<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:dc="http://purl.org/dc/elements/1.1/"
	xmlns:atom="http://www.w3.org/2005/Atom"
	xmlns:sy="http://purl.org/rss/1.0/modules/syndication/"
		>
<channel>
	<title>Comments on: A Few Thoughts on Nvidia&#8217;s Fermi</title>
	<atom:link href="http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/</link>
	<description>The Future is So Last Year...</description>
	<lastBuildDate>Thu, 12 Aug 2010 18:15:37 -0700</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: michael</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13625</link>
		<dc:creator>michael</dc:creator>
		<pubDate>Tue, 19 Jan 2010 08:03:18 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13625</guid>
		<description>what applications do you need these monster cards anyway?????  WHY NOT MAKE A VIDEO CARD THAT LASTS FOR A YEAR WITHOUT UPGRADES. you might be helping more people then you think, instead of making money.</description>
		<content:encoded><![CDATA[<p>what applications do you need these monster cards anyway?????  WHY NOT MAKE A VIDEO CARD THAT LASTS FOR A YEAR WITHOUT UPGRADES. you might be helping more people then you think, instead of making money.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Carandiru</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13291</link>
		<dc:creator>Carandiru</dc:creator>
		<pubDate>Sat, 03 Oct 2009 00:13:07 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13291</guid>
		<description>The bottom line - when we know - the performance difference between the Radeon 5800 series and the Fermi series in relation to cost. Eg.) 15% more FPS for the average consumer for $100 more today ?

Not too many applications currently available for the consumer that leverage CUDA. Step in the right direction, but at what cost to NVIDIA ?</description>
		<content:encoded><![CDATA[<p>The bottom line &#8211; when we know &#8211; the performance difference between the Radeon 5800 series and the Fermi series in relation to cost. Eg.) 15% more FPS for the average consumer for $100 more today ?</p>
<p>Not too many applications currently available for the consumer that leverage CUDA. Step in the right direction, but at what cost to NVIDIA ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: jasoncross</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13287</link>
		<dc:creator>jasoncross</dc:creator>
		<pubDate>Fri, 02 Oct 2009 00:24:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13287</guid>
		<description>Well, Nvidia has been pushing Tesla products into the supercomputing space for some time now, and this chip seems to put even more design considerations toward that space. What is interesting to me is that those design choices come at a cost in terms of graphics performance per watt or perf per mm^2.

These things take a few years to design and build, and it could be that Nvidia predicted several years ago that GP-GPU would simply be much further along to broad industry adoption than it is. And now, they&#039;re in the position of trying to make their market fit their product, instead of the other way around.

It&#039;s going to be interesting to see what this means in the long run. What the small size derivative chips of Fermi will be like, and if the same &quot;graphics for compute&quot; trade-offs cost them design wins in the notebook and mainstream desktop space. Or, will those products differ substantially, dropping ECC support and reducing cache per shader processor and so on?</description>
		<content:encoded><![CDATA[<p>Well, Nvidia has been pushing Tesla products into the supercomputing space for some time now, and this chip seems to put even more design considerations toward that space. What is interesting to me is that those design choices come at a cost in terms of graphics performance per watt or perf per mm^2.</p>
<p>These things take a few years to design and build, and it could be that Nvidia predicted several years ago that GP-GPU would simply be much further along to broad industry adoption than it is. And now, they&#8217;re in the position of trying to make their market fit their product, instead of the other way around.</p>
<p>It&#8217;s going to be interesting to see what this means in the long run. What the small size derivative chips of Fermi will be like, and if the same &#8220;graphics for compute&#8221; trade-offs cost them design wins in the notebook and mainstream desktop space. Or, will those products differ substantially, dropping ECC support and reducing cache per shader processor and so on?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Screemer</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13286</link>
		<dc:creator>Screemer</dc:creator>
		<pubDate>Thu, 01 Oct 2009 23:10:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13286</guid>
		<description>it looks like nvidia is moving to a differnt business field with this cards. my guess would be that they are trying to push into the supercomputer market. 

http://www.brightsideofnews.com/news/2009/9/30/nvidia-gt300-fermi-cgpu-to-power-worlds-most-powerful-supercomputer.aspx</description>
		<content:encoded><![CDATA[<p>it looks like nvidia is moving to a differnt business field with this cards. my guess would be that they are trying to push into the supercomputer market. </p>
<p><a href="http://www.brightsideofnews.com/news/2009/9/30/nvidia-gt300-fermi-cgpu-to-power-worlds-most-powerful-supercomputer.aspx" rel="nofollow">http://www.brightsideofnews.com/news/2009/9/30/nvidia-gt300-fermi-cgpu-to-power-worlds-most-powerful-supercomputer.aspx</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Netmaker</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13285</link>
		<dc:creator>Netmaker</dc:creator>
		<pubDate>Thu, 01 Oct 2009 22:29:01 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13285</guid>
		<description>Nvidia is trying to differentiate itself ahead of Intel and ATI including sophisticated integrated graphics with their CPUs.  

Otherwise it will be &quot;game over&quot; for them.</description>
		<content:encoded><![CDATA[<p>Nvidia is trying to differentiate itself ahead of Intel and ATI including sophisticated integrated graphics with their CPUs.  </p>
<p>Otherwise it will be &#8220;game over&#8221; for them.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: [JC]Thoughts on Nvidia</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13284</link>
		<dc:creator>[JC]Thoughts on Nvidia</dc:creator>
		<pubDate>Thu, 01 Oct 2009 21:37:04 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13284</guid>
		<description>[...]  [...]</description>
		<content:encoded><![CDATA[<p>[...]  [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Meh</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13283</link>
		<dc:creator>Meh</dc:creator>
		<pubDate>Thu, 01 Oct 2009 21:36:02 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13283</guid>
		<description>pff. useless opinion. If your so good, go make a card yourself.</description>
		<content:encoded><![CDATA[<p>pff. useless opinion. If your so good, go make a card yourself.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: This is getting Nstrange - TechSpot OpenBoards</title>
		<link>http://www.jasoncross.org/2009/09/30/a-few-thoughts-on-nvidias-fermi/comment-page-1/#comment-13282</link>
		<dc:creator>This is getting Nstrange - TechSpot OpenBoards</dc:creator>
		<pubDate>Thu, 01 Oct 2009 20:38:40 +0000</pubDate>
		<guid isPermaLink="false">http://www.jasoncross.org/?p=404#comment-13282</guid>
		<description>[...] This is getting Nstrange     cant quite figure out what Nvidia is up to, it looks like they got caught with their shorts down. any thoughts?  http://www.jasoncross.org/2009/09/30...ermi/#more-404 [...]</description>
		<content:encoded><![CDATA[<p>[...] This is getting Nstrange     cant quite figure out what Nvidia is up to, it looks like they got caught with their shorts down. any thoughts?  <a href="http://www.jasoncross.org/2009/09/30...ermi/#more-404" rel="nofollow">http://www.jasoncross.org/2009/09/30&#8230;ermi/#more-404</a> [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>
