Chm: Add auto-scaled benchmark and set num_threads to 64 #252
Conversation
By default, the thread count for the CHM benchmark is set to 80, which does not scale with the number of threads per socket across different platforms. This patch introduces an auto-scaled benchmark configuration that sets the thread count dynamically based on the number of logical threads available on a single socket, enabling fair performance comparison across different platforms at the single-socket level.
Different server has different cpus on single socket, some are less than 80. Also there are some threads are used for management and control purposes. To enable performance comparison under the same core count, set num_threads to 64.
|
Hi @zongyao8752593! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
meta-cla
bot
added
the
CLA Signed
|
@excelle08 has imported this pull request. If you are a Meta employee, you can view this in D85879022. |
1 participant
1, Add auto-scaled benchmark for chm.
By default, the thread count for the CHM benchmark is set to 80, which does not scale with the number of threads per socket across different platforms. This patch introduces an auto-scaled benchmark configuration that sets the thread count dynamically based on the number of logical threads available on a single socket, enabling fair performance comparison across different platforms at the single-socket level.
2, Set num_threads to 64.
Different server has different cpus on single socket, some are less than 80, one of our server has 72 cpus. Also there are some threads are used for management and control purposes. To enable performance comparison under the same core count, set num_threads to 64.