Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1LnvA9-00066N-65 for qemu-devel@nongnu.org; Sun, 29 Mar 2009 09:34:57 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1LnvA7-000667-Gm for qemu-devel@nongnu.org; Sun, 29 Mar 2009 09:34:56 -0400 Received: from [199.232.76.173] (port=49323 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1LnvA7-000664-By for qemu-devel@nongnu.org; Sun, 29 Mar 2009 09:34:55 -0400 Received: from hall.aurel32.net ([88.191.82.174]:43377) by monty-python.gnu.org with esmtps (TLS-1.0:RSA_AES_256_CBC_SHA1:32) (Exim 4.60) (envelope-from ) id 1LnvA6-0008AQ-V8 for qemu-devel@nongnu.org; Sun, 29 Mar 2009 09:34:55 -0400 Received: from aurel32 by hall.aurel32.net with local (Exim 4.69) (envelope-from ) id 1LnvA5-0003hv-29 for qemu-devel@nongnu.org; Sun, 29 Mar 2009 15:34:53 +0200 Date: Sun, 29 Mar 2009 15:34:53 +0200 From: Aurelien Jarno Subject: Re: [Qemu-devel] [PATCH 0/4] target-ppc: create TCG slots for registers based on CPU Message-ID: <20090329133453.GA12026@hall.aurel32.net> References: <1238275817-9758-1-git-send-email-froydnj@codesourcery.com> <20090328225443.GL20944@hall.aurel32.net> <20090329001834.GK7336@codesourcery.com> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline In-Reply-To: <20090329001834.GK7336@codesourcery.com> Sender: Aurelien Jarno 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 On Sat, Mar 28, 2009 at 05:18:34PM -0700, Nathan Froyd wrote: > On Sat, Mar 28, 2009 at 11:54:43PM +0100, Aurelien Jarno wrote: > > On Sat, Mar 28, 2009 at 02:30:13PM -0700, Nathan Froyd wrote: > > > I am not a TCG expert, but there are several loops in TCG over all > > > globals and it seems like those loops would go faster if they didn't > > > have to consider registers that would never be touched. If this patch > > > series makes no difference in TCG's performance, then I'd be glad to > > > have an explanation of why that's the case. > > > > Do you actually have run a benchmark with those changes? TCG is > > sometimes a bit strange, and some optimizations does not change the > > execution speed, while others improve it a lot. It is very difficult to > > predict what will give a gain or not. > > > > Suggestions of benchmarks: gzip/bzip2 on a big file using user emulation > > or a compilation in system emulation. > > Benchmarking? Pffft. ;) > > A benchmarking session with qemu-ppc and bzip2/bunzip2 on ~400MB files > and a 603e emulated CPU suggests that these changes are not terribly > beneficial (maybe 1% improvement, if that). I don't imagine that a > similarly stressful benchmark in system emulation would be much > different. Consider the patch series withdrawn. > I have done a few profiling on qemu-system-ppc and qemu-system-mips. You are actually right that the loop on the TCG variables lists takes time. This is mainly due to the call of save_globals() for TCG functions marked as TCG_OPF_CALL_CLOBBER. However it looks like it should be better to address this comment first before trying to reduce the number of TCG variables: /* XXX: for load/store we could do that only for the slow path (i.e. when a memory callback is called) */ However for the PowerPC target, what really kills the performance is the call to ppc_store_sr(), basically done by the Linux kernel for each context switch. In the chip the SR register selection is done before the TLB, while we emulated both the SR and the TLB with the QEMU TLB, this means we have to do a tlb_flush(env, 1) each time. This is time expensive, and also kills the performance as it has to be filled again. -- Aurelien Jarno GPG: 1024D/F1BCDB73 aurelien@aurel32.net http://www.aurel32.net