From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 105573 invoked by alias); 10 Jul 2015 10:12:41 -0000 Mailing-List: contact jit-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Post: List-Help: List-Subscribe: Sender: jit-owner@gcc.gnu.org Received: (qmail 105554 invoked by uid 89); 10 Jul 2015 10:12:40 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Checked: by ClamAV 0.98.7 on sourceware.org X-Virus-Found: No X-Spam-SWARE-Status: No, score=-1.5 required=5.0 tests=AWL,BAYES_00,KAM_LAZY_DOMAIN_SECURITY,RCVD_IN_DNSWL_LOW autolearn=no version=3.3.2 X-Spam-Status: No, score=-1.5 required=5.0 tests=AWL,BAYES_00,KAM_LAZY_DOMAIN_SECURITY,RCVD_IN_DNSWL_LOW autolearn=no version=3.3.2 X-Spam-Checker-Version: SpamAssassin 3.3.2 (2011-06-06) on sourceware.org X-Spam-Level: X-HELO: mail-yk0-f182.google.com X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:mime-version:in-reply-to:references:date :message-id:subject:from:to:cc:content-type; bh=c2m8jPwD8trt9mdHuNbwOckf+ztBjvoxugnsTTsOPR4=; b=ehSW17B4Qw9sftH6stwUEw4UHA8h0nAM1dBKRmzHMR+OrXqgK7bTIfLsi8RfztgcBC x9rYWu0f3Ue3LH1cromjhCLx5ndlazjQ46ekhEnJo14OXzxMEA+mdzsh6JZjJErcpW9s IwyKAwG6gG55+AnqN9xvRGLgot70uTMWIuOSxsiaKy3oMz7VqzF1+YERxEX+3yZnHG4L FYfKBuiSt6d7MY31Zs6njEf8CxbTnoIR3XhR5aWwwrVNWvqAhLnFoJuiyzpAKbJ3BAyA 1SAFYc3ez5OOYKQRT81dJCsrMG/RQte4jiKQIe1CgsWQDC48PJk8lmnqWhd7PNm3jHMe NiYQ== X-Gm-Message-State: ALoCoQmai432Em2Rwyb3e9WN2YswY/O8PYJzifWW/YWyQCrs4QuKn1wJNOdk2tCOpFEQRPA5jgrD MIME-Version: 1.0 X-Received: by 10.129.27.6 with SMTP id b6mr21711057ywb.134.1436523157339; Fri, 10 Jul 2015 03:12:37 -0700 (PDT) In-Reply-To: References: <1436365266.24803.65.camel@surprise> <1436367926.24803.71.camel@surprise> <1436369443.24803.75.camel@surprise> <1436377619.24803.97.camel@surprise> <1436382217.24803.101.camel@surprise> <1436385256.24803.107.camel@surprise> <1436469764.24803.156.camel@surprise> <1436476508.24803.168.camel@surprise> <1436477075.24803.171.camel@surprise> <1436484627.24803.173.camel@surprise> <1436489129.24803.174.camel@surprise> Date: Thu, 01 Jan 2015 00:00:00 -0000 Message-ID: Subject: Re: [PATCH] PR jit/66812: Candidate fix for for the code generation issue, v1 From: Dibyendu Majumdar To: David Malcolm Cc: jit@gcc.gnu.org Content-Type: text/plain; charset=UTF-8 X-SW-Source: 2015-q3/txt/msg00077.txt.bz2 On 10 July 2015 at 08:38, Dibyendu Majumdar wrote: > On 10 July 2015 at 01:45, David Malcolm wrote: >>> however performance degraded similar to when >>> -fno-strict-aliasing is used. >> >> Bother. What kind of numbers are we talking about? >> > > I will post some numbers tonight. > I will not compare performance with LLVM here as I have a workaround for the code that causes segmentation fault in libgccjit - so the benchmarks are probably impacted due to this. Here is a comparison of the benchmarks with / without the fix. 1. fornum_test1.lua without fix: 2e-6 with fix: 2.053 2. fornum_test2.ravi without fix: 1.04 with fix: 3.14 3. mandel1.ravi without fix: 3.52 with fix: 5.94 4. fannkuchen.ravi without fix: 11.29 with fix: 16.98 5. matmul1.ravi 1000 without fix: 5.13 with fix: 11.28 > I am beginning to think that using unions was not a good idea - I > should do it the way I implement the LLVM version - i.e. use a struct > and emulate the union functionality. I think unions are just hard for > the optimizer to reason about. > > Unfortunately this means a bit of rework - so I won't know if the > struct approach is better until after I have done the changes and > compared results. >