[Bf-cycles] Re : Re : Cycles on Nvidia Kepler

myke@octopod-studio.com myke at octopod-studio.com
Tue Sep 25 23:59:48 CEST 2012

Hi, i don t know why exactly the gk104 is slower than gf110, the double precision problem don t explain everything. But it seems that the gk104 is clearly an unfinished product. A Guy from pny have said to me today, that  kepler 1 & 2 are like Windows vista and 7. Same economic cause, same urgency, same result... But every renderer i ve tried give the same speed ratio result.  i ve stopped my tests around r50100, so i m perhaps outdated...

----- Reply message -----
De : "Мукаев Виктор" <vitos1g at gmail.com>
Pour : <bf-cycles at blender.org>
Objet : [Bf-cycles] Re : Cycles on Nvidia Kepler
Date : mar., sept. 25, 2012 12:45
As far as i know, Keplers are lacking of good memory management. There were some nvidia guys at Siggraph that mentioned it.

>Message: 5

>Date: Tue, 25 Sep 2012 10:26:11 +0200

From: " myke at octopod-studio.com " <myke at octopod-studio.com>

Subject: [Bf-cycles] Re :  Cycles on Nvidia Kepler

To: bf-cycles at blender.org,bf-cycles at blender.org

Message-ID: < at ns0.ovh.net>

Content-Type: text/plain; charset="utf-8"

Hi, i ve made a lots of testing about this, and actually the gk104 gpu familly is really weak on double precision op?rations...

So, every 6xx gpu are slower than 5xx ... 5 cores of 6xx = 1 core of 5xx in double...

Only one version of blender on graphicall have succeded to run cycles on an Asus 680 dcuii , but i ve also made some tests with iray and other gpu renderer... It s the same...

Nvidia have said that the first kepler 2 will come with the tesla k20, and new quadro and gtx after... 6 month to wait minimum...

So i ve built for a little studio a rendering machine with 4 580 gainward phantom 3 go, and i think it s the better price/speed actual solution...

But i think that Brecht will say more about this. ( don't think that s possible to convert everything in single pr?cision )


-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.blender.org/pipermail/bf-cycles/attachments/20120925/838d9c18/attachment.htm 

More information about the Bf-cycles mailing list