulX>(dlgSoftFloat64FPMulX));
+            SetDelegateInfo(dlgSoftFloat64FPNegMulAdd, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPNegMulAdd>(dlgSoftFloat64FPNegMulAdd));
+            SetDelegateInfo(dlgSoftFloat64FPNegMulSub, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPNegMulSub>(dlgSoftFloat64FPNegMulSub));
+            SetDelegateInfo(dlgSoftFloat64FPRecipEstimate, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRecipEstimate>(dlgSoftFloat64FPRecipEstimate));
+            SetDelegateInfo(dlgSoftFloat64FPRecipEstimateFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRecipEstimateFpscr>(dlgSoftFloat64FPRecipEstimateFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPRecipStep, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRecipStep>(dlgSoftFloat64FPRecipStep)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPRecipStepFused, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRecipStepFused>(dlgSoftFloat64FPRecipStepFused));
+            SetDelegateInfo(dlgSoftFloat64FPRecpX, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRecpX>(dlgSoftFloat64FPRecpX));
+            SetDelegateInfo(dlgSoftFloat64FPRSqrtEstimate, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRSqrtEstimate>(dlgSoftFloat64FPRSqrtEstimate));
+            SetDelegateInfo(dlgSoftFloat64FPRSqrtEstimateFpscr, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRSqrtEstimateFpscr>(dlgSoftFloat64FPRSqrtEstimateFpscr)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPRSqrtStep, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRSqrtStep>(dlgSoftFloat64FPRSqrtStep)); // A32 only.
+            SetDelegateInfo(dlgSoftFloat64FPRSqrtStepFused, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPRSqrtStepFused>(dlgSoftFloat64FPRSqrtStepFused));
+            SetDelegateInfo(dlgSoftFloat64FPSqrt, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPSqrt>(dlgSoftFloat64FPSqrt));
+            SetDelegateInfo(dlgSoftFloat64FPSub, Marshal.GetFunctionPointerForDelegate<SoftFloat64FPSub>(dlgSoftFloat64FPSub));
+
+            SetDelegateInfo(dlgSoftFloat64_16FPConvert, Marshal.GetFunctionPointerForDelegate<SoftFloat64_16FPConvert>(dlgSoftFloat64_16FPConvert));
         }
 
         private delegate double MathAbs(double value);

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/Renderer/Server/Performance/PerformanceManager.cs

@@ -18,16 +18,12 @@ namespace Ryujinx.Audio.Renderer.Server.Performance
 
             if (version == 2)
             {
-                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion2,
-                                                 PerformanceEntryVersion2,
-                                                 PerformanceDetailVersion2>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
+                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion2, PerformanceEntryVersion2, PerformanceDetailVersion2>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
             }
 
             if (version == 1)
             {
-                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion1,
-                    PerformanceEntryVersion1,
-                    PerformanceDetailVersion1>.GetRequiredBufferSizeForPerformanceMetricsPerFrame(ref parameter);
+                return (ulong)PerformanceManagerGeneric<PerformanceFrameHeaderVersion1, 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());
-            Environment.SetEnvironmentVariable("__GL_THREADED_OPTIMIZATIONS", enabled ? "1" : "0");
+            OsUtils.SetEnvironmentVariableNoCaching("mesa_glthread", enabled.ToString().ToLower());
+            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/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/Capabilities.cs

@@ -71,6 +71,8 @@ namespace Ryujinx.Graphics.GAL
 
         public readonly int GatherBiasPrecision;
 
+        public readonly ulong MaximumGpuMemory;
+
         public Capabilities(
             TargetApi api,
             string vendorName,
@@ -131,7 +133,8 @@ namespace Ryujinx.Graphics.GAL
             int shaderSubgroupSize,
             int storageBufferOffsetAlignment,
             int textureBufferOffsetAlignment,
-            int gatherBiasPrecision)
+            int gatherBiasPrecision,
+            ulong maximumGpuMemory)
         {
             Api = api;
             VendorName = vendorName;
@@ -193,6 +196,7 @@ namespace Ryujinx.Graphics.GAL
             StorageBufferOffsetAlignment = storageBufferOffsetAlignment;
             TextureBufferOffsetAlignment = textureBufferOffsetAlignment;
             GatherBiasPrecision = gatherBiasPrecision;
+            MaximumGpuMemory = maximumGpuMemory;
         }
     }
 }

src/Ryujinx.Graphics.GAL/IImageArray.cs

@@ -4,7 +4,6 @@ namespace Ryujinx.Graphics.GAL
 {
     public interface IImageArray : IDisposable
     {
-        void SetFormats(int index, Format[] imageFormats);
         void SetImages(int index, ITexture[] images);
     }
 }

src/Ryujinx.Graphics.GAL/IPipeline.cs

@@ -58,7 +58,7 @@ namespace Ryujinx.Graphics.GAL
 
         void SetIndexBuffer(BufferRange buffer, IndexType type);
 
-        void SetImage(ShaderStage stage, int binding, ITexture texture, Format imageFormat);
+        void SetImage(ShaderStage stage, int binding, ITexture texture);
         void SetImageArray(ShaderStage stage, int binding, IImageArray array);
         void SetImageArraySeparate(ShaderStage stage, int setIndex, IImageArray array);
 

src/Ryujinx.Graphics.GAL/ITexture.cs

@@ -1,4 +1,4 @@
-using System.Buffers;
+using Ryujinx.Common.Memory;
 
 namespace Ryujinx.Graphics.GAL
 {
@@ -18,30 +18,30 @@ namespace Ryujinx.Graphics.GAL
         PinnedSpan<byte> GetData(int layer, int level);
 
         /// <summary>
-        /// Sets the texture data. The data passed as a <see cref="IMemoryOwner{Byte}" /> will be disposed when
+        /// Sets the texture data. The data passed as a <see cref="MemoryOwner{Byte}" /> will be disposed when
         /// the operation completes.
         /// </summary>
         /// <param name="data">Texture data bytes</param>
-        void SetData(IMemoryOwner<byte> data);
+        void SetData(MemoryOwner<byte> data);
 
         /// <summary>
-        /// Sets the texture data. The data passed as a <see cref="IMemoryOwner{Byte}" /> will be disposed when
+        /// Sets the texture data. The data passed as a <see cref="MemoryOwner{Byte}" /> will be disposed when
         /// the operation completes.
         /// </summary>
         /// <param name="data">Texture data bytes</param>
         /// <param name="layer">Target layer</param>
         /// <param name="level">Target level</param>
-        void SetData(IMemoryOwner<byte> data, int layer, int level);
+        void SetData(MemoryOwner<byte> data, int layer, int level);
 
         /// <summary>
-        /// Sets the texture data. The data passed as a <see cref="IMemoryOwner{Byte}" /> will be disposed when
+        /// Sets the texture data. The data passed as a <see cref="MemoryOwner{Byte}" /> will be disposed when
         /// the operation completes.
         /// </summary>
         /// <param name="data">Texture data bytes</param>
         /// <param name="layer">Target layer</param>
         /// <param name="level">Target level</param>
         /// <param name="region">Target sub-region of the texture to update</param>
-        void SetData(IMemoryOwner<byte> data, int layer, int level, Rectangle<int> region);
+        void SetData(MemoryOwner<byte> data, int layer, int level, Rectangle<int> region);
 
         void SetStorage(BufferRange buffer);
 

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

@@ -67,7 +67,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             Register<CounterEventFlushCommand>(CommandType.CounterEventFlush);
 
             Register<ImageArrayDisposeCommand>(CommandType.ImageArrayDispose);
-            Register<ImageArraySetFormatsCommand>(CommandType.ImageArraySetFormats);
             Register<ImageArraySetImagesCommand>(CommandType.ImageArraySetImages);
 
             Register<ProgramDisposeCommand>(CommandType.ProgramDispose);

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

@@ -27,7 +27,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading
         CounterEventFlush,
 
         ImageArrayDispose,
-        ImageArraySetFormats,
         ImageArraySetImages,
 
         ProgramDispose,

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

@@ -1,26 +0,0 @@
-using Ryujinx.Graphics.GAL.Multithreading.Model;
-using Ryujinx.Graphics.GAL.Multithreading.Resources;
-
-namespace Ryujinx.Graphics.GAL.Multithreading.Commands.ImageArray
-{
-    struct ImageArraySetFormatsCommand : IGALCommand, IGALCommand<ImageArraySetFormatsCommand>
-    {
-        public readonly CommandType CommandType => CommandType.ImageArraySetFormats;
-        private TableRef<ThreadedImageArray> _imageArray;
-        private int _index;
-        private TableRef<Format[]> _imageFormats;
-
-        public void Set(TableRef<ThreadedImageArray> imageArray, int index, TableRef<Format[]> imageFormats)
-        {
-            _imageArray = imageArray;
-            _index = index;
-            _imageFormats = imageFormats;
-        }
-
-        public static void Run(ref ImageArraySetFormatsCommand command, ThreadedRenderer threaded, IRenderer renderer)
-        {
-            ThreadedImageArray imageArray = command._imageArray.Get(threaded);
-            imageArray.Base.SetFormats(command._index, command._imageFormats.Get(threaded));
-        }
-    }
-}

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

@@ -10,19 +10,17 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Commands
         private ShaderStage _stage;
         private int _binding;
         private TableRef<ITexture> _texture;
-        private Format _imageFormat;
 
-        public void Set(ShaderStage stage, int binding, TableRef<ITexture> texture, Format imageFormat)
+        public void Set(ShaderStage stage, int binding, TableRef<ITexture> texture)
         {
             _stage = stage;
             _binding = binding;
             _texture = texture;
-            _imageFormat = imageFormat;
         }
 
         public static void Run(ref SetImageCommand command, ThreadedRenderer threaded, IRenderer renderer)
         {
-            renderer.Pipeline.SetImage(command._stage, command._binding, command._texture.GetAs<ThreadedTexture>(threaded)?.Base, command._imageFormat);
+            renderer.Pipeline.SetImage(command._stage, command._binding, command._texture.GetAs<ThreadedTexture>(threaded)?.Base);
         }
     }
 }

src/Ryujinx.Graphics.GAL/Multithreading/Commands/Texture/TextureSetDataCommand.cs

@@ -1,6 +1,6 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL.Multithreading.Model;
 using Ryujinx.Graphics.GAL.Multithreading.Resources;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
 {
@@ -8,9 +8,9 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
     {
         public readonly CommandType CommandType => CommandType.TextureSetData;
         private TableRef<ThreadedTexture> _texture;
-        private TableRef<IMemoryOwner<byte>> _data;
+        private TableRef<MemoryOwner<byte>> _data;
 
-        public void Set(TableRef<ThreadedTexture> texture, TableRef<IMemoryOwner<byte>> data)
+        public void Set(TableRef<ThreadedTexture> texture, TableRef<MemoryOwner<byte>> data)
         {
             _texture = texture;
             _data = data;

src/Ryujinx.Graphics.GAL/Multithreading/Commands/Texture/TextureSetDataSliceCommand.cs

@@ -1,6 +1,6 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL.Multithreading.Model;
 using Ryujinx.Graphics.GAL.Multithreading.Resources;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
 {
@@ -8,11 +8,11 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
     {
         public readonly CommandType CommandType => CommandType.TextureSetDataSlice;
         private TableRef<ThreadedTexture> _texture;
-        private TableRef<IMemoryOwner<byte>> _data;
+        private TableRef<MemoryOwner<byte>> _data;
         private int _layer;
         private int _level;
 
-        public void Set(TableRef<ThreadedTexture> texture, TableRef<IMemoryOwner<byte>> data, int layer, int level)
+        public void Set(TableRef<ThreadedTexture> texture, TableRef<MemoryOwner<byte>> data, int layer, int level)
         {
             _texture = texture;
             _data = data;

src/Ryujinx.Graphics.GAL/Multithreading/Commands/Texture/TextureSetDataSliceRegionCommand.cs

@@ -1,6 +1,6 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL.Multithreading.Model;
 using Ryujinx.Graphics.GAL.Multithreading.Resources;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
 {
@@ -8,12 +8,12 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Commands.Texture
     {
         public readonly CommandType CommandType => CommandType.TextureSetDataSliceRegion;
         private TableRef<ThreadedTexture> _texture;
-        private TableRef<IMemoryOwner<byte>> _data;
+        private TableRef<MemoryOwner<byte>> _data;
         private int _layer;
         private int _level;
         private Rectangle<int> _region;
 
-        public void Set(TableRef<ThreadedTexture> texture, TableRef<IMemoryOwner<byte>> data, int layer, int level, Rectangle<int> region)
+        public void Set(TableRef<ThreadedTexture> texture, TableRef<MemoryOwner<byte>> data, int layer, int level, Rectangle<int> region)
         {
             _texture = texture;
             _data = data;

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

@@ -27,12 +27,6 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Resources
             _renderer.QueueCommand();
         }
 
-        public void SetFormats(int index, Format[] imageFormats)
-        {
-            _renderer.New<ImageArraySetFormatsCommand>().Set(Ref(this), index, Ref(imageFormats));
-            _renderer.QueueCommand();
-        }
-
         public void SetImages(int index, ITexture[] images)
         {
             _renderer.New<ImageArraySetImagesCommand>().Set(Ref(this), index, Ref(images));

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

@@ -1,6 +1,6 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL.Multithreading.Commands.Texture;
 using Ryujinx.Graphics.GAL.Multithreading.Model;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.GAL.Multithreading.Resources
 {
@@ -111,21 +111,21 @@ namespace Ryujinx.Graphics.GAL.Multithreading.Resources
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data)
+        public void SetData(MemoryOwner<byte> data)
         {
             _renderer.New<TextureSetDataCommand>().Set(Ref(this), Ref(data));
             _renderer.QueueCommand();
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level)
+        public void SetData(MemoryOwner<byte> data, int layer, int level)
         {
             _renderer.New<TextureSetDataSliceCommand>().Set(Ref(this), Ref(data), layer, level);
             _renderer.QueueCommand();
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
+        public void SetData(MemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
         {
             _renderer.New<TextureSetDataSliceRegionCommand>().Set(Ref(this), Ref(data), layer, level, region);
             _renderer.QueueCommand();

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

@@ -177,9 +177,9 @@ namespace Ryujinx.Graphics.GAL.Multithreading
             _renderer.QueueCommand();
         }
 
-        public void SetImage(ShaderStage stage, int binding, ITexture texture, Format imageFormat)
+        public void SetImage(ShaderStage stage, int binding, ITexture texture)
         {
-            _renderer.New<SetImageCommand>().Set(stage, binding, Ref(texture), imageFormat);
+            _renderer.New<SetImageCommand>().Set(stage, binding, Ref(texture));
             _renderer.QueueCommand();
         }
 

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/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.GAL/UpscaleType.cs

@@ -5,5 +5,6 @@ namespace Ryujinx.Graphics.GAL
         Bilinear,
         Nearest,
         Fsr,
+        Area,
     }
 }

src/Ryujinx.Graphics.Gpu/Engine/Dma/DmaClass.cs

@@ -1,10 +1,10 @@
 using Ryujinx.Common;
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.Device;
 using Ryujinx.Graphics.Gpu.Engine.Threed;
 using Ryujinx.Graphics.Gpu.Memory;
 using Ryujinx.Graphics.Texture;
 using System;
-using System.Buffers;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
@@ -276,8 +276,6 @@ namespace Ryujinx.Graphics.Gpu.Engine.Dma
                     dstBaseOffset += dstStride * (yCount - 1);
                 }
 
-                ReadOnlySpan<byte> srcSpan = memoryManager.GetSpan(srcGpuVa + (ulong)srcBaseOffset, srcSize, true);
-
                 // If remapping is disabled, we always copy the components directly, in order.
                 // If it's enabled, but the mapping is just XYZW, we also copy them in order.
                 bool isIdentityRemap = !remap ||
@@ -289,6 +287,52 @@ namespace Ryujinx.Graphics.Gpu.Engine.Dma
                 bool completeSource = IsTextureCopyComplete(src, srcLinear, srcBpp, srcStride, xCount, yCount);
                 bool completeDest = IsTextureCopyComplete(dst, dstLinear, dstBpp, dstStride, xCount, yCount);
 
+                // Check if the source texture exists on the GPU, if it does, do a GPU side copy.
+                // Otherwise, we would need to flush the source texture which is costly.
+                // We don't expect the source to be linear in such cases, as linear source usually indicates buffer or CPU written data.
+
+                if (completeSource && completeDest && !srcLinear && isIdentityRemap)
+                {
+                    var source = memoryManager.Physical.TextureCache.FindTexture(
+                        memoryManager,
+                        srcGpuVa,
+                        srcBpp,
+                        srcStride,
+                        src.Height,
+                        xCount,
+                        yCount,
+                        srcLinear,
+                        src.MemoryLayout.UnpackGobBlocksInY(),
+                        src.MemoryLayout.UnpackGobBlocksInZ());
+
+                    if (source != null && source.Height == yCount)
+                    {
+                        source.SynchronizeMemory();
+
+                        var target = memoryManager.Physical.TextureCache.FindOrCreateTexture(
+                            memoryManager,
+                            source.Info.FormatInfo,
+                            dstGpuVa,
+                            xCount,
+                            yCount,
+                            dstStride,
+                            dstLinear,
+                            dst.MemoryLayout.UnpackGobBlocksInY(),
+                            dst.MemoryLayout.UnpackGobBlocksInZ());
+
+                        if (source.ScaleFactor != target.ScaleFactor)
+                        {
+                            target.PropagateScale(source);
+                        }
+
+                        source.HostTexture.CopyTo(target.HostTexture, 0, 0);
+                        target.SignalModified();
+                        return;
+                    }
+                }
+
+                ReadOnlySpan<byte> srcSpan = memoryManager.GetSpan(srcGpuVa + (ulong)srcBaseOffset, srcSize, true);
+
                 // Try to set the texture data directly,
                 // but only if we are doing a complete copy,
                 // and not for block linear to linear copies, since those are typically accessed from the CPU.
@@ -309,7 +353,7 @@ namespace Ryujinx.Graphics.Gpu.Engine.Dma
 
                     if (target != null)
                     {
-                        IMemoryOwner<byte> data;
+                        MemoryOwner<byte> data;
                         if (srcLinear)
                         {
                             data = LayoutConverter.ConvertLinearStridedToLinear(

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/ShaderTexture.cs

@@ -1,5 +1,6 @@
 using Ryujinx.Common.Logging;
 using Ryujinx.Graphics.GAL;
+using Ryujinx.Graphics.Gpu.Image;
 using Ryujinx.Graphics.Shader;
 
 namespace Ryujinx.Graphics.Gpu.Engine
@@ -61,51 +62,51 @@ namespace Ryujinx.Graphics.Gpu.Engine
         /// </summary>
         /// <param name="format">Shader image format</param>
         /// <returns>Texture format</returns>
-        public static Format GetFormat(TextureFormat format)
+        public static FormatInfo GetFormatInfo(TextureFormat format)
         {
             return format switch
             {
 #pragma warning disable IDE0055 // Disable formatting
-                TextureFormat.R8Unorm           => Format.R8Unorm,
-                TextureFormat.R8Snorm           => Format.R8Snorm,
-                TextureFormat.R8Uint            => Format.R8Uint,
-                TextureFormat.R8Sint            => Format.R8Sint,
-                TextureFormat.R16Float          => Format.R16Float,
-                TextureFormat.R16Unorm          => Format.R16Unorm,
-                TextureFormat.R16Snorm          => Format.R16Snorm,
-                TextureFormat.R16Uint           => Format.R16Uint,
-                TextureFormat.R16Sint           => Format.R16Sint,
-                TextureFormat.R32Float          => Format.R32Float,
-                TextureFormat.R32Uint           => Format.R32Uint,
-                TextureFormat.R32Sint           => Format.R32Sint,
-                TextureFormat.R8G8Unorm         => Format.R8G8Unorm,
-                TextureFormat.R8G8Snorm         => Format.R8G8Snorm,
-                TextureFormat.R8G8Uint          => Format.R8G8Uint,
-                TextureFormat.R8G8Sint          => Format.R8G8Sint,
-                TextureFormat.R16G16Float       => Format.R16G16Float,
-                TextureFormat.R16G16Unorm       => Format.R16G16Unorm,
-                TextureFormat.R16G16Snorm       => Format.R16G16Snorm,
-                TextureFormat.R16G16Uint        => Format.R16G16Uint,
-                TextureFormat.R16G16Sint        => Format.R16G16Sint,
-                TextureFormat.R32G32Float       => Format.R32G32Float,
-                TextureFormat.R32G32Uint        => Format.R32G32Uint,
-                TextureFormat.R32G32Sint        => Format.R32G32Sint,
-                TextureFormat.R8G8B8A8Unorm     => Format.R8G8B8A8Unorm,
-                TextureFormat.R8G8B8A8Snorm     => Format.R8G8B8A8Snorm,
-                TextureFormat.R8G8B8A8Uint      => Format.R8G8B8A8Uint,
-                TextureFormat.R8G8B8A8Sint      => Format.R8G8B8A8Sint,
-                TextureFormat.R16G16B16A16Float => Format.R16G16B16A16Float,
-                TextureFormat.R16G16B16A16Unorm => Format.R16G16B16A16Unorm,
-                TextureFormat.R16G16B16A16Snorm => Format.R16G16B16A16Snorm,
-                TextureFormat.R16G16B16A16Uint  => Format.R16G16B16A16Uint,
-                TextureFormat.R16G16B16A16Sint  => Format.R16G16B16A16Sint,
-                TextureFormat.R32G32B32A32Float => Format.R32G32B32A32Float,
-                TextureFormat.R32G32B32A32Uint  => Format.R32G32B32A32Uint,
-                TextureFormat.R32G32B32A32Sint  => Format.R32G32B32A32Sint,
-                TextureFormat.R10G10B10A2Unorm  => Format.R10G10B10A2Unorm,
-                TextureFormat.R10G10B10A2Uint   => Format.R10G10B10A2Uint,
-                TextureFormat.R11G11B10Float    => Format.R11G11B10Float,
-                _                               => 0,
+                TextureFormat.R8Unorm           => new(Format.R8Unorm, 1, 1, 1, 1),
+                TextureFormat.R8Snorm           => new(Format.R8Snorm, 1, 1, 1, 1),
+                TextureFormat.R8Uint            => new(Format.R8Uint, 1, 1, 1, 1),
+                TextureFormat.R8Sint            => new(Format.R8Sint, 1, 1, 1, 1),
+                TextureFormat.R16Float          => new(Format.R16Float, 1, 1, 2, 1),
+                TextureFormat.R16Unorm          => new(Format.R16Unorm, 1, 1, 2, 1),
+                TextureFormat.R16Snorm          => new(Format.R16Snorm, 1, 1, 2, 1),
+                TextureFormat.R16Uint           => new(Format.R16Uint, 1, 1, 2, 1),
+                TextureFormat.R16Sint           => new(Format.R16Sint, 1, 1, 2, 1),
+                TextureFormat.R32Float          => new(Format.R32Float, 1, 1, 4, 1),
+                TextureFormat.R32Uint           => new(Format.R32Uint, 1, 1, 4, 1),
+                TextureFormat.R32Sint           => new(Format.R32Sint, 1, 1, 4, 1),
+                TextureFormat.R8G8Unorm         => new(Format.R8G8Unorm, 1, 1, 2, 2),
+                TextureFormat.R8G8Snorm         => new(Format.R8G8Snorm, 1, 1, 2, 2),
+                TextureFormat.R8G8Uint          => new(Format.R8G8Uint, 1, 1, 2, 2),
+                TextureFormat.R8G8Sint          => new(Format.R8G8Sint, 1, 1, 2, 2),
+                TextureFormat.R16G16Float       => new(Format.R16G16Float, 1, 1, 4, 2),
+                TextureFormat.R16G16Unorm       => new(Format.R16G16Unorm, 1, 1, 4, 2),
+                TextureFormat.R16G16Snorm       => new(Format.R16G16Snorm, 1, 1, 4, 2),
+                TextureFormat.R16G16Uint        => new(Format.R16G16Uint, 1, 1, 4, 2),
+                TextureFormat.R16G16Sint        => new(Format.R16G16Sint, 1, 1, 4, 2),
+                TextureFormat.R32G32Float       => new(Format.R32G32Float, 1, 1, 8, 2),
+                TextureFormat.R32G32Uint        => new(Format.R32G32Uint, 1, 1, 8, 2),
+                TextureFormat.R32G32Sint        => new(Format.R32G32Sint, 1, 1, 8, 2),
+                TextureFormat.R8G8B8A8Unorm     => new(Format.R8G8B8A8Unorm, 1, 1, 4, 4),
+                TextureFormat.R8G8B8A8Snorm     => new(Format.R8G8B8A8Snorm, 1, 1, 4, 4),
+                TextureFormat.R8G8B8A8Uint      => new(Format.R8G8B8A8Uint, 1, 1, 4, 4),
+                TextureFormat.R8G8B8A8Sint      => new(Format.R8G8B8A8Sint, 1, 1, 4, 4),
+                TextureFormat.R16G16B16A16Float => new(Format.R16G16B16A16Float, 1, 1, 8, 4),
+                TextureFormat.R16G16B16A16Unorm => new(Format.R16G16B16A16Unorm, 1, 1, 8, 4),
+                TextureFormat.R16G16B16A16Snorm => new(Format.R16G16B16A16Snorm, 1, 1, 8, 4),
+                TextureFormat.R16G16B16A16Uint  => new(Format.R16G16B16A16Uint, 1, 1, 8, 4),
+                TextureFormat.R16G16B16A16Sint  => new(Format.R16G16B16A16Sint, 1, 1, 8, 4),
+                TextureFormat.R32G32B32A32Float => new(Format.R32G32B32A32Float, 1, 1, 16, 4),
+                TextureFormat.R32G32B32A32Uint  => new(Format.R32G32B32A32Uint, 1, 1, 16, 4),
+                TextureFormat.R32G32B32A32Sint  => new(Format.R32G32B32A32Sint, 1, 1, 16, 4),
+                TextureFormat.R10G10B10A2Unorm  => new(Format.R10G10B10A2Unorm, 1, 1, 4, 4),
+                TextureFormat.R10G10B10A2Uint   => new(Format.R10G10B10A2Uint, 1, 1, 4, 4),
+                TextureFormat.R11G11B10Float    => new(Format.R11G11B10Float, 1, 1, 4, 3),
+                _                               => FormatInfo.Invalid,
 #pragma warning restore IDE0055
             };
         }

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/Image/AutoDeleteCache.cs

@@ -1,3 +1,4 @@
+using System;
 using System.Collections;
 using System.Collections.Generic;
 
@@ -46,7 +47,11 @@ namespace Ryujinx.Graphics.Gpu.Image
     {
         private const int MinCountForDeletion = 32;
         private const int MaxCapacity = 2048;
-        private const ulong MaxTextureSizeCapacity = 1024 * 1024 * 1024; // MB;
+        private const ulong MinTextureSizeCapacity = 512 * 1024 * 1024;
+        private const ulong MaxTextureSizeCapacity = 4UL * 1024 * 1024 * 1024;
+        private const ulong DefaultTextureSizeCapacity = 1UL * 1024 * 1024 * 1024;
+        private const float MemoryScaleFactor = 0.50f;
+        private ulong _maxCacheMemoryUsage = 0;
 
         private readonly LinkedList<Texture> _textures;
         private ulong _totalSize;
@@ -56,6 +61,25 @@ namespace Ryujinx.Graphics.Gpu.Image
 
         private readonly Dictionary<TextureDescriptor, ShortTextureCacheEntry> _shortCacheLookup;
 
+        /// <summary>
+        /// Initializes the cache, setting the maximum texture capacity for the specified GPU context.
+        /// </summary>
+        /// <remarks>
+        /// If the backend GPU has 0 memory capacity, the cache size defaults to `DefaultTextureSizeCapacity`.
+        /// </remarks>
+        /// <param name="context">The GPU context that the cache belongs to</param>
+        public void Initialize(GpuContext context)
+        {
+            var cacheMemory = (ulong)(context.Capabilities.MaximumGpuMemory * MemoryScaleFactor);
+
+            _maxCacheMemoryUsage = Math.Clamp(cacheMemory, MinTextureSizeCapacity, MaxTextureSizeCapacity);
+
+            if (context.Capabilities.MaximumGpuMemory == 0)
+            {
+                _maxCacheMemoryUsage = DefaultTextureSizeCapacity;
+            }
+        }
+
         /// <summary>
         /// Creates a new instance of the automatic deletion cache.
         /// </summary>
@@ -85,7 +109,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             texture.CacheNode = _textures.AddLast(texture);
 
             if (_textures.Count > MaxCapacity ||
-                (_totalSize > MaxTextureSizeCapacity && _textures.Count >= MinCountForDeletion))
+                (_totalSize > _maxCacheMemoryUsage && _textures.Count >= MinCountForDeletion))
             {
                 RemoveLeastUsedTexture();
             }
@@ -110,7 +134,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     _textures.AddLast(texture.CacheNode);
                 }
 
-                if (_totalSize > MaxTextureSizeCapacity && _textures.Count >= MinCountForDeletion)
+                if (_totalSize > _maxCacheMemoryUsage && _textures.Count >= MinCountForDeletion)
                 {
                     RemoveLeastUsedTexture();
                 }

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

@@ -7,6 +7,11 @@ namespace Ryujinx.Graphics.Gpu.Image
     /// </summary>
     readonly struct FormatInfo
     {
+        /// <summary>
+        /// An invalid texture format.
+        /// </summary>
+        public static FormatInfo Invalid { get; } = new(0, 0, 0, 0, 0);
+
         /// <summary>
         /// A default, generic RGBA8 texture format.
         /// </summary>
@@ -23,7 +28,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <remarks>
         /// Must be 1 for non-compressed formats.
         /// </remarks>
-        public int BlockWidth { get; }
+        public byte BlockWidth { get; }
 
         /// <summary>
         /// The block height for compressed formats.
@@ -31,17 +36,17 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <remarks>
         /// Must be 1 for non-compressed formats.
         /// </remarks>
-        public int BlockHeight { get; }
+        public byte BlockHeight { get; }
 
         /// <summary>
         /// The number of bytes occupied by a single pixel in memory of the texture data.
         /// </summary>
-        public int BytesPerPixel { get; }
+        public byte BytesPerPixel { get; }
 
         /// <summary>
         /// The maximum number of components this format has defined (in RGBA order).
         /// </summary>
-        public int Components { get; }
+        public byte Components { get; }
 
         /// <summary>
         /// Whenever or not the texture format is a compressed format. Determined from block size.
@@ -57,10 +62,10 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="bytesPerPixel">The number of bytes occupied by a single pixel in memory of the texture data</param>
         public FormatInfo(
             Format format,
-            int blockWidth,
-            int blockHeight,
-            int bytesPerPixel,
-            int components)
+            byte blockWidth,
+            byte blockHeight,
+            byte bytesPerPixel,
+            byte components)
         {
             Format = format;
             BlockWidth = blockWidth;

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

@@ -13,6 +13,11 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// </summary>
         public bool IsDisposed { get; private set; }
 
+        /// <summary>
+        /// True if the sampler has sRGB conversion enabled, false otherwise.
+        /// </summary>
+        public bool IsSrgb { get; }
+
         /// <summary>
         /// Host sampler object.
         /// </summary>
@@ -30,6 +35,8 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="descriptor">The Maxwell sampler descriptor</param>
         public Sampler(GpuContext context, SamplerDescriptor descriptor)
         {
+            IsSrgb = descriptor.UnpackSrgb();
+
             MinFilter minFilter = descriptor.UnpackMinFilter();
             MagFilter magFilter = descriptor.UnpackMagFilter();
 

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

@@ -113,6 +113,15 @@ namespace Ryujinx.Graphics.Gpu.Image
             return (CompareOp)(((Word0 >> 10) & 7) + 1);
         }
 
+        /// <summary>
+        /// Unpacks the sampler sRGB format flag.
+        /// </summary>
+        /// <returns>True if the has sampler is sRGB conversion enabled, false otherwise</returns>
+        public readonly bool UnpackSrgb()
+        {
+            return (Word0 & (1 << 13)) != 0;
+        }
+
         /// <summary>
         /// Unpacks and converts the maximum anisotropy value used for texture anisotropic filtering.
         /// </summary>

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;
@@ -6,7 +7,6 @@ using Ryujinx.Graphics.Texture.Astc;
 using Ryujinx.Memory;
 using Ryujinx.Memory.Range;
 using System;
-using System.Buffers;
 using System.Collections.Generic;
 using System.Diagnostics;
 using System.Linq;
@@ -661,7 +661,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
             }
 
-            IMemoryOwner<byte> result = ConvertToHostCompatibleFormat(data);
+            MemoryOwner<byte> result = ConvertToHostCompatibleFormat(data);
 
             if (ScaleFactor != 1f && AllowScaledSetData())
             {
@@ -684,7 +684,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// Uploads new texture data to the host GPU.
         /// </summary>
         /// <param name="data">New data</param>
-        public void SetData(IMemoryOwner<byte> data)
+        public void SetData(MemoryOwner<byte> data)
         {
             BlacklistScale();
 
@@ -703,7 +703,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="data">New data</param>
         /// <param name="layer">Target layer</param>
         /// <param name="level">Target level</param>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level)
+        public void SetData(MemoryOwner<byte> data, int layer, int level)
         {
             BlacklistScale();
 
@@ -721,7 +721,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="layer">Target layer</param>
         /// <param name="level">Target level</param>
         /// <param name="region">Target sub-region of the texture to update</param>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
+        public void SetData(MemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
         {
             BlacklistScale();
 
@@ -739,7 +739,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="level">Mip level to convert</param>
         /// <param name="single">True to convert a single slice</param>
         /// <returns>Converted data</returns>
-        public IMemoryOwner<byte> ConvertToHostCompatibleFormat(ReadOnlySpan<byte> data, int level = 0, bool single = false)
+        public MemoryOwner<byte> ConvertToHostCompatibleFormat(ReadOnlySpan<byte> data, int level = 0, bool single = false)
         {
             int width = Info.Width;
             int height = Info.Height;
@@ -754,7 +754,7 @@ namespace Ryujinx.Graphics.Gpu.Image
 
             int sliceDepth = single ? 1 : depth;
 
-            IMemoryOwner<byte> linear;
+            MemoryOwner<byte> linear;
 
             if (Info.IsLinear)
             {
@@ -787,7 +787,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     data);
             }
 
-            IMemoryOwner<byte> result = linear;
+            MemoryOwner<byte> result = linear;
 
             // Handle compressed cases not supported by the host:
             // - ASTC is usually not supported on desktop cards.
@@ -805,7 +805,7 @@ 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}";
 
@@ -831,19 +831,19 @@ namespace Ryujinx.Graphics.Gpu.Image
                     case Format.Etc2RgbaUnorm:
                         using (result)
                         {
-                            return ETC2Decoder.DecodeRgba(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return ETC2Decoder.DecodeRgba(result.Span, width, height, sliceDepth, levels, layers);
                         }
                     case Format.Etc2RgbPtaSrgb:
                     case Format.Etc2RgbPtaUnorm:
                         using (result)
                         {
-                            return ETC2Decoder.DecodePta(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return ETC2Decoder.DecodePta(result.Span, width, height, sliceDepth, levels, layers);
                         }
                     case Format.Etc2RgbSrgb:
                     case Format.Etc2RgbUnorm:
                         using (result)
                         {
-                            return ETC2Decoder.DecodeRgb(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return ETC2Decoder.DecodeRgb(result.Span, width, height, sliceDepth, levels, layers);
                         }
                 }
             }
@@ -855,43 +855,43 @@ namespace Ryujinx.Graphics.Gpu.Image
                     case Format.Bc1RgbaUnorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC1(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return BCnDecoder.DecodeBC1(result.Span, width, height, sliceDepth, levels, layers);
                         }
                     case Format.Bc2Srgb:
                     case Format.Bc2Unorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC2(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return BCnDecoder.DecodeBC2(result.Span, width, height, sliceDepth, levels, layers);
                         }
                     case Format.Bc3Srgb:
                     case Format.Bc3Unorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC3(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return BCnDecoder.DecodeBC3(result.Span, width, height, sliceDepth, levels, layers);
                         }
                     case Format.Bc4Snorm:
                     case Format.Bc4Unorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC4(result.Memory.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc4Snorm);
+                            return BCnDecoder.DecodeBC4(result.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc4Snorm);
                         }
                     case Format.Bc5Snorm:
                     case Format.Bc5Unorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC5(result.Memory.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc5Snorm);
+                            return BCnDecoder.DecodeBC5(result.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc5Snorm);
                         }
                     case Format.Bc6HSfloat:
                     case Format.Bc6HUfloat:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC6(result.Memory.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc6HSfloat);
+                            return BCnDecoder.DecodeBC6(result.Span, width, height, sliceDepth, levels, layers, Format == Format.Bc6HSfloat);
                         }
                     case Format.Bc7Srgb:
                     case Format.Bc7Unorm:
                         using (result)
                         {
-                            return BCnDecoder.DecodeBC7(result.Memory.Span, width, height, sliceDepth, levels, layers);
+                            return BCnDecoder.DecodeBC7(result.Span, width, height, sliceDepth, levels, layers);
                         }
                 }
             }
@@ -899,7 +899,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             {
                 using (result)
                 {
-                    var converted = PixelConverter.ConvertR4G4ToR4G4B4A4(result.Memory.Span, width);
+                    var converted = PixelConverter.ConvertR4G4ToR4G4B4A4(result.Span, width);
 
                     if (_context.Capabilities.SupportsR4G4B4A4Format)
                     {
@@ -909,7 +909,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     {
                         using (converted)
                         {
-                            return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(converted.Memory.Span, width);
+                            return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(converted.Span, width);
                         }
                     }
                 }
@@ -920,7 +920,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                 {
                     using (result)
                     {
-                        return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(result.Memory.Span, width);
+                        return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(result.Span, width);
                     }
                 }
             }
@@ -932,24 +932,24 @@ namespace Ryujinx.Graphics.Gpu.Image
                     case Format.R5G6B5Unorm:
                         using (result)
                         {
-                            return PixelConverter.ConvertR5G6B5ToR8G8B8A8(result.Memory.Span, width);
+                            return PixelConverter.ConvertR5G6B5ToR8G8B8A8(result.Span, width);
                         }
                     case Format.B5G5R5A1Unorm:
                     case Format.R5G5B5X1Unorm:
                     case Format.R5G5B5A1Unorm:
                         using (result)
                         {
-                            return PixelConverter.ConvertR5G5B5ToR8G8B8A8(result.Memory.Span, width, Format == Format.R5G5B5X1Unorm);
+                            return PixelConverter.ConvertR5G5B5ToR8G8B8A8(result.Span, width, Format == Format.R5G5B5X1Unorm);
                         }
                     case Format.A1B5G5R5Unorm:
                         using (result)
                         {
-                            return PixelConverter.ConvertA1B5G5R5ToR8G8B8A8(result.Memory.Span, width);
+                            return PixelConverter.ConvertA1B5G5R5ToR8G8B8A8(result.Span, width);
                         }
                     case Format.R4G4B4A4Unorm:
                         using (result)
                         {
-                            return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(result.Memory.Span, width);
+                            return PixelConverter.ConvertR4G4B4A4ToR8G8B8A8(result.Span, width);
                         }
                 }
             }

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

@@ -17,7 +17,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <summary>
         /// For images, indicates the format specified on the shader.
         /// </summary>
-        public Format Format { get; }
+        public FormatInfo FormatInfo { get; }
 
         /// <summary>
         /// Shader texture host set index.
@@ -58,17 +58,17 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// Constructs the texture binding information structure.
         /// </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="formatInfo">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 set, int binding, int arrayLength, int cbufSlot, int handle, TextureUsageFlags flags)
+        public TextureBindingInfo(Target target, FormatInfo formatInfo, int set, int binding, int arrayLength, int cbufSlot, int handle, TextureUsageFlags flags)
         {
             Target = target;
-            Format = format;
+            FormatInfo = formatInfo;
             Set = set;
             Binding = binding;
             ArrayLength = arrayLength;
@@ -96,7 +96,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             int cbufSlot,
             int handle,
             TextureUsageFlags flags,
-            bool isSamplerOnly) : this(target, 0, set, binding, arrayLength, cbufSlot, handle, flags)
+            bool isSamplerOnly) : this(target, FormatInfo.Invalid, 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 ||
-                        (sampler == null && SamplerPool.IsValidId(samplerId) && !SamplerPool.GetDescriptorRef(samplerId).Equals(descriptor)))
+                    foreach ((int samplerId, (Sampler sampler, SamplerDescriptor descriptor)) in SamplerIds)
                     {
-                        return true;
+                        if (SamplerPool.GetCachedItem(samplerId) != sampler ||
+                            (sampler == null && SamplerPool.IsValidId(samplerId) && !SamplerPool.GetDescriptorRef(samplerId).Equals(descriptor)))
+                        {
+                            return true;
+                        }
                     }
                 }
 
@@ -656,7 +659,6 @@ namespace Ryujinx.Graphics.Gpu.Image
             int length = (isSampler ? samplerPool.MaximumId : texturePool.MaximumId) + 1;
             length = Math.Min(length, bindingInfo.ArrayLength);
 
-            Format[] formats = isImage ? new Format[bindingInfo.ArrayLength] : null;
             ISampler[] samplers = isImage ? null : new ISampler[bindingInfo.ArrayLength];
             ITexture[] textures = new ITexture[bindingInfo.ArrayLength];
 
@@ -671,7 +673,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                 }
                 else
                 {
-                    ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(index, out texture);
+                    ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(index, bindingInfo.FormatInfo, out texture);
 
                     if (texture != null)
                     {
@@ -694,8 +696,6 @@ namespace Ryujinx.Graphics.Gpu.Image
                 ITexture hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
                 ISampler hostSampler = sampler?.GetHostSampler(texture);
 
-                Format format = bindingInfo.Format;
-
                 if (hostTexture != null && texture.Target == Target.TextureBuffer)
                 {
                     // Ensure that the buffer texture is using the correct buffer as storage.
@@ -703,26 +703,15 @@ namespace Ryujinx.Graphics.Gpu.Image
                     // to ensure we're not using a old buffer that was already deleted.
                     if (isImage)
                     {
-                        if (format == 0 && texture != null)
-                        {
-                            format = texture.Format;
-                        }
-
-                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index);
                     }
                     else
                     {
-                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index);
                     }
                 }
                 else if (isImage)
                 {
-                    if (format == 0 && texture != null)
-                    {
-                        format = texture.Format;
-                    }
-
-                    formats[index] = format;
                     textures[index] = hostTexture;
                 }
                 else
@@ -734,7 +723,6 @@ namespace Ryujinx.Graphics.Gpu.Image
 
             if (isImage)
             {
-                entry.ImageArray.SetFormats(0, formats);
                 entry.ImageArray.SetImages(0, textures);
 
                 SetImageArray(stage, bindingInfo, entry.ImageArray);
@@ -860,7 +848,6 @@ namespace Ryujinx.Graphics.Gpu.Image
 
             entry.UpdateData(cachedTextureBuffer, cachedSamplerBuffer, separateSamplerBuffer);
 
-            Format[] formats = isImage ? new Format[bindingInfo.ArrayLength] : null;
             ISampler[] samplers = isImage ? null : new ISampler[bindingInfo.ArrayLength];
             ITexture[] textures = new ITexture[bindingInfo.ArrayLength];
 
@@ -880,7 +867,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     samplerId = TextureHandle.UnpackSamplerId(packedId);
                 }
 
-                ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(textureId, out Texture texture);
+                ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(textureId, bindingInfo.FormatInfo, out Texture texture);
 
                 if (texture != null)
                 {
@@ -899,15 +886,19 @@ 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;
 
-                Format format = bindingInfo.Format;
+                if (!isImage && bindingInfo.Target != Target.TextureBuffer)
+                {
+                    Sampler sampler = samplerPool?.Get(samplerId);
+
+                    entry.SamplerIds[samplerId] = (sampler, samplerPool?.GetDescriptorRef(samplerId) ?? default);
+
+                    hostSampler = sampler?.GetHostSampler(texture);
+                }
 
                 if (hostTexture != null && texture.Target == Target.TextureBuffer)
                 {
@@ -916,26 +907,15 @@ namespace Ryujinx.Graphics.Gpu.Image
                     // to ensure we're not using a old buffer that was already deleted.
                     if (isImage)
                     {
-                        if (format == 0 && texture != null)
-                        {
-                            format = texture.Format;
-                        }
-
-                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.ImageArray, hostTexture, texture.Range, bindingInfo, index);
                     }
                     else
                     {
-                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index, format);
+                        _channel.BufferManager.SetBufferTextureStorage(stage, entry.TextureArray, hostTexture, texture.Range, bindingInfo, index);
                     }
                 }
                 else if (isImage)
                 {
-                    if (format == 0 && texture != null)
-                    {
-                        format = texture.Format;
-                    }
-
-                    formats[index] = format;
                     textures[index] = hostTexture;
                 }
                 else
@@ -947,7 +927,6 @@ namespace Ryujinx.Graphics.Gpu.Image
 
             if (isImage)
             {
-                entry.ImageArray.SetFormats(0, formats);
                 entry.ImageArray.SetImages(0, textures);
 
                 SetImageArray(stage, bindingInfo, entry.ImageArray);

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

@@ -187,7 +187,9 @@ namespace Ryujinx.Graphics.Gpu.Image
         {
             (TexturePool texturePool, SamplerPool samplerPool) = GetPools();
 
-            return (texturePool.Get(textureId), samplerPool.Get(samplerId));
+            Sampler sampler = samplerPool?.Get(samplerId);
+
+            return (texturePool.Get(textureId, sampler?.IsSrgb ?? true), sampler);
         }
 
         /// <summary>
@@ -508,12 +510,12 @@ namespace Ryujinx.Graphics.Gpu.Image
                 state.TextureHandle = textureId;
                 state.SamplerHandle = samplerId;
 
-                ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(textureId, out Texture texture);
+                Sampler sampler = samplerPool?.Get(samplerId);
+
+                ref readonly TextureDescriptor descriptor = ref texturePool.GetForBinding(textureId, sampler?.IsSrgb ?? true, out Texture texture);
 
                 specStateMatches &= specState.MatchesTexture(stage, index, descriptor);
 
-                Sampler sampler = samplerPool?.Get(samplerId);
-
                 ITexture hostTexture = texture?.GetTargetTexture(bindingInfo.Target);
                 ISampler hostSampler = sampler?.GetHostSampler(texture);
 
@@ -522,7 +524,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     // Ensure that the buffer texture is using the correct buffer as storage.
                     // Buffers are frequently re-created to accommodate larger data, so we need to re-bind
                     // to ensure we're not using a old buffer that was already deleted.
-                    _channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range, bindingInfo, bindingInfo.Format, false);
+                    _channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range, bindingInfo, false);
 
                     // Cache is not used for buffer texture, it must always rebind.
                     state.CachedTexture = null;
@@ -616,6 +618,7 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                 if (!poolModified &&
                     state.TextureHandle == textureId &&
+                    state.ImageFormat == bindingInfo.FormatInfo.Format &&
                     state.CachedTexture != null &&
                     state.CachedTexture.InvalidatedSequence == state.InvalidatedSequence)
                 {
@@ -629,26 +632,22 @@ namespace Ryujinx.Graphics.Gpu.Image
                         cachedTexture.SignalModified();
                     }
 
-                    Format format = bindingInfo.Format == 0 ? cachedTexture.Format : bindingInfo.Format;
-
-                    if (state.ImageFormat != format ||
-                        ((usageFlags & TextureUsageFlags.NeedsScaleValue) != 0 &&
-                        UpdateScale(state.CachedTexture, usageFlags, scaleIndex, stage)))
+                    if ((usageFlags & TextureUsageFlags.NeedsScaleValue) != 0 && UpdateScale(state.CachedTexture, usageFlags, scaleIndex, stage))
                     {
                         ITexture hostTextureRebind = state.CachedTexture.GetTargetTexture(bindingInfo.Target);
 
                         state.Texture = hostTextureRebind;
-                        state.ImageFormat = format;
 
-                        _context.Renderer.Pipeline.SetImage(stage, bindingInfo.Binding, hostTextureRebind, format);
+                        _context.Renderer.Pipeline.SetImage(stage, bindingInfo.Binding, hostTextureRebind);
                     }
 
                     continue;
                 }
 
                 state.TextureHandle = textureId;
+                state.ImageFormat = bindingInfo.FormatInfo.Format;
 
-                ref readonly TextureDescriptor descriptor = ref pool.GetForBinding(textureId, out Texture texture);
+                ref readonly TextureDescriptor descriptor = ref pool.GetForBinding(textureId, bindingInfo.FormatInfo, out Texture texture);
 
                 specStateMatches &= specState.MatchesImage(stage, index, descriptor);
 
@@ -660,14 +659,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     // Buffers are frequently re-created to accommodate larger data, so we need to re-bind
                     // to ensure we're not using a old buffer that was already deleted.
 
-                    Format format = bindingInfo.Format;
-
-                    if (format == 0 && texture != null)
-                    {
-                        format = texture.Format;
-                    }
-
-                    _channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range, bindingInfo, format, true);
+                    _channel.BufferManager.SetBufferTextureStorage(stage, hostTexture, texture.Range, bindingInfo, true);
 
                     // Cache is not used for buffer texture, it must always rebind.
                     state.CachedTexture = null;
@@ -689,16 +681,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     {
                         state.Texture = hostTexture;
 
-                        Format format = bindingInfo.Format;
-
-                        if (format == 0 && texture != null)
-                        {
-                            format = texture.Format;
-                        }
-
-                        state.ImageFormat = format;
-
-                        _context.Renderer.Pipeline.SetImage(stage, bindingInfo.Binding, hostTexture, format);
+                        _context.Renderer.Pipeline.SetImage(stage, bindingInfo.Binding, hostTexture);
                     }
 
                     state.CachedTexture = texture;

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

@@ -68,6 +68,14 @@ namespace Ryujinx.Graphics.Gpu.Image
             _cache = new AutoDeleteCache();
         }
 
+        /// <summary>
+        /// Initializes the cache, setting the maximum texture capacity for the specified GPU context.
+        /// </summary>
+        public void Initialize()
+        {
+            _cache.Initialize(_context);
+        }
+
         /// <summary>
         /// Handles marking of textures written to a memory region being (partially) remapped.
         /// </summary>
@@ -347,6 +355,53 @@ namespace Ryujinx.Graphics.Gpu.Image
             return texture;
         }
 
+        /// <summary>
+        /// Tries to find an existing texture, or create a new one if not found.
+        /// </summary>
+        /// <param name="memoryManager">GPU memory manager where the texture is mapped</param>
+        /// <param name="formatInfo">Format of the texture</param>
+        /// <param name="gpuAddress">GPU virtual address of the texture</param>
+        /// <param name="xCount">Texture width in bytes</param>
+        /// <param name="yCount">Texture height</param>
+        /// <param name="stride">Texture stride if linear, otherwise ignored</param>
+        /// <param name="isLinear">Indicates if the texture is linear or block linear</param>
+        /// <param name="gobBlocksInY">GOB blocks in Y for block linear textures</param>
+        /// <param name="gobBlocksInZ">GOB blocks in Z for 3D block linear textures</param>
+        /// <returns>The texture</returns>
+        public Texture FindOrCreateTexture(
+            MemoryManager memoryManager,
+            FormatInfo formatInfo,
+            ulong gpuAddress,
+            int xCount,
+            int yCount,
+            int stride,
+            bool isLinear,
+            int gobBlocksInY,
+            int gobBlocksInZ)
+        {
+            TextureInfo info = new(
+                gpuAddress,
+                xCount / formatInfo.BytesPerPixel,
+                yCount,
+                1,
+                1,
+                1,
+                1,
+                stride,
+                isLinear,
+                gobBlocksInY,
+                gobBlocksInZ,
+                1,
+                Target.Texture2D,
+                formatInfo);
+
+            Texture texture = FindOrCreateTexture(memoryManager, TextureSearchFlags.ForCopy, info, 0, sizeHint: new Size(xCount, yCount, 1));
+
+            texture?.SynchronizeMemory();
+
+            return texture;
+        }
+
         /// <summary>
         /// Tries to find an existing texture, or create a new one if not found.
         /// </summary>
@@ -468,13 +523,11 @@ namespace Ryujinx.Graphics.Gpu.Image
             int gobBlocksInY = dsState.MemoryLayout.UnpackGobBlocksInY();
             int gobBlocksInZ = dsState.MemoryLayout.UnpackGobBlocksInZ();
 
+            layered &= size.UnpackIsLayered();
+
             Target target;
 
-            if (dsState.MemoryLayout.UnpackIsTarget3D())
-            {
-                target = Target.Texture3D;
-            }
-            else if ((samplesInX | samplesInY) != 1)
+            if ((samplesInX | samplesInY) != 1)
             {
                 target = size.Depth > 1 && layered
                     ? Target.Texture2DMultisampleArray

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

@@ -739,7 +739,8 @@ namespace Ryujinx.Graphics.Gpu.Image
             }
 
             return (lhsFormat.Format == Format.R8G8B8A8Unorm && rhsFormat.Format == Format.R32G32B32A32Float) ||
-                   (lhsFormat.Format == Format.R8Unorm && rhsFormat.Format == Format.R8G8B8A8Unorm);
+                   (lhsFormat.Format == Format.R8Unorm && rhsFormat.Format == Format.R8G8B8A8Unorm) ||
+                   (lhsFormat.Format == Format.R8Unorm && rhsFormat.Format == Format.R32Uint);
         }
 
         /// <summary>

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

@@ -1,3 +1,4 @@
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL;
 using Ryujinx.Graphics.Gpu.Memory;
 using Ryujinx.Graphics.Texture;
@@ -5,7 +6,6 @@ using Ryujinx.Memory;
 using Ryujinx.Memory.Range;
 using Ryujinx.Memory.Tracking;
 using System;
-using System.Buffers;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 
@@ -445,7 +445,7 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                             ReadOnlySpan<byte> data = dataSpan[(offset - spanBase)..];
 
-                            IMemoryOwner<byte> result = Storage.ConvertToHostCompatibleFormat(data, info.BaseLevel + level, true);
+                            MemoryOwner<byte> result = Storage.ConvertToHostCompatibleFormat(data, info.BaseLevel + level, true);
 
                             Storage.SetData(result, info.BaseLayer + layer, info.BaseLevel + level);
                         }

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
@@ -74,6 +75,76 @@ namespace Ryujinx.Graphics.Gpu.Image
         private readonly ConcurrentQueue<DereferenceRequest> _dereferenceQueue = new();
         private TextureDescriptor _defaultDescriptor;
 
+        /// <summary>
+        /// List of textures that shares the same memory region, but have different formats.
+        /// </summary>
+        private class TextureAliasList
+        {
+            /// <summary>
+            /// Alias texture.
+            /// </summary>
+            /// <param name="Format">Texture format</param>
+            /// <param name="Texture">Texture</param>
+            private readonly record struct Alias(Format Format, Texture Texture);
+
+            /// <summary>
+            /// List of texture aliases.
+            /// </summary>
+            private readonly List<Alias> _aliases;
+
+            /// <summary>
+            /// Creates a new instance of the texture alias list.
+            /// </summary>
+            public TextureAliasList()
+            {
+                _aliases = new List<Alias>();
+            }
+
+            /// <summary>
+            /// Adds a new texture alias.
+            /// </summary>
+            /// <param name="format">Alias format</param>
+            /// <param name="texture">Alias texture</param>
+            public void Add(Format format, Texture texture)
+            {
+                _aliases.Add(new Alias(format, texture));
+                texture.IncrementReferenceCount();
+            }
+
+            /// <summary>
+            /// Finds a texture with the requested format, or returns null if not found.
+            /// </summary>
+            /// <param name="format">Format to find</param>
+            /// <returns>Texture with the requested format, or null if not found</returns>
+            public Texture Find(Format format)
+            {
+                foreach (var alias in _aliases)
+                {
+                    if (alias.Format == format)
+                    {
+                        return alias.Texture;
+                    }
+                }
+
+                return null;
+            }
+
+            /// <summary>
+            /// Removes all alias textures.
+            /// </summary>
+            public void Destroy()
+            {
+                foreach (var entry in _aliases)
+                {
+                    entry.Texture.DecrementReferenceCount();
+                }
+
+                _aliases.Clear();
+            }
+        }
+
+        private readonly Dictionary<Texture, TextureAliasList> _aliasLists;
+
         /// <summary>
         /// Linked list node used on the texture pool cache.
         /// </summary>
@@ -94,6 +165,7 @@ namespace Ryujinx.Graphics.Gpu.Image
         public TexturePool(GpuContext context, GpuChannel channel, ulong address, int maximumId) : base(context, channel.MemoryManager.Physical, address, maximumId)
         {
             _channel = channel;
+            _aliasLists = new Dictionary<Texture, TextureAliasList>();
         }
 
         /// <summary>
@@ -114,14 +186,13 @@ namespace Ryujinx.Graphics.Gpu.Image
 
                 if (texture == null)
                 {
-                    TextureInfo info = GetInfo(descriptor, out int layerSize);
-
                     // The dereference queue can put our texture back on the cache.
                     if ((texture = ProcessDereferenceQueue(id)) != null)
                     {
                         return ref descriptor;
                     }
 
+                    TextureInfo info = GetInfo(descriptor, out int layerSize);
                     texture = PhysicalMemory.TextureCache.FindOrCreateTexture(_channel.MemoryManager, TextureSearchFlags.ForSampler, info, layerSize);
 
                     // If this happens, then the texture address is invalid, we can't add it to the cache.
@@ -156,6 +227,17 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="id">ID of the texture. This is effectively a zero-based index</param>
         /// <returns>The texture with the given ID</returns>
         public override Texture Get(int id)
+        {
+            return Get(id, srgbSampler: true);
+        }
+
+        /// <summary>
+        /// Gets the texture with the given ID.
+        /// </summary>
+        /// <param name="id">ID of the texture. This is effectively a zero-based index</param>
+        /// <param name="srgbSampler">Whether the texture is being accessed with a sampler that has sRGB conversion enabled</param>
+        /// <returns>The texture with the given ID</returns>
+        public Texture Get(int id, bool srgbSampler)
         {
             if ((uint)id >= Items.Length)
             {
@@ -169,7 +251,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                 SynchronizeMemory();
             }
 
-            GetInternal(id, out Texture texture);
+            GetForBinding(id, srgbSampler, out Texture texture);
 
             return texture;
         }
@@ -181,9 +263,10 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// This method assumes that the pool has been manually synchronized before doing binding.
         /// </remarks>
         /// <param name="id">ID of the texture. This is effectively a zero-based index</param>
+        /// <param name="srgbSampler">Whether the texture is being accessed with a sampler that has sRGB conversion enabled</param>
         /// <param name="texture">The texture with the given ID</param>
         /// <returns>The texture descriptor with the given ID</returns>
-        public ref readonly TextureDescriptor GetForBinding(int id, out Texture texture)
+        public ref readonly TextureDescriptor GetForBinding(int id, bool srgbSampler, out Texture texture)
         {
             if ((uint)id >= Items.Length)
             {
@@ -193,9 +276,66 @@ namespace Ryujinx.Graphics.Gpu.Image
 
             // When getting for binding, assume the pool has already been synchronized.
 
+            if (!srgbSampler)
+            {
+                // If the sampler does not have the sRGB bit enabled, then the texture can't use a sRGB format.
+                ref readonly TextureDescriptor tempDescriptor = ref GetDescriptorRef(id);
+
+                if (tempDescriptor.UnpackSrgb() && FormatTable.TryGetTextureFormat(tempDescriptor.UnpackFormat(), isSrgb: false, out FormatInfo formatInfo))
+                {
+                    // Get a view of the texture with the right format.
+                    return ref GetForBinding(id, formatInfo, out texture);
+                }
+            }
+
             return ref GetInternal(id, out texture);
         }
 
+        /// <summary>
+        /// Gets the texture descriptor and texture with the given ID.
+        /// </summary>
+        /// <remarks>
+        /// This method assumes that the pool has been manually synchronized before doing binding.
+        /// </remarks>
+        /// <param name="id">ID of the texture. This is effectively a zero-based index</param>
+        /// <param name="formatInfo">Texture format information</param>
+        /// <param name="texture">The texture with the given ID</param>
+        /// <returns>The texture descriptor with the given ID</returns>
+        public ref readonly TextureDescriptor GetForBinding(int id, FormatInfo formatInfo, out Texture texture)
+        {
+            if ((uint)id >= Items.Length)
+            {
+                texture = null;
+                return ref _defaultDescriptor;
+            }
+
+            ref readonly TextureDescriptor descriptor = ref GetInternal(id, out texture);
+
+            if (texture != null && formatInfo.Format != 0 && texture.Format != formatInfo.Format)
+            {
+                if (!_aliasLists.TryGetValue(texture, out TextureAliasList aliasList))
+                {
+                    _aliasLists.Add(texture, aliasList = new TextureAliasList());
+                }
+
+                texture = aliasList.Find(formatInfo.Format);
+
+                if (texture == null)
+                {
+                    TextureInfo info = GetInfo(descriptor, out int layerSize);
+                    info = ChangeFormat(info, formatInfo);
+                    texture = PhysicalMemory.TextureCache.FindOrCreateTexture(_channel.MemoryManager, TextureSearchFlags.ForSampler, info, layerSize);
+
+                    if (texture != null)
+                    {
+                        aliasList.Add(formatInfo.Format, texture);
+                    }
+                }
+            }
+
+            return ref descriptor;
+        }
+
         /// <summary>
         /// Checks if the pool was modified, and returns the last sequence number where a modification was detected.
         /// </summary>
@@ -233,6 +373,7 @@ namespace Ryujinx.Graphics.Gpu.Image
             else
             {
                 texture.DecrementReferenceCount();
+                RemoveAliasList(texture);
             }
         }
 
@@ -326,6 +467,8 @@ namespace Ryujinx.Graphics.Gpu.Image
                 {
                     texture.DecrementReferenceCount();
                 }
+
+                RemoveAliasList(texture);
             }
 
             return null;
@@ -368,6 +511,7 @@ namespace Ryujinx.Graphics.Gpu.Image
                     if (Interlocked.Exchange(ref Items[id], null) != null)
                     {
                         texture.DecrementReferenceCount(this, id);
+                        RemoveAliasList(texture);
                     }
                 }
             }
@@ -490,6 +634,8 @@ 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 +686,34 @@ 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.
@@ -591,6 +765,57 @@ namespace Ryujinx.Graphics.Gpu.Image
                    component == SwizzleComponent.Green;
         }
 
+        /// <summary>
+        /// Changes the format on the texture information structure, and also adjusts the width for the new format if needed.
+        /// </summary>
+        /// <param name="info">Texture information</param>
+        /// <param name="dstFormat">New format</param>
+        /// <returns>Texture information with the new format</returns>
+        private static TextureInfo ChangeFormat(in TextureInfo info, FormatInfo dstFormat)
+        {
+            int width = info.Width;
+
+            if (info.FormatInfo.BytesPerPixel != dstFormat.BytesPerPixel)
+            {
+                int stride = width * info.FormatInfo.BytesPerPixel;
+                width = stride / dstFormat.BytesPerPixel;
+            }
+
+            return new TextureInfo(
+                info.GpuAddress,
+                width,
+                info.Height,
+                info.DepthOrLayers,
+                info.Levels,
+                info.SamplesInX,
+                info.SamplesInY,
+                info.Stride,
+                info.IsLinear,
+                info.GobBlocksInY,
+                info.GobBlocksInZ,
+                info.GobBlocksInTileX,
+                info.Target,
+                dstFormat,
+                info.DepthStencilMode,
+                info.SwizzleR,
+                info.SwizzleG,
+                info.SwizzleB,
+                info.SwizzleA);
+        }
+
+        /// <summary>
+        /// Removes all aliases for a texture.
+        /// </summary>
+        /// <param name="texture">Texture to have the aliases removed</param>
+        private void RemoveAliasList(Texture texture)
+        {
+            if (_aliasLists.TryGetValue(texture, out TextureAliasList aliasList))
+            {
+                _aliasLists.Remove(texture);
+                aliasList.Destroy();
+            }
+        }
+
         /// <summary>
         /// Decrements the reference count of the texture.
         /// This indicates that the texture pool is not using it anymore.
@@ -598,7 +823,11 @@ namespace Ryujinx.Graphics.Gpu.Image
         /// <param name="item">The texture to be deleted</param>
         protected override void Delete(Texture item)
         {
-            item?.DecrementReferenceCount(this);
+            if (item != null)
+            {
+                item.DecrementReferenceCount(this);
+                RemoveAliasList(item);
+            }
         }
 
         public override void Dispose()

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

@@ -509,7 +509,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
 
                     if (binding.IsImage)
                     {
-                        _context.Renderer.Pipeline.SetImage(binding.Stage, binding.BindingInfo.Binding, binding.Texture, binding.Format);
+                        _context.Renderer.Pipeline.SetImage(binding.Stage, binding.BindingInfo.Binding, binding.Texture);
                     }
                     else
                     {
@@ -873,12 +873,11 @@ namespace Ryujinx.Graphics.Gpu.Memory
             ITexture texture,
             MultiRange range,
             TextureBindingInfo bindingInfo,
-            Format format,
             bool isImage)
         {
             _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
-            _bufferTextures.Add(new BufferTextureBinding(stage, texture, range, bindingInfo, format, isImage));
+            _bufferTextures.Add(new BufferTextureBinding(stage, texture, range, bindingInfo, isImage));
         }
 
         /// <summary>
@@ -897,12 +896,11 @@ namespace Ryujinx.Graphics.Gpu.Memory
             ITexture texture,
             MultiRange range,
             TextureBindingInfo bindingInfo,
-            int index,
-            Format format)
+            int index)
         {
             _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
-            _bufferTextureArrays.Add(new BufferTextureArrayBinding<ITextureArray>(array, texture, range, bindingInfo, index, format));
+            _bufferTextureArrays.Add(new BufferTextureArrayBinding<ITextureArray>(array, texture, range, bindingInfo, index));
         }
 
         /// <summary>
@@ -921,12 +919,11 @@ namespace Ryujinx.Graphics.Gpu.Memory
             ITexture texture,
             MultiRange range,
             TextureBindingInfo bindingInfo,
-            int index,
-            Format format)
+            int index)
         {
             _channel.MemoryManager.Physical.BufferCache.CreateBuffer(range, BufferStageUtils.TextureBuffer(stage, bindingInfo.Flags));
 
-            _bufferImageArrays.Add(new BufferTextureArrayBinding<IImageArray>(array, texture, range, bindingInfo, index, format));
+            _bufferImageArrays.Add(new BufferTextureArrayBinding<IImageArray>(array, texture, range, bindingInfo, index));
         }
 
         /// <summary>

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

@@ -34,33 +34,26 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         public int Index { get; }
 
-        /// <summary>
-        /// The image format for the binding.
-        /// </summary>
-        public Format Format { get; }
-
         /// <summary>
         /// Create a new buffer texture binding.
         /// </summary>
+        /// <param name="array">Array</param>
         /// <param name="texture">Buffer texture</param>
         /// <param name="range">Physical ranges of memory where the buffer texture data is located</param>
         /// <param name="bindingInfo">Binding info</param>
         /// <param name="index">Index of the binding on the array</param>
-        /// <param name="format">Binding format</param>
         public BufferTextureArrayBinding(
             T array,
             ITexture texture,
             MultiRange range,
             TextureBindingInfo bindingInfo,
-            int index,
-            Format format)
+            int index)
         {
             Array = array;
             Texture = texture;
             Range = range;
             BindingInfo = bindingInfo;
             Index = index;
-            Format = format;
         }
     }
 }

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

@@ -30,11 +30,6 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// </summary>
         public TextureBindingInfo BindingInfo { get; }
 
-        /// <summary>
-        /// The image format for the binding.
-        /// </summary>
-        public Format Format { get; }
-
         /// <summary>
         /// Whether the binding is for an image or a sampler.
         /// </summary>
@@ -47,21 +42,18 @@ namespace Ryujinx.Graphics.Gpu.Memory
         /// <param name="texture">Buffer texture</param>
         /// <param name="range">Physical ranges of memory where the buffer texture data is located</param>
         /// <param name="bindingInfo">Binding info</param>
-        /// <param name="format">Binding format</param>
         /// <param name="isImage">Whether the binding is for an image or a sampler</param>
         public BufferTextureBinding(
             ShaderStage stage,
             ITexture texture,
             MultiRange range,
             TextureBindingInfo bindingInfo,
-            Format format,
             bool isImage)
         {
             Stage = stage;
             Texture = texture;
             Range = range;
             BindingInfo = bindingInfo;
-            Format = format;
             IsImage = isImage;
         }
     }

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

@@ -1,8 +1,8 @@
 using Ryujinx.Common.Memory;
+using Ryujinx.Graphics.Gpu.Image;
 using Ryujinx.Memory;
 using Ryujinx.Memory.Range;
 using System;
-using System.Buffers;
 using System.Collections.Generic;
 using System.Runtime.CompilerServices;
 using System.Runtime.InteropServices;
@@ -65,6 +65,7 @@ namespace Ryujinx.Graphics.Gpu.Memory
             MemoryUnmapped += Physical.BufferCache.MemoryUnmappedHandler;
             MemoryUnmapped += VirtualRangeCache.MemoryUnmappedHandler;
             MemoryUnmapped += CounterCache.MemoryUnmappedHandler;
+            Physical.TextureCache.Initialize();
         }
 
         /// <summary>
@@ -242,9 +243,9 @@ 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

@@ -86,11 +86,11 @@ namespace Ryujinx.Graphics.Gpu.Shader
                 ImageBindings[i] = stage.Info.Images.Select(descriptor =>
                 {
                     Target target = ShaderTexture.GetTarget(descriptor.Type);
-                    Format format = ShaderTexture.GetFormat(descriptor.Format);
+                    FormatInfo formatInfo = ShaderTexture.GetFormatInfo(descriptor.Format);
 
                     var result = new TextureBindingInfo(
                         target,
-                        format,
+                        formatInfo,
                         descriptor.Set,
                         descriptor.Binding,
                         descriptor.ArrayLength,

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 = 6921;
+        private const uint CodeGenVersion = 7353;
 
         private const string SharedTocFileName = "shared.toc";
         private const string SharedDataFileName = "shared.data";

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

@@ -78,9 +78,9 @@ namespace Ryujinx.Graphics.Gpu.Shader
             ResourceStages stages = vertexAsCompute ? ResourceStages.Compute | ResourceStages.Vertex : VtgStages;
 
             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.BufferImage, imageSetIndex, 0, rrc.ReservedImages);
+            PopulateDescriptorAndUsages(stages, ResourceType.BufferImage, imageSetIndex, 0, rrc.ReservedImages, true);
         }
 
         /// <summary>
@@ -91,10 +91,11 @@ namespace Ryujinx.Graphics.Gpu.Shader
         /// <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>
-        private void PopulateDescriptorAndUsages(ResourceStages stages, ResourceType type, int setIndex, int start, int count)
+        /// <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>
@@ -216,11 +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));
             }
         }
 
@@ -238,7 +240,8 @@ namespace Ryujinx.Graphics.Gpu.Shader
                     buffer.Binding,
                     1,
                     isStorage ? ResourceType.StorageBuffer : ResourceType.UniformBuffer,
-                    stages));
+                    stages,
+                    buffer.Flags.HasFlag(BufferUsageFlags.Write)));
             }
         }
 
@@ -254,7 +257,12 @@ namespace Ryujinx.Graphics.Gpu.Shader
             {
                 ResourceType type = GetTextureResourceType(texture, isImage);
 
-                GetUsages(texture.Set).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)));
             }
         }
 

src/Ryujinx.Graphics.Gpu/Window.cs

@@ -131,7 +131,7 @@ namespace Ryujinx.Graphics.Gpu
             bool isLinear,
             int gobBlocksInY,
             Format format,
-            int bytesPerPixel,
+            byte bytesPerPixel,
             ImageCrop crop,
             Action<GpuContext, object> acquireCallback,
             Action<object> releaseCallback,

src/Ryujinx.Graphics.OpenGL/Effects/AreaScalingFilter.cs

@@ -0,0 +1,106 @@
+using OpenTK.Graphics.OpenGL;
+using Ryujinx.Common;
+using Ryujinx.Graphics.GAL;
+using Ryujinx.Graphics.OpenGL.Image;
+using System;
+using static Ryujinx.Graphics.OpenGL.Effects.ShaderHelper;
+
+namespace Ryujinx.Graphics.OpenGL.Effects
+{
+    internal class AreaScalingFilter : IScalingFilter
+    {
+        private readonly OpenGLRenderer _renderer;
+        private int _inputUniform;
+        private int _outputUniform;
+        private int _srcX0Uniform;
+        private int _srcX1Uniform;
+        private int _srcY0Uniform;
+        private int _scalingShaderProgram;
+        private int _srcY1Uniform;
+        private int _dstX0Uniform;
+        private int _dstX1Uniform;
+        private int _dstY0Uniform;
+        private int _dstY1Uniform;
+
+        public float Level { get; set; }
+
+        public AreaScalingFilter(OpenGLRenderer renderer)
+        {
+            Initialize();
+
+            _renderer = renderer;
+        }
+
+        public void Dispose()
+        {
+            if (_scalingShaderProgram != 0)
+            {
+                GL.DeleteProgram(_scalingShaderProgram);
+            }
+        }
+
+        private void Initialize()
+        {
+            var scalingShader = EmbeddedResources.ReadAllText("Ryujinx.Graphics.OpenGL/Effects/Shaders/area_scaling.glsl");
+
+            _scalingShaderProgram = CompileProgram(scalingShader, ShaderType.ComputeShader);
+
+            _inputUniform = GL.GetUniformLocation(_scalingShaderProgram, "Source");
+            _outputUniform = GL.GetUniformLocation(_scalingShaderProgram, "imgOutput");
+
+            _srcX0Uniform = GL.GetUniformLocation(_scalingShaderProgram, "srcX0");
+            _srcX1Uniform = GL.GetUniformLocation(_scalingShaderProgram, "srcX1");
+            _srcY0Uniform = GL.GetUniformLocation(_scalingShaderProgram, "srcY0");
+            _srcY1Uniform = GL.GetUniformLocation(_scalingShaderProgram, "srcY1");
+            _dstX0Uniform = GL.GetUniformLocation(_scalingShaderProgram, "dstX0");
+            _dstX1Uniform = GL.GetUniformLocation(_scalingShaderProgram, "dstX1");
+            _dstY0Uniform = GL.GetUniformLocation(_scalingShaderProgram, "dstY0");
+            _dstY1Uniform = GL.GetUniformLocation(_scalingShaderProgram, "dstY1");
+        }
+
+        public void Run(
+            TextureView view,
+            TextureView destinationTexture,
+            int width,
+            int height,
+            Extents2D source,
+            Extents2D destination)
+        {
+            int previousProgram = GL.GetInteger(GetPName.CurrentProgram);
+            int previousUnit = GL.GetInteger(GetPName.ActiveTexture);
+            GL.ActiveTexture(TextureUnit.Texture0);
+            int previousTextureBinding = GL.GetInteger(GetPName.TextureBinding2D);
+
+            GL.BindImageTexture(0, destinationTexture.Handle, 0, false, 0, TextureAccess.ReadWrite, SizedInternalFormat.Rgba8);
+
+            int threadGroupWorkRegionDim = 16;
+            int dispatchX = (width + (threadGroupWorkRegionDim - 1)) / threadGroupWorkRegionDim;
+            int dispatchY = (height + (threadGroupWorkRegionDim - 1)) / threadGroupWorkRegionDim;
+
+            // Scaling pass
+            GL.UseProgram(_scalingShaderProgram);
+            view.Bind(0);
+            GL.Uniform1(_inputUniform, 0);
+            GL.Uniform1(_outputUniform, 0);
+            GL.Uniform1(_srcX0Uniform, (float)source.X1);
+            GL.Uniform1(_srcX1Uniform, (float)source.X2);
+            GL.Uniform1(_srcY0Uniform, (float)source.Y1);
+            GL.Uniform1(_srcY1Uniform, (float)source.Y2);
+            GL.Uniform1(_dstX0Uniform, (float)destination.X1);
+            GL.Uniform1(_dstX1Uniform, (float)destination.X2);
+            GL.Uniform1(_dstY0Uniform, (float)destination.Y1);
+            GL.Uniform1(_dstY1Uniform, (float)destination.Y2);
+            GL.DispatchCompute(dispatchX, dispatchY, 1);
+
+            GL.UseProgram(previousProgram);
+            GL.MemoryBarrier(MemoryBarrierFlags.ShaderImageAccessBarrierBit);
+
+            (_renderer.Pipeline as Pipeline).RestoreImages1And2();
+
+            GL.ActiveTexture(TextureUnit.Texture0);
+            GL.BindTexture(TextureTarget.Texture2D, previousTextureBinding);
+
+            GL.ActiveTexture((TextureUnit)previousUnit);
+        }
+    }
+}

src/Ryujinx.Graphics.OpenGL/Effects/FsrScalingFilter.cs

@@ -18,7 +18,7 @@ namespace Ryujinx.Graphics.OpenGL.Effects
         private int _srcY0Uniform;
         private int _scalingShaderProgram;
         private int _sharpeningShaderProgram;
-        private float _scale = 1;
+        private float _sharpeningLevel = 1;
         private int _srcY1Uniform;
         private int _dstX0Uniform;
         private int _dstX1Uniform;
@@ -30,10 +30,10 @@ namespace Ryujinx.Graphics.OpenGL.Effects
 
         public float Level
         {
-            get => _scale;
+            get => _sharpeningLevel;
             set
             {
-                _scale = MathF.Max(0.01f, value);
+                _sharpeningLevel = MathF.Max(0.01f, value);
             }
         }
 

src/Ryujinx.Graphics.OpenGL/Effects/ShaderHelper.cs

@@ -1,4 +1,5 @@
 using OpenTK.Graphics.OpenGL;
+using Ryujinx.Common.Logging;
 
 namespace Ryujinx.Graphics.OpenGL.Effects
 {
@@ -6,18 +7,7 @@ namespace Ryujinx.Graphics.OpenGL.Effects
     {
         public static int CompileProgram(string shaderCode, ShaderType shaderType)
         {
-            var shader = GL.CreateShader(shaderType);
-            GL.ShaderSource(shader, shaderCode);
-            GL.CompileShader(shader);
-
-            var program = GL.CreateProgram();
-            GL.AttachShader(program, shader);
-            GL.LinkProgram(program);
-
-            GL.DetachShader(program, shader);
-            GL.DeleteShader(shader);
-
-            return program;
+            return CompileProgram(new string[] { shaderCode }, shaderType);
         }
 
         public static int CompileProgram(string[] shaders, ShaderType shaderType)
@@ -26,6 +16,15 @@ namespace Ryujinx.Graphics.OpenGL.Effects
             GL.ShaderSource(shader, shaders.Length, shaders, (int[])null);
             GL.CompileShader(shader);
 
+            GL.GetShader(shader, ShaderParameter.CompileStatus, out int isCompiled);
+            if (isCompiled == 0)
+            {
+                string log = GL.GetShaderInfoLog(shader);
+                Logger.Error?.Print(LogClass.Gpu, $"Failed to compile effect shader:\n\n{log}\n");
+                GL.DeleteShader(shader);
+                return 0;
+            }
+
             var program = GL.CreateProgram();
             GL.AttachShader(program, shader);
             GL.LinkProgram(program);

src/Ryujinx.Graphics.OpenGL/Effects/Shaders/area_scaling.glsl

@@ -0,0 +1,119 @@
+#version 430 core
+precision mediump float;
+layout (local_size_x = 16, local_size_y = 16) in;
+layout(rgba8, binding = 0, location=0) uniform image2D imgOutput;
+layout( location=1 ) uniform sampler2D Source;
+layout( location=2 ) uniform float srcX0;
+layout( location=3 ) uniform float srcX1;
+layout( location=4 ) uniform float srcY0;
+layout( location=5 ) uniform float srcY1;
+layout( location=6 ) uniform float dstX0;
+layout( location=7 ) uniform float dstX1;
+layout( location=8 ) uniform float dstY0;
+layout( location=9 ) uniform float dstY1;
+
+/***** Area Sampling *****/
+
+// By Sam Belliveau and Filippo Tarpini. Public Domain license.
+// Effectively a more accurate sharp bilinear filter when upscaling,
+// that also works as a mathematically perfect downscale filter.
+// https://entropymine.com/imageworsener/pixelmixing/
+// https://github.com/obsproject/obs-studio/pull/1715
+// https://legacy.imagemagick.org/Usage/filter/
+vec4 AreaSampling(vec2 xy)
+{
+    // Determine the sizes of the source and target images.
+    vec2 source_size = vec2(abs(srcX1 - srcX0), abs(srcY1 - srcY0));
+    vec2 target_size = vec2(abs(dstX1 - dstX0), abs(dstY1 - dstY0));
+    vec2 inverted_target_size = vec2(1.0) / target_size;
+
+    // Compute the top-left and bottom-right corners of the target pixel box.
+    vec2 t_beg = floor(xy - vec2(dstX0 < dstX1 ? dstX0 : dstX1, dstY0 < dstY1 ? dstY0 : dstY1));
+    vec2 t_end = t_beg + vec2(1.0, 1.0);
+
+    // Convert the target pixel box to source pixel box.
+    vec2 beg = t_beg * inverted_target_size * source_size;
+    vec2 end = t_end * inverted_target_size * source_size;
+
+    // Compute the top-left and bottom-right corners of the pixel box.
+    ivec2 f_beg = ivec2(beg);
+    ivec2 f_end = ivec2(end);
+
+    // Compute how much of the start and end pixels are covered horizontally & vertically.
+    float area_w = 1.0 - fract(beg.x);
+    float area_n = 1.0 - fract(beg.y);
+    float area_e = fract(end.x);
+    float area_s = fract(end.y);
+
+    // Compute the areas of the corner pixels in the pixel box.
+    float area_nw = area_n * area_w;
+    float area_ne = area_n * area_e;
+    float area_sw = area_s * area_w;
+    float area_se = area_s * area_e;
+
+    // Initialize the color accumulator.
+    vec4 avg_color = vec4(0.0, 0.0, 0.0, 0.0);
+
+    // Accumulate corner pixels.
+    avg_color += area_nw * texelFetch(Source, ivec2(f_beg.x, f_beg.y), 0);
+    avg_color += area_ne * texelFetch(Source, ivec2(f_end.x, f_beg.y), 0);
+    avg_color += area_sw * texelFetch(Source, ivec2(f_beg.x, f_end.y), 0);
+    avg_color += area_se * texelFetch(Source, ivec2(f_end.x, f_end.y), 0);
+
+    // Determine the size of the pixel box.
+    int x_range = int(f_end.x - f_beg.x - 0.5);
+    int y_range = int(f_end.y - f_beg.y - 0.5);
+
+    // Accumulate top and bottom edge pixels.
+    for (int x = f_beg.x + 1; x <= f_beg.x + x_range; ++x)
+    {
+        avg_color += area_n * texelFetch(Source, ivec2(x, f_beg.y), 0);
+        avg_color += area_s * texelFetch(Source, ivec2(x, f_end.y), 0);
+    }
+
+    // Accumulate left and right edge pixels and all the pixels in between.
+    for (int y = f_beg.y + 1; y <= f_beg.y + y_range; ++y)
+    {
+        avg_color += area_w * texelFetch(Source, ivec2(f_beg.x, y), 0);
+        avg_color += area_e * texelFetch(Source, ivec2(f_end.x, y), 0);
+
+        for (int x = f_beg.x + 1; x <= f_beg.x + x_range; ++x)
+        {
+            avg_color += texelFetch(Source, ivec2(x, y), 0);
+        }
+    }
+
+    // Compute the area of the pixel box that was sampled.
+    float area_corners = area_nw + area_ne + area_sw + area_se;
+    float area_edges = float(x_range) * (area_n + area_s) + float(y_range) * (area_w + area_e);
+    float area_center = float(x_range) * float(y_range);
+
+    // Return the normalized average color.
+    return avg_color / (area_corners + area_edges + area_center);
+}
+
+float insideBox(vec2 v, vec2 bLeft, vec2 tRight) {
+    vec2 s = step(bLeft, v) - step(tRight, v);
+    return s.x * s.y;
+}
+
+vec2 translateDest(vec2 pos) {
+    vec2 translatedPos = vec2(pos.x, pos.y);
+    translatedPos.x = dstX1 < dstX0 ? dstX1 - translatedPos.x : translatedPos.x;
+    translatedPos.y = dstY0 > dstY1 ? dstY0 + dstY1 - translatedPos.y - 1 : translatedPos.y;
+    return translatedPos;
+}
+
+void main()
+{
+    vec2 bLeft = vec2(dstX0 < dstX1 ? dstX0 : dstX1, dstY0 < dstY1 ? dstY0 : dstY1);
+    vec2 tRight = vec2(dstX1 > dstX0 ? dstX1 : dstX0, dstY1 > dstY0 ? dstY1 : dstY0);
+    ivec2 loc = ivec2(gl_GlobalInvocationID.x, gl_GlobalInvocationID.y);
+    if (insideBox(loc, bLeft, tRight) == 0) {
+        imageStore(imgOutput, loc, vec4(0, 0, 0, 1));
+        return;
+    }
+
+    vec4 outColor = AreaSampling(loc);
+    imageStore(imgOutput, ivec2(translateDest(loc)), vec4(outColor.rgb, 1));
+}

src/Ryujinx.Graphics.OpenGL/Effects/Shaders/fsr_scaling.glsl

@@ -85,4 +85,4 @@ void main() {
     CurrFilter(gxy);
     gxy.x -= 8u;
     CurrFilter(gxy);
-}
+}

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

@@ -1,6 +1,5 @@
 using OpenTK.Graphics.OpenGL;
 using Ryujinx.Graphics.GAL;
-using System;
 
 namespace Ryujinx.Graphics.OpenGL.Image
 {
@@ -19,14 +18,6 @@ namespace Ryujinx.Graphics.OpenGL.Image
             _images = new TextureRef[size];
         }
 
-        public void SetFormats(int index, GAL.Format[] imageFormats)
-        {
-            for (int i = 0; i < imageFormats.Length; i++)
-            {
-                _images[index + i].Format = imageFormats[i];
-            }
-        }
-
         public void SetImages(int index, ITexture[] images)
         {
             for (int i = 0; i < images.Length; i++)
@@ -36,6 +27,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
                 if (image is TextureBase imageBase)
                 {
                     _images[index + i].Handle = imageBase.Handle;
+                    _images[index + i].Format = imageBase.Format;
                 }
                 else
                 {

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

@@ -1,7 +1,7 @@
 using OpenTK.Graphics.OpenGL;
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL;
 using System;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.OpenGL.Image
 {
@@ -55,9 +55,9 @@ namespace Ryujinx.Graphics.OpenGL.Image
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data)
+        public void SetData(MemoryOwner<byte> data)
         {
-            var dataSpan = data.Memory.Span;
+            var dataSpan = data.Span;
 
             Buffer.SetData(_buffer, _bufferOffset, dataSpan[..Math.Min(dataSpan.Length, _bufferSize)]);
 
@@ -65,13 +65,13 @@ namespace Ryujinx.Graphics.OpenGL.Image
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level)
+        public void SetData(MemoryOwner<byte> data, int layer, int level)
         {
             throw new NotSupportedException();
         }
 
         /// <inheritdoc/>
-        public void SetData(IMemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
+        public void SetData(MemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
         {
             throw new NotSupportedException();
         }

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

@@ -1,8 +1,8 @@
 using OpenTK.Graphics.OpenGL;
 using Ryujinx.Common;
+using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.GAL;
 using System;
-using System.Buffers;
 using System.Diagnostics;
 
 namespace Ryujinx.Graphics.OpenGL.Image
@@ -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++)
             {
@@ -448,13 +448,13 @@ namespace Ryujinx.Graphics.OpenGL.Image
             }
         }
 
-        public void SetData(IMemoryOwner<byte> data)
+        public void SetData(MemoryOwner<byte> data)
         {
             using (data = EnsureDataFormat(data))
             {
                 unsafe
                 {
-                    var dataSpan = data.Memory.Span;
+                    var dataSpan = data.Span;
                     fixed (byte* ptr = dataSpan)
                     {
                         ReadFrom((IntPtr)ptr, dataSpan.Length);
@@ -463,13 +463,13 @@ namespace Ryujinx.Graphics.OpenGL.Image
             }
         }
 
-        public void SetData(IMemoryOwner<byte> data, int layer, int level)
+        public void SetData(MemoryOwner<byte> data, int layer, int level)
         {
             using (data = EnsureDataFormat(data))
             {
                 unsafe
                 {
-                    fixed (byte* ptr = data.Memory.Span)
+                    fixed (byte* ptr = data.Span)
                     {
                         int width = Math.Max(Info.Width >> level, 1);
                         int height = Math.Max(Info.Height >> level, 1);
@@ -480,7 +480,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
             }
         }
 
-        public void SetData(IMemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
+        public void SetData(MemoryOwner<byte> data, int layer, int level, Rectangle<int> region)
         {
             using (data = EnsureDataFormat(data))
             {
@@ -489,7 +489,7 @@ namespace Ryujinx.Graphics.OpenGL.Image
 
                 unsafe
                 {
-                    fixed (byte* ptr = data.Memory.Span)
+                    fixed (byte* ptr = data.Span)
                     {
                         ReadFrom2D(
                             (IntPtr)ptr,
@@ -522,13 +522,13 @@ namespace Ryujinx.Graphics.OpenGL.Image
             ReadFrom2D(data, layer, level, x, y, width, height, mipSize);
         }
 
-        private IMemoryOwner<byte> EnsureDataFormat(IMemoryOwner<byte> data)
+        private MemoryOwner<byte> EnsureDataFormat(MemoryOwner<byte> data)
         {
             if (Format == Format.S8UintD24Unorm)
             {
                 using (data)
                 {
-                    return FormatConverter.ConvertS8D24ToD24S8(data.Memory.Span);
+                    return FormatConverter.ConvertS8D24ToD24S8(data.Span);
                 }
             }
 
@@ -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

@@ -202,7 +202,8 @@ namespace Ryujinx.Graphics.OpenGL
                 shaderSubgroupSize: Constants.MaxSubgroupSize,
                 storageBufferOffsetAlignment: HwCapabilities.StorageBufferOffsetAlignment,
                 textureBufferOffsetAlignment: HwCapabilities.TextureBufferOffsetAlignment,
-                gatherBiasPrecision: intelWindows || amdWindows ? 8 : 0); // Precision is 8 for these vendors on Vulkan.
+                gatherBiasPrecision: intelWindows || amdWindows ? 8 : 0, // Precision is 8 for these vendors on Vulkan.
+                maximumGpuMemory: 0);
         }
 
         public void SetBufferData(BufferHandle buffer, int offset, ReadOnlySpan<byte> data)

src/Ryujinx.Graphics.OpenGL/Pipeline.cs

@@ -45,7 +45,7 @@ namespace Ryujinx.Graphics.OpenGL
 
         private readonly Vector4<int>[] _fpIsBgra = new Vector4<int>[SupportBuffer.FragmentIsBgraCount];
 
-        private readonly (TextureBase, Format)[] _images;
+        private readonly TextureBase[] _images;
         private TextureBase _unit0Texture;
         private Sampler _unit0Sampler;
 
@@ -78,7 +78,7 @@ namespace Ryujinx.Graphics.OpenGL
             _fragmentOutputMap = uint.MaxValue;
             _componentMasks = uint.MaxValue;
 
-            _images = new (TextureBase, Format)[SavedImages];
+            _images = new TextureBase[SavedImages];
 
             _tfbs = new BufferHandle[Constants.MaxTransformFeedbackBuffers];
             _tfbTargets = new BufferRange[Constants.MaxTransformFeedbackBuffers];
@@ -935,11 +935,11 @@ namespace Ryujinx.Graphics.OpenGL
             SetFrontFace(_frontFace = frontFace.Convert());
         }
 
-        public void SetImage(ShaderStage stage, int binding, ITexture texture, Format imageFormat)
+        public void SetImage(ShaderStage stage, int binding, ITexture texture)
         {
             if ((uint)binding < SavedImages)
             {
-                _images[binding] = (texture as TextureBase, imageFormat);
+                _images[binding] = texture as TextureBase;
             }
 
             if (texture == null)
@@ -950,7 +950,7 @@ namespace Ryujinx.Graphics.OpenGL
 
             TextureBase texBase = (TextureBase)texture;
 
-            SizedInternalFormat format = FormatTable.GetImageFormat(imageFormat);
+            SizedInternalFormat format = FormatTable.GetImageFormat(texBase.Format);
 
             if (format != 0)
             {
@@ -1622,11 +1622,11 @@ namespace Ryujinx.Graphics.OpenGL
         {
             for (int i = 0; i < SavedImages; i++)
             {
-                (TextureBase texBase, Format imageFormat) = _images[i];
+                TextureBase texBase = _images[i];
 
                 if (texBase != null)
                 {
-                    SizedInternalFormat format = FormatTable.GetImageFormat(imageFormat);
+                    SizedInternalFormat format = FormatTable.GetImageFormat(texBase.Format);
 
                     if (format != 0)
                     {

src/Ryujinx.Graphics.OpenGL/Ryujinx.Graphics.OpenGL.csproj

@@ -21,6 +21,7 @@
     <EmbeddedResource Include="Effects\Shaders\ffx_fsr1.h" />
     <EmbeddedResource Include="Effects\Shaders\ffx_a.h" />
     <EmbeddedResource Include="Effects\Shaders\fsr_scaling.glsl" />
+    <EmbeddedResource Include="Effects\Shaders\area_scaling.glsl" />
   </ItemGroup>
 
   <ItemGroup>

src/Ryujinx.Graphics.OpenGL/Window.cs

@@ -373,6 +373,16 @@ namespace Ryujinx.Graphics.OpenGL
                         _isLinear = false;
                         _scalingFilter.Level = _scalingFilterLevel;
 
+                        RecreateUpscalingTexture();
+                        break;
+                    case ScalingFilter.Area:
+                        if (_scalingFilter is not AreaScalingFilter)
+                        {
+                            _scalingFilter?.Dispose();
+                            _scalingFilter = new AreaScalingFilter(_renderer);
+                        }
+                        _isLinear = false;
+
                         RecreateUpscalingTexture();
                         break;
                 }

src/Ryujinx.Graphics.Shader/Instructions/InstEmitMemory.cs

@@ -222,30 +222,14 @@ namespace Ryujinx.Graphics.Shader.Instructions
                         context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
                     }
                     break;
-                case AtomOp.And:
-                    if (type == AtomSize.S32 || type == AtomSize.U32)
+                case AtomOp.Min:
+                    if (type == AtomSize.S32)
                     {
-                        res = context.AtomicAnd(storageKind, e0, e1, value);
+                        res = context.AtomicMinS32(storageKind, e0, e1, value);
                     }
-                    else
+                    else if (type == AtomSize.U32)
                     {
-                        context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
-                    }
-                    break;
-                case AtomOp.Xor:
-                    if (type == AtomSize.S32 || type == AtomSize.U32)
-                    {
-                        res = context.AtomicXor(storageKind, e0, e1, value);
-                    }
-                    else
-                    {
-                        context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
-                    }
-                    break;
-                case AtomOp.Or:
-                    if (type == AtomSize.S32 || type == AtomSize.U32)
-                    {
-                        res = context.AtomicOr(storageKind, e0, e1, value);
+                        res = context.AtomicMinU32(storageKind, e0, e1, value);
                     }
                     else
                     {
@@ -266,20 +250,49 @@ namespace Ryujinx.Graphics.Shader.Instructions
                         context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
                     }
                     break;
-                case AtomOp.Min:
-                    if (type == AtomSize.S32)
+                case AtomOp.And:
+                    if (type == AtomSize.S32 || type == AtomSize.U32)
                     {
-                        res = context.AtomicMinS32(storageKind, e0, e1, value);
-                    }
-                    else if (type == AtomSize.U32)
-                    {
-                        res = context.AtomicMinU32(storageKind, e0, e1, value);
+                        res = context.AtomicAnd(storageKind, e0, e1, value);
                     }
                     else
                     {
                         context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
                     }
                     break;
+                case AtomOp.Or:
+                    if (type == AtomSize.S32 || type == AtomSize.U32)
+                    {
+                        res = context.AtomicOr(storageKind, e0, e1, value);
+                    }
+                    else
+                    {
+                        context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
+                    }
+                    break;
+                case AtomOp.Xor:
+                    if (type == AtomSize.S32 || type == AtomSize.U32)
+                    {
+                        res = context.AtomicXor(storageKind, e0, e1, value);
+                    }
+                    else
+                    {
+                        context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
+                    }
+                    break;
+                case AtomOp.Exch:
+                    if (type == AtomSize.S32 || type == AtomSize.U32)
+                    {
+                        res = context.AtomicSwap(storageKind, e0, e1, value);
+                    }
+                    else
+                    {
+                        context.TranslatorContext.GpuAccessor.Log($"Invalid reduction type: {type}.");
+                    }
+                    break;
+                default:
+                    context.TranslatorContext.GpuAccessor.Log($"Invalid atomic operation: {op}.");
+                    break;
             }
 
             return res;

src/Ryujinx.Graphics.Shader/Translation/Optimizations/Utils.cs

@@ -138,6 +138,8 @@ namespace Ryujinx.Graphics.Shader.Translation.Optimizations
                 // Ensure that conditions met for that branch are also met for the current one.
                 // Prefer the latest sources for the phi node.
 
+                int undefCount = 0;
+
                 for (int i = phiNode.SourcesCount - 1; i >= 0; i--)
                 {
                     BasicBlock phiBlock = phiNode.GetBlock(i);
@@ -159,6 +161,26 @@ namespace Ryujinx.Graphics.Shader.Translation.Optimizations
                             return match;
                         }
                     }
+                    else if (phiSource.Type == OperandType.Undefined)
+                    {
+                        undefCount++;
+                    }
+                }
+
+                // If all sources but one are undefined, we can assume that the one
+                // that is not undefined is the right one.
+
+                if (undefCount == phiNode.SourcesCount - 1)
+                {
+                    for (int i = phiNode.SourcesCount - 1; i >= 0; i--)
+                    {
+                        Operand phiSource = phiNode.GetSource(i);
+
+                        if (phiSource.Type != OperandType.Undefined)
+                        {
+                            return phiSource;
+                        }
+                    }
                 }
             }
 

src/Ryujinx.Graphics.Shader/Translation/RegisterUsage.cs

@@ -155,9 +155,14 @@ namespace Ryujinx.Graphics.Shader.Translation
                         localInputs[block.Index] |= GetMask(register) & ~localOutputs[block.Index];
                     }
 
-                    if (operation.Dest != null && operation.Dest.Type == OperandType.Register)
+                    for (int dstIndex = 0; dstIndex < operation.DestsCount; dstIndex++)
                     {
-                        localOutputs[block.Index] |= GetMask(operation.Dest.GetRegister());
+                        Operand dest = operation.GetDest(dstIndex);
+
+                        if (dest != null && dest.Type == OperandType.Register)
+                        {
+                            localOutputs[block.Index] |= GetMask(dest.GetRegister());
+                        }
                     }
                 }
             }

src/Ryujinx.Graphics.Shader/Translation/Translator.cs

@@ -190,7 +190,7 @@ namespace Ryujinx.Graphics.Shader.Translation
 
             if (stage == ShaderStage.Vertex)
             {
-                InitializePositionOutput(context);
+                InitializeVertexOutputs(context);
             }
 
             UInt128 usedAttributes = context.TranslatorContext.AttributeUsage.NextInputAttributesComponents;
@@ -236,12 +236,20 @@ namespace Ryujinx.Graphics.Shader.Translation
             }
         }
 
-        private static void InitializePositionOutput(EmitterContext context)
+        private static void InitializeVertexOutputs(EmitterContext context)
         {
             for (int c = 0; c < 4; c++)
             {
                 context.Store(StorageKind.Output, IoVariable.Position, null, Const(c), ConstF(c == 3 ? 1f : 0f));
             }
+
+            if (context.Program.ClipDistancesWritten != 0)
+            {
+                for (int i = 0; i < 8; i++)
+                {
+                    context.Store(StorageKind.Output, IoVariable.ClipDistance, null, Const(i), ConstF(0f));
+                }
+            }
         }
 
         private static void InitializeOutput(EmitterContext context, int location, bool perPatch)

src/Ryujinx.Graphics.Texture/Astc/AstcDecoder.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common.Memory;
 using Ryujinx.Common.Utilities;
 using System;
-using System.Buffers;
 using System.Diagnostics;
 using System.Linq;
 using System.Runtime.CompilerServices;
@@ -293,9 +292,9 @@ namespace Ryujinx.Graphics.Texture.Astc
             int depth,
             int levels,
             int layers,
-            out IMemoryOwner<byte> decoded)
+            out MemoryOwner<byte> decoded)
         {
-            decoded = ByteMemoryPool.Rent(QueryDecompressedSize(width, height, depth, levels, layers));
+            decoded = MemoryOwner<byte>.Rent(QueryDecompressedSize(width, height, depth, levels, layers));
 
             AstcDecoder decoder = new(data, decoded.Memory, blockWidth, blockHeight, width, height, depth, levels, layers);
 

src/Ryujinx.Graphics.Texture/BCnDecoder.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common;
 using Ryujinx.Common.Memory;
 using System;
-using System.Buffers;
 using System.Buffers.Binary;
 using System.Runtime.InteropServices;
 using System.Runtime.Intrinsics;
@@ -14,7 +13,7 @@ namespace Ryujinx.Graphics.Texture
         private const int BlockWidth = 4;
         private const int BlockHeight = 4;
 
-        public static IMemoryOwner<byte> DecodeBC1(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeBC1(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             int size = 0;
 
@@ -23,12 +22,12 @@ namespace Ryujinx.Graphics.Texture
                 size += Math.Max(1, width >> l) * Math.Max(1, height >> l) * Math.Max(1, depth >> l) * layers * 4;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
 
             Span<byte> tile = stackalloc byte[BlockWidth * BlockHeight * 4];
 
             Span<uint> tileAsUint = MemoryMarshal.Cast<byte, uint>(tile);
-            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             Span<Vector128<byte>> tileAsVector128 = MemoryMarshal.Cast<byte, Vector128<byte>>(tile);
 
@@ -102,7 +101,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC2(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeBC2(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             int size = 0;
 
@@ -111,12 +110,12 @@ namespace Ryujinx.Graphics.Texture
                 size += Math.Max(1, width >> l) * Math.Max(1, height >> l) * Math.Max(1, depth >> l) * layers * 4;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
 
             Span<byte> tile = stackalloc byte[BlockWidth * BlockHeight * 4];
 
             Span<uint> tileAsUint = MemoryMarshal.Cast<byte, uint>(tile);
-            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             Span<Vector128<byte>> tileAsVector128 = MemoryMarshal.Cast<byte, Vector128<byte>>(tile);
 
@@ -197,7 +196,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC3(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeBC3(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             int size = 0;
 
@@ -206,13 +205,13 @@ namespace Ryujinx.Graphics.Texture
                 size += Math.Max(1, width >> l) * Math.Max(1, height >> l) * Math.Max(1, depth >> l) * layers * 4;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
 
             Span<byte> tile = stackalloc byte[BlockWidth * BlockHeight * 4];
             Span<byte> rPal = stackalloc byte[8];
 
             Span<uint> tileAsUint = MemoryMarshal.Cast<byte, uint>(tile);
-            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputAsUint = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             Span<Vector128<byte>> tileAsVector128 = MemoryMarshal.Cast<byte, Vector128<byte>>(tile);
 
@@ -294,7 +293,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC4(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
+        public static MemoryOwner<byte> DecodeBC4(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
         {
             int size = 0;
 
@@ -306,8 +305,8 @@ namespace Ryujinx.Graphics.Texture
             // Backends currently expect a stride alignment of 4 bytes, so output width must be aligned.
             int alignedWidth = BitUtils.AlignUp(width, 4);
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
-            Span<byte> outputSpan = output.Memory.Span;
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
+            Span<byte> outputSpan = output.Span;
 
             ReadOnlySpan<ulong> data64 = MemoryMarshal.Cast<byte, ulong>(data);
 
@@ -402,7 +401,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC5(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
+        public static MemoryOwner<byte> DecodeBC5(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
         {
             int size = 0;
 
@@ -414,7 +413,7 @@ namespace Ryujinx.Graphics.Texture
             // Backends currently expect a stride alignment of 4 bytes, so output width must be aligned.
             int alignedWidth = BitUtils.AlignUp(width, 2);
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
 
             ReadOnlySpan<ulong> data64 = MemoryMarshal.Cast<byte, ulong>(data);
 
@@ -423,7 +422,7 @@ namespace Ryujinx.Graphics.Texture
             Span<byte> rPal = stackalloc byte[8];
             Span<byte> gPal = stackalloc byte[8];
 
-            Span<ushort> outputAsUshort = MemoryMarshal.Cast<byte, ushort>(output.Memory.Span);
+            Span<ushort> outputAsUshort = MemoryMarshal.Cast<byte, ushort>(output.Span);
 
             Span<uint> rTileAsUint = MemoryMarshal.Cast<byte, uint>(rTile);
             Span<uint> gTileAsUint = MemoryMarshal.Cast<byte, uint>(gTile);
@@ -527,7 +526,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC6(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
+        public static MemoryOwner<byte> DecodeBC6(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers, bool signed)
         {
             int size = 0;
 
@@ -536,8 +535,8 @@ namespace Ryujinx.Graphics.Texture
                 size += Math.Max(1, width >> l) * Math.Max(1, height >> l) * Math.Max(1, depth >> l) * layers * 8;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
-            Span<byte> outputSpan = output.Memory.Span;
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
+            Span<byte> outputSpan = output.Span;
 
             int inputOffset = 0;
             int outputOffset = 0;
@@ -566,7 +565,7 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeBC7(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeBC7(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             int size = 0;
 
@@ -575,8 +574,8 @@ namespace Ryujinx.Graphics.Texture
                 size += Math.Max(1, width >> l) * Math.Max(1, height >> l) * Math.Max(1, depth >> l) * layers * 4;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
-            Span<byte> outputSpan = output.Memory.Span;
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
+            Span<byte> outputSpan = output.Span;
 
             int inputOffset = 0;
             int outputOffset = 0;

src/Ryujinx.Graphics.Texture/BCnEncoder.cs

@@ -2,7 +2,6 @@ using Ryujinx.Common;
 using Ryujinx.Common.Memory;
 using Ryujinx.Graphics.Texture.Encoders;
 using System;
-using System.Buffers;
 
 namespace Ryujinx.Graphics.Texture
 {
@@ -11,7 +10,7 @@ namespace Ryujinx.Graphics.Texture
         private const int BlockWidth = 4;
         private const int BlockHeight = 4;
 
-        public static IMemoryOwner<byte> EncodeBC7(Memory<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> EncodeBC7(Memory<byte> data, int width, int height, int depth, int levels, int layers)
         {
             int size = 0;
 
@@ -23,7 +22,7 @@ namespace Ryujinx.Graphics.Texture
                 size += w * h * 16 * Math.Max(1, depth >> l) * layers;
             }
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(size);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(size);
             Memory<byte> outputMemory = output.Memory;
 
             int imageBaseIOffs = 0;

src/Ryujinx.Graphics.Texture/ETC2Decoder.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common;
 using Ryujinx.Common.Memory;
 using System;
-using System.Buffers;
 using System.Buffers.Binary;
 using System.Runtime.InteropServices;
 
@@ -51,15 +50,15 @@ namespace Ryujinx.Graphics.Texture
             new int[] { -3, -5, -7, -9, 2, 4, 6, 8 },
         };
 
-        public static IMemoryOwner<byte> DecodeRgb(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeRgb(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             ReadOnlySpan<ulong> dataUlong = MemoryMarshal.Cast<byte, ulong>(data);
 
             int inputOffset = 0;
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(CalculateOutputSize(width, height, depth, levels, layers));
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(CalculateOutputSize(width, height, depth, levels, layers));
 
-            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Span);
             Span<uint> tile = stackalloc uint[BlockWidth * BlockHeight];
 
             int imageBaseOOffs = 0;
@@ -113,15 +112,15 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodePta(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodePta(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             ReadOnlySpan<ulong> dataUlong = MemoryMarshal.Cast<byte, ulong>(data);
 
             int inputOffset = 0;
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(CalculateOutputSize(width, height, depth, levels, layers));
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(CalculateOutputSize(width, height, depth, levels, layers));
 
-            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Span);
             Span<uint> tile = stackalloc uint[BlockWidth * BlockHeight];
 
             int imageBaseOOffs = 0;
@@ -170,15 +169,15 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> DecodeRgba(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
+        public static MemoryOwner<byte> DecodeRgba(ReadOnlySpan<byte> data, int width, int height, int depth, int levels, int layers)
         {
             ReadOnlySpan<ulong> dataUlong = MemoryMarshal.Cast<byte, ulong>(data);
 
             int inputOffset = 0;
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(CalculateOutputSize(width, height, depth, levels, layers));
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(CalculateOutputSize(width, height, depth, levels, layers));
 
-            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputUint = MemoryMarshal.Cast<byte, uint>(output.Span);
             Span<uint> tile = stackalloc uint[BlockWidth * BlockHeight];
 
             int imageBaseOOffs = 0;

src/Ryujinx.Graphics.Texture/LayoutConverter.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common;
 using Ryujinx.Common.Memory;
 using System;
-using System.Buffers;
 using System.Runtime.Intrinsics;
 using static Ryujinx.Graphics.Texture.BlockLinearConstants;
 
@@ -95,7 +94,7 @@ namespace Ryujinx.Graphics.Texture
             };
         }
 
-        public static IMemoryOwner<byte> ConvertBlockLinearToLinear(
+        public static MemoryOwner<byte> ConvertBlockLinearToLinear(
             int width,
             int height,
             int depth,
@@ -121,8 +120,8 @@ namespace Ryujinx.Graphics.Texture
                 blockHeight,
                 bytesPerPixel);
 
-            IMemoryOwner<byte> outputOwner = ByteMemoryPool.Rent(outSize);
-            Span<byte> output = outputOwner.Memory.Span;
+            MemoryOwner<byte> outputOwner = MemoryOwner<byte>.Rent(outSize);
+            Span<byte> output = outputOwner.Span;
 
             int outOffs = 0;
 
@@ -249,7 +248,7 @@ namespace Ryujinx.Graphics.Texture
             return outputOwner;
         }
 
-        public static IMemoryOwner<byte> ConvertLinearStridedToLinear(
+        public static MemoryOwner<byte> ConvertLinearStridedToLinear(
             int width,
             int height,
             int blockWidth,
@@ -265,8 +264,8 @@ namespace Ryujinx.Graphics.Texture
             int outStride = BitUtils.AlignUp(w * bytesPerPixel, HostStrideAlignment);
             lineSize = Math.Min(lineSize, outStride);
 
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(h * outStride);
-            Span<byte> outSpan = output.Memory.Span;
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(h * outStride);
+            Span<byte> outSpan = output.Span;
 
             int outOffs = 0;
             int inOffs = 0;

src/Ryujinx.Graphics.Texture/PixelConverter.cs

@@ -1,7 +1,6 @@
 using Ryujinx.Common;
 using Ryujinx.Common.Memory;
 using System;
-using System.Buffers;
 using System.Runtime.InteropServices;
 using System.Runtime.Intrinsics;
 using System.Runtime.Intrinsics.X86;
@@ -21,13 +20,14 @@ namespace Ryujinx.Graphics.Texture
             return (remainder, outRemainder, length / stride);
         }
 
-        public unsafe static IMemoryOwner<byte> ConvertR4G4ToR4G4B4A4(ReadOnlySpan<byte> data, int width)
+        public unsafe static MemoryOwner<byte> ConvertR4G4ToR4G4B4A4(ReadOnlySpan<byte> data, int width)
         {
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(data.Length * 2);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(data.Length * 2);
+            Span<byte> outputSpan = output.Span;
 
             (int remainder, int outRemainder, int height) = GetLineRemainders(data.Length, width, 1, 2);
 
-            Span<ushort> outputSpan = MemoryMarshal.Cast<byte, ushort>(output.Memory.Span);
+            Span<ushort> outputSpanUInt16 = MemoryMarshal.Cast<byte, ushort>(outputSpan);
 
             if (remainder == 0)
             {
@@ -38,7 +38,7 @@ namespace Ryujinx.Graphics.Texture
                     int sizeTrunc = data.Length & ~7;
                     start = sizeTrunc;
 
-                    fixed (byte* inputPtr = data, outputPtr = output.Memory.Span)
+                    fixed (byte* inputPtr = data, outputPtr = outputSpan)
                     {
                         for (ulong offset = 0; offset < (ulong)sizeTrunc; offset += 8)
                         {
@@ -49,7 +49,7 @@ namespace Ryujinx.Graphics.Texture
 
                 for (int i = start; i < data.Length; i++)
                 {
-                    outputSpan[i] = data[i];
+                    outputSpanUInt16[i] = data[i];
                 }
             }
             else
@@ -61,7 +61,7 @@ namespace Ryujinx.Graphics.Texture
                 {
                     for (int x = 0; x < width; x++)
                     {
-                        outputSpan[outOffset++] = data[offset++];
+                        outputSpanUInt16[outOffset++] = data[offset++];
                     }
 
                     offset += remainder;
@@ -72,16 +72,16 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> ConvertR5G6B5ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
+        public static MemoryOwner<byte> ConvertR5G6B5ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
         {
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(data.Length * 2);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(data.Length * 2);
             int offset = 0;
             int outOffset = 0;
 
             (int remainder, int outRemainder, int height) = GetLineRemainders(data.Length, width, 2, 4);
 
             ReadOnlySpan<ushort> inputSpan = MemoryMarshal.Cast<byte, ushort>(data);
-            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             for (int y = 0; y < height; y++)
             {
@@ -109,16 +109,16 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> ConvertR5G5B5ToR8G8B8A8(ReadOnlySpan<byte> data, int width, bool forceAlpha)
+        public static MemoryOwner<byte> ConvertR5G5B5ToR8G8B8A8(ReadOnlySpan<byte> data, int width, bool forceAlpha)
         {
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(data.Length * 2);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(data.Length * 2);
             int offset = 0;
             int outOffset = 0;
 
             (int remainder, int outRemainder, int height) = GetLineRemainders(data.Length, width, 2, 4);
 
             ReadOnlySpan<ushort> inputSpan = MemoryMarshal.Cast<byte, ushort>(data);
-            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             for (int y = 0; y < height; y++)
             {
@@ -146,16 +146,16 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> ConvertA1B5G5R5ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
+        public static MemoryOwner<byte> ConvertA1B5G5R5ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
         {
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(data.Length * 2);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(data.Length * 2);
             int offset = 0;
             int outOffset = 0;
 
             (int remainder, int outRemainder, int height) = GetLineRemainders(data.Length, width, 2, 4);
 
             ReadOnlySpan<ushort> inputSpan = MemoryMarshal.Cast<byte, ushort>(data);
-            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             for (int y = 0; y < height; y++)
             {
@@ -183,16 +183,16 @@ namespace Ryujinx.Graphics.Texture
             return output;
         }
 
-        public static IMemoryOwner<byte> ConvertR4G4B4A4ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
+        public static MemoryOwner<byte> ConvertR4G4B4A4ToR8G8B8A8(ReadOnlySpan<byte> data, int width)
         {
-            IMemoryOwner<byte> output = ByteMemoryPool.Rent(data.Length * 2);
+            MemoryOwner<byte> output = MemoryOwner<byte>.Rent(data.Length * 2);
             int offset = 0;
             int outOffset = 0;
 
             (int remainder, int outRemainder, int height) = GetLineRemainders(data.Length, width, 2, 4);
 
             ReadOnlySpan<ushort> inputSpan = MemoryMarshal.Cast<byte, ushort>(data);
-            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Memory.Span);
+            Span<uint> outputSpan = MemoryMarshal.Cast<byte, uint>(output.Span);
 
             for (int y = 0; y < height; y++)
             {

src/Ryujinx.Graphics.Vulkan/BarrierBatch.cs

@@ -1,6 +1,7 @@
 using Silk.NET.Vulkan;
 using System;
 using System.Collections.Generic;
+using System.Runtime.CompilerServices;
 
 namespace Ryujinx.Graphics.Vulkan
 {
@@ -8,22 +9,55 @@ namespace Ryujinx.Graphics.Vulkan
     {
         private const int MaxBarriersPerCall = 16;
 
+        private const AccessFlags BaseAccess = AccessFlags.ShaderReadBit | AccessFlags.ShaderWriteBit;
+        private const AccessFlags BufferAccess = AccessFlags.IndexReadBit | AccessFlags.VertexAttributeReadBit | AccessFlags.UniformReadBit;
+        private const AccessFlags CommandBufferAccess = AccessFlags.IndirectCommandReadBit;
+
         private readonly VulkanRenderer _gd;
 
         private readonly NativeArray<MemoryBarrier> _memoryBarrierBatch = new(MaxBarriersPerCall);
         private readonly NativeArray<BufferMemoryBarrier> _bufferBarrierBatch = new(MaxBarriersPerCall);
         private readonly NativeArray<ImageMemoryBarrier> _imageBarrierBatch = new(MaxBarriersPerCall);
 
-        private readonly List<BarrierWithStageFlags<MemoryBarrier>> _memoryBarriers = new();
-        private readonly List<BarrierWithStageFlags<BufferMemoryBarrier>> _bufferBarriers = new();
-        private readonly List<BarrierWithStageFlags<ImageMemoryBarrier>> _imageBarriers = new();
+        private readonly List<BarrierWithStageFlags<MemoryBarrier, int>> _memoryBarriers = new();
+        private readonly List<BarrierWithStageFlags<BufferMemoryBarrier, int>> _bufferBarriers = new();
+        private readonly List<BarrierWithStageFlags<ImageMemoryBarrier, TextureStorage>> _imageBarriers = new();
         private int _queuedBarrierCount;
 
+        private enum IncoherentBarrierType
+        {
+            None,
+            Texture,
+            All,
+            CommandBuffer
+        }
+
+        private bool _feedbackLoopActive;
+        private PipelineStageFlags _incoherentBufferWriteStages;
+        private PipelineStageFlags _incoherentTextureWriteStages;
+        private PipelineStageFlags _extraStages;
+        private IncoherentBarrierType _queuedIncoherentBarrier;
+        private bool _queuedFeedbackLoopBarrier;
+
         public BarrierBatch(VulkanRenderer gd)
         {
             _gd = gd;
         }
 
+        public static (AccessFlags Access, PipelineStageFlags Stages) GetSubpassAccessSuperset(VulkanRenderer gd)
+        {
+            AccessFlags access = BufferAccess;
+            PipelineStageFlags stages = PipelineStageFlags.AllGraphicsBit;
+
+            if (gd.TransformFeedbackApi != null)
+            {
+                access |= AccessFlags.TransformFeedbackWriteBitExt;
+                stages |= PipelineStageFlags.TransformFeedbackBitExt;
+            }
+
+            return (access, stages);
+        }
+
         private readonly record struct StageFlags : IEquatable<StageFlags>
         {
             public readonly PipelineStageFlags Source;
@@ -36,47 +70,150 @@ namespace Ryujinx.Graphics.Vulkan
             }
         }
 
-        private readonly struct BarrierWithStageFlags<T> where T : unmanaged
+        private readonly struct BarrierWithStageFlags<T, T2> where T : unmanaged
         {
             public readonly StageFlags Flags;
             public readonly T Barrier;
+            public readonly T2 Resource;
 
             public BarrierWithStageFlags(StageFlags flags, T barrier)
             {
                 Flags = flags;
                 Barrier = barrier;
+                Resource = default;
             }
 
-            public BarrierWithStageFlags(PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags, T barrier)
+            public BarrierWithStageFlags(PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags, T barrier, T2 resource)
             {
                 Flags = new StageFlags(srcStageFlags, dstStageFlags);
                 Barrier = barrier;
+                Resource = resource;
             }
         }
 
-        private void QueueBarrier<T>(List<BarrierWithStageFlags<T>> list, T barrier, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags) where T : unmanaged
+        private void QueueBarrier<T, T2>(List<BarrierWithStageFlags<T, T2>> list, T barrier, T2 resource, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags) where T : unmanaged
         {
-            list.Add(new BarrierWithStageFlags<T>(srcStageFlags, dstStageFlags, barrier));
+            list.Add(new BarrierWithStageFlags<T, T2>(srcStageFlags, dstStageFlags, barrier, resource));
             _queuedBarrierCount++;
         }
 
         public void QueueBarrier(MemoryBarrier barrier, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags)
         {
-            QueueBarrier(_memoryBarriers, barrier, srcStageFlags, dstStageFlags);
+            QueueBarrier(_memoryBarriers, barrier, default, srcStageFlags, dstStageFlags);
         }
 
         public void QueueBarrier(BufferMemoryBarrier barrier, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags)
         {
-            QueueBarrier(_bufferBarriers, barrier, srcStageFlags, dstStageFlags);
+            QueueBarrier(_bufferBarriers, barrier, default, srcStageFlags, dstStageFlags);
         }
 
-        public void QueueBarrier(ImageMemoryBarrier barrier, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags)
+        public void QueueBarrier(ImageMemoryBarrier barrier, TextureStorage resource, PipelineStageFlags srcStageFlags, PipelineStageFlags dstStageFlags)
         {
-            QueueBarrier(_imageBarriers, barrier, srcStageFlags, dstStageFlags);
+            QueueBarrier(_imageBarriers, barrier, resource, srcStageFlags, dstStageFlags);
         }
 
-        public unsafe void Flush(CommandBuffer cb, bool insideRenderPass, Action endRenderPass)
+        [MethodImpl(MethodImplOptions.AggressiveInlining)]
+        public unsafe void FlushMemoryBarrier(ShaderCollection program, bool inRenderPass)
         {
+            if (_queuedIncoherentBarrier > IncoherentBarrierType.None)
+            {
+                // We should emit a memory barrier if there's a write access in the program (current program, or program since last barrier)
+                bool hasTextureWrite = _incoherentTextureWriteStages != PipelineStageFlags.None;
+                bool hasBufferWrite = _incoherentBufferWriteStages != PipelineStageFlags.None;
+                bool hasBufferBarrier = _queuedIncoherentBarrier > IncoherentBarrierType.Texture;
+
+                if (hasTextureWrite || (hasBufferBarrier && hasBufferWrite))
+                {
+                    AccessFlags access = BaseAccess;
+
+                    PipelineStageFlags stages = inRenderPass ? PipelineStageFlags.AllGraphicsBit : PipelineStageFlags.AllCommandsBit;
+
+                    if (hasBufferBarrier && hasBufferWrite)
+                    {
+                        access |= BufferAccess;
+
+                        if (_gd.TransformFeedbackApi != null)
+                        {
+                            access |= AccessFlags.TransformFeedbackWriteBitExt;
+                            stages |= PipelineStageFlags.TransformFeedbackBitExt;
+                        }
+                    }
+
+                    if (_queuedIncoherentBarrier == IncoherentBarrierType.CommandBuffer)
+                    {
+                        access |= CommandBufferAccess;
+                        stages |= PipelineStageFlags.DrawIndirectBit;
+                    }
+
+                    MemoryBarrier barrier = new MemoryBarrier()
+                    {
+                        SType = StructureType.MemoryBarrier,
+                        SrcAccessMask = access,
+                        DstAccessMask = access
+                    };
+
+                    QueueBarrier(barrier, stages, stages);
+
+                    _incoherentTextureWriteStages = program?.IncoherentTextureWriteStages ?? PipelineStageFlags.None;
+
+                    if (_queuedIncoherentBarrier > IncoherentBarrierType.Texture)
+                    {
+                        if (program != null)
+                        {
+                            _incoherentBufferWriteStages = program.IncoherentBufferWriteStages | _extraStages;
+                        }
+                        else
+                        {
+                            _incoherentBufferWriteStages = PipelineStageFlags.None;
+                        }
+                    }
+
+                    _queuedIncoherentBarrier = IncoherentBarrierType.None;
+                    _queuedFeedbackLoopBarrier = false;
+                }
+                else if (_feedbackLoopActive && _queuedFeedbackLoopBarrier)
+                {
+                    // Feedback loop barrier.
+
+                    MemoryBarrier barrier = new MemoryBarrier()
+                    {
+                        SType = StructureType.MemoryBarrier,
+                        SrcAccessMask = AccessFlags.ShaderWriteBit,
+                        DstAccessMask = AccessFlags.ShaderReadBit
+                    };
+
+                    QueueBarrier(barrier, PipelineStageFlags.FragmentShaderBit, PipelineStageFlags.AllGraphicsBit);
+
+                    _queuedFeedbackLoopBarrier = false;
+                }
+
+                _feedbackLoopActive = false;
+            }
+        }
+
+        public unsafe void Flush(CommandBufferScoped cbs, bool inRenderPass, RenderPassHolder rpHolder, Action endRenderPass)
+        {
+            Flush(cbs, null, false, inRenderPass, rpHolder, endRenderPass);
+        }
+
+        public unsafe void Flush(CommandBufferScoped cbs, ShaderCollection program, bool feedbackLoopActive, bool inRenderPass, RenderPassHolder rpHolder, Action endRenderPass)
+        {
+            if (program != null)
+            {
+                _incoherentBufferWriteStages |= program.IncoherentBufferWriteStages | _extraStages;
+                _incoherentTextureWriteStages |= program.IncoherentTextureWriteStages;
+            }
+
+            _feedbackLoopActive |= feedbackLoopActive;
+
+            FlushMemoryBarrier(program, inRenderPass);
+
+            if (!inRenderPass && rpHolder != null)
+            {
+                // Render pass is about to begin. Queue any fences that normally interrupt the pass.
+                rpHolder.InsertForcedFences(cbs);
+            }
+
             while (_queuedBarrierCount > 0)
             {
                 int memoryCount = 0;
@@ -86,20 +223,20 @@ namespace Ryujinx.Graphics.Vulkan
                 bool hasBarrier = false;
                 StageFlags flags = default;
 
-                static void AddBarriers<T>(
+                static void AddBarriers<T, T2>(
                     Span<T> target,
                     ref int queuedBarrierCount,
                     ref bool hasBarrier,
                     ref StageFlags flags,
                     ref int count,
-                    List<BarrierWithStageFlags<T>> list) where T : unmanaged
+                    List<BarrierWithStageFlags<T, T2>> list) where T : unmanaged
                 {
                     int firstMatch = -1;
                     int end = list.Count;
 
                     for (int i = 0; i < list.Count; i++)
                     {
-                        BarrierWithStageFlags<T> barrier = list[i];
+                        BarrierWithStageFlags<T, T2> barrier = list[i];
 
                         if (!hasBarrier)
                         {
@@ -162,21 +299,60 @@ namespace Ryujinx.Graphics.Vulkan
                     }
                 }
 
-                if (insideRenderPass)
+                if (inRenderPass && _imageBarriers.Count > 0)
                 {
                     // Image barriers queued in the batch are meant to be globally scoped,
                     // but inside a render pass they're scoped to just the range of the render pass.
 
                     // On MoltenVK, we just break the rules and always use image barrier.
                     // On desktop GPUs, all barriers are globally scoped, so we just replace it with a generic memory barrier.
-                    // TODO: On certain GPUs, we need to split render pass so the barrier scope is global. When this is done,
-                    //       notify the resource that it should add a barrier as soon as a render pass ends to avoid this in future.
+                    // Generally, we want to avoid this from happening in the future, so flag the texture to immediately
+                    // emit a barrier whenever the current render pass is bound again.
 
-                    if (!_gd.IsMoltenVk)
+                    bool anyIsNonAttachment = false;
+
+                    foreach (BarrierWithStageFlags<ImageMemoryBarrier, TextureStorage> barrier in _imageBarriers)
                     {
+                        // If the binding is an attachment, don't add it as a forced fence.
+                        bool isAttachment = rpHolder.ContainsAttachment(barrier.Resource);
+
+                        if (!isAttachment)
+                        {
+                            rpHolder.AddForcedFence(barrier.Resource, barrier.Flags.Dest);
+                            anyIsNonAttachment = true;
+                        }
+                    }
+
+                    if (_gd.IsTBDR)
+                    {
+                        if (!_gd.IsMoltenVk)
+                        {
+                            if (!anyIsNonAttachment)
+                            {
+                                // This case is a feedback loop. To prevent this from causing an absolute performance disaster,
+                                // remove the barriers entirely.
+                                // If this is not here, there will be a lot of single draw render passes.
+                                // TODO: explicit handling for feedback loops, likely outside this class.
+
+                                _queuedBarrierCount -= _imageBarriers.Count;
+                                _imageBarriers.Clear();
+                            }
+                            else
+                            {
+                                // TBDR GPUs are sensitive to barriers, so we need to end the pass to ensure the data is available.
+                                // Metal already has hazard tracking so MVK doesn't need this.
+                                endRenderPass();
+                                inRenderPass = false;
+                            }
+                        }
+                    }
+                    else
+                    {
+                        // Generic pipeline memory barriers will work for desktop GPUs.
+                        // They do require a few more access flags on the subpass dependency, though.
                         foreach (var barrier in _imageBarriers)
                         {
-                            _memoryBarriers.Add(new BarrierWithStageFlags<MemoryBarrier>(
+                            _memoryBarriers.Add(new BarrierWithStageFlags<MemoryBarrier, int>(
                                 barrier.Flags,
                                 new MemoryBarrier()
                                 {
@@ -190,6 +366,22 @@ namespace Ryujinx.Graphics.Vulkan
                     }
                 }
 
+                if (inRenderPass && _memoryBarriers.Count > 0)
+                {
+                    PipelineStageFlags allFlags = PipelineStageFlags.None;
+
+                    foreach (var barrier in _memoryBarriers)
+                    {
+                        allFlags |= barrier.Flags.Dest;
+                    }
+
+                    if (allFlags.HasFlag(PipelineStageFlags.DrawIndirectBit) || !_gd.SupportsRenderPassBarrier(allFlags))
+                    {
+                        endRenderPass();
+                        inRenderPass = false;
+                    }
+                }
+
                 AddBarriers(_memoryBarrierBatch.AsSpan(), ref _queuedBarrierCount, ref hasBarrier, ref flags, ref memoryCount, _memoryBarriers);
                 AddBarriers(_bufferBarrierBatch.AsSpan(), ref _queuedBarrierCount, ref hasBarrier, ref flags, ref bufferCount, _bufferBarriers);
                 AddBarriers(_imageBarrierBatch.AsSpan(), ref _queuedBarrierCount, ref hasBarrier, ref flags, ref imageCount, _imageBarriers);
@@ -198,14 +390,14 @@ namespace Ryujinx.Graphics.Vulkan
                 {
                     PipelineStageFlags srcStageFlags = flags.Source;
 
-                    if (insideRenderPass)
+                    if (inRenderPass)
                     {
                         // Inside a render pass, barrier stages can only be from rasterization.
                         srcStageFlags &= ~PipelineStageFlags.ComputeShaderBit;
                     }
 
                     _gd.Api.CmdPipelineBarrier(
-                        cb,
+                        cbs.CommandBuffer,
                         srcStageFlags,
                         flags.Dest,
                         0,
@@ -219,6 +411,43 @@ namespace Ryujinx.Graphics.Vulkan
             }
         }
 
+        private void QueueIncoherentBarrier(IncoherentBarrierType type)
+        {
+            if (type > _queuedIncoherentBarrier)
+            {
+                _queuedIncoherentBarrier = type;
+            }
+
+            _queuedFeedbackLoopBarrier = true;
+        }
+
+        public void QueueTextureBarrier()
+        {
+            QueueIncoherentBarrier(IncoherentBarrierType.Texture);
+        }
+
+        public void QueueMemoryBarrier()
+        {
+            QueueIncoherentBarrier(IncoherentBarrierType.All);
+        }
+
+        public void QueueCommandBufferBarrier()
+        {
+            QueueIncoherentBarrier(IncoherentBarrierType.CommandBuffer);
+        }
+
+        public void EnableTfbBarriers(bool enable)
+        {
+            if (enable)
+            {
+                _extraStages |= PipelineStageFlags.TransformFeedbackBitExt;
+            }
+            else
+            {
+                _extraStages &= ~PipelineStageFlags.TransformFeedbackBitExt;
+            }
+        }
+
         public void Dispose()
         {
             _memoryBarrierBatch.Dispose();

src/Ryujinx.Graphics.Vulkan/BufferHolder.cs

@@ -122,7 +122,7 @@ namespace Ryujinx.Graphics.Vulkan
                 Range = (uint)size,
             };
 
-            _gd.Api.CreateBufferView(_device, bufferViewCreateInfo, null, out var bufferView).ThrowOnError();
+            _gd.Api.CreateBufferView(_device, in bufferViewCreateInfo, null, out var bufferView).ThrowOnError();
 
             return new Auto<DisposableBufferView>(new DisposableBufferView(_gd.Api, _device, bufferView), this, _waitable, _buffer);
         }
@@ -153,7 +153,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PipelineStageFlags.AllCommandsBit,
                     DependencyFlags.DeviceGroupBit,
                     1,
-                    memoryBarrier,
+                    in memoryBarrier,
                     0,
                     null,
                     0,
@@ -770,7 +770,7 @@ namespace Ryujinx.Graphics.Vulkan
                 0,
                 null,
                 1,
-                memoryBarrier,
+                in memoryBarrier,
                 0,
                 null);
         }

src/Ryujinx.Graphics.Vulkan/BufferManager.cs

@@ -221,7 +221,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PBufferBinds = &bufferBind
                 };
 
-                gd.Api.QueueBindSparse(gd.Queue, 1, bindSparseInfo, default).ThrowOnError();
+                gd.Api.QueueBindSparse(gd.Queue, 1, in bindSparseInfo, default).ThrowOnError();
             }
 
             var holder = new BufferHolder(gd, _device, buffer, (int)size, storageAllocations);

src/Ryujinx.Graphics.Vulkan/BufferState.cs

@@ -25,7 +25,10 @@ namespace Ryujinx.Graphics.Vulkan
             {
                 var buffer = _buffer.Get(cbs, _offset, _size, true).Value;
 
-                gd.TransformFeedbackApi.CmdBindTransformFeedbackBuffers(cbs.CommandBuffer, binding, 1, buffer, (ulong)_offset, (ulong)_size);
+                ulong offset = (ulong)_offset;
+                ulong size = (ulong)_size;
+
+                gd.TransformFeedbackApi.CmdBindTransformFeedbackBuffers(cbs.CommandBuffer, binding, 1, in buffer, in offset, in size);
             }
         }
 

src/Ryujinx.Graphics.Vulkan/CommandBufferPool.cs

@@ -31,11 +31,9 @@ namespace Ryujinx.Graphics.Vulkan
             public int SubmissionCount;
             public CommandBuffer CommandBuffer;
             public FenceHolder Fence;
-            public SemaphoreHolder Semaphore;
 
             public List<IAuto> Dependants;
             public List<MultiFenceHolder> Waitables;
-            public HashSet<SemaphoreHolder> Dependencies;
 
             public void Initialize(Vk api, Device device, CommandPool pool)
             {
@@ -47,11 +45,10 @@ namespace Ryujinx.Graphics.Vulkan
                     Level = CommandBufferLevel.Primary,
                 };
 
-                api.AllocateCommandBuffers(device, allocateInfo, out CommandBuffer);
+                api.AllocateCommandBuffers(device, in allocateInfo, out CommandBuffer);
 
                 Dependants = new List<IAuto>();
                 Waitables = new List<MultiFenceHolder>();
-                Dependencies = new HashSet<SemaphoreHolder>();
             }
         }
 
@@ -86,7 +83,7 @@ namespace Ryujinx.Graphics.Vulkan
                         CommandPoolCreateFlags.ResetCommandBufferBit,
             };
 
-            api.CreateCommandPool(device, commandPoolCreateInfo, null, out _pool).ThrowOnError();
+            api.CreateCommandPool(device, in commandPoolCreateInfo, null, out _pool).ThrowOnError();
 
             // We need at least 2 command buffers to get texture data in some cases.
             _totalCommandBuffers = isLight ? 2 : MaxCommandBuffers;
@@ -143,14 +140,6 @@ namespace Ryujinx.Graphics.Vulkan
             }
         }
 
-        public void AddDependency(int cbIndex, CommandBufferScoped dependencyCbs)
-        {
-            Debug.Assert(_commandBuffers[cbIndex].InUse);
-            var semaphoreHolder = _commandBuffers[dependencyCbs.CommandBufferIndex].Semaphore;
-            semaphoreHolder.Get();
-            _commandBuffers[cbIndex].Dependencies.Add(semaphoreHolder);
-        }
-
         public void AddWaitable(int cbIndex, MultiFenceHolder waitable)
         {
             ref var entry = ref _commandBuffers[cbIndex];
@@ -264,7 +253,7 @@ namespace Ryujinx.Graphics.Vulkan
                             SType = StructureType.CommandBufferBeginInfo,
                         };
 
-                        _api.BeginCommandBuffer(entry.CommandBuffer, commandBufferBeginInfo).ThrowOnError();
+                        _api.BeginCommandBuffer(entry.CommandBuffer, in commandBufferBeginInfo).ThrowOnError();
 
                         return new CommandBufferScoped(this, entry.CommandBuffer, cursor);
                     }
@@ -322,7 +311,7 @@ namespace Ryujinx.Graphics.Vulkan
 
                         lock (_queueLock)
                         {
-                            _api.QueueSubmit(_queue, 1, sInfo, entry.Fence.GetUnsafe()).ThrowOnError();
+                            _api.QueueSubmit(_queue, 1, in sInfo, entry.Fence.GetUnsafe()).ThrowOnError();
                         }
                     }
                 }
@@ -354,14 +343,8 @@ namespace Ryujinx.Graphics.Vulkan
                 waitable.RemoveBufferUses(cbIndex);
             }
 
-            foreach (var dependency in entry.Dependencies)
-            {
-                dependency.Put();
-            }
-
             entry.Dependants.Clear();
             entry.Waitables.Clear();
-            entry.Dependencies.Clear();
             entry.Fence?.Dispose();
 
             if (refreshFence)

src/Ryujinx.Graphics.Vulkan/CommandBufferScoped.cs

@@ -26,11 +26,6 @@ namespace Ryujinx.Graphics.Vulkan
             _pool.AddWaitable(CommandBufferIndex, waitable);
         }
 
-        public void AddDependency(CommandBufferScoped dependencyCbs)
-        {
-            _pool.AddDependency(CommandBufferIndex, dependencyCbs);
-        }
-
         public FenceHolder GetFence()
         {
             return _pool.GetFence(CommandBufferIndex);

src/Ryujinx.Graphics.Vulkan/DescriptorSetCollection.cs

@@ -43,7 +43,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PBufferInfo = &bufferInfo,
                 };
 
-                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
             }
         }
 
@@ -66,7 +66,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PBufferInfo = pBufferInfo,
                 };
 
-                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
             }
         }
 
@@ -84,7 +84,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PImageInfo = &imageInfo,
                 };
 
-                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
             }
         }
 
@@ -107,7 +107,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PImageInfo = pImageInfo,
                 };
 
-                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
             }
         }
 
@@ -144,7 +144,7 @@ namespace Ryujinx.Graphics.Vulkan
                             PImageInfo = pImageInfo,
                         };
 
-                        _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                        _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
 
                         i += count - 1;
                     }
@@ -166,7 +166,7 @@ namespace Ryujinx.Graphics.Vulkan
                     PTexelBufferView = &texelBufferView,
                 };
 
-                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
             }
         }
 
@@ -200,7 +200,7 @@ namespace Ryujinx.Graphics.Vulkan
                             PTexelBufferView = pTexelBufferView + i,
                         };
 
-                        _holder.Api.UpdateDescriptorSets(_holder.Device, 1, writeDescriptorSet, 0, null);
+                        _holder.Api.UpdateDescriptorSets(_holder.Device, 1, in writeDescriptorSet, 0, null);
                     }
 
                     i += count;