topic missing arg in oneMKL doc in Intel® oneAPI Math Kernel Library

missing arg in oneMKL doc

syk1 — Mon, 13 Sep 2021 03:56:52 GMT

see gemm batch strided

https://software.intel.com/content/www/us/en/develop/documentation/onemkl-developer-reference-fortran/top/blas-and-sparse-blas-routines/blas-like-extensions/gemm-batch-strided.html

call sgemm_batch_strided(transa, transb, m, n, k, alpha, a, lda, stridea, b, ldb, strideb, c, ldc, stridec, batch_size)

There should be a beta between strideb and c.

This value will scale c with beta for accumulation.

It's missing in the official doc.

Re:missing arg in oneMKL doc

VidyalathaB_Intel — Tue, 14 Sep 2021 07:16:37 GMT

Hi,

Thanks for bringing it to our notice.

We are looking into it, we will get back to you soon.

Regards,

Vidya.

Re:missing arg in oneMKL doc

Gennady_F_Intel — Tue, 14 Sep 2021 12:43:23 GMT

The issue is escalated and will be fixed in one of the next updates. We will keep this thread updated.

-Gennady

Re:missing arg in oneMKL doc

Gennady_F_Intel — Fri, 01 Oct 2021 03:34:50 GMT

Intel oneAPI Math Kernel Library (oneMKL) version 2021.4 is now available. The MKL Developer Reference has been updated.

Re:missing arg in oneMKL doc

Gennady_F_Intel — Fri, 01 Oct 2021 03:35:09 GMT

This issue has been resolved and we will no longer respond to this thread. If you require additional assistance from Intel, please start a new thread. Any further interaction in this thread will be considered community only.