From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 10309 invoked by alias); 18 Mar 2004 19:15:25 -0000 Mailing-List: contact gcc-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-owner@gcc.gnu.org Received: (qmail 10275 invoked from network); 18 Mar 2004 19:15:24 -0000 Received: from unknown (HELO www.eyesopen.COM) (12.96.199.11) by sources.redhat.com with SMTP; 18 Mar 2004 19:15:24 -0000 Received: from localhost (roger@localhost) by www.eyesopen.COM (8.11.6/8.11.6) with ESMTP id i2IHxq723271; Thu, 18 Mar 2004 10:59:52 -0700 Date: Thu, 18 Mar 2004 19:18:00 -0000 From: Roger Sayle To: Jan Hubicka cc: gcc@gcc.gnu.org Subject: Re: x87 float truncation/accuracy (gcc vs. icc/msvc) In-Reply-To: <20040318183718.GC25385@atrey.karlin.mff.cuni.cz> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-SW-Source: 2004-03/txt/msg01077.txt.bz2 On Thu, 18 Mar 2004, Jan Hubicka wrote: > You can just cut&paste the extendsfdf implementation. Basically it > immitate move pattern for x87 but do proper conversions for SSE. > I was very tempted to do this for a while (and sent patch back in 98 > or so) but there appeared to be consensus that the truncations are > very important, but it does not seem to be the practice. If you can find the original posting and/or refresh this patch against mainline, I'll be happy to review it for you, provided any change in current functionality is guarded by flag_unsafe_math_optimizations. > If you want to get really good about elliminating the truncations, you > will need to play the games with combiner patterns containing truncates, > silimarly as we do for extensions but this is tricky (you will face > pattern explosion). Indeed. This was my major concern about modelling truncation like extension. i386.md already contains a large number of patterns intended purely to provide "*ext" variants of floating point operations. I wasn't sure if these were required by the i386 backend's extend?f?f2 implementation. Thanks for your help, Roger --