<?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: Interview: MATLAB Support for GPUs a Game-Changer</title>
	<atom:link href="http://insidehpc.com/2010/10/04/interview-matlab-support-for-gpus-a-game-changer/feed/" rel="self" type="application/rss+xml" />
	<link>http://insidehpc.com/2010/10/04/interview-matlab-support-for-gpus-a-game-changer/</link>
	<description>HPC News Without the Noise for Supercomputing Professionals &#124; insideHPC</description>
	<lastBuildDate>Fri, 03 May 2013 04:44:25 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1.1</generator>
	<item>
		<title>By: John Melonakos</title>
		<link>http://insidehpc.com/2010/10/04/interview-matlab-support-for-gpus-a-game-changer/#comment-261800</link>
		<dc:creator>John Melonakos</dc:creator>
		<pubDate>Fri, 15 Oct 2010 19:52:56 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=14077#comment-261800</guid>
		<description>Jacket is the only product that has all of the following (PCT and GPUmat do not have these):

Reduction Function Support (e.g. SUM, FIND, MIN, MAX, ANY, ALL, etc.)
Convolution Function Support (e.g. CONV, CONV2, CONVN, FILTER2, etc.)
Linear Algebra Support (e.g. INV, SVD, EIG, MLDIVIDE, QR, LU, etc.)

Simply pointing out that you get what you pay for with GPUmat or you get what you will wait a long time for with PCT...</description>
		<content:encoded><![CDATA[<p>Jacket is the only product that has all of the following (PCT and GPUmat do not have these):</p>
<p>Reduction Function Support (e.g. SUM, FIND, MIN, MAX, ANY, ALL, etc.)<br />
Convolution Function Support (e.g. CONV, CONV2, CONVN, FILTER2, etc.)<br />
Linear Algebra Support (e.g. INV, SVD, EIG, MLDIVIDE, QR, LU, etc.)</p>
<p>Simply pointing out that you get what you pay for with GPUmat or you get what you will wait a long time for with PCT&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Sam</title>
		<link>http://insidehpc.com/2010/10/04/interview-matlab-support-for-gpus-a-game-changer/#comment-261698</link>
		<dc:creator>Sam</dc:creator>
		<pubDate>Fri, 15 Oct 2010 12:34:59 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=14077#comment-261698</guid>
		<description>Or also GPUMat (http://www.gp-you.org/), which is  free (but  not open source), all these three groups (Parallel Toolbox, GPUMat and JackRabbit) use the same approach, they declare a new datatype (or more precisely a new class) and provide a long list of operations that execute on the GPU (+,-, *, fft, etc)

It would be great to have some benchmarks, by far I can tell that GPUMat gave us just some moderate speed-ups (4 to 10 times), we still prefer to write our own mexFunctions  to get the max of performance</description>
		<content:encoded><![CDATA[<p>Or also GPUMat (<a href="http://www.gp-you.org/" rel="nofollow">http://www.gp-you.org/</a>), which is  free (but  not open source), all these three groups (Parallel Toolbox, GPUMat and JackRabbit) use the same approach, they declare a new datatype (or more precisely a new class) and provide a long list of operations that execute on the GPU (+,-, *, fft, etc)</p>
<p>It would be great to have some benchmarks, by far I can tell that GPUMat gave us just some moderate speed-ups (4 to 10 times), we still prefer to write our own mexFunctions  to get the max of performance</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: John Melonakos</title>
		<link>http://insidehpc.com/2010/10/04/interview-matlab-support-for-gpus-a-game-changer/#comment-259878</link>
		<dc:creator>John Melonakos</dc:creator>
		<pubDate>Mon, 04 Oct 2010 22:58:30 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=14077#comment-259878</guid>
		<description>If you&#039;re curious, you might consider giving Jacket a try for running MATLAB on the GPU - here:  http://www.accelereyes.com/products/compare</description>
		<content:encoded><![CDATA[<p>If you&#8217;re curious, you might consider giving Jacket a try for running MATLAB on the GPU &#8211; here:  <a href="http://www.accelereyes.com/products/compare" rel="nofollow">http://www.accelereyes.com/products/compare</a></p>
]]></content:encoded>
	</item>
</channel>
</rss>
