New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[KT][ESIMD sort] Potential performance improvements #1312

Open

dmitriy-sobolev opened this issue Dec 11, 2023 · 0 comments

Assignees

Labels

Contributor

dmitriy-sobolev commented Dec 11, 2023

These are the gaps which remain after the main review (#1257):

Use global block load functions instead of gather when possible.
See discussion: [KT] ESIMD-based radix sort kernel templates #1257 (comment) and [KT] ESIMD-based radix sort kernel templates #1257 (comment)
Shrink types: variables and loop counters.
See discussions: [KT] ESIMD-based radix sort kernel templates #1257 (comment) and [KT] ESIMD-based radix sort kernel templates #1257 (comment)
Replace loops by vector operations.
See discussion: [KT] ESIMD-based radix sort kernel templates #1257 (comment)
Consider __data_per_work_item to be 32 (if this is a minimal granularity of data_per_workitem)
See discussion: [KT] ESIMD-based radix sort kernel templates #1257 (comment)

The text was updated successfully, but these errors were encountered:

dmitriy-sobolev added the enhancement label

dmitriy-sobolev self-assigned this

dmitriy-sobolev mentioned this issue

[KT] ESIMD-based radix sort kernel templates #1257

Merged

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment