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.

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

try refactor of L2 on simd8float32 #3794

Draft
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

mengdilin
Copy link
Contributor

Differential Revision: D60925434

Summary:
Pull Request resolved: facebookresearch#3613

As a demo for Mengdi.

The steps to fully migrate to simdlib are:

1. change all function interfaces to use the generic simd8float32 and friends prototypes -- make sure it compiles on fbcode.

2. make sure it also compiles on ARM

3. see which functions can be mirgrated to only use the generic codepath

4. benchmark if the simd emulated path is competitve with the scalar (for platforms without specific SIMD support)

The rationale here is that there are many SIMD instructions that are straightforward, like adding or subtracting registers, they can be put in common between implementations. The only code that may remain with arch-specific intrinsics is where they way of doing things is very different between AVX and NEON.

Differential Revision: D59395882
Differential Revision: D60925434
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D60925434

@alexanderguzhva
Copy link
Contributor

@mengdilin please use a standard term horizontal_sum() instead of accumulate()

// bit shift by 16 -> uint32_t(v) << 16

// load 8 as i32 and bit shift by 16
simd8uint32 code_256i = load8_16bits_as_uint32(code, i);
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

maybe easier to load as simd32uint8 and cast to simd8uint32

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

5 participants