From mboxrd@z Thu Jan  1 00:00:00 1970
From: ludovic.courtes@inria.fr (Ludovic =?utf-8?Q?Court=C3=A8s?=)
Subject: Re: Packaging BLIS
Date: Mon, 11 Sep 2017 09:12:15 +0200
Message-ID: <87fubtg14g.fsf@inria.fr>
References: <87inhhw1ms.fsf@elephly.net> <87a82s9cw3.fsf@gnu.org>
	<87wp5ufkqs.fsf@albion.it.manchester.ac.uk> <87k21nerqa.fsf@inria.fr>
	<87inh2zog7.fsf@albion.it.manchester.ac.uk>
	<87a826tslo.fsf_-_@inria.fr>
	<87tw0com1x.fsf@albion.it.manchester.ac.uk>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
Return-path: <guix-devel-bounces+gcggd-guix-devel=m.gmane.org@gnu.org>
Received: from eggs.gnu.org ([2001:4830:134:3::10]:37529)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <ludovic.courtes@inria.fr>) id 1drItL-0003d9-Iy
	for guix-devel@gnu.org; Mon, 11 Sep 2017 03:12:24 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <ludovic.courtes@inria.fr>) id 1drItI-000668-D0
	for guix-devel@gnu.org; Mon, 11 Sep 2017 03:12:23 -0400
In-Reply-To: <87tw0com1x.fsf@albion.it.manchester.ac.uk> (Dave Love's message
	of "Fri, 08 Sep 2017 23:36:10 +0100")
List-Id: "Development of GNU Guix and the GNU System distribution."
	<guix-devel.gnu.org>
List-Unsubscribe: <https://lists.gnu.org/mailman/options/guix-devel>,
	<mailto:guix-devel-request@gnu.org?subject=unsubscribe>
List-Archive: <http://lists.gnu.org/archive/html/guix-devel/>
List-Post: <mailto:guix-devel@gnu.org>
List-Help: <mailto:guix-devel-request@gnu.org?subject=help>
List-Subscribe: <https://lists.gnu.org/mailman/listinfo/guix-devel>,
	<mailto:guix-devel-request@gnu.org?subject=subscribe>
Errors-To: guix-devel-bounces+gcggd-guix-devel=m.gmane.org@gnu.org
Sender: "Guix-devel" <guix-devel-bounces+gcggd-guix-devel=m.gmane.org@gnu.org>
To: Dave Love <fx@gnu.org>
Cc: guix-devel <guix-devel@gnu.org>

Dave Love <fx@gnu.org> skribis:

> ludovic.courtes@inria.fr (Ludovic Court=C3=A8s) writes:
>
>> That caught my attention so I packaged BLIS:
>>
>>   https://git.savannah.gnu.org/cgit/guix.git/commit/?id=3D5a7deb117424ff=
4d430b771b50e534cf065c0ba1
>>
>> There are several =E2=80=9Cflavors=E2=80=9D of BLIS, so you can always r=
ebuild your
>> favorite program with:
>>
>>   --with-input=3Dopenblas=3Dblis-haswell
>>
>> and similar (or even =E2=80=98--with-graft=3Dblis=3Dblis-haswell=E2=80=
=99 where applicable).
>
> I'm not aware of an advantage of BLIS over OpenBLAS except for KNL (and
> maybe Skylake Xeon, if that's covered).  My interest was specifically
> for avx512.  (BLIS is documented as basically a research effort, which I
> think explains the way it's built.)

OK, I haven=E2=80=99t done any benchmarking yet.

>> Hopefully the issue you linked to above will be fixed in future versions
>> of BLIS, at which point we can probably provide a single =E2=80=9Cblis=
=E2=80=9D package.
>>
>> Ludo=E2=80=99.
>
> I still think it's important to be able to select the BLAS at run time
> with dynamic linking.  I suppose the trick I used for rpm will work
> similarly, though I'm not sure how ld.so behaves in Guix.

ld.so does not honor /etc/ld.so.{conf,cache}, but apart from that it
works as usual.

HTH,
Ludo=E2=80=99.