From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: Big git diff speedup by avoiding x86 "fast string" memcmp Date: Thu, 16 Dec 2010 09:57:16 -0800 (PST) Message-ID: <20101216.095716.71123831.davem@davemloft.net> References: <4D08BF5D.1060509@panasas.com> <20101215.100055.226772943.davem@davemloft.net> <4D09E185.2040600@panasas.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <4D09E185.2040600@panasas.com> Sender: linux-kernel-owner@vger.kernel.org To: bharrosh@panasas.com Cc: npiggin@gmail.com, hooanon05@yahoo.co.jp, npiggin@kernel.dk, torvalds@linux-foundation.org, linux-arch@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org List-Id: linux-arch.vger.kernel.org From: Boaz Harrosh Date: Thu, 16 Dec 2010 11:53:09 +0200 > You miss understood me. I'm saying that we know the beggining of the > string is aligned and Nick offered to pad the last long, so surly > a shift by 2 (or 3) + the reduction of the 12 dec-and-test to 3 > should give you an optimization? Indeed, we could do something interesting in the case where both strings are tail padded like that. From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from 74-93-104-97-Washington.hfc.comcastbusiness.net ([74.93.104.97]:36386 "EHLO sunset.davemloft.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752284Ab0LPR4r (ORCPT ); Thu, 16 Dec 2010 12:56:47 -0500 Date: Thu, 16 Dec 2010 09:57:16 -0800 (PST) Message-ID: <20101216.095716.71123831.davem@davemloft.net> Subject: Re: Big git diff speedup by avoiding x86 "fast string" memcmp From: David Miller In-Reply-To: <4D09E185.2040600@panasas.com> References: <4D08BF5D.1060509@panasas.com> <20101215.100055.226772943.davem@davemloft.net> <4D09E185.2040600@panasas.com> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: linux-arch-owner@vger.kernel.org List-ID: To: bharrosh@panasas.com Cc: npiggin@gmail.com, hooanon05@yahoo.co.jp, npiggin@kernel.dk, torvalds@linux-foundation.org, linux-arch@vger.kernel.org, x86@kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Message-ID: <20101216175716.VS_pDddhyEKxPsBVrBx-LRGGHQWh6ki2cAHfxLxiFwA@z> From: Boaz Harrosh Date: Thu, 16 Dec 2010 11:53:09 +0200 > You miss understood me. I'm saying that we know the beggining of the > string is aligned and Nick offered to pad the last long, so surly > a shift by 2 (or 3) + the reduction of the 12 dec-and-test to 3 > should give you an optimization? Indeed, we could do something interesting in the case where both strings are tail padded like that.