From owner-freebsd-current@FreeBSD.ORG Tue Feb 19 23:10:03 2013 Return-Path: Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.freebsd.org (mx1.FreeBSD.org [8.8.178.115]) by hub.freebsd.org (Postfix) with ESMTP id 87FFA119; Tue, 19 Feb 2013 23:10:03 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 30B00F93; Tue, 19 Feb 2013 23:10:02 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1U7wJw-003NOT-Jy>; Wed, 20 Feb 2013 00:09:56 +0100 Received: from e178020162.adsl.alicedsl.de ([85.178.20.162] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1U7wJw-002uBQ-G1>; Wed, 20 Feb 2013 00:09:56 +0100 Message-ID: <5124063D.2060604@zedat.fu-berlin.de> Date: Wed, 20 Feb 2013 00:09:49 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:17.0) Gecko/20130131 Thunderbird/17.0.2 MIME-Version: 1.0 To: Current FreeBSD , freebsd-performance@freebsd.org Subject: PathScale EKO Path 5 not for FreeBSD anymore? X-Enigmail-Version: 1.4.6 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigDF36890EC952228A8D9A2C83" X-Originating-IP: 85.178.20.162 X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 19 Feb 2013 23:10:03 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigDF36890EC952228A8D9A2C83 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: quoted-printable A while ago - approximately three years from now, i was looking for a GPGPU capable solution for usage on FreeBSD and I stepped into the compilers from PathScale which are supposed to handle OpenACC (like OpenMP #pragma omp, but in this case #pragma openacc instead). Well, there was hope since PathScale obviously had a FreeBSD commercial solution. It was in BETA stage that time, I applied for getting a testing copy, but never got an answer, even having had contact to Christopher Bergstr=F6m, CTO at PathScale. Looking today at Phoronix, (http://www.phoronix.com/scan.php?page=3Darticle&item=3Dpathscale_ekopath= _5beta&num=3D1), I read this benchmarking and followed the links which say that PathScale opensourced their compiler suite a while ago (http://www.phoronix.com/scan.php?page=3Darticle&item=3Dpathscale_ekopath= 4_open&num=3D1) I was curious and looked at PathScales website where I found three years ago also FreeBSD mentioned as a supported platform, but see foryourself, what supported platforms today mentioned there: http://www.pathscale.com/ekopath-compiler-suite Well, at the end, this means there is simply no binary or package that could be installed easily for scientists interested in that compiler. I do not know whether there are motivations to produce a FreeBSD 10/9 compatible package from the newly emitted PathScale EKO Patch 5 Beta compiler sources, which are available at github: https://github.com/path64/compiler Well, the official website of PathScale doens't mention FreeBSD anymore and this must have a reason why they droped support or any intention to support that OS. From the perspective of a "user", I'm the lonely "idiot" within kilometres using FreeBSD for my day-to-day scientifice work and sacrifice myself not having GPGPU capabilities. Something is really going into the wrong direction here. I'm very interested in the reasoning why PathScale droped FreeBSD and I guess it would be nice to reveal the reasons. Am I blind or is this again another erosion process of an operating system usefull even for scientific purposes? Well, I'm aware that my posting triggers again a lot of emotional discussions (I guess), since it did in the past. I try to evaluate the situation from the perspective of a "user", not someone who needs to be a Os engineer to use an OS. It is a kind of deep running frustration to see how the next great compiler suite for scientific purpose is simply vanishing - as it did with the NAG compilers which were offered for freeBSD as well as other OSs at the end of 1990s. Now there is no offering anymore. Regards, Oliver --------------enigDF36890EC952228A8D9A2C83 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.19 (FreeBSD) iQEcBAEBAgAGBQJRJAZDAAoJEOgBcD7A/5N8AzAIAM3mS2GJqQqZIskvfKUh4MjB 4lIunyq7XcD/PvkrV/epTl36wEswPTWjTgEUCmStbaHd6EvfJCNkTuGYp2/uP+u1 QMOQBBmhOtIeFMNrW9oxi0nGV/jbN5bSXzV1Tki2/0DIUnoCzBWtATLsBiJZ58Su mAenGSclKXjBFJAPEZ9akX4k4GMpChulQ551X6ZFHsN79f4HFzJpm9sS8lcFp51d frgbEUNbG789RSyTf383J3zo85hCJlzPK8zGERZBRv+ylIYbym30WVz48J2FN+MJ q3aafx+1llpA5OZhVxNFFatgtN0q9cD4jCxG36277Egbetb3/7ASt41sin4KQjI= =UC73 -----END PGP SIGNATURE----- --------------enigDF36890EC952228A8D9A2C83--