From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759924Ab3BZU77 (ORCPT ); Tue, 26 Feb 2013 15:59:59 -0500 Received: from relais.videotron.ca ([24.201.245.36]:15805 "EHLO relais.videotron.ca" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1759658Ab3BZU76 (ORCPT ); Tue, 26 Feb 2013 15:59:58 -0500 MIME-version: 1.0 Content-transfer-encoding: 7BIT Content-type: TEXT/PLAIN; CHARSET=US-ASCII Date: Tue, 26 Feb 2013 15:59:56 -0500 (EST) From: Nicolas Pitre To: "Markus F.X.J. Oberhumer" Cc: Kyungsik Lee , Andrew Morton , Russell King , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , Michal Marek , linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-kbuild@vger.kernel.org, x86@kernel.org, celinux-dev@lists.celinuxforum.org, Nitin Gupta , Richard Purdie , Josh Triplett , Joe Millenbach , David Sterba , Richard Cochran , Albin Tonnerre , Egon Alter , hyojun.im@lge.com, chan.jeong@lge.com, raphael.andy.lee@gmail.com Subject: Re: [RFC PATCH v2 0/4] Add support for LZ4-compressed kernel In-reply-to: <512D1C12.4080109@oberhumer.com> Message-id: References: <1361859870-15751-1-git-send-email-kyungsik.lee@lge.com> <512D1C12.4080109@oberhumer.com> User-Agent: Alpine 2.03 (LFD 1266 2009-07-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 26 Feb 2013, Markus F.X.J. Oberhumer wrote: > On 2013-02-26 07:24, Kyungsik Lee wrote: > > Hi, > > > > [...] > > > > Through the benchmark, it was found that -Os Compiler flag for > > decompress.o brought better decompression performance in most of cases > > (ex, different compiler and hardware spec.) in ARM architecture. > > > > Lastly, CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is not always the best > > option even though it is supported. The decompression speed can be > > slightly slower in some cases. > > > > This patchset is based on 3.8. > > > > Any comments are appreciated. > > Did you actually *try* the new LZO version and the patch (which is attached > once again) as explained in https://lkml.org/lkml/2013/2/3/367 ? > > Because the new LZO version is faster than LZ4 in my testing, at least > when comparing apples with apples and enabling unaligned access in > BOTH versions: > > armv7 (Cortex-A9), Linaro gcc-4.6 -O3, Silesia test corpus, 256 kB block-size: > > compression speed decompression speed > > LZO-2012 : 44 MB/sec 117 MB/sec no unaligned access > LZO-2013-UA : 47 MB/sec 167 MB/sec Unaligned Access > LZ4 r88 UA : 46 MB/sec 154 MB/sec Unaligned Access To be fair, you should also take into account the compressed size of a typical ARM kernel. Sometimes a slightly slower decompressor may be faster overall if the compressed image to work on is smaller. Nicolas