Re: ublas Digest, Vol 130, Issue 8
palik imre <[email protected]>
| Newsgroups | gmane.comp.lib.boost.ublas |
|---|---|
| Message-ID | <[email protected]> |
vectorisation: -Ofast vectorises even better. (Though the results might be off somewhat)BTW, this is one of the big issues with the vanila ublas implementation. I mean that it doesn't vectorise.
On Friday, 22 January 2016, 0:30, "[email protected]" <[email protected]> wrote:
From: nasos <[email protected]>
To: [email protected]
Subject: Re: [ublas] Matrix multiplication performance
Message-ID: <[email protected]>
Content-Type: text/plain; charset="windows-1252"; Format="flowed"
Michael,
please see below
On 01/21/2016 05:23 PM, Michael Lehn wrote:
> Hi Nasos,
>
> first of all I don?t want to take wrong credits and want to point out
> that this is not my algorithm. It is based on
>
> http://www.cs.utexas.edu/users/flame/pubs/blis2_toms_rev3.pdf
>
> https://github.com/flame/blis
>
> For a few cores (4-8) it can easily made multithreaded. For
> many-cores like Intel Xeon Phi this is a bit more
> sophisticated but still not too hard.
Setting up Phis is indeed an issue, especially because they are "locked"
with icpc. Openmp is working properly though.
> The demo I posted does not use micro kernels that exploit SSE, AVX or
> FMA instructions. With that the matrix product is on par with Intel
> MKL. Just like BLIS. For my platforms I wrote
> my own micro-kernels but the interface of function ugemm is compatible
> to BLIS.
>
If you compile with -O3 I think you are getting near optimal SSE
vectorization. gcc is truly impressive and intel is even more.