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

[do not merge] Enable smem-epilogue and manual fix sync #3563

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

zasdfgbnm
Copy link
Collaborator

@zasdfgbnm zasdfgbnm commented Dec 11, 2024

In this branch, I enabled the smem epilogue, dump a kernel, and manually fixes #3561 by modifying the generated kernel. This will be the baseline of my other experiments. nsys benchmark on H200 is attached into this branch, here is the result:

 Time (%)  Total Time (ns)  Instances  Avg (ns)  Med (ns)  Min (ns)  Max (ns)  StdDev (ns)                                                  Name

 --------  ---------------  ---------  --------  --------  --------  --------  -----------  ----------------------------------------------------------------------------------------------------
     34.3           135137          1  135137.0  135137.0    135137    135137          0.0  <unnamed>::nvfuser_none_f0_c0_r0_g0(<unnamed>::Tensor<<unnamed>::__half, (int)3, (int)3>, <unnamed>…
     22.2            87521          1   87521.0   87521.0     87521     87521          0.0  nvjet_hsh_256x128_64x4_1x2_h_bz_coopA_NTT

nvFuser/cuBLAS = 64.8%

The command I used to run the benchmark:

NVFUSER_EXTERNAL_SRC="__tmp_kernel_none_f0_c0_r0_g0.cu" nsys nvprof ./bin/test_matmul --gtest_filter=HopperMatmulTest.HSH_NT_128BSwizzle

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Missing sync in matmul kernel
2 participants