Skip to content
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

Add vectorized unpacking for 8, 16, and 64 bit integers #2276

Closed
tustvold opened this issue Aug 2, 2022 · 0 comments · Fixed by #2278
Closed

Add vectorized unpacking for 8, 16, and 64 bit integers #2276

tustvold opened this issue Aug 2, 2022 · 0 comments · Fixed by #2278
Assignees
@tustvold
Labels
enhancement Any new improvement worthy of a entry in the changelog parquet Changes to the parquet crate performance

Comments

@tustvold
Copy link
Contributor

tustvold commented Aug 2, 2022

Is your feature request related to a problem or challenge? Please describe what you are trying to do.

Currently we have vectorised unpacking of 32-bit integers. We then extend or truncate this to support smaller or larger destination types.

Describe the solution you'd like

I would like optimised kernels for all 4 common sizes of packed representation

Describe alternatives you've considered

Additional context
@tustvold tustvold added the enhancement Any new improvement worthy of a entry in the changelog label Aug 2, 2022
@tustvold tustvold self-assigned this Aug 2, 2022
tustvold added a commit to tustvold/arrow-rs that referenced this issue Aug 2, 2022
@tustvold
Add unpack8, unpack16, unpack64 (apache#2276)
766e478
tustvold added a commit to tustvold/arrow-rs that referenced this issue Aug 2, 2022
@tustvold
Add unpack8, unpack16, unpack64 (apache#2276)
fd82128
This was referenced Aug 2, 2022
Merged
Open
tustvold added a commit that referenced this issue Aug 3, 2022
@tustvold
Add unpack8, unpack16, unpack64 (#2276) ~10-50% faster (#2278)
8a092e3 
* Add unpack8, unpack16, unpack64 (#2276)

* Add zero-extend fallback

* Fix copy-elision

* Switch to using seq_macro

* Remove unused function

* Update docs
@alamb alamb added parquet Changes to the parquet crate performance labels Aug 4, 2022
@alamb alamb changed the title Add unpack8, unpack16 and unpack64 Add vectorized unpacking for 8, 16, and 64 bit integers Aug 4, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@tustvold tustvold

Labels
enhancement Any new improvement worthy of a entry in the changelog parquet Changes to the parquet crate performance
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Add unpack8, unpack16, unpack64 (#2276) ~10-50% faster tustvold/arrow-rs
2 participants
@alamb @tustvold