Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.
6977 Discussions

cblas_gemm_s8s8s32 not support？

qiang__zhang
Beginner
‎04-16-2020 01:12 AM
477 Views

Dear sir，

I hava a question：

I read the oneDNN code， that seams cblas_gemm_s8s8s32（） is not implemented，just cblas_gemm_s8u8s32，why？

Because ISA of intel （AVX2？）has not special instructions that can execute multiplying or adding  operation when the two vectors have the same data type (either s8/s8 or u8/u8)？

 

Thank you！

0 Kudos

Link Copied

1 Reply
Gennady_F_Intel
Moderator
‎04-16-2020 09:10 PM
477 Views

Yes, mkl provides cblas_gemm_s8u8s32 API only as there are no specific instructions to perform s8s8s32 operations. The latest CPU contains vpmaddubsw instruction which supports only s8u8s32.

 

 

 

0 Kudos
Copy link
Reply

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.