<?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:go='http://ns.gigaom.com/'
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: Does the Cloud Need a Specialized Chip?</title>
	<atom:link href="http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/feed/" rel="self" type="application/rss+xml" />
	<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/</link>
	<description></description>
	<lastBuildDate>Fri, 10 Feb 2012 19:16:52 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: Nvidia Shows Off Its Survival Skills With IBM Win &#171; wesley83&#039;s Blog</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243174</link>
		<dc:creator><![CDATA[Nvidia Shows Off Its Survival Skills With IBM Win &#171; wesley83&#039;s Blog]]></dc:creator>
		<pubDate>Tue, 18 May 2010 18:43:33 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243174</guid>
		<description><![CDATA[&lt;p&gt;[...] IBM made to push it into the HPC market as well as into the data center, but it turns out the market didn’t want the Cell [...]&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>[...] IBM made to push it into the HPC market as well as into the data center, but it turns out the market didn’t want the Cell [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Nvidia Shows Off Its Survival Skills With IBM Win</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243173</link>
		<dc:creator><![CDATA[Nvidia Shows Off Its Survival Skills With IBM Win]]></dc:creator>
		<pubDate>Tue, 18 May 2010 16:01:35 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243173</guid>
		<description><![CDATA[&lt;p&gt;[...] IBM made to push it into the HPC market as well as into the data center, but it turns out the market didn&#8217;t want the Cell [...]&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>[...] IBM made to push it into the HPC market as well as into the data center, but it turns out the market didn&#8217;t want the Cell [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Incomplete Thought: The Other Side Of Cloud &#8211; Where The (Wild) Infrastructure Things Are&#8230; &#124; Rational Survivability</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243172</link>
		<dc:creator><![CDATA[Incomplete Thought: The Other Side Of Cloud &#8211; Where The (Wild) Infrastructure Things Are&#8230; &#124; Rational Survivability]]></dc:creator>
		<pubDate>Wed, 10 Mar 2010 01:13:16 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243172</guid>
		<description><![CDATA[&lt;p&gt;[...] Does the Cloud Need a Specialized Chip? (gigaom.com) [...]&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>[...] Does the Cloud Need a Specialized Chip? (gigaom.com) [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: digitrunner</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243171</link>
		<dc:creator><![CDATA[digitrunner]]></dc:creator>
		<pubDate>Tue, 09 Mar 2010 15:11:18 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243171</guid>
		<description><![CDATA[&lt;p&gt;I&#039;ve looked at clouds from both sides now,
From up and down, and still somehow
It&#039;s cloud illusions i recall.
I really don&#039;t know clouds at all.
LOL sorry Cheese I couldn&#039;t resist&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>I&#8217;ve looked at clouds from both sides now,<br />
From up and down, and still somehow<br />
It&#8217;s cloud illusions i recall.<br />
I really don&#8217;t know clouds at all.<br />
LOL sorry Cheese I couldn&#8217;t resist</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: digitrunner</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243170</link>
		<dc:creator><![CDATA[digitrunner]]></dc:creator>
		<pubDate>Tue, 09 Mar 2010 15:06:06 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243170</guid>
		<description><![CDATA[&lt;p&gt;Tilera has figured out a way to get a lot of cores to talk without having to pause to listen to one another, LOL women perfected that concept a long time ago :P&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>Tilera has figured out a way to get a lot of cores to talk without having to pause to listen to one another, LOL women perfected that concept a long time ago :P</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Cheese</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243169</link>
		<dc:creator><![CDATA[Cheese]]></dc:creator>
		<pubDate>Tue, 09 Mar 2010 11:10:10 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243169</guid>
		<description><![CDATA[&lt;p&gt;If anything, the cloud needs cheaper and (even) less power hungry chips. And not necessarily more cores. The Cell processor is out there for a while now and with few takers (in the cloud space).&lt;/p&gt;

&lt;p&gt;The big server farmers (Google, facebook, twitter, ..) happy with their versions of Map-Reduce, probably prioritize power bill reductions. I don&#039;t mean they wouldn&#039;t want cheaper hardware, but then it really needs to be cheaper, while still being &quot;commodity&quot; for the software they need to run.&lt;/p&gt;

&lt;p&gt;On the consumer devices side, at the risk of being proven utterly un-imaginative, the question that begs to be asked is - why would anyone need 48 cores? That brings us back to the classic problem of parallel computing - Is it (still) worth it?&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>If anything, the cloud needs cheaper and (even) less power hungry chips. And not necessarily more cores. The Cell processor is out there for a while now and with few takers (in the cloud space).</p>
<p>The big server farmers (Google, facebook, twitter, ..) happy with their versions of Map-Reduce, probably prioritize power bill reductions. I don&#8217;t mean they wouldn&#8217;t want cheaper hardware, but then it really needs to be cheaper, while still being &#8220;commodity&#8221; for the software they need to run.</p>
<p>On the consumer devices side, at the risk of being proven utterly un-imaginative, the question that begs to be asked is &#8211; why would anyone need 48 cores? That brings us back to the classic problem of parallel computing &#8211; Is it (still) worth it?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Brian Mastenbrook</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243168</link>
		<dc:creator><![CDATA[Brian Mastenbrook]]></dc:creator>
		<pubDate>Mon, 08 Mar 2010 22:21:59 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243168</guid>
		<description><![CDATA[&lt;p&gt;The lack of cache coherency isn&#039;t necessarily a deal-killer in this application, provided that there are still high-speed message-passing interconnects on the board. Tilera also encourages the use of their built-in message-passing fabric for application.&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>The lack of cache coherency isn&#8217;t necessarily a deal-killer in this application, provided that there are still high-speed message-passing interconnects on the board. Tilera also encourages the use of their built-in message-passing fabric for application.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Lina Inverse</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243167</link>
		<dc:creator><![CDATA[Lina Inverse]]></dc:creator>
		<pubDate>Mon, 08 Mar 2010 21:47:20 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243167</guid>
		<description><![CDATA[&lt;p&gt;Intel&#039;s “single-chip cloud computer” is more of an experiment that&#039;s using the term cloud for its current hype.  The chip has no provision for cache coherency and they&#039;re only fabricating about 100, which will find homes in universities and research labs where we will see if this approach is useful.&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>Intel&#8217;s “single-chip cloud computer” is more of an experiment that&#8217;s using the term cloud for its current hype.  The chip has no provision for cache coherency and they&#8217;re only fabricating about 100, which will find homes in universities and research labs where we will see if this approach is useful.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Stacey Higginbotham</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243166</link>
		<dc:creator><![CDATA[Stacey Higginbotham]]></dc:creator>
		<pubDate>Mon, 08 Mar 2010 20:15:21 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243166</guid>
		<description><![CDATA[&lt;p&gt;Your last point about attracting startups to architect their apps to Tilera before they get big is a good one. Thanks!&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>Your last point about attracting startups to architect their apps to Tilera before they get big is a good one. Thanks!</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Brian Mastenbrook</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243165</link>
		<dc:creator><![CDATA[Brian Mastenbrook]]></dc:creator>
		<pubDate>Mon, 08 Mar 2010 19:19:06 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243165</guid>
		<description><![CDATA[&lt;p&gt;Intel has made some attempts to gain inroads in the line-speed network processing market with Nehalem-based platforms, but ultimately their general-purpose processors just don&#039;t pack the throughput punch necessary for this sort of application. Tilera&#039;s main threats are Oracle (nee Sun)&#039;s CoolThreads processors and Cavium&#039;s Octeon (at the low end), along with a few other specialized processors. IBM&#039;s recently-disclosed PowerPC-based network processor and Intel&#039;s &quot;single-chip cloud&quot; also play in this space; if either of those makes it to market, it could put a significant dent in Tilera&#039;s ambitions.&lt;/p&gt;

&lt;p&gt;Tilera does seem to have ambitions in the broader network application market, but these ambitions are probably doomed from the get-go. The advantage of a commodity architecture is the easy spring-board for development. Few cloud service providers will stop to rearchitect their application for maximum throughput after it hits big; rather, they&#039;ll look for more effective ways to scale their existing architecture. If Tilera really does want to play here, it should offer a low-cost developer kit to enable startups to target applications to their processor. Otherwise, they&#039;re depending on businesses to make the leap to depending on their platform without having had the opportunity to discover the advantages in a low-risk environment.&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>Intel has made some attempts to gain inroads in the line-speed network processing market with Nehalem-based platforms, but ultimately their general-purpose processors just don&#8217;t pack the throughput punch necessary for this sort of application. Tilera&#8217;s main threats are Oracle (nee Sun)&#8217;s CoolThreads processors and Cavium&#8217;s Octeon (at the low end), along with a few other specialized processors. IBM&#8217;s recently-disclosed PowerPC-based network processor and Intel&#8217;s &#8220;single-chip cloud&#8221; also play in this space; if either of those makes it to market, it could put a significant dent in Tilera&#8217;s ambitions.</p>
<p>Tilera does seem to have ambitions in the broader network application market, but these ambitions are probably doomed from the get-go. The advantage of a commodity architecture is the easy spring-board for development. Few cloud service providers will stop to rearchitect their application for maximum throughput after it hits big; rather, they&#8217;ll look for more effective ways to scale their existing architecture. If Tilera really does want to play here, it should offer a low-cost developer kit to enable startups to target applications to their processor. Otherwise, they&#8217;re depending on businesses to make the leap to depending on their platform without having had the opportunity to discover the advantages in a low-risk environment.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Eric</title>
		<link>http://gigaom.com/2010/03/08/does-the-cloud-need-a-specialized-chip/#comment-243164</link>
		<dc:creator><![CDATA[Eric]]></dc:creator>
		<pubDate>Mon, 08 Mar 2010 19:01:14 +0000</pubDate>
		<guid isPermaLink="false">http://gigaom.com/?p=104254#comment-243164</guid>
		<description><![CDATA[&lt;p&gt;I think the interesting question here isn&#039;t really about the specific details of their technology... it is about the dynamics of the marketplace.  Transmeta and others have attempted the &quot;we have a better architecture for the future that is drive by &quot; and they have all failed.  Is that because Intel is just better?  Because they have so much money and marketplace power that they can prevent anyone else from getting traction?  Because no one trend is so overriding that it completely changes the processor marketplace?  I&#039;m not sure - but we haven&#039;t seen anyone ride one of those trends to success...&lt;/p&gt;]]></description>
		<content:encoded><![CDATA[<p>I think the interesting question here isn&#8217;t really about the specific details of their technology&#8230; it is about the dynamics of the marketplace.  Transmeta and others have attempted the &#8220;we have a better architecture for the future that is drive by &#8221; and they have all failed.  Is that because Intel is just better?  Because they have so much money and marketplace power that they can prevent anyone else from getting traction?  Because no one trend is so overriding that it completely changes the processor marketplace?  I&#8217;m not sure &#8211; but we haven&#8217;t seen anyone ride one of those trends to success&#8230;</p>
]]></content:encoded>
	</item>
</channel>
</rss>

