From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758076AbcDHKbr (ORCPT ); Fri, 8 Apr 2016 06:31:47 -0400 Received: from smtprelay0253.hostedemail.com ([216.40.44.253]:37365 "EHLO smtprelay.hostedemail.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1756819AbcDHKbq (ORCPT ); Fri, 8 Apr 2016 06:31:46 -0400 X-Session-Marker: 6A6F6540706572636865732E636F6D X-Spam-Summary: 2,0,0,,d41d8cd98f00b204,joe@perches.com,:::::::::::::::::,RULES_HIT:41:355:379:541:599:973:988:989:1260:1277:1311:1313:1314:1345:1359:1373:1437:1515:1516:1518:1534:1539:1593:1594:1711:1714:1730:1747:1777:1792:2393:2559:2562:2828:2895:3138:3139:3140:3141:3142:3351:3622:3865:3866:3867:3868:3870:3871:3872:4303:4321:5007:10004:10400:10848:11026:11473:11658:11914:12048:12438:12517:12519:12740:13069:13161:13229:13311:13357:13439:13894:14659:21080:21324:30012:30054:30064:30091,0,RBL:none,CacheIP:none,Bayesian:0.5,0.5,0.5,Netcheck:none,DomainCache:0,MSF:not bulk,SPF:fn,MSBL:0,DNSBL:none,Custom_rules:0:0:0,LFtime:1,LUA_SUMMARY:none X-HE-Tag: bells36_4947bb2fe5418 X-Filterd-Recvd-Size: 1571 Message-ID: <1460111501.1800.28.camel@perches.com> Subject: Re: [PATCH] sched/fair: Optimize sum computation with a lookup table From: Joe Perches To: Yuyang Du , peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org Cc: bsegall@google.com, pjt@google.com, morten.rasmussen@arm.com, vincent.guittot@linaro.org, dietmar.eggemann@arm.com Date: Fri, 08 Apr 2016 03:31:41 -0700 In-Reply-To: <1460081240-8074-1-git-send-email-yuyang.du@intel.com> References: <1460081240-8074-1-git-send-email-yuyang.du@intel.com> Content-Type: text/plain; charset="ISO-8859-1" X-Mailer: Evolution 3.18.5.2-0ubuntu1 Mime-Version: 1.0 Content-Transfer-Encoding: 8bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2016-04-08 at 10:07 +0800, Yuyang Du wrote: > __compute_runnable_contrib() uses a loop to compute sum, whereas a > table lookup can do it faster in a constant time. Perhaps this becomes rather fragile code overly dependent on the current #define values of LOAD_AVG_MAX_N and LOAD_AVG_PERIOD. Perhaps this comment just above the definitions of LOAD_AVG_MAX_N and LOAD_AVG_PERIOD should be updated to include this new table:  * Note: The tables runnable_avg_yN_inv and runnable_avg_yN_sum are  * dependent on this value. Perhaps the __ prefix for __accumulated_sum_N32 is odd as both of the runnable_avg_yN_ tables are not __ prefixed.