Skip to content

Comments

Provide modified versions of ruby's matmul#24

Open
IceDragon200 wants to merge 1 commit intoattractivechaos:masterfrom
IceDragon200:ruby-alts
Open

Provide modified versions of ruby's matmul#24
IceDragon200 wants to merge 1 commit intoattractivechaos:masterfrom
IceDragon200:ruby-alts

Conversation

@IceDragon200
Copy link
Contributor

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.

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant