<?xml version="1.0" encoding="UTF-8"?>
<rss version="2.0">
  <channel>
    <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/244287</link>
    <title>MATLAB Central Newsreader - Does Jacket really works?</title>
    <description>Feed for thread: Does Jacket really works?</description>
    <language>en-us</language>
    <copyright>&amp;copy;1994-2012 by MathWorks, Inc.</copyright>
    <webmaster>webmaster@mathworks.com</webmaster>
    <generator>MATLAB Central Newsreader</generator>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <ttl>60</ttl>
    <image>
      <title>MathWorks</title>
      <url>http://www.mathworks.com/images/membrane_icon.gif</url>
    </image>
    <item>
      <pubDate>Thu, 26 Feb 2009 10:43:01 -0500</pubDate>
      <title>Re: Does Jacket really works?</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/244287#630981</link>
      <author>Alejandro </author>
      <description>I wondered the same thing. Anyway, it looks quite suspicious that you have to register to get a pricing. I checked and for personal (non-commercial) use the price was $2400 .  This is more expensive than the basic individual license for MATLAB itself!! &lt;br&gt;
&lt;br&gt;
So, I am not planning to purchase jacket. I'm working on writing my own .mex files for CUDA support. I've seen some nice examples here at MATLAB central. I hope that we as a community manage to get the standard matrix operations working in CUDA.&lt;br&gt;
&lt;br&gt;
&lt;br&gt;
Jaime Zamora &amp;lt;jaime.zamora@gmail.com&amp;gt; wrote in message &amp;lt;a946e43c-6290-4e49-94e7-65734a3cd7e7@c12g2000yqj.googlegroups.com&amp;gt;...&lt;br&gt;
&amp;gt; I just found this:&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; &lt;a href=&quot;http://www.jrti.com/products/software/accelereyes_jacket.html&quot;&gt;http://www.jrti.com/products/software/accelereyes_jacket.html&lt;/a&gt;&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt;  Jacket is a GPU engine for MATLAB=AE. Jacket enables standard MATLAB&lt;br&gt;
&amp;gt; code to run on any NVIDIA CUDA-capable GPU, from the GeForce 8400 to&lt;br&gt;
&amp;gt; the Tesla C1060. Jacket introduces new data types to MATLAB which let&lt;br&gt;
&amp;gt; you move your data and computations to the GPU.&lt;br&gt;
&amp;gt; Jacket is not another GPU API, nor is it simply a collection of GPU&lt;br&gt;
&amp;gt; MEX functions. Rather, it is a complete and transparent system,&lt;br&gt;
&amp;gt; automatically making memory transfer and execution optimization&lt;br&gt;
&amp;gt; decisions. Jacket uses a compile on-the-fly system to allow GPU&lt;br&gt;
&amp;gt; functions to run in MATLAB's interpretive style.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Does it really works? It speeds up all toolboxes? Is there anyone&lt;br&gt;
&amp;gt; familiar with it?&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Best,&lt;br&gt;
&amp;gt; Jaime</description>
    </item>
    <item>
      <pubDate>Wed, 11 Feb 2009 15:58:09 -0500</pubDate>
      <title>Does Jacket really works?</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/244287#627651</link>
      <author>Jaime Zamora</author>
      <description>I just found this:&lt;br&gt;
&lt;br&gt;
&lt;a href=&quot;http://www.jrti.com/products/software/accelereyes_jacket.html&quot;&gt;http://www.jrti.com/products/software/accelereyes_jacket.html&lt;/a&gt;&lt;br&gt;
&lt;br&gt;
&amp;nbsp;Jacket is a GPU engine for MATLAB=AE. Jacket enables standard MATLAB&lt;br&gt;
code to run on any NVIDIA CUDA-capable GPU, from the GeForce 8400 to&lt;br&gt;
the Tesla C1060. Jacket introduces new data types to MATLAB which let&lt;br&gt;
you move your data and computations to the GPU.&lt;br&gt;
Jacket is not another GPU API, nor is it simply a collection of GPU&lt;br&gt;
MEX functions. Rather, it is a complete and transparent system,&lt;br&gt;
automatically making memory transfer and execution optimization&lt;br&gt;
decisions. Jacket uses a compile on-the-fly system to allow GPU&lt;br&gt;
functions to run in MATLAB's interpretive style.&lt;br&gt;
&lt;br&gt;
Does it really works? It speeds up all toolboxes? Is there anyone&lt;br&gt;
familiar with it?&lt;br&gt;
&lt;br&gt;
Best,&lt;br&gt;
Jaime</description>
    </item>
    <item>
      <pubDate>Tue, 28 Apr 2009 23:39:01 -0400</pubDate>
      <title>Re: Does Jacket really works?</title>
      <link>http://www.mathworks.com/matlabcentral/newsreader/view_thread/244287#646019</link>
      <author>The GP-you Group The GP-you Group</author>
      <description>Jaime Zamora &amp;lt;jaime.zamora@gmail.com&amp;gt; wrote in message &amp;lt;a946e43c-6290-4e49-94e7-65734a3cd7e7@c12g2000yqj.googlegroups.com&amp;gt;...&lt;br&gt;
&amp;gt; I just found this:&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; &lt;a href=&quot;http://www.jrti.com/products/software/accelereyes_jacket.html&quot;&gt;http://www.jrti.com/products/software/accelereyes_jacket.html&lt;/a&gt;&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt;  Jacket is a GPU engine for MATLAB=AE. Jacket enables standard MATLAB&lt;br&gt;
&amp;gt; code to run on any NVIDIA CUDA-capable GPU, from the GeForce 8400 to&lt;br&gt;
&amp;gt; the Tesla C1060. Jacket introduces new data types to MATLAB which let&lt;br&gt;
&amp;gt; you move your data and computations to the GPU.&lt;br&gt;
&amp;gt; Jacket is not another GPU API, nor is it simply a collection of GPU&lt;br&gt;
&amp;gt; MEX functions. Rather, it is a complete and transparent system,&lt;br&gt;
&amp;gt; automatically making memory transfer and execution optimization&lt;br&gt;
&amp;gt; decisions. Jacket uses a compile on-the-fly system to allow GPU&lt;br&gt;
&amp;gt; functions to run in MATLAB's interpretive style.&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Does it really works? It speeds up all toolboxes? Is there anyone&lt;br&gt;
&amp;gt; familiar with it?&lt;br&gt;
&amp;gt; &lt;br&gt;
&amp;gt; Best,&lt;br&gt;
&amp;gt; Jaime&lt;br&gt;
&lt;br&gt;
Hi,&lt;br&gt;
&lt;br&gt;
you can try our Freeware library GPUmat from &lt;a href=&quot;http://www.gp-you.org.&quot;&gt;http://www.gp-you.org.&lt;/a&gt; GPUmat enables Matlab code to run on GPUs. Check the documentation to find out how many features we have implemented. Its for free!&lt;br&gt;
&lt;br&gt;
Thanks,&lt;br&gt;
The GP-you Group</description>
    </item>
  </channel>
</rss>

