<?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: Cisco&#8217;s move out of InfiniBand early, but may ultimately prove correct</title>
	<atom:link href="http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/feed/" rel="self" type="application/rss+xml" />
	<link>http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/</link>
	<description>HPC News Without the Noise for Supercomputing Professionals &#124; insideHPC</description>
	<lastBuildDate>Sun, 19 May 2013 10:46:54 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.1.1</generator>
	<item>
		<title>By: Rumors of Infiniband&#8217;s (imminent) demise &#8230; &#171; scalability.org</title>
		<link>http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/#comment-178707</link>
		<dc:creator>Rumors of Infiniband&#8217;s (imminent) demise &#8230; &#171; scalability.org</dc:creator>
		<pubDate>Tue, 18 Aug 2009 13:33:21 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=6727#comment-178707</guid>
		<description>[...] are greatly exaggerated. John at InsideHPC has an article on Cisco&#8217;s move out of Infiniband which refers to another article on [...]</description>
		<content:encoded><![CDATA[<p>[...] are greatly exaggerated. John at InsideHPC has an article on Cisco&#8217;s move out of Infiniband which refers to another article on [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mark Hahn</title>
		<link>http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/#comment-178595</link>
		<dc:creator>Mark Hahn</dc:creator>
		<pubDate>Mon, 17 Aug 2009 18:57:38 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=6727#comment-178595</guid>
		<description>IB is big in HPC, but not because IB is so great.  it&#039;s merely more attractive than the alternatives (Gb, 10G).  if there were an ethernet-like alternative that came close to the same bandwidth and latency numbers, IB would have real competition.  for instance, Gb persists and even makes a lot of sense in some cases where speed (either lat or bw) is not important.  10G is attractive for its ease of interop, but has so far been dramatically more expensive, not to mention slower than IB.  in other words, IB&#039;s closest competitor seems to be 10G and it has work to do on cost, bandwidth and latency...</description>
		<content:encoded><![CDATA[<p>IB is big in HPC, but not because IB is so great.  it&#8217;s merely more attractive than the alternatives (Gb, 10G).  if there were an ethernet-like alternative that came close to the same bandwidth and latency numbers, IB would have real competition.  for instance, Gb persists and even makes a lot of sense in some cases where speed (either lat or bw) is not important.  10G is attractive for its ease of interop, but has so far been dramatically more expensive, not to mention slower than IB.  in other words, IB&#8217;s closest competitor seems to be 10G and it has work to do on cost, bandwidth and latency&#8230;</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Cisco &#124; All Days Long</title>
		<link>http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/#comment-178583</link>
		<dc:creator>Cisco &#124; All Days Long</dc:creator>
		<pubDate>Mon, 17 Aug 2009 17:40:21 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=6727#comment-178583</guid>
		<description>[...]  Cisco&#039;s move out of InfiniBand early, but may ultimately prove &#8230;  By John West  insideHPC: HPC news for supercomputing professionals.   insideHPC &#8211; http://insidehpc.com/ [...]</description>
		<content:encoded><![CDATA[<p>[...]  Cisco&#39;s move out of InfiniBand early, but may ultimately prove &#8230;  By John West  insideHPC: HPC news for supercomputing professionals.   insideHPC &#8211; <a href="http://insidehpc.com/" rel="nofollow">http://insidehpc.com/</a> [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: &#160; Cisco&#39;s move out of InfiniBand early, but may ultimately prove &#8230;&#160;by&#160;Cisco Information Technology</title>
		<link>http://insidehpc.com/2009/08/17/ciscos-move-out-of-infiniband-early-but-may-ultimately-prove-correct/#comment-178557</link>
		<dc:creator>&#160; Cisco&#39;s move out of InfiniBand early, but may ultimately prove &#8230;&#160;by&#160;Cisco Information Technology</dc:creator>
		<pubDate>Mon, 17 Aug 2009 14:22:27 +0000</pubDate>
		<guid isPermaLink="false">http://insidehpc.com/?p=6727#comment-178557</guid>
		<description>[...] Go here to see the original: Cisco&#039;s move out of InfiniBand early, but may ultimately prove &#8230; [...]</description>
		<content:encoded><![CDATA[<p>[...] Go here to see the original: Cisco&#39;s move out of InfiniBand early, but may ultimately prove &#8230; [...]</p>
]]></content:encoded>
	</item>
</channel>
</rss>
