[HLSL][DirectX] Fix dot2add DXIL operation to use float overload
#152781
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
llvmbot
added
clang
|
@llvm/pr-subscribers-clang @llvm/pr-subscribers-backend-directx Author: Kaitlin Peng (kmpeng) ChangesFixes #152585. The Full diff: https://github.com/llvm/llvm-project/pull/152781.diff 3 Files Affected:
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
}
|
|
@llvm/pr-subscribers-hlsl Author: Kaitlin Peng (kmpeng) ChangesFixes #152585. The Full diff: https://github.com/llvm/llvm-project/pull/152781.diff 3 Files Affected:
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
}
|
kmpeng
force-pushed
the
bugfix/dot2add-overload
branch
from
4447521 to
81d1e32
Compare
farzonl
reviewed
Aug 11, 2025
farzonl
approved these changes
Aug 11, 2025
kmpeng
force-pushed
the
bugfix/dot2add-overload
branch
from
ab68be8 to
3fede1b
Compare
kmpeng
force-pushed
the
bugfix/dot2add-overload
branch
from
3fede1b to
88b605f
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #152585.
The
dot2addDXILOpFunction should bedx.op.dot2AddHalf.f32(i.e. it has a single overload that's a float, rather than no overloads). It was also being defined for too low of a DXIL version - dxc says SM6.4.