Provide modified versions of ruby's matmul #24
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
Surprisingly, I expected the flat array to be faster but its about the same or even worse performance than the original in some scenarios, I assume thermal throttling since I tested this on an old gen-2 i7 laptop cpu. However, changing the Arrays to initialize their values inline saw a nice improvement (tested with 400 instead of 1500, since this is potato hardware and the latter takes FOREVER) Tests averaged around 15s, but the inline test can be as fast as 12.5s, would be interesting to see the numbers on the M1 chip
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Outdated suggestions cannot be applied.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.
In preparation to try a matmul for elixir, I figured I'd try refactoring the ruby matmul first to get a feel for it and managed to squeeze a bit more performance out of the code, the inline version tries to initialize the arrays through a single pass, this can save quite a bit of time as you don't need to do two passes over the array (once to zero all entries and then again to actual set the values).
I expected the flat_array implementation to do better, but it's about the same performance as the regular version, I suspect it might be the extra overhead from integer math or the way ruby allocates arrays internally.
None the less, I provide these as an improvement or alternative takes, the elixir version will be next.