vleeuwenmenno/Ryujinx
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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
35 changed files with 445 additions and 265 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
src/Ryujinx.Graphics.Shader/StructuredIr/HelperFunctionsMask.cs
View File

@ -7,10 +7,6 @@ namespace Ryujinx.Graphics.Shader.StructuredIr
{
MultiplyHighS32 = 1 << 2,
MultiplyHighU32 = 1 << 3,
Shuffle = 1 << 4,
ShuffleDown = 1 << 5,
ShuffleUp = 1 << 6,
ShuffleXor = 1 << 7,
SwizzleAdd = 1 << 10,
FSI = 1 << 11,
}

11
src/Ryujinx.Graphics.Shader/StructuredIr/InstructionInfo.cs
View File

@ -109,14 +109,15 @@ namespace Ryujinx.Graphics.Shader.StructuredIr
Add(Instruction.PackDouble2x32, AggregateType.FP64, AggregateType.U32, AggregateType.U32);
Add(Instruction.PackHalf2x16, AggregateType.U32, AggregateType.FP32, AggregateType.FP32);
Add(Instruction.ReciprocalSquareRoot, AggregateType.Scalar, AggregateType.Scalar);
Add(Instruction.Return, AggregateType.Void, AggregateType.U32);
Add(Instruction.Round, AggregateType.Scalar, AggregateType.Scalar);
Add(Instruction.ShiftLeft, AggregateType.S32, AggregateType.S32, AggregateType.S32);
Add(Instruction.ShiftRightS32, AggregateType.S32, AggregateType.S32, AggregateType.S32);
Add(Instruction.ShiftRightU32, AggregateType.U32, AggregateType.U32, AggregateType.S32);
Add(Instruction.Shuffle, AggregateType.FP32, AggregateType.FP32, AggregateType.U32, AggregateType.U32, AggregateType.Bool);
Add(Instruction.ShuffleDown, AggregateType.FP32, AggregateType.FP32, AggregateType.U32, AggregateType.U32, AggregateType.Bool);
Add(Instruction.ShuffleUp, AggregateType.FP32, AggregateType.FP32, AggregateType.U32, AggregateType.U32, AggregateType.Bool);
Add(Instruction.ShuffleXor, AggregateType.FP32, AggregateType.FP32, AggregateType.U32, AggregateType.U32, AggregateType.Bool);
Add(Instruction.Shuffle, AggregateType.FP32, AggregateType.FP32, AggregateType.U32);
Add(Instruction.ShuffleDown, AggregateType.FP32, AggregateType.FP32, AggregateType.U32);
Add(Instruction.ShuffleUp, AggregateType.FP32, AggregateType.FP32, AggregateType.U32);
Add(Instruction.ShuffleXor, AggregateType.FP32, AggregateType.FP32, AggregateType.U32);
Add(Instruction.Sine, AggregateType.Scalar, AggregateType.Scalar);
Add(Instruction.SquareRoot, AggregateType.Scalar, AggregateType.Scalar);
Add(Instruction.Store, AggregateType.Void);
@ -131,7 +132,7 @@ namespace Ryujinx.Graphics.Shader.StructuredIr
Add(Instruction.VoteAll, AggregateType.Bool, AggregateType.Bool);
Add(Instruction.VoteAllEqual, AggregateType.Bool, AggregateType.Bool);
Add(Instruction.VoteAny, AggregateType.Bool, AggregateType.Bool);
#pragma warning restore IDE0055v
#pragma warning restore IDE0055
}
private static void Add(Instruction inst, AggregateType destType, params AggregateType[] srcTypes)

12
src/Ryujinx.Graphics.Shader/StructuredIr/StructuredProgram.cs
View File

@ -282,18 +282,6 @@ namespace Ryujinx.Graphics.Shader.StructuredIr
case Instruction.MultiplyHighU32:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.MultiplyHighU32;
break;
case Instruction.Shuffle:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.Shuffle;
break;
case Instruction.ShuffleDown:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.ShuffleDown;
break;
case Instruction.ShuffleUp:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.ShuffleUp;
break;
case Instruction.ShuffleXor:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.ShuffleXor;
break;
case Instruction.SwizzleAdd:
context.Info.HelperFunctionsMask |= HelperFunctionsMask.SwizzleAdd;
break;