Return-Path: Received: from [208.97.132.66] (HELO homiemail-a27.g.dreamhost.com) by media-motion.tv (CommuniGate Pro SMTP 4.2.10) with ESMTP id 4747638 for AE-List@media-motion.tv; Fri, 15 Jun 2012 06:23:36 +0200 Received: from homiemail-a27.g.dreamhost.com (localhost [127.0.0.1]) by homiemail-a27.g.dreamhost.com (Postfix) with ESMTP id B67E0598058 for ; Thu, 14 Jun 2012 21:26:20 -0700 (PDT) DomainKey-Signature: a=rsa-sha1; c=nofws; d=louai.org; h=mime-version :in-reply-to:references:from:date:message-id:subject:to: content-type; q=dns; s=louai.org; b=ZT3xK0cLy9siqdsK2MAS8V2iMWw9 zJvt/SEG4SCvROVLdm2UaJgzuBuz4xsMh1J8uYT1hTFdC1TVQFadMhrhg+tF3IwX 9kWADzuGABUUR719mpR4N93AwFG/nZcsjz0yIyc16YMFhRupJ3YlRA1gVSdfCIOV QnDy7/o8mtMChvY= DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=louai.org; h=mime-version :in-reply-to:references:from:date:message-id:subject:to: content-type; s=louai.org; bh=FXvNSbKAiLquWVIa7H7ldkWiIcg=; b=Gp wWCFY0+NfGsU/m91B3cW+Cryh1DiZtoP358678Fnk5UegKvMUh5cSGrtNn4JzGHg h9vBCjuyqRxdCgnHLQlX/tUY2zgcVLrad6rdT87uu1YJUKlGk6bLvRwLENeSgQ2X 0hsjterPucNuWZgKxCps2S0zJM75JJkwKOjPLlKG4= Received: from mail-yx0-f169.google.com (mail-yx0-f169.google.com [209.85.213.169]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (No client certificate requested) (Authenticated sender: me@louai.org) by homiemail-a27.g.dreamhost.com (Postfix) with ESMTPSA id 8A92B598057 for ; Thu, 14 Jun 2012 21:26:20 -0700 (PDT) Received: by yenr5 with SMTP id r5so1507056yen.28 for ; Thu, 14 Jun 2012 21:26:19 -0700 (PDT) Received: by 10.50.237.73 with SMTP id va9mr346717igc.3.1339734379570; Thu, 14 Jun 2012 21:26:19 -0700 (PDT) MIME-Version: 1.0 Received: by 10.50.213.5 with HTTP; Thu, 14 Jun 2012 21:25:49 -0700 (PDT) In-Reply-To: References: From: Louai Abu-Osba Date: Fri, 15 Jun 2012 00:25:49 -0400 Message-ID: Subject: Re: [AE] [OT] Benchmarking AE CUDA on nVidia GTX 580 vs. GTX 680 - SHOCKING RESULTS To: After Effects Mail List Content-Type: multipart/alternative; boundary=f46d0447a119c9a66504c27b371e --f46d0447a119c9a66504c27b371e Content-Type: text/plain; charset=ISO-8859-1 I got 24:46 on an unsupported GTX 460M, with 1.5 GB VRAM. Much slower than the big cards, but waaaaaaaaaaaaaaaaaaaaaaaaaaaaaaay faster than CPU. On Thu, Jun 14, 2012 at 6:23 PM, rendernyc wrote: > ran your test on macpro3,1 with GTX 570 2.5GB at 6:47 > > On Sat, May 26, 2012 at 2:50 PM, Teddy Gage wrote: > >> Well, shocking if you care about this sort of thing. So after some >> struggles getting the GTX 680 to work with AE CS6 11.0.1 I finally got it >> working. How would the 3 GB VRAM GTX 580, with 500 CUDA cores stack up to >> the brand new 2 GB VRAM GTX 680 with 1,500 CUDA cores? >> >> Would it be worth upgrading if you already owned a 580? Would the extra 1 >> GB VRAM make a difference for the older card? >> >> Well I came up with a benchmark (228K) available HEREthat maxes out the GPU and tests your CUDA processing ability. You will >> need about 900 MB local space for the output and the new 11.0.1 patch >> (probably). >> >> Now a lot of figures are at play here but with the project using 100% GPU >> and 25% CPU I think it's a decent bench for comparing graphics cards. Here >> are the results: >> >> GTX 680 (2GB) = 6 min. 11 sec to render >> GTX 680 (2GB) (overclocked) = 5 min. 52 s >> GTX 580 (3GB) = 5 min. 42 s >> >> So the GTX 580 with 3GB VRAM is faster. Now it's hard to say whether >> that's because the architecture is more compute-friendly, or the extra GB >> of VRAM makes that much of a difference. >> >> Considering I got the 580 for about $415 shipped used on eBay, I'd say >> for now nobody needs to rush out and buy a 680. It's performance is nearly >> as good, and great if you are focusing on games, but not for purely compute >> / cuda / mercury in CS6 >> >> I would love to hear some results on a 4GB 680, a 590 or a 690, let me >> know >> >> TG >> >> -- >> Animator & Editor >> www.teddygage.com >> Brooklyn >> >> > > > -- > danny princz > > exposedideas.com > --f46d0447a119c9a66504c27b371e Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable I got 24:46 on an unsupported GTX 460M, with 1.5 GB VRAM. Much slower than = the big cards, but waaaaaaaaaaaaaaaaaaaaaaaaaaaaaaay faster than CPU.=A0
On Thu, Jun 14, 2012 at 6:23 PM, rendernyc = <rendernyc@gmail.com> wrote:
ran your test on macpro3,1 with GTX 570 2.5G= B at 6:47

On Sat, May 26, 2012 at 2:50 PM= , Teddy Gage <teddygage@gmail.com> wrote:
=A0=A0=A0=A0 Well, shocking if you care abou= t this sort of thing. So after some struggles getting the GTX 680 to work w= ith AE CS6 11.0.1 I finally got it working. How would the 3 GB VRAM GTX 580= , with 500 CUDA cores stack up to the brand new 2 GB VRAM GTX 680 with 1,50= 0 CUDA cores?

Would it be worth upgrading if you already owned a 580? Would the extra= 1 GB VRAM make a difference for the older card?

Well I came up with= a benchmark (228K) available HERE that maxes out the GPU and tests your CUDA p= rocessing ability. You will need about 900 MB local space for the output an= d the new 11.0.1 patch (probably).

Now a lot of figures are at play here but with the project using 100% G= PU and 25% CPU I think it's a decent bench for comparing graphics cards= . Here are the results:

GTX 680 (2GB) =3D 6 min. 11 sec to render GTX 680 (2GB) (overclocked) =3D 5 min. 52 s
GTX 580 (3GB) =3D 5 min. 42 = s

So the GTX 580 with 3GB VRAM is faster. Now it's hard to say w= hether that's because the architecture is more compute-friendly, or the= extra GB of VRAM makes that much of a difference.

Considering I got the 580 for about $415 shipped used on eBay, I'd = say for now nobody needs to rush out and buy a 680. It's performance is= nearly as good, and great if you are focusing on games, but not for purely= compute / cuda / mercury in CS6

I would love to hear some results on a 4GB 680, a 590 or a 690, let me = know

TG

--
Animator & Editor
= www.teddygage.com
Brooklyn




--
danny princz=

exposedideas.= com

--f46d0447a119c9a66504c27b371e--