Skip to content

[HLSL] Correct LinAlg OuterProduct accumulator use #8662

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
Jack Elliott (JoeCitizen) merged 1 commit into from
Jul 28, 2026
Merged

[HLSL] Correct LinAlg OuterProduct accumulator use #8662

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 4 additions & 2 deletions tools/clang/unittests/HLSLExec/LinAlgTests.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1395,7 +1395,6 @@ static D3D12_LINEAR_ALGEBRA_DATATYPE toLinAlgDataType(ComponentType CT) {
}

static const char OuterProductShader[] = R"(
#define USE_A 0
#define SCOPE_THREAD 0

RWByteAddressBuffer Input : register(u0);
Expand All @@ -1416,7 +1415,7 @@ static const char OuterProductShader[] = R"(
}

__builtin_LinAlgMatrix
[[__LinAlgMatrix_Attributes(COMP_TYPE, M_DIM, N_DIM, USE_A, SCOPE_THREAD)]]
[[__LinAlgMatrix_Attributes(COMP_TYPE, M_DIM, N_DIM, USE, SCOPE_THREAD)]]
Mat;
__builtin_LinAlg_MatrixOuterProduct(Mat, VecA, VecB);

Expand All @@ -1434,6 +1433,8 @@ static void runOuterProduct(ID3D12Device *Device,
VERIFY_IS_TRUE(
Params.Layout == MatrixLayout::OuterProductOptimal,
"Outer product must output its matrix in OuterProductOptimal layout");
VERIFY_IS_TRUE(Params.Use == MatrixUse::Accumulator,
"Outer product must output an accumulator matrix");
const size_t NumVecElements = Params.M + Params.N;
const size_t InBuffSize = NumVecElements * elementSize(Params.CompType);
const size_t NumMatElements = Params.totalElements();
Expand Down Expand Up @@ -1502,6 +1503,7 @@ void DxilConf_SM610_LinAlg::OuterProduct_Thread_16x16_F16() {
Params.CompType = ComponentType::F16;
Params.M = 16;
Params.N = 16;
Params.Use = MatrixUse::Accumulator;
Params.Scope = MatrixScope::Thread;
Params.Layout = MatrixLayout::OuterProductOptimal;
Params.NumThreads = 1;
Expand Down
Loading