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

Use MSVC vld1q_u8_ex and vst1q_u8_ex intrinsics for NEON code #1689

Open
ccawley2011 opened this issue Feb 21, 2024 · 1 comment
Open

Use MSVC vld1q_u8_ex and vst1q_u8_ex intrinsics for NEON code #1689

ccawley2011 opened this issue Feb 21, 2024 · 1 comment
Labels
Architecture Architecture specific Build Env

Comments

@ccawley2011
Copy link
Contributor

MSVC provides variants of vld1q_u8 and vst1q_u8 with an additional parameter specifying the alignment in bits. It might be beneficial to make use of this where available.
@mtl1979
Copy link
Collaborator

mtl1979 commented Feb 22, 2024

As far as I know, those _ex variants only make difference for AArch32 and are equivalent to non-_ex versions on AArch64.

Unless we get alignment exceptions in the code, I don't see any benefit in using the _ex variants. We only support ARMv7 when using MSVC for 32-bit ARM.

@nmoinvaz nmoinvaz added Build Env Architecture Architecture specific labels Feb 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
Architecture Architecture specific Build Env
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@nmoinvaz @mtl1979 @ccawley2011