From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.33) id 1Bqe9z-0000C4-H4 for qemu-devel@nongnu.org; Fri, 30 Jul 2004 16:39:23 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.33) id 1Bqe9y-0000Ag-1h for qemu-devel@nongnu.org; Fri, 30 Jul 2004 16:39:23 -0400 Received: from [199.232.76.173] (helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.33) id 1Bqe9x-0000AL-Mm for qemu-devel@nongnu.org; Fri, 30 Jul 2004 16:39:21 -0400 Received: from [200.103.228.135] (helo=listas.ambientebrasil.com.br) by monty-python.gnu.org with esmtp (Exim 4.34) id 1Bqe6K-0002tL-IH for qemu-devel@nongnu.org; Fri, 30 Jul 2004 16:35:42 -0400 Received: from [10.0.0.30] (jacaranda.ambientebrasil [10.0.0.30]) by listas.ambientebrasil.com.br (Postfix) with ESMTP id 910F4528849 for ; Fri, 30 Jul 2004 16:14:11 -0300 (GMT+3) Message-ID: <410A9DF5.5080906@ambientebrasil.com.br> Date: Fri, 30 Jul 2004 16:13:57 -0300 From: Leonardo Marques de Souza MIME-Version: 1.0 Subject: Re: [Qemu-devel] (TEST) CFLAGS options + qemu 0.60 References: <41091370.7070805@ambientebrasil.com.br> <2ad73a04072909275dceacc2@mail.gmail.com> <41096B3A.2090801@ambientebrasil.com.br> In-Reply-To: <41096B3A.2090801@ambientebrasil.com.br> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Works great! so im doing some benchmarks to see any general diference. i trying PCMark 2002, any other sugestion? I think the benchmark programs is a good choice to test virtual CPU, becouse they use a lot of optimized intructions. Well, when i use -mregpar=x, que qemu made a lot of 'booboos'. Some time start, others guest Win98 and Linux crash... not recomended for "production" hehe :P Leonardo Marques de Souza wrote: > Thanks! > > Im looking for > > I'll try to workarround compilation problem, doing it by hand, > it happens only with help.c (well, all help.c in qemu tree) > > enter in i386 , i386-softemu , ppc-softemu > and doing: > > gcc -Wall -O2 -march=pentium -fno-strict-aliasing > -fomit-frame-pointer -I. -I/root/qemu-0.6.0/target-i386 > -I/root/qemu-0.6.0 -D_GNU_SOURCE -I/root/qemu-0.6.0/slirp -c -o > helper.o /root/qemu-0.6.0/target-i386/helper.c > > just return to root tree compilation and do make again to continue. > > I will see what instable qemu will be with -regparm=[1..3]. :)