Allow users specify number of threads when running on CPU via the extension to --always-cpu arg #1601
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
I have changed the
--always-cpuargument to integer, if in the command line this argument is followed by a number greater than 0 it will be used intorch.set_num_threads()and override the default value.On my 8 core AMD 7840U which supports 16 threads I noticed I got ~70% CPU utilization while running image generation. As i discovered PyTorch doesn't seem to be benefiting from SMT and sets the number of threads to the number of physical cores.
By increasing the number of threads from default 8 to 15 I received ~5% performance increase and 100% CPU utilization (see screenshots).
8 threads, 78.2 seconds/iteration
15 threads, 72.8% seconds/iteration
