<?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/"
	xmlns:georss="http://www.georss.org/georss" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:media="http://search.yahoo.com/mrss/"
		>
<channel>
	<title>Comments on: About</title>
	<atom:link href="http://theaccelerator.wordpress.com/about/feed/" rel="self" type="application/rss+xml" />
	<link>http://theaccelerator.wordpress.com</link>
	<description>A Critical Look at Hardware-Accelerated Computing</description>
	<lastBuildDate>Wed, 20 Aug 2008 14:09:06 +0000</lastBuildDate>
	<generator>http://wordpress.com/</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Rupert Baines</title>
		<link>http://theaccelerator.wordpress.com/about/#comment-5</link>
		<dc:creator>Rupert Baines</dc:creator>
		<pubDate>Wed, 22 Aug 2007 07:05:55 +0000</pubDate>
		<guid isPermaLink="false">#comment-5</guid>
		<description>Hi

I like your blog.

Gor referred here after the comments on Mathstar &amp; Tilera, which I totally agree with.

We too are a multi-core architecture. I like to think we have done it diffently to those guys:
- Focussed on tools before silicon, so it actually is possible to prgam (whodathunk it...?)
- Thought about applications and &quot;where are we going to sell it?&quot; before we started.

That&#039;s my biggest raised eye-brow on Tilera.   Anyone who claims &quot;We can do everything&quot; is really saying &quot;We do not know what we are any good at&quot; - which is quick direction post to the graveyard....

Claiming they can L4-L7 acceleration *and* video smells strongly of &quot;ummm... lets name something sexy and hope someone bits&quot;

As I say, I believe (hope!) we have approached it differently.

Certainly the fact we have survived six years and are shipping large volumes of multi-core provessors to credible customers (Intel, Nortel, Samsung, etc) seems to bear that out.

Happy to chat

Rupert</description>
		<content:encoded><![CDATA[<p>Hi</p>
<p>I like your blog.</p>
<p>Gor referred here after the comments on Mathstar &amp; Tilera, which I totally agree with.</p>
<p>We too are a multi-core architecture. I like to think we have done it diffently to those guys:<br />
- Focussed on tools before silicon, so it actually is possible to prgam (whodathunk it&#8230;?)<br />
- Thought about applications and &#8220;where are we going to sell it?&#8221; before we started.</p>
<p>That&#8217;s my biggest raised eye-brow on Tilera.   Anyone who claims &#8220;We can do everything&#8221; is really saying &#8220;We do not know what we are any good at&#8221; &#8211; which is quick direction post to the graveyard&#8230;.</p>
<p>Claiming they can L4-L7 acceleration *and* video smells strongly of &#8220;ummm&#8230; lets name something sexy and hope someone bits&#8221;</p>
<p>As I say, I believe (hope!) we have approached it differently.</p>
<p>Certainly the fact we have survived six years and are shipping large volumes of multi-core provessors to credible customers (Intel, Nortel, Samsung, etc) seems to bear that out.</p>
<p>Happy to chat</p>
<p>Rupert</p>
]]></content:encoded>
	</item>
</channel>
</rss>
