llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-backend-directx Author: Kaitlin Peng (kmpeng) <details> <summary>Changes</summary> Fixes #<!-- -->152585. The `dot2add` DXILOpFunction should be `dx.op.dot2AddHalf.f32` (i.e. it has [a single overload that's a float](https://github.com/microsoft/DirectXShaderCompiler/blob/main/utils/hct/hctdb.py#L3960), rather than no overloads). It was also being defined for too low of a DXIL version - [dxc says SM6.4](https://github.com/microsoft/DirectXShaderCompiler/blob/main/utils/hct/hctdb.py#L740). --- Full diff: https://github.com/llvm/llvm-project/pull/152781.diff 3 Files Affected: - (modified) clang/test/CodeGenHLSL/builtins/dot2add.hlsl (+1-1) - (modified) llvm/lib/Target/DirectX/DXIL.td (+5-5) - (modified) llvm/test/CodeGen/DirectX/dot2add.ll (+2-2) ``````````diff diff --git a/clang/test/CodeGenHLSL/builtins/dot2add.hlsl b/clang/test/CodeGenHLSL/builtins/dot2add.hlsl index c345e17476e08..7c3a48e476306 100644 --- a/clang/test/CodeGenHLSL/builtins/dot2add.hlsl +++ b/clang/test/CodeGenHLSL/builtins/dot2add.hlsl @@ -1,5 +1,5 @@ // RUN: %clang_cc1 -finclude-default-header -fnative-half-type -triple \ -// RUN: dxil-pc-shadermodel6.3-compute %s -emit-llvm -o - | \ +// RUN: dxil-pc-shadermodel6.4-compute %s -emit-llvm -o - | \ // RUN: FileCheck %s --check-prefixes=CHECK,CHECK-DXIL // RUN: %clang_cc1 -finclude-default-header -fnative-half-type -triple \ // RUN: spirv-pc-vulkan-compute %s -emit-llvm -o - | \ diff --git a/llvm/lib/Target/DirectX/DXIL.td b/llvm/lib/Target/DirectX/DXIL.td index 492e0784cedd0..c65ead45e2c7e 100644 --- a/llvm/lib/Target/DirectX/DXIL.td +++ b/llvm/lib/Target/DirectX/DXIL.td @@ -1108,11 +1108,11 @@ def RawBufferStore : DXILOp<140, rawBufferStore> { def Dot2AddHalf : DXILOp<162, dot2AddHalf> { let Doc = "2D half dot product with accumulate to float"; let intrinsics = [IntrinSelect<int_dx_dot2add>]; - let arguments = [FloatTy, HalfTy, HalfTy, HalfTy, HalfTy]; - let result = FloatTy; - let overloads = [Overloads<DXIL1_0, []>]; - let stages = [Stages<DXIL1_0, [all_stages]>]; - let attributes = [Attributes<DXIL1_0, [ReadNone]>]; + let arguments = [OverloadTy, HalfTy, HalfTy, HalfTy, HalfTy]; + let result = OverloadTy; + let overloads = [Overloads<DXIL1_4, [FloatTy]>]; + let stages = [Stages<DXIL1_4, [all_stages]>]; + let attributes = [Attributes<DXIL1_4, [ReadNone]>]; } def Dot4AddI8Packed : DXILOp<163, dot4AddPacked> { diff --git a/llvm/test/CodeGen/DirectX/dot2add.ll b/llvm/test/CodeGen/DirectX/dot2add.ll index 3a2bbcc074f2d..5e1cf405752ba 100644 --- a/llvm/test/CodeGen/DirectX/dot2add.ll +++ b/llvm/test/CodeGen/DirectX/dot2add.ll @@ -1,4 +1,4 @@ -; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.3-compute %s | FileCheck %s +; RUN: opt -S -dxil-op-lower -mtriple=dxil-pc-shadermodel6.4-compute %s | FileCheck %s define noundef float @dot2add_simple(<2 x half> noundef %a, <2 x half> noundef %b, float %acc) { entry: @@ -7,7 +7,7 @@ entry: %bx = extractelement <2 x half> %b, i32 0 %by = extractelement <2 x half> %b, i32 1 -; CHECK: call float @dx.op.dot2AddHalf(i32 162, float %acc, half %ax, half %ay, half %bx, half %by) +; CHECK: call float @dx.op.dot2AddHalf.f32(i32 162, float %acc, half %ax, half %ay, half %bx, half %by) %ret = call float @llvm.dx.dot2add(float %acc, half %ax, half %ay, half %bx, half %by) ret float %ret } `````````` </details> https://github.com/llvm/llvm-project/pull/152781 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
