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.

Sign up for GitHub

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

Jump to bottom

[Benchmarks] Add microbenchmark with A^t@B #2424

Closed
Egor-Krivov opened this issue Oct 4, 2024 · 0 comments · Fixed by #2430
Closed

[Benchmarks] Add microbenchmark with A^t@B #2424

Egor-Krivov opened this issue Oct 4, 2024 · 0 comments · Fixed by #2430
Assignees
@Egor-Krivov
Labels
enhancement New feature or request performance
Milestone
4.3 [Performance]...

Comments

@Egor-Krivov
Copy link
Contributor

This GEMM is relevant for GEMM backprop for example

Related to #1795
@Egor-Krivov Egor-Krivov mentioned this issue Oct 4, 2024
Closed
@vlad-penkin vlad-penkin added enhancement New feature or request performance labels Oct 4, 2024
@vlad-penkin vlad-penkin added this to the 4.3 [Performance] Tracking milestone Oct 4, 2024
@Egor-Krivov Egor-Krivov mentioned this issue Oct 7, 2024
Merged
Egor-Krivov added a commit that referenced this issue Oct 8, 2024
@Egor-Krivov
Add A^t@B benchmark (#2430)
b12d0dd 
Based on this feedback
#2408 (review)

Changed GEMM benchmark to include transposed matrices case.

Closes #2424
Relates to
#1795

A@B^t case is important because weight matrix is often stored in [M, K]
format. For example, in
https://pytorch.org/docs/stable/generated/torch.nn.Linear.html
Right now we are about 1.5 times slower on XPU against raw torch for
that case.


A^t@B case is important because it's part of matmul backprop. Right now
we are about 4 times slower on XPU against raw torch for that case.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Egor-Krivov Egor-Krivov

Labels
enhancement New feature or request performance
Projects
None yet
Milestone
4.3 [Performance] Tracking
Development

Successfully merging a pull request may close this issue.

Add A^t@B benchmark intel/intel-xpu-backend-for-triton
2 participants
@Egor-Krivov @vlad-penkin