aboutsummaryrefslogtreecommitdiff
path: root/src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs
diff options
context:
space:
mode:
authorgdkchan <gab.dark.100@gmail.com>2023-08-16 21:31:07 -0300
committerGitHub <noreply@github.com>2023-08-16 21:31:07 -0300
commit6ed613a6e6a66d57d2fdb045d926e42dfcdd3206 (patch)
tree3dbd8e34edf12925f49a0a6c1229e3565b5cfd4f /src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs
parent64079c034c1c3a18133542d6ac745490149d8043 (diff)
Fix vote and shuffle shader instructions on AMD GPUs (#5540)1.1.995
* 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
Diffstat (limited to 'src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs')
-rw-r--r--src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs95
1 files changed, 9 insertions, 86 deletions
diff --git a/src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs b/src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs
index 98c1b9d2..719ccf0c 100644
--- a/src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs
+++ b/src/Ryujinx.Graphics.Shader/CodeGen/Spirv/Instructions.cs
@@ -231,7 +231,7 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Spirv
var execution = context.Constant(context.TypeU32(), Scope.Subgroup);
var maskVector = context.GroupNonUniformBallot(uvec4Type, execution, context.Get(AggregateType.Bool, source));
- var mask = context.CompositeExtract(context.TypeU32(), maskVector, (SpvLiteralInteger)0);
+ var mask = context.CompositeExtract(context.TypeU32(), maskVector, (SpvLiteralInteger)operation.Index);
return new OperationResult(AggregateType.U32, mask);
}
@@ -1100,117 +1100,40 @@ namespace Ryujinx.Graphics.Shader.CodeGen.Spirv
private static OperationResult GenerateShuffle(CodeGenContext context, AstOperation operation)
{
- var x = context.GetFP32(operation.GetSource(0));
+ var value = context.GetFP32(operation.GetSource(0));
var index = context.GetU32(operation.GetSource(1));
- var mask = context.GetU32(operation.GetSource(2));
- var const31 = context.Constant(context.TypeU32(), 31);
- var const8 = context.Constant(context.TypeU32(), 8);
-
- var clamp = context.BitwiseAnd(context.TypeU32(), mask, const31);
- var segMask = context.BitwiseAnd(context.TypeU32(), context.ShiftRightLogical(context.TypeU32(), mask, const8), const31);
- var notSegMask = context.Not(context.TypeU32(), segMask);
- var clampNotSegMask = context.BitwiseAnd(context.TypeU32(), clamp, notSegMask);
- var indexNotSegMask = context.BitwiseAnd(context.TypeU32(), index, notSegMask);
-
- var threadId = GetScalarInput(context, IoVariable.SubgroupLaneId);
-
- var minThreadId = context.BitwiseAnd(context.TypeU32(), threadId, segMask);
- var maxThreadId = context.BitwiseOr(context.TypeU32(), minThreadId, clampNotSegMask);
- var srcThreadId = context.BitwiseOr(context.TypeU32(), indexNotSegMask, minThreadId);
- var valid = context.ULessThanEqual(context.TypeBool(), srcThreadId, maxThreadId);
- var value = context.GroupNonUniformShuffle(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), x, srcThreadId);
- var result = context.Select(context.TypeFP32(), valid, value, x);
-
- var validLocal = (AstOperand)operation.GetSource(3);
-
- context.Store(context.GetLocalPointer(validLocal), context.BitcastIfNeeded(validLocal.VarType, AggregateType.Bool, valid));
+ var result = context.GroupNonUniformShuffle(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), value, index);
return new OperationResult(AggregateType.FP32, result);
}
private static OperationResult GenerateShuffleDown(CodeGenContext context, AstOperation operation)
{
- var x = context.GetFP32(operation.GetSource(0));
+ var value = context.GetFP32(operation.GetSource(0));
var index = context.GetU32(operation.GetSource(1));
- var mask = context.GetU32(operation.GetSource(2));
-
- var const31 = context.Constant(context.TypeU32(), 31);
- var const8 = context.Constant(context.TypeU32(), 8);
-
- var clamp = context.BitwiseAnd(context.TypeU32(), mask, const31);
- var segMask = context.BitwiseAnd(context.TypeU32(), context.ShiftRightLogical(context.TypeU32(), mask, const8), const31);
- var notSegMask = context.Not(context.TypeU32(), segMask);
- var clampNotSegMask = context.BitwiseAnd(context.TypeU32(), clamp, notSegMask);
-
- var threadId = GetScalarInput(context, IoVariable.SubgroupLaneId);
-
- var minThreadId = context.BitwiseAnd(context.TypeU32(), threadId, segMask);
- var maxThreadId = context.BitwiseOr(context.TypeU32(), minThreadId, clampNotSegMask);
- var srcThreadId = context.IAdd(context.TypeU32(), threadId, index);
- var valid = context.ULessThanEqual(context.TypeBool(), srcThreadId, maxThreadId);
- var value = context.GroupNonUniformShuffle(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), x, srcThreadId);
- var result = context.Select(context.TypeFP32(), valid, value, x);
-
- var validLocal = (AstOperand)operation.GetSource(3);
- context.Store(context.GetLocalPointer(validLocal), context.BitcastIfNeeded(validLocal.VarType, AggregateType.Bool, valid));
+ var result = context.GroupNonUniformShuffleDown(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), value, index);
return new OperationResult(AggregateType.FP32, result);
}
private static OperationResult GenerateShuffleUp(CodeGenContext context, AstOperation operation)
{
- var x = context.GetFP32(operation.GetSource(0));
+ var value = context.GetFP32(operation.GetSource(0));
var index = context.GetU32(operation.GetSource(1));
- var mask = context.GetU32(operation.GetSource(2));
- var const31 = context.Constant(context.TypeU32(), 31);
- var const8 = context.Constant(context.TypeU32(), 8);
-
- var segMask = context.BitwiseAnd(context.TypeU32(), context.ShiftRightLogical(context.TypeU32(), mask, const8), const31);
-
- var threadId = GetScalarInput(context, IoVariable.SubgroupLaneId);
-
- var minThreadId = context.BitwiseAnd(context.TypeU32(), threadId, segMask);
- var srcThreadId = context.ISub(context.TypeU32(), threadId, index);
- var valid = context.SGreaterThanEqual(context.TypeBool(), srcThreadId, minThreadId);
- var value = context.GroupNonUniformShuffle(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), x, srcThreadId);
- var result = context.Select(context.TypeFP32(), valid, value, x);
-
- var validLocal = (AstOperand)operation.GetSource(3);
-
- context.Store(context.GetLocalPointer(validLocal), context.BitcastIfNeeded(validLocal.VarType, AggregateType.Bool, valid));
+ var result = context.GroupNonUniformShuffleUp(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), value, index);
return new OperationResult(AggregateType.FP32, result);
}
private static OperationResult GenerateShuffleXor(CodeGenContext context, AstOperation operation)
{
- var x = context.GetFP32(operation.GetSource(0));
+ var value = context.GetFP32(operation.GetSource(0));
var index = context.GetU32(operation.GetSource(1));
- var mask = context.GetU32(operation.GetSource(2));
-
- var const31 = context.Constant(context.TypeU32(), 31);
- var const8 = context.Constant(context.TypeU32(), 8);
-
- var clamp = context.BitwiseAnd(context.TypeU32(), mask, const31);
- var segMask = context.BitwiseAnd(context.TypeU32(), context.ShiftRightLogical(context.TypeU32(), mask, const8), const31);
- var notSegMask = context.Not(context.TypeU32(), segMask);
- var clampNotSegMask = context.BitwiseAnd(context.TypeU32(), clamp, notSegMask);
-
- var threadId = GetScalarInput(context, IoVariable.SubgroupLaneId);
-
- var minThreadId = context.BitwiseAnd(context.TypeU32(), threadId, segMask);
- var maxThreadId = context.BitwiseOr(context.TypeU32(), minThreadId, clampNotSegMask);
- var srcThreadId = context.BitwiseXor(context.TypeU32(), threadId, index);
- var valid = context.ULessThanEqual(context.TypeBool(), srcThreadId, maxThreadId);
- var value = context.GroupNonUniformShuffle(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), x, srcThreadId);
- var result = context.Select(context.TypeFP32(), valid, value, x);
-
- var validLocal = (AstOperand)operation.GetSource(3);
- context.Store(context.GetLocalPointer(validLocal), context.BitcastIfNeeded(validLocal.VarType, AggregateType.Bool, valid));
+ var result = context.GroupNonUniformShuffleXor(context.TypeFP32(), context.Constant(context.TypeU32(), (int)Scope.Subgroup), value, index);
return new OperationResult(AggregateType.FP32, result);
}
generated by cgit v1.2.3-70-g09d2 (git 2.48.1) at 2025-03-25 01:38:01 +0000