<?xml version="1.0" encoding="UTF-8" ?>
<?xml-stylesheet type="text/xsl" media="screen" href="/styles/xslt/rss.xslt"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:trackback="http://madskills.com/public/xml/rss/module/trackback/" xmlns:wfw="http://wellformedweb.org/CommentAPI/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/" xmlns:media="http://search.yahoo.com/mrss/" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:c9="http://channel9.msdn.com">
<channel>
	<title>Comment Feed for Channel 9 - DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
	<atom:link rel="self" type="application/rss+xml" href="http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance/RSS"></atom:link>
	<image>
		<url>http://ecn.channel9.msdn.com/o9/ch9/9/2/7/7/5/5/DirectCompute210_512_ch9.png</url>
		<title>Channel 9 - DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<link></link>
	</image>
	<description> Join James Fung from Developer Technology at NVIDIA as he covers the following advanced topics for DirectCompute: &amp;nbsp;&amp;nbsp; Work distribution best practices&amp;nbsp;&amp;nbsp; Compute shader code best practices&amp;nbsp;&amp;nbsp; Algorithm selection best practices&amp;nbsp;&amp;nbsp; Multi-GPU best practices He also gives an example problem, scan/reduction, and then goes through various optimizations for that problem. For more information on DirectCompute, download the PDC 2009 DirectCompute HOL,&amp;nbsp;watch&amp;nbsp;the DirectCompute Roundtable discussion, see the full DirectCompute lecture series,&amp;nbsp;and download the slides for this lecture. </description>
	<link></link>
	<language>en</language>
	<pubDate>Wed, 19 Jun 2013 11:08:36 GMT</pubDate>
	<lastBuildDate>Wed, 19 Jun 2013 11:08:36 GMT</lastBuildDate>
	<generator>Rev9</generator>
	<item>
		<title>Re: DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<description>
			<![CDATA[
<p>Where we can find the presentations?</p>
<p>The code is not visible in the movies</p>
<p>posted by stefandylgerov</p>]]>
		</description>
		<link>http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634143739960000000</link>
		<pubDate>Sat, 10 Jul 2010 15:53:16 GMT</pubDate>
		<guid isPermaLink="true">http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634143739960000000</guid>
		<dc:creator>stefandylgerov</dc:creator>
	</item>
	<item>
		<title>Re: DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<description>
			<![CDATA[
<p>The relevant links should be in the description to the right of the video (<a href="http://code.msdn.microsoft.com/Project/Download/FileDownload.aspx?ProjectName=DirectComputeLecture&amp;DownloadId=12929">http://code.msdn.microsoft.com/Project/Download/FileDownload.aspx?ProjectName=DirectComputeLecture&amp;DownloadId=12929</a>)
 is the link to the slide deck.&nbsp; The code that he uses is similar to that included in the DirectCompute Hands on Lab (HOL) which is also linked in the description.&nbsp;Hope that helps!</p>
<p>posted by gclassy</p>]]>
		</description>
		<link>http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634145534050000000</link>
		<pubDate>Mon, 12 Jul 2010 17:43:25 GMT</pubDate>
		<guid isPermaLink="true">http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634145534050000000</guid>
		<dc:creator>gclassy</dc:creator>
	</item>
	<item>
		<title>Re: DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<description>
			<![CDATA[
<p>Here's an interesting question:</p>
<p>Wont we get the same problem in the GPU as in the CPU when all applications start using the GPU ? ( contention, GPU gets overloaded, which means delays, etc... )</p>
<p>So in other words we are just moving/postponing the problem.<br /><br />Do you have any thoughts about this ?</p>
<p>posted by Mr Crash</p>]]>
		</description>
		<link>http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634165611880000000</link>
		<pubDate>Wed, 04 Aug 2010 23:26:28 GMT</pubDate>
		<guid isPermaLink="true">http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634165611880000000</guid>
		<dc:creator>Mr Crash</dc:creator>
	</item>
	<item>
		<title>Re: DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<description>
			<![CDATA[
<p>I think overall its letting the system make use of all resources, GPU and CPU.&nbsp; Certainly its possible that down the line, applications could begin to contend for GPU resources.&nbsp; But,&nbsp;there will be tasks that remain on the CPU and many that can make new
 use of the GPU (and often need it intermittently) so overall it'll make better use of whats available.
</p>
<p>posted by fungja</p>]]>
		</description>
		<link>http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634166323050000000</link>
		<pubDate>Thu, 05 Aug 2010 19:11:45 GMT</pubDate>
		<guid isPermaLink="true">http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634166323050000000</guid>
		<dc:creator>fungja</dc:creator>
	</item>
	<item>
		<title>Re: DirectCompute Lecture Series 210: GPU Optimizations and Performance</title>
		<description>
			<![CDATA[ <p>Some slides (for example, #35 and 36) were apparently taken as-is from the older presentation by Mark Harris (<a href="http://developer.download.nvidia.com/compute/cuda/1_1/Website/projects/reduction/doc/reduction.pdf">http&#58;&#47;&#47;developer.download.nvidia.com&#47;compute&#47;cuda&#47;1_1&#47;Website&#47;projects&#47;reduction&#47;doc&#47;reduction.pdf</a>) and contain code from CUDA version of the reduction optimization experiment.</p><p>In my opinion, description of algorithm cascading along with Brent’s theorem is pretty important, but unfortunately it is missing in the current talk. Otherwise, great lecture, thank you James!</p><p>posted by AlexeyKamenev</p>]]>
		</description>
		<link>http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634220886910000000</link>
		<pubDate>Thu, 07 Oct 2010 22:51:31 GMT</pubDate>
		<guid isPermaLink="true">http://channel9.msdn.com/Blogs/gclassy/DirectCompute-Lecture-Series-210-GPU-Optimizations-and-Performance#c634220886910000000</guid>
		<dc:creator>AlexeyKamenev</dc:creator>
	</item>
</channel>
</rss>