Skip to content

GPU support via NVBLAS #239

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

Closed
wants to merge 1 commit into from
Closed

GPU support via NVBLAS #239

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
24 changes: 19 additions & 5 deletions ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,6 +96,8 @@ typedef void* thread_ret_t;
#include <Accelerate/Accelerate.h>
#elif GGML_USE_OPENBLAS
#include <cblas.h>
// sgemm
extern void sgemm_(char* transa, char* transb, int* m, int* n, int* k, float* alpha, float* a, int* lda, float* b, int* ldb, float* beta, float* c, int* ldc);
#endif

// floating point type used to accumulate sums
Expand Down Expand Up @@ -4588,11 +4590,23 @@ void ggml_compute_forward_mul_mat_f16_f32(

// zT = y * xT
{
cblas_sgemm(CblasRowMajor, CblasNoTrans, CblasTrans,
ne11, ne01, ne10,
1.0f, y, ne10,
x, ne10,
0.0f, d, ne01);
//cblas_sgemm(CblasRowMajor, CblasNoTrans, CblasTrans,
// ne11, ne01, ne10,
// 1.0f, y, ne10,
// x, ne10,
// 0.0f, d, ne01);

// this is compatible with nvblas
float one = 1.0f;
float zero = 0.0f;
sgemm_(
"T", "N",
&ne0, &ne1, &ne10,
&one,
x, &ne10,
y, &ne10,
&zero,
d, &ne0);
}
}
}
Expand Down