From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (qmail 13150 invoked by alias); 4 Jun 2004 14:26:27 -0000 Mailing-List: contact gcc-bugs-help@gcc.gnu.org; run by ezmlm Precedence: bulk List-Archive: List-Post: List-Help: Sender: gcc-bugs-owner@gcc.gnu.org Received: (qmail 13142 invoked by uid 48); 4 Jun 2004 14:26:26 -0000 Date: Fri, 04 Jun 2004 14:26:00 -0000 Message-ID: <20040604142626.13141.qmail@sourceware.org> From: "dimfair at yahoo dot com" To: gcc-bugs@gcc.gnu.org In-Reply-To: <20040604130940.15820.dimfair@yahoo.com> References: <20040604130940.15820.dimfair@yahoo.com> Reply-To: gcc-bugzilla@gcc.gnu.org Subject: [Bug c++/15820] GCC emits MOVAPS to load unaligned data in case when -O2 is invoked X-Bugzilla-Reason: CC X-SW-Source: 2004-06/txt/msg00470.txt.bz2 List-Id: ------- Additional Comments From dimfair at yahoo dot com 2004-06-04 14:26 ------- (In reply to comment #2) > To be more explicit: if you pass this function an unaligned pointer, > how can you expect the compiler to do something about it? > > W. test function is a (specially) simplified inversion of 6x6 matrix function which get src aligned parameter always. I'm sure this is a compiler's bug, because gcc uses MOVAPS for loading of __m64 parameter of _mm_loadh_pi which _can be unaligned_ according to Intel's specs (BTW, I found this bug when I ported healthy program from Intel's compiler to GCC). NOTE: test function is meaningless (but correct!) because I tried to make the shortest testcase (try to comment ANY line and bug disappeared). Dmitry (it's my name :)) ) -- What |Removed |Added ---------------------------------------------------------------------------- Status|RESOLVED |UNCONFIRMED Resolution|INVALID | http://gcc.gnu.org/bugzilla/show_bug.cgi?id=15820