Skip to content
This repository was archived by the owner on Aug 22, 2024. It is now read-only.

add NEON support where SSE is supported #1150

Merged
merged 6 commits into from
Apr 13, 2020
Merged

Conversation

tomoaki0705
Copy link
Contributor

@tomoaki0705 tomoaki0705 commented Mar 24, 2020

Fixes #1118

Description of the changes:

  • Added NEON implementation of rgbz.c
  • Only supposed to work on aarch64. Arm 32bit is excluded intentionally.
  • Using sse2neon could be faster to implement but that couldn't leverage the vst3 instruction that NEON has

Before submitting a Pull Request:

I tested changes on:

  • Windows
  • Linux
  • Ran transformation_ut on Jetson TX2 (Aarch64) without actual device

@msftclas
Copy link

msftclas commented Mar 24, 2020

CLA assistant check
All CLA requirements met.

@wes-b wes-b self-assigned this Mar 24, 2020
@wes-b
Copy link
Contributor

wes-b commented Mar 24, 2020

This is great!

@tomoaki0705
Copy link
Contributor Author

Thank you wes-b.
Please let me know anything I can do more on this PR.
Best

@wes-b
Copy link
Contributor

wes-b commented Mar 31, 2020

/azp run

@azure-pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@wes-b
Copy link
Contributor

wes-b commented Mar 31, 2020

/azp run

@azure-pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@wes-b
Copy link
Contributor

wes-b commented Mar 31, 2020

/azp run

@azure-pipelines
Copy link

Azure Pipelines successfully started running 1 pipeline(s).

@tkircher
Copy link

tkircher commented Apr 9, 2020

Any news on getting this merged?

@wes-b wes-b merged commit b033d2e into microsoft:develop Apr 13, 2020
@tomoaki0705 tomoaki0705 deleted the neon branch April 13, 2020 20:52
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[ARM NEON] Transformation API's needs to be optimizes in Neon
4 participants