From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753006Ab1HPCgk (ORCPT ); Mon, 15 Aug 2011 22:36:40 -0400 Received: from lennier.cc.vt.edu ([198.82.162.213]:39251 "EHLO lennier.cc.vt.edu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751528Ab1HPCgj (ORCPT ); Mon, 15 Aug 2011 22:36:39 -0400 X-Mailer: exmh version 2.7.2 01/07/2005 with nmh-1.3-dev To: Borislav Petkov Cc: Ingo Molnar , melwyn lobo , linux-kernel@vger.kernel.org, "H. Peter Anvin" , Thomas Gleixner , Linus Torvalds , Peter Zijlstra , borislav.petkov@amd.com Subject: Re: x86 memcpy performance In-Reply-To: Your message of "Sun, 14 Aug 2011 11:59:10 +0200." <20110814095910.GA18809@liondog.tnic> From: Valdis.Kletnieks@vt.edu References: <20110812195220.GA29051@elte.hu> <20110814095910.GA18809@liondog.tnic> Mime-Version: 1.0 Content-Type: multipart/signed; boundary="==_Exmh_1313462075_2709P"; micalg=pgp-sha1; protocol="application/pgp-signature" Content-Transfer-Encoding: 7bit Date: Mon, 15 Aug 2011 22:34:35 -0400 Message-ID: <6296.1313462075@turing-police.cc.vt.edu> X-Mirapoint-Received-SPF: 198.82.161.152 auth3.smtp.vt.edu Valdis.Kletnieks@vt.edu 2 pass X-Junkmail-Status: score=10/50, host=vivi.cc.vt.edu X-Junkmail-Signature-Raw: score=unknown, refid=str=0001.0A02020A.4E49D741.0051,ss=1,fgs=0, ip=0.0.0.0, so=2010-07-22 22:03:31, dmn=2009-09-10 00:05:08, mode=single engine X-Junkmail-IWF: false Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org --==_Exmh_1313462075_2709P Content-Type: text/plain; charset=us-ascii On Sun, 14 Aug 2011 11:59:10 +0200, Borislav Petkov said: > Benchmarking with 10000 iterations, average results: > size XM MM speedup > 119 540.58 449.491 0.8314969419 > 12273 2307.86 4042.88 1.751787902 > 13924 2431.8 4224.48 1.737184756 > 14335 2469.4 4218.82 1.708440514 > 15018 2675.67 1904.07 0.711622886 > 16374 2989.75 5296.26 1.771470902 > 24564 4262.15 7696.86 1.805863077 > 27852 4362.53 3347.72 0.7673805572 > 28672 5122.8 7113.14 1.388524413 > 30033 4874.62 8740.04 1.792967931 The numbers for 15018 and 27852 are *way* odd for the MM case. I don't feel really good about this till we understand what happened for those two cases. Also, anytime I see "10000 iterations", I ask myself if the benchmark rigging took proper note of hot/cold cache issues. That *may* explain the two oddball results we see above - but not knowing more about how it was benched, it's hard to say. --==_Exmh_1313462075_2709P Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (GNU/Linux) Comment: Exmh version 2.5 07/13/2001 iD8DBQFOSdc7cC3lWbTT17ARAr/1AJ9quwosDW/OPJDNOh40a1bS8i7QXwCgpxFh 8UCMlMWC3cBCx7YH+JUORvk= =IvNi -----END PGP SIGNATURE----- --==_Exmh_1313462075_2709P--