Skip to content

Conversation

@jorgecarleitao
Copy link
Contributor

No description provided.

@jorgecarleitao
Copy link
Contributor Author

cc @Dandandan. It seems that the gather won't help (at least in skylake-avx512).

@Dandandan
Copy link

Dandandan commented Nov 25, 2021

Interesting!
On my computer (no avx512 AFAIK) the core_simd_take benchmark is slightly (~6-7%) faster than naive_take.

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.

3 participants