Skip to content

[BenchGC] attach DLTI for mlir module #312

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

Merged
merged 56 commits into from
Sep 10, 2024
Merged

Conversation

xurui1995
Copy link
Contributor

@xurui1995 xurui1995 commented Sep 2, 2024

  • add code for getting the cpuinfo
  • provides --cpu_cache_sizes and --max_vector_width for user to add the dlti manually
  • using env GC_NUM_THREADS to set the 'num_threads' of dlti

@xurui1995
Copy link
Contributor Author

xurui1995 commented Sep 3, 2024

Currently there is a issue for the lib py-cpuinfo on the CI machine, the l1_data_cache_size is from the 'lscpu' output, and the value is 4.5 MiB which can not be converted into int bytes and seems not the per core size.
I am trying some new solutions for getting cache size.

@xurui1995 xurui1995 added WIP work in progress and removed ready to review labels Sep 3, 2024
@xurui1995 xurui1995 added ready to review and removed WIP work in progress labels Sep 5, 2024
@xurui1995 xurui1995 merged commit 9f9e5aa into intel:main Sep 10, 2024
6 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

MLIR MLP benchmarking driver lacks DLTI config info
5 participants