[Numpy-discussion] ENH: Proposal to add KML_BLAS support

[Ralf Gommers]

On Mon, Feb 22, 2021 at 1:44 PM Matti Picus <matti.picus at gmail.com> wrote:

> On 2/22/21 2:13 PM, ChunLin Fang wrote:
>
>   Hi all,
>     Whether you're running apps on your phone or the world's fastest
> supercomputer, you're most likely running ARM. Many major events have
> occurred related to ARM archtecture:
>
>    - Apple may have done the most to make ARM relatively relevant in
>    popular culture with its new ARM-based M1 processor.
>    - Amazon Web Services launched its Graviton2 processors based on the
>    Arm architecture , which promise up to 40% better performance from
>    comparable x86-based instances for 20% less.
>    - Microsoft currently uses Arm-based chips from Qualcomm in some of
>    its Surface PCs.
>    - Huawei unveiled a new chipset called the Kunpeng based on ARM,
>    designed to go into its new TaiShan servers, in a bid to boost its nascent
>    cloud business.
>
>      So It's obvious that ARM will become more and more popular in the
> future, Since Intel MKL has provide good accelerate support for X86-based
> chips, Huawei also published KML_BLAS
> <https://kunpeng.huawei.com/en/#/developer/devkit/library>(kunpeng math
> library blas) that can make full advantage of ARM-based chips,  KML_BLAS is
> a mathematical library for basic linear algebra operations. it provides
> three levels of high-performance vector operations: vector-vector
> operations, vector-matrix operations, and matrix-matrix operations. The
> performance advantage is shown in the attachment compared with OpenBlas.
> Can we add KML_BLAS support to numpy?
>
> Cheers,
> Chunlin Fang(github ID:Qiyu8)
>
>
> Thanks, I hadn't heard of this library before. I am a bit confused as to
> the link: did you mean this?
> https://www.huaweicloud.com/kunpeng/software/KML_BLAS.html
>
>
> Is there something beyond choosing KML_BLAS in the site.cfg file that
> needs to be done to support it?
>
Support in numpy.distutils probably, analogous to what we did for BLIS for
example: https://github.com/numpy/numpy/pull/7294/files.

The other thing could be "ship aarch64 wheels with KML_BLAS support instead
of OpenBLAS". That we can only do if KML_BLAS would be open source.

Cheers,
Ralf


What is the license/redistribution policy?
>
Matti
>
>
> _______________________________________________
> NumPy-Discussion mailing list
> NumPy-Discussion at python.org
> https://mail.python.org/mailman/listinfo/numpy-discussion
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mail.python.org/pipermail/numpy-discussion/attachments/20210222/8939d405/attachment-0001.html>