Skip to content

[HLSL][SPIR-V] implement SV_GroupID semantic lowering #121521

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jan 4, 2025
Merged

[HLSL][SPIR-V] implement SV_GroupID semantic lowering #121521

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
21114c4
[HLSL][SPIR-V] implement SV_GroupID semantic lowering
Jan 2, 2025
b4cde3b
Clean up SV_GroupID.ll test
Jan 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion clang/lib/CodeGen/CGHLSLRuntime.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -395,7 +395,7 @@ llvm::Value *CGHLSLRuntime::emitInputSemantic(IRBuilder<> &B,
return buildVectorInput(B, GroupThreadIDIntrinsic, Ty);
}
if (D.hasAttr<HLSLSV_GroupIDAttr>()) {
llvm::Function *GroupIDIntrinsic = CGM.getIntrinsic(Intrinsic::dx_group_id);
llvm::Function *GroupIDIntrinsic = CGM.getIntrinsic(getGroupIdIntrinsic());
return buildVectorInput(B, GroupIDIntrinsic, Ty);
}
assert(false && "Unhandled parameter attribute");
Expand Down
1 change: 1 addition & 0 deletions clang/lib/CodeGen/CGHLSLRuntime.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,6 +87,7 @@ class CGHLSLRuntime {
GENERATE_HLSL_INTRINSIC_FUNCTION(Radians, radians)
GENERATE_HLSL_INTRINSIC_FUNCTION(ThreadId, thread_id)
GENERATE_HLSL_INTRINSIC_FUNCTION(GroupThreadId, thread_id_in_group)
GENERATE_HLSL_INTRINSIC_FUNCTION(GroupId, group_id)
GENERATE_HLSL_INTRINSIC_FUNCTION(FDot, fdot)
GENERATE_HLSL_INTRINSIC_FUNCTION(SDot, sdot)
GENERATE_HLSL_INTRINSIC_FUNCTION(UDot, udot)
Expand Down
34 changes: 19 additions & 15 deletions clang/test/CodeGenHLSL/semantics/SV_GroupID.hlsl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,32 +1,36 @@
// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.3-library -x hlsl -emit-llvm -finclude-default-header -disable-llvm-passes -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple dxil-pc-shadermodel6.3-library -x hlsl -emit-llvm -finclude-default-header -disable-llvm-passes -o - %s | FileCheck %s --check-prefixes=CHECK,CHECK-DXIL -DTARGET=dx
// RUN: %clang_cc1 -triple spirv-linux-vulkan-library -x hlsl -emit-llvm -finclude-default-header -disable-llvm-passes -o - %s | FileCheck %s --check-prefixes=CHECK,CHECK-SPIRV -DTARGET=spv

// Make sure SV_GroupID translated into dx.group.id.
// Make sure SV_GroupID translated into dx.group.id for directx target and spv.group.id for spirv target.

// CHECK: define void @foo()
// CHECK: %[[#ID:]] = call i32 @llvm.dx.group.id(i32 0)
// CHECK: call void @{{.*}}foo{{.*}}(i32 %[[#ID]])
// CHECK: define void @foo()
// CHECK: %[[#ID:]] = call i32 @llvm.[[TARGET]].group.id(i32 0)
// CHECK-DXIL: call void @{{.*}}foo{{.*}}(i32 %[[#ID]])
// CHECK-SPIRV: call spir_func void @{{.*}}foo{{.*}}(i32 %[[#ID]])
[shader("compute")]
[numthreads(8,8,1)]
void foo(uint Idx : SV_GroupID) {}

// CHECK: define void @bar()
// CHECK: %[[#ID_X:]] = call i32 @llvm.dx.group.id(i32 0)
// CHECK: %[[#ID_X_:]] = insertelement <2 x i32> poison, i32 %[[#ID_X]], i64 0
// CHECK: %[[#ID_Y:]] = call i32 @llvm.dx.group.id(i32 1)
// CHECK: %[[#ID_XY:]] = insertelement <2 x i32> %[[#ID_X_]], i32 %[[#ID_Y]], i64 1
// CHECK: call void @{{.*}}bar{{.*}}(<2 x i32> %[[#ID_XY]])
// CHECK: define void @bar()
// CHECK: %[[#ID_X:]] = call i32 @llvm.[[TARGET]].group.id(i32 0)
// CHECK: %[[#ID_X_:]] = insertelement <2 x i32> poison, i32 %[[#ID_X]], i64 0
// CHECK: %[[#ID_Y:]] = call i32 @llvm.[[TARGET]].group.id(i32 1)
// CHECK: %[[#ID_XY:]] = insertelement <2 x i32> %[[#ID_X_]], i32 %[[#ID_Y]], i64 1
// CHECK-DXIL: call void @{{.*}}bar{{.*}}(<2 x i32> %[[#ID_XY]])
// CHECK-SPIRV: call spir_func void @{{.*}}bar{{.*}}(<2 x i32> %[[#ID_XY]])
[shader("compute")]
[numthreads(8,8,1)]
void bar(uint2 Idx : SV_GroupID) {}

// CHECK: define void @test()
// CHECK: %[[#ID_X:]] = call i32 @llvm.dx.group.id(i32 0)
// CHECK: %[[#ID_X:]] = call i32 @llvm.[[TARGET]].group.id(i32 0)
// CHECK: %[[#ID_X_:]] = insertelement <3 x i32> poison, i32 %[[#ID_X]], i64 0
// CHECK: %[[#ID_Y:]] = call i32 @llvm.dx.group.id(i32 1)
// CHECK: %[[#ID_Y:]] = call i32 @llvm.[[TARGET]].group.id(i32 1)
// CHECK: %[[#ID_XY:]] = insertelement <3 x i32> %[[#ID_X_]], i32 %[[#ID_Y]], i64 1
// CHECK: %[[#ID_Z:]] = call i32 @llvm.dx.group.id(i32 2)
// CHECK: %[[#ID_Z:]] = call i32 @llvm.[[TARGET]].group.id(i32 2)
// CHECK: %[[#ID_XYZ:]] = insertelement <3 x i32> %[[#ID_XY]], i32 %[[#ID_Z]], i64 2
// CHECK: call void @{{.*}}test{{.*}}(<3 x i32> %[[#ID_XYZ]])
// CHECK-DXIL: call void @{{.*}}test{{.*}}(<3 x i32> %[[#ID_XYZ]])
// CHECK-SPIRV: call spir_func void @{{.*}}test{{.*}}(<3 x i32> %[[#ID_XYZ]])
[shader("compute")]
[numthreads(8,8,1)]
void test(uint3 Idx : SV_GroupID) {}
1 change: 1 addition & 0 deletions llvm/include/llvm/IR/IntrinsicsSPIRV.td
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,6 +59,7 @@ let TargetPrefix = "spv" in {

// The following intrinsic(s) are mirrored from IntrinsicsDirectX.td for HLSL support.
def int_spv_thread_id : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
def int_spv_group_id : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
def int_spv_thread_id_in_group : Intrinsic<[llvm_i32_ty], [llvm_i32_ty], [IntrNoMem, IntrWillReturn]>;
def int_spv_all : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_any_ty], [IntrNoMem]>;
def int_spv_any : DefaultAttrsIntrinsic<[llvm_i1_ty], [llvm_any_ty], [IntrNoMem]>;
Expand Down
8 changes: 8 additions & 0 deletions llvm/lib/Target/SPIRV/SPIRVInstructionSelector.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2881,6 +2881,14 @@ bool SPIRVInstructionSelector::selectIntrinsic(Register ResVReg,
// translated to a `LocalInvocationId` builtin variable
return loadVec3BuiltinInputID(SPIRV::BuiltIn::LocalInvocationId, ResVReg,
ResType, I);
case Intrinsic::spv_group_id:
// The HLSL SV_GroupId semantic is lowered to
// llvm.spv.group.id intrinsic in LLVM IR for SPIR-V backend.
//
// In SPIR-V backend, llvm.spv.group.id is now translated to a `WorkgroupId`
// builtin variable
return loadVec3BuiltinInputID(SPIRV::BuiltIn::WorkgroupId, ResVReg, ResType,
I);
case Intrinsic::spv_fdot:
return selectFloatDot(ResVReg, ResType, I);
case Intrinsic::spv_udot:
Expand Down
82 changes: 82 additions & 0 deletions llvm/test/CodeGen/SPIRV/hlsl-intrinsics/SV_GroupID.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,82 @@
; RUN: llc -O0 -verify-machineinstrs -mtriple=spirv-vulkan-unknown %s -o - | FileCheck %s
; RUN: %if spirv-tools %{ llc -O0 -mtriple=spirv-vulkan-unknown %s -o - -filetype=obj | spirv-val %}

; This file generated from the following command:
; clang -cc1 -triple spirv-vulkan-library -x hlsl -emit-llvm -disable-llvm-passes -finclude-default-header - -o - <<EOF
; [shader("compute")]
; [numthreads(1,1,1)]
; void main(uint3 ID : SV_GroupID) {}
; EOF

; CHECK-DAG: %[[#int:]] = OpTypeInt 32 0
; CHECK-DAG: %[[#v3int:]] = OpTypeVector %[[#int]] 3
; CHECK-DAG: %[[#ptr_Input_v3int:]] = OpTypePointer Input %[[#v3int]]
; CHECK-DAG: %[[#tempvar:]] = OpUndef %[[#v3int]]
; CHECK-DAG: %[[#WorkgroupId:]] = OpVariable %[[#ptr_Input_v3int]] Input

; CHECK-DAG: OpEntryPoint GLCompute {{.*}} %[[#WorkgroupId]]
; CHECK-DAG: OpName %[[#WorkgroupId]] "__spirv_BuiltInWorkgroupId"
; CHECK-DAG: OpDecorate %[[#WorkgroupId]] LinkageAttributes "__spirv_BuiltInWorkgroupId" Import
; CHECK-DAG: OpDecorate %[[#WorkgroupId]] BuiltIn WorkgroupId

; ModuleID = '-'
source_filename = "-"
target datalayout = "e-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-n8:16:32:64-G1"
target triple = "spirv-unknown-vulkan-library"

; Function Attrs: alwaysinline convergent mustprogress norecurse nounwind
define internal spir_func void @_Z4mainDv3_j(<3 x i32> noundef %ID) #0 {
entry:
%0 = call token @llvm.experimental.convergence.entry()
%ID.addr = alloca <3 x i32>, align 16
store <3 x i32> %ID, ptr %ID.addr, align 16
ret void
}

; Function Attrs: convergent noinline norecurse
define void @main() #1 {
entry:
%0 = call token @llvm.experimental.convergence.entry()

; CHECK: %[[#load:]] = OpLoad %[[#v3int]] %[[#WorkgroupId]]
; CHECK: %[[#load0:]] = OpCompositeExtract %[[#int]] %[[#load]] 0
%1 = call i32 @llvm.spv.group.id(i32 0)

; CHECK: %[[#tempvar:]] = OpCompositeInsert %[[#v3int]] %[[#load0]] %[[#tempvar]]
%2 = insertelement <3 x i32> poison, i32 %1, i64 0

; CHECK: %[[#load:]] = OpLoad %[[#v3int]] %[[#WorkgroupId]]
; CHECK: %[[#load1:]] = OpCompositeExtract %[[#int]] %[[#load]] 1
%3 = call i32 @llvm.spv.group.id(i32 1)

; CHECK: %[[#tempvar:]] = OpCompositeInsert %[[#v3int]] %[[#load1]] %[[#tempvar]] 1
%4 = insertelement <3 x i32> %2, i32 %3, i64 1

; CHECK: %[[#load:]] = OpLoad %[[#v3int]] %[[#WorkgroupId]]
; CHECK: %[[#load2:]] = OpCompositeExtract %[[#int]] %[[#load]] 2
%5 = call i32 @llvm.spv.group.id(i32 2)

; CHECK: %[[#tempvar:]] = OpCompositeInsert %[[#v3int]] %[[#load2]] %[[#tempvar]] 2
%6 = insertelement <3 x i32> %4, i32 %5, i64 2

call spir_func void @_Z4mainDv3_j(<3 x i32> %6) [ "convergencectrl"(token %0) ]
ret void
}

; Function Attrs: convergent nocallback nofree nosync nounwind willreturn memory(none)
declare token @llvm.experimental.convergence.entry() #2

; Function Attrs: nounwind willreturn memory(none)
declare i32 @llvm.spv.group.id(i32) #3

attributes #0 = { alwaysinline convergent mustprogress norecurse nounwind "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
attributes #1 = { convergent noinline norecurse "hlsl.numthreads"="1,1,1" "hlsl.shader"="compute" "no-trapping-math"="true" "stack-protector-buffer-size"="8" }
attributes #2 = { convergent nocallback nofree nosync nounwind willreturn memory(none) }
attributes #3 = { nounwind willreturn memory(none) }

!llvm.module.flags = !{!0, !1}
!llvm.ident = !{!2}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{i32 4, !"dx.disable_optimizations", i32 1}
!2 = !{!"clang version 20.0.0git (https://github.com/llvm/llvm-project.git 4075ddad7183e6f0b66e2c8cc7a03b461a8038e6)"}
Loading