Add SVE2 support in xsimd as a fundable project.#314
Conversation
|
@HaudinFlorence is attempting to deploy a commit to the QuantStack Team on Vercel. A member of the Team first needs to authorize it. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
| @@ -0,0 +1,10 @@ | |||
| #### Overview | |||
| xsimd is a C++ header-only library that abstracts SIMD (vectorization) intrinsics behind a single, generic API. The same code - `xsimd::batch<float>` - compiles to optimal machine code on x86 SSE/AVX, ARM NEON, RISC-V, and WebAssembly, with no runtime overhead. When an intrinsic is missing on a given target, xsimd falls back gracefully rather than failing or leaving the developer to write platform-specific branches. This is why projects like Mozilla Firefox, Apache Arrow, and Pythran have adopted it as their vectorization layer. | |||
There was a problem hiding this comment.
Sorry I'm late to the party.
Wanted to add:
This is why projects like Mozilla Firefox, Apache Arrow, and Pythran have adopted it as their vectorization layer.
This is why projects like Mozilla Firefox, Apache Arrow, Meta Velox, KDE Krita, and Pythran have adopted it as their vectorization layer.
|
|
||
| We propose to implement a complete xsimd::sve2 backend — all arithmetic, mathematical, and reduction operations . The work will be fully tested, documented, and merged upstream into the public repository under the existing BSD 3-Clause license. | ||
|
|
||
| ##### Are you interested in this project? Either entirely or partially, contact us for more information on how to help us fund it No newline at end of file |
There was a problem hiding this comment.
And towards the end 👀 @SylvainCorlay
Funding this development will directly enhance the cutting-edge data processing workflow using Arrow and Velox, paving the way for the future of ARM computing!
There was a problem hiding this comment.
@AntoinePrv Can you please check PR #316. Thanks
3 participants
cc @AntoinePrv