<?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: An Amazon EC2 cluster for BLAST searching ?</title>
	<atom:link href="http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/feed/" rel="self" type="application/rss+xml" />
	<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/</link>
	<description></description>
	<pubDate>Wed, 07 Jan 2009 17:58:08 +0000</pubDate>
	<generator>http://wordpress.org/?v=2.7</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: That Science Blog Meme Thing Going Around &#124; Your bones got a little machine</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-158</link>
		<dc:creator>That Science Blog Meme Thing Going Around &#124; Your bones got a little machine</dc:creator>
		<pubDate>Sun, 16 Nov 2008 23:14:43 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-158</guid>
		<description>[...] research. I didn&#8217;t really feel qualified to comment a length, since it largely stemmed from a &#8216;what if&#8217; type idea I blogged about. But I gave my perspective [...]</description>
		<content:encoded><![CDATA[<p>[...] research. I didn&#8217;t really feel qualified to comment a length, since it largely stemmed from a &#8216;what if&#8217; type idea I blogged about. But I gave my perspective [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: cariaso</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-34</link>
		<dc:creator>cariaso</dc:creator>
		<pubDate>Sat, 21 Apr 2007 18:18:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-34</guid>
		<description>I've got mpiBLAST working well inside EC2. If you'd like to try it out, you will find this document helpful. &lt;br/&gt;&lt;a HREF="http://mpiblast.pbwiki.com/AmazonEC2" REL="nofollow"&gt;http://mpiblast.pbwiki.com/AmazonEC2&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;Also see the discussion at &lt;a HREF="http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2" REL="nofollow"&gt;nodalpoint&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;I will be at BioIT World at the end of April, and happy to discuss this topic with others.&lt;br/&gt;&lt;br/&gt;&lt;br/&gt;Mike Cariaso * Bioinformatics Software * &lt;a HREF="http://www.cariaso.com/" REL="nofollow"&gt;http://www.cariaso.com/&lt;/a&gt;</description>
		<content:encoded><![CDATA[<p>I&#8217;ve got mpiBLAST working well inside EC2. If you&#8217;d like to try it out, you will find this document helpful. <br /><a HREF="http://mpiblast.pbwiki.com/AmazonEC2" REL="nofollow">http://mpiblast.pbwiki.com/AmazonEC2</a></p>
<p>Also see the discussion at <a HREF="http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2" REL="nofollow">nodalpoint</a></p>
<p>I will be at BioIT World at the end of April, and happy to discuss this topic with others.</p>
<p>Mike Cariaso * Bioinformatics Software * <a HREF="http://www.cariaso.com/" REL="nofollow">http://www.cariaso.com/</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Andrew Perry</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-33</link>
		<dc:creator>Andrew Perry</dc:creator>
		<pubDate>Tue, 10 Apr 2007 04:44:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-33</guid>
		<description>Yes, I was given a beta account last week ... so it took just under a month. Shame I don't have as much time to spend playing with it now, but I'll still poke away at it slowly over the next few months. Looks like Peter has done most of the heavy lifting for MPI with his &lt;a HREF="http://www.datawrangling.com/on-demand-mpi-cluster-with-python-and-ec2-part-1-of-3.html" REL="nofollow"&gt;On-Demand MPI Cluster with Python and EC2&lt;/a&gt; tutorial. Pretty sweet !</description>
		<content:encoded><![CDATA[<p>Yes, I was given a beta account last week &#8230; so it took just under a month. Shame I don&#8217;t have as much time to spend playing with it now, but I&#8217;ll still poke away at it slowly over the next few months. Looks like Peter has done most of the heavy lifting for MPI with his <a HREF="http://www.datawrangling.com/on-demand-mpi-cluster-with-python-and-ec2-part-1-of-3.html" REL="nofollow">On-Demand MPI Cluster with Python and EC2</a> tutorial. Pretty sweet !</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Andrew Mitry</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-32</link>
		<dc:creator>Andrew Mitry</dc:creator>
		<pubDate>Tue, 10 Apr 2007 04:23:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-32</guid>
		<description>Did Amazon give you an EC2 beta slot yet?  I just tried to sign up for EC2 and got the same message - just curious how long it'll be before they open more slots.</description>
		<content:encoded><![CDATA[<p>Did Amazon give you an EC2 beta slot yet?  I just tried to sign up for EC2 and got the same message - just curious how long it&#8217;ll be before they open more slots.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Peter</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-26</link>
		<dc:creator>Peter</dc:creator>
		<pubDate>Sun, 18 Mar 2007 02:42:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-26</guid>
		<description>I've started posting a tutorial describing a "roll-your-own" style MPI cluster on EC2. By the end, I'll upload a public ami and some benchmark results. I'm hoping Amazon can find a way to support faster interconnect for at least a subset of the machines.&lt;br/&gt;&lt;br/&gt;&lt;a HREF="http://www.datawrangling.com/on-demand-mpi-cluster-with-python-and-ec2-part-1-of-3.html" REL="nofollow"&gt;On-Demand MPI Cluster with Python and EC2 (part 1 of 3)&lt;/a&gt;</description>
		<content:encoded><![CDATA[<p>I&#8217;ve started posting a tutorial describing a &#8220;roll-your-own&#8221; style MPI cluster on EC2. By the end, I&#8217;ll upload a public ami and some benchmark results. I&#8217;m hoping Amazon can find a way to support faster interconnect for at least a subset of the machines.</p>
<p><a HREF="http://www.datawrangling.com/on-demand-mpi-cluster-with-python-and-ec2-part-1-of-3.html" REL="nofollow">On-Demand MPI Cluster with Python and EC2 (part 1 of 3)</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Andrew Perry</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-24</link>
		<dc:creator>Andrew Perry</dc:creator>
		<pubDate>Wed, 07 Mar 2007 03:55:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-24</guid>
		<description>I'm guessing I'll probably just have to sit tight and wait for Amazon to open up some more EC2 'beta' slots. In the meantime, I've tried to start playing with S3 in preparation ... it's been 48 hours and my account is still not 'authorized' .. not that I'm in any hurry, but my credit card appears valid for buying books and junk from Amazon, so I don't see why authorization should take this long. Anyhow, no choice but to just wait for them to do what they've gotta do ....&lt;br/&gt;&lt;br/&gt;----&lt;br/&gt;&lt;br/&gt;&lt;i&gt;If I have ever made any valuable discoveries, it has been owing more to patient attention, than to any other talent&lt;/i&gt; -- &lt;b&gt;(Sir) Isaac Newton&lt;/b&gt;&lt;br/&gt;&lt;br/&gt;&lt;i&gt;I am extraordinarily patient, provided I get my own way in the end&lt;/i&gt; -- &lt;b&gt;Margaret Thatcher&lt;/b&gt;</description>
		<content:encoded><![CDATA[<p>I&#8217;m guessing I&#8217;ll probably just have to sit tight and wait for Amazon to open up some more EC2 &#8216;beta&#8217; slots. In the meantime, I&#8217;ve tried to start playing with S3 in preparation &#8230; it&#8217;s been 48 hours and my account is still not &#8216;authorized&#8217; .. not that I&#8217;m in any hurry, but my credit card appears valid for buying books and junk from Amazon, so I don&#8217;t see why authorization should take this long. Anyhow, no choice but to just wait for them to do what they&#8217;ve gotta do &#8230;.</p>
<p>&#8212;-</p>
<p><i>If I have ever made any valuable discoveries, it has been owing more to patient attention, than to any other talent</i> &#8212; <b>(Sir) Isaac Newton</b></p>
<p><i>I am extraordinarily patient, provided I get my own way in the end</i> &#8212; <b>Margaret Thatcher</b></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Evan</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-23</link>
		<dc:creator>Evan</dc:creator>
		<pubDate>Mon, 05 Mar 2007 18:02:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-23</guid>
		<description>I looked into this same possibility when EC2 was first announced, and decided that it wasn't worth the hassle, mainly for the persistence and memory issues you mention. Plus at the time infrastructure for deploying EC2 instances wasn't good. It has probably improved by now.&lt;br/&gt;&lt;br/&gt;I do have an EC2 beta account that I never used. I assume it is still valid. Maybe I could transfer it to you somehow?</description>
		<content:encoded><![CDATA[<p>I looked into this same possibility when EC2 was first announced, and decided that it wasn&#8217;t worth the hassle, mainly for the persistence and memory issues you mention. Plus at the time infrastructure for deploying EC2 instances wasn&#8217;t good. It has probably improved by now.</p>
<p>I do have an EC2 beta account that I never used. I assume it is still valid. Maybe I could transfer it to you somehow?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Greg</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-22</link>
		<dc:creator>Greg</dc:creator>
		<pubDate>Mon, 05 Mar 2007 16:55:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-22</guid>
		<description>I'm having dificulty with the comments on the blogger system, as they are all in Chinese with no option to get back to English...&lt;br/&gt;&lt;br/&gt;I don't have trackbacks running on nodalpoint so I'll do it manually:&lt;br/&gt;&lt;br/&gt;&lt;a HREF="http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2" REL="nofollow"&gt;http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2&lt;/a&gt;&lt;br/&gt;&lt;br/&gt;Hopefully, Amazon's EC2 people will come across this post and open up an account for you. I would be genuinely interested in seeing how something like this would work as a intermediate step between having a virtual cluster and putting down big money for your own hardware.&lt;br/&gt;&lt;br/&gt;Especially as a lot of institutions are adverse to spending money. At lease the powers that be at UNSW were :</description>
		<content:encoded><![CDATA[<p>I&#8217;m having dificulty with the comments on the blogger system, as they are all in Chinese with no option to get back to English&#8230;</p>
<p>I don&#8217;t have trackbacks running on nodalpoint so I&#8217;ll do it manually:</p>
<p><a HREF="http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2" REL="nofollow">http://www.nodalpoint.org/2007/03/05/virtual_bioinformatics_clusters_with_ec2</a></p>
<p>Hopefully, Amazon&#8217;s EC2 people will come across this post and open up an account for you. I would be genuinely interested in seeing how something like this would work as a intermediate step between having a virtual cluster and putting down big money for your own hardware.</p>
<p>Especially as a lot of institutions are adverse to spending money. At lease the powers that be at UNSW were :</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: David</title>
		<link>http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/comment-page-1/#comment-21</link>
		<dc:creator>David</dc:creator>
		<pubDate>Mon, 05 Mar 2007 02:09:00 +0000</pubDate>
		<guid isPermaLink="false">http://blog.pansapiens.com/2007/03/04/an-amazon-ec2-cluster-for-blast-searching/#comment-21</guid>
		<description>&lt;i&gt;(Actually EC2 instances have shared gigabit interconnects , but since several instances might share the same ethernet card, gigabit performance 'per node' can't be expected. I guess the 250 Mb/s figure means that there are probably four EC2 instances per physical server/ethernet card ??).&lt;/i&gt;&lt;br/&gt;&lt;br/&gt;Each physical system is dual processor, with two instances per system.&lt;br/&gt;&lt;br/&gt;- Dave</description>
		<content:encoded><![CDATA[<p><i>(Actually EC2 instances have shared gigabit interconnects , but since several instances might share the same ethernet card, gigabit performance &#8216;per node&#8217; can&#8217;t be expected. I guess the 250 Mb/s figure means that there are probably four EC2 instances per physical server/ethernet card ??).</i></p>
<p>Each physical system is dual processor, with two instances per system.</p>
<p>- Dave</p>
]]></content:encoded>
	</item>
</channel>
</rss>
