Intel® oneAPI Data Parallel C++
Support for Intel® oneAPI DPC++ Compiler, Intel® oneAPI DPC++ Library, Intel ICX Compiler , Intel® DPC++ Compatibility Tool, and GDB*

example of subgroup shuffle?

Scout
Beginner
1,213 Views

hello, I'm looking into how to use subgroup shuffle to get maximum performance for matrix multiply. And I searched online and couldn't find an example of how to use the "shuffle" feature to share data within work-items in a sub-group. Attached article gives some instructions but there is no full code. Is there any read-to-go code to demostrate how to use "shuffle"? Thanks in advance! 

0 Kudos
4 Replies
Scout
Beginner
1,184 Views
0 Kudos
NoorjahanSk_Intel
Moderator
1,163 Views

Hi,


Thanks for reaching out to us.


Please refer to the below link for more details regarding sub_group_shuffle


https://www.intel.com/content/www/us/en/develop/documentation/oneapi-gpu-optimization-guide/top/kernels/sub-group.html#sub-groups-and-simd-vectorization_data-sharing


You can also refer to Data Parallel C++ Textbook page no: 116 for more details on sub_group.


Thanks & Regards,

Noorjahan.


0 Kudos
NoorjahanSk_Intel
Moderator
1,111 Views

Hi,


We haven't heard back from you. Could you please provide an update on your issue?


Thanks & Regards,

Noorjahan.


0 Kudos
NoorjahanSk_Intel
Moderator
1,073 Views

Hi,


I have not heard back from you, so I will close this inquiry now. If you need further assistance, please post a new question.


Thanks & Regards,

Noorjahan.


0 Kudos
Reply