From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jim Westfall Subject: Re: fma4/avx under xen Date: Fri, 4 May 2012 09:04:59 -0700 Message-ID: <20120504160459.GX5985@surrealistic.net> References: <20120502185402.GV5985@surrealistic.net> <4FA3BD2602000078000818F7@nat28.tlf.novell.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: Content-Disposition: inline In-Reply-To: <4FA3BD2602000078000818F7@nat28.tlf.novell.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Jan Beulich Cc: xen-devel@lists.xen.org List-Id: xen-devel@lists.xenproject.org Jan Beulich wrote [05.04.12]: > >>> On 02.05.12 at 20:54, Jim Westfall wrote: > > The summary is that when gcc compiles something with -mfma4 it also > > enables the use of the avx instruction set. Since by default xen > > disables avx it leads to invalid opcodes. > > Not that I know of, at least not anymore in current -unstable. > > > This ends up being kinda nasty with the multiarch glibc since its doing > > stuff like > > > > (HAS_FMA4 ? run_fma4_func() : (HAS_AVX ? run_avx_func() : run_func())) > > The question is what (runtime) tests HAS_FMA includes. I know that > some glibc versions had a broken AVX check (which only checked for > the AVX feature flag, while the specification explicitly states that > a prerequisite check of the OSXSAVE feature flag is also necessary). Its just a basic cpuid() call and seeing if the FMA4 bit is set. I will bug the glibc guys. Thanks for the feedback. jim