mirrors/ryujinx
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Fix vote and shuffle shader instructions on AMD GPUs (#5540)

Browse source 
* Move shuffle handling out of the backend to a transform pass

* Handle subgroup sizes higher than 32

* Stop using the subgroup size control extension

* Make GenerateShuffleFunction static

* Shader cache version bump
This commit is contained in:
gdkchan 2023-08-16 21:31:07 -03:00 • committed by GitHub
parent 64079c034c
commit 6ed613a6e6
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
35 changed files with 445 additions and 265 deletions
Download patch file Download diff file Expand all files Collapse all files

21
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Declarations.cs
View file

@ -25,6 +25,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl
{
context.AppendLine("#extension GL_KHR_shader_subgroup_basic : enable");
context.AppendLine("#extension GL_KHR_shader_subgroup_ballot : enable");
context.AppendLine("#extension GL_KHR_shader_subgroup_shuffle : enable");
}
context.AppendLine("#extension GL_ARB_shader_group_vote : enable");
@ -201,26 +202,6 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/MultiplyHighU32.glsl");
}
if ((info.HelperFunctionsMask & HelperFunctionsMask.Shuffle) != 0)
{
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/Shuffle.glsl");
}
if ((info.HelperFunctionsMask & HelperFunctionsMask.ShuffleDown) != 0)
{
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleDown.glsl");
}
if ((info.HelperFunctionsMask & HelperFunctionsMask.ShuffleUp) != 0)
{
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleUp.glsl");
}
if ((info.HelperFunctionsMask & HelperFunctionsMask.ShuffleXor) != 0)
{
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleXor.glsl");
}
if ((info.HelperFunctionsMask & HelperFunctionsMask.SwizzleAdd) != 0)
{
AppendHelperFunction(context, "Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/SwizzleAdd.glsl");

4
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/HelperFunctionNames.cs
View file

@ -5,10 +5,6 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl
public static string MultiplyHighS32 = "Helper_MultiplyHighS32";
public static string MultiplyHighU32 = "Helper_MultiplyHighU32";
public static string Shuffle = "Helper_Shuffle";
public static string ShuffleDown = "Helper_ShuffleDown";
public static string ShuffleUp = "Helper_ShuffleUp";
public static string ShuffleXor = "Helper_ShuffleXor";
public static string SwizzleAdd = "Helper_SwizzleAdd";
}
}

11
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/Shuffle.glsl
View file

@ -1,11 +0,0 @@
float Helper_Shuffle(float x, uint index, uint mask, out bool valid)
{
uint clamp = mask & 0x1fu;
uint segMask = (mask >> 8) & 0x1fu;
uint minThreadId = $SUBGROUP_INVOCATION$ & segMask;
uint maxThreadId = minThreadId | (clamp & ~segMask);
uint srcThreadId = (index & ~segMask) | minThreadId;
valid = srcThreadId <= maxThreadId;
float v = $SUBGROUP_BROADCAST$(x, srcThreadId);
return valid ? v : x;
}

11
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleDown.glsl
View file

@ -1,11 +0,0 @@
float Helper_ShuffleDown(float x, uint index, uint mask, out bool valid)
{
uint clamp = mask & 0x1fu;
uint segMask = (mask >> 8) & 0x1fu;
uint minThreadId = $SUBGROUP_INVOCATION$ & segMask;
uint maxThreadId = minThreadId | (clamp & ~segMask);
uint srcThreadId = $SUBGROUP_INVOCATION$ + index;
valid = srcThreadId <= maxThreadId;
float v = $SUBGROUP_BROADCAST$(x, srcThreadId);
return valid ? v : x;
}

9
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleUp.glsl
View file

@ -1,9 +0,0 @@
float Helper_ShuffleUp(float x, uint index, uint mask, out bool valid)
{
uint segMask = (mask >> 8) & 0x1fu;
uint minThreadId = $SUBGROUP_INVOCATION$ & segMask;
uint srcThreadId = $SUBGROUP_INVOCATION$ - index;
valid = int(srcThreadId) >= int(minThreadId);
float v = $SUBGROUP_BROADCAST$(x, srcThreadId);
return valid ? v : x;
}

11
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/HelperFunctions/ShuffleXor.glsl
View file

@ -1,11 +0,0 @@
float Helper_ShuffleXor(float x, uint index, uint mask, out bool valid)
{
uint clamp = mask & 0x1fu;
uint segMask = (mask >> 8) & 0x1fu;
uint minThreadId = $SUBGROUP_INVOCATION$ & segMask;
uint maxThreadId = minThreadId | (clamp & ~segMask);
uint srcThreadId = $SUBGROUP_INVOCATION$ ^ index;
valid = srcThreadId <= maxThreadId;
float v = $SUBGROUP_BROADCAST$(x, srcThreadId);
return valid ? v : x;
}

4
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Instructions/InstGen.cs
View file

@ -9,6 +9,7 @@ using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenFSI;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenHelper;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenMemory;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenPacking;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenShuffle;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenVector;
using static Ryujinx.Graphics.Shader.StructuredIr.InstructionInfo;
@ -174,6 +175,9 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
case Instruction.PackHalf2x16:
return PackHalf2x16(context, operation);
case Instruction.Shuffle:
return Shuffle(context, operation);
case Instruction.Store:
return Store(context, operation);

5
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Instructions/InstGenBallot.cs
View file

@ -13,14 +13,15 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
AggregateType dstType = GetSrcVarType(operation.Inst, 0);
string arg = GetSoureExpr(context, operation.GetSource(0), dstType);
char component = "xyzw"[operation.Index];
if (context.HostCapabilities.SupportsShaderBallot)
{
return $"unpackUint2x32(ballotARB({arg})).x";
return $"unpackUint2x32(ballotARB({arg})).{component}";
}
else
{
return $"subgroupBallot({arg}).x";
return $"subgroupBallot({arg}).{component}";
}
}
}

8
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Instructions/InstGenHelper.cs
View file

@ -108,10 +108,10 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
Add(Instruction.ShiftLeft, InstType.OpBinary, "<<", 3);
Add(Instruction.ShiftRightS32, InstType.OpBinary, ">>", 3);
Add(Instruction.ShiftRightU32, InstType.OpBinary, ">>", 3);
Add(Instruction.Shuffle, InstType.CallQuaternary, HelperFunctionNames.Shuffle);
Add(Instruction.ShuffleDown, InstType.CallQuaternary, HelperFunctionNames.ShuffleDown);
Add(Instruction.ShuffleUp, InstType.CallQuaternary, HelperFunctionNames.ShuffleUp);
Add(Instruction.ShuffleXor, InstType.CallQuaternary, HelperFunctionNames.ShuffleXor);
Add(Instruction.Shuffle, InstType.Special);
Add(Instruction.ShuffleDown, InstType.CallBinary, "subgroupShuffleDown");
Add(Instruction.ShuffleUp, InstType.CallBinary, "subgroupShuffleUp");
Add(Instruction.ShuffleXor, InstType.CallBinary, "subgroupShuffleXor");
Add(Instruction.Sine, InstType.CallUnary, "sin");
Add(Instruction.SquareRoot, InstType.CallUnary, "sqrt");
Add(Instruction.Store, InstType.Special);

25
src/Ryujinx.Graphics.Shader/CodeGen/Glsl/Instructions/InstGenShuffle.cs Normal file
View file

@ -0,0 +1,25 @@
using Ryujinx.Graphics.Shader.StructuredIr;
using Ryujinx.Graphics.Shader.Translation;
using static Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions.InstGenHelper;
namespace Ryujinx.Graphics.Shader.CodeGen.Glsl.Instructions
{
static class InstGenShuffle
{
public static string Shuffle(CodeGenContext context, AstOperation operation)
{
string value = GetSoureExpr(context, operation.GetSource(0), AggregateType.FP32);
string index = GetSoureExpr(context, operation.GetSource(1), AggregateType.U32);
if (context.HostCapabilities.SupportsShaderBallot)
{
return $"readInvocationARB({value}, {index})";
}
else
{
return $"subgroupShuffle({value}, {index})";
}
}
}
}