Attempt to improve threading in ggml #343
Draft
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
|
Lot's of things have changed in six months, including that the segfault that happened when running more than 18 threads is now gone. Should we try this again? I attempted to rebase to mainline and tried to resolve the conflicts, but my runs livelock... so I clearly missed something. If you can rebase this branch and get it functional, I can help test. |
|
Would also like to see this rebased, as I'm having threading issues when running this as an XPC Service. |
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Outdated suggestions cannot be applied.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.
ref #200
Instead of creating and joining new threads for each graph compute, we create a thread pool with active threads and make them wait on a condition variable instead of joining.
Surprisingly, this does not seem to improve the performance.
It is actually degraded. Not sure what is going on.