Skip to content
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.

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

Update GEMM XeTLA kernel of triton benchmarks #1597

Merged
merged 2 commits into from
Jul 24, 2024

Conversation

ESI-SYD
Copy link
Contributor

@ESI-SYD ESI-SYD commented Jul 10, 2024

@ESI-SYD ESI-SYD marked this pull request as draft July 10, 2024 05:55
@LiyangLingIntel
Copy link
Contributor

Based on the comment #1564 (comment), can you help change the folder name from "xetla_benchmark" to like "triton_kernels_benchmark". Because XeTLA performance is just for reference, we are actually measure Triton perf, current name is a bit confusing.

@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch 2 times, most recently from 737b0bb to fad7617 Compare July 10, 2024 07:25
@ESI-SYD ESI-SYD marked this pull request as ready for review July 12, 2024 01:28
@ESI-SYD ESI-SYD marked this pull request as draft July 12, 2024 06:58
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch from 90ed5c3 to 75b32f1 Compare July 12, 2024 07:10
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch 8 times, most recently from f68862f to 44f3fef Compare July 22, 2024 06:23
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch from 44f3fef to ab6dac4 Compare July 23, 2024 08:27
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch from ab6dac4 to e9dbbe8 Compare July 23, 2024 08:28
@ESI-SYD ESI-SYD marked this pull request as ready for review July 23, 2024 08:29
UR_L0_IN_ORDER_BARRIER_BY_SIGNAL=0 \
IGC_DisableLoopUnroll=1 \
NEO_CACHE_PERSISTENT=0 \
SYCL_PROGRAM_COMPILE_OPTIONS=" -vc-codegen -vc-disable-indvars-opt -doubleGRF -Xfinalizer ' -printregusage -enableBCR -DPASTokenReduction ' " \
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Here, it is necessary to specifically introduce SYCL_PROGRAM_COMPILE_OPTIONS to make XeTLA compile flag taking effect

@ESI-SYD ESI-SYD requested a review from pbchekin July 23, 2024 08:35
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch from 69994e3 to 5af1f42 Compare July 24, 2024 06:08
@ESI-SYD ESI-SYD force-pushed the yudong/align_gemm_microbench branch from 5af1f42 to b9de4c7 Compare July 24, 2024 06:48
@ESI-SYD ESI-SYD merged commit c97b7c5 into llvm-target Jul 24, 2024
6 of 7 checks passed
@ESI-SYD ESI-SYD deleted the yudong/align_gemm_microbench branch July 24, 2024 08:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[Productize GEMM performance #2] Update GEMM XeTLA kernel in triton repo
3 participants