<div dir="ltr">I heard that 6xx series each cuda core was 3 times less powerfull compare to 5xx series cores. Though they were much better in terms of power consuption, which was main feature of 6xx series(no links, just words, so can't be sure) So i think CUDA cores nowadays isn't right value for measuring performance, ti's important, but not the main. We should stick to total transistors count per GPU :)<br>
Message: 5<br><div><div><div class="gmail_extra"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
Date: Fri, 28 Mar 2014 23:50:22 +0100<br>
From: GeKo <<a href="mailto:geko.pua@gmail.com">geko.pua@gmail.com</a>><br>
Subject: Re: [Bf-cycles] Bottleneck of gpu render<br>
To: <a href="mailto:bf-cycles@blender.org">bf-cycles@blender.org</a><br>
Message-ID:<br>
<<a href="mailto:CAK8Fe3GDNztWkaQoJUGJEO4Kg3vH2cUDCbOYENqQ0Eq9ZDHZ6g@mail.gmail.com">CAK8Fe3GDNztWkaQoJUGJEO4Kg3vH2cUDCbOYENqQ0Eq9ZDHZ6g@mail.gmail.com</a>><br>
Content-Type: text/plain; charset="iso-8859-1"<br>
<br>
But i really mean about the way that cycles process de model. I dont have<br>
any knowledge about raytracing render, but i am shocked about how the new<br>
hardware know improve so much rhe rendering, even when they have 5 time<br>
more cores.<br>
On 28 Mar 2014 23:11, "Brecht Van Lommel" <<a href="mailto:brechtvanlommel@pandora.be">brechtvanlommel@pandora.be</a>><br>
wrote:<br>
<br>
> There are various possibilities:<br>
><br>
> * Memory and texture memory read/write bottlenecks<br>
> * Different Mhz for cores<br>
> * Different GPU architecture<br>
> * Not all cores occupied due to divergence or mismatched batch sizes<br>
> * CPU Overhead<br>
><br>
> There's too many interacting parts to be sure without closely<br>
> investigating.<br>
><br>
> Brecht.<br>
><br>
> On Fri, Mar 28, 2014 at 9:30 PM, GeKo <<a href="mailto:geko.pua@gmail.com">geko.pua@gmail.com</a>> wrote:<br>
> > Short question, Why the execution time don't decrease "linearly"<br>
> according<br>
> > to the number of cuda cores?<br>
> ><br>
> > _______________________________________________<br>
> > Bf-cycles mailing list<br>
> > <a href="mailto:Bf-cycles@blender.org">Bf-cycles@blender.org</a><br>
> > <a href="http://lists.blender.org/mailman/listinfo/bf-cycles" target="_blank">http://lists.blender.org/mailman/listinfo/bf-cycles</a><br>
> ><br>
> _______________________________________________<br>
> Bf-cycles mailing list<br>
> <a href="mailto:Bf-cycles@blender.org">Bf-cycles@blender.org</a><br>
> <a href="http://lists.blender.org/mailman/listinfo/bf-cycles" target="_blank">http://lists.blender.org/mailman/listinfo/bf-cycles</a><br>
><br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <a href="http://lists.blender.org/pipermail/bf-cycles/attachments/20140328/b1414405/attachment-0001.htm" target="_blank">http://lists.blender.org/pipermail/bf-cycles/attachments/20140328/b1414405/attachment-0001.htm</a><br>
</blockquote></div><br></div></div></div></div>