Intel® Optimized AI Frameworks
Receive community support for questions related to PyTorch* and TensorFlow* frameworks.
Announcements
FPGA community forums and blogs on community.intel.com are migrating to the new Altera Community and are read-only. For urgent support needs during this transition, please visit the FPGA Design Resources page or contact an Altera Authorized Distributor.

signed 8-bit * signed 8-bit VNNI

lin__chiungliang
Beginner
1,731 Views

Hi,

I'm trying to use VNNI in my program.

I ran the sample code, which do MAC operation by _mm512_dpbusds_epi32,

I found that it's singed 8-bit and unsigned 8-bit operation

Does there any optimized instruction support

1. signed 8-bit and signed 8-bit MAC operation

2. unsigned 8-bit and unsigned 8-bit MAC operation

Lot of thanks

chiungliang

0 Kudos
3 Replies
AthiraM_Intel
Moderator
1,731 Views

Hi,

We are forwarding this case to technical experts.They will assist you shortly.

Thanks

0 Kudos
Louie_T_Intel
Moderator
1,731 Views

Hi chiungliang

sorry for late response.

this question is more related to general compiler issue, and it would be better to let our compiler experts to answer this question.

This forum can help on DL libraries and framework related questions, but you should get better support for intrinsic programming in compiler forum.

Would you mind posting the same question in below forum?

https://software.intel.com/en-us/forums/intel-c-compiler

 

thanks

0 Kudos
ArunJ_Intel
Moderator
1,731 Views

Closing this case as it is adressed in intel-c-compiler forum. Link to question is given below

 

https://software.intel.com/en-us/forums/intel-c-compiler/topic/849943

0 Kudos
Reply