Skip to content
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

fix: BLAS batch strided needs sufficiently new MKL #49

Merged
merged 1 commit into from
Sep 29, 2023
Merged

fix: BLAS batch strided needs sufficiently new MKL #49

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
4 changes: 2 additions & 2 deletions c++/nda/blas/interface/cxx_interface.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -135,15 +135,15 @@ namespace nda::blas::f77 {

void gemm_batch_strided(char op_a, char op_b, int M, int N, int K, double alpha, const double *A, int LDA, int strideA, const double *B, int LDB,
int strideB, double beta, double *C, int LDC, int strideC, int batch_count) {
#ifdef NDA_USE_MKL
#if defined(NDA_USE_MKL) && INTEL_MKL_VERSION >= 20200002
dgemm_batch_strided(&op_a, &op_b, &M, &N, &K, &alpha, A, &LDA, &strideA, B, &LDB, &strideB, &beta, C, &LDC, &strideC, &batch_count);
#else
for (int i = 0; i < batch_count; ++i) gemm(op_a, op_b, M, N, K, alpha, A + i * strideA, LDA, B + i * strideB, LDB, beta, C + i * strideC, LDC);
#endif
}
void gemm_batch_strided(char op_a, char op_b, int M, int N, int K, dcomplex alpha, const dcomplex *A, int LDA, int strideA, const dcomplex *B,
int LDB, int strideB, dcomplex beta, dcomplex *C, int LDC, int strideC, int batch_count) {
#ifdef NDA_USE_MKL
#if defined(NDA_USE_MKL) && INTEL_MKL_VERSION >= 20200002
zgemm_batch_strided(&op_a, &op_b, &M, &N, &K, mklcplx(&alpha), mklcplx(A), &LDA, &strideA, mklcplx(B), &LDB, &strideB, mklcplx(&beta), mklcplx(C),
&LDC, &strideC, &batch_count);
#else
Expand Down
Loading