<?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: How to process a million songs in 20 minutes</title>
	<atom:link href="http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/feed/" rel="self" type="application/rss+xml" />
	<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/</link>
	<description>a blog about music technology by Paul Lamere</description>
	<lastBuildDate>Fri, 24 May 2013 00:58:19 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>By: Thierry BM</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-16590</link>
		<dc:creator><![CDATA[Thierry BM]]></dc:creator>
		<pubDate>Sun, 23 Oct 2011 02:03:47 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-16590</guid>
		<description><![CDATA[Fun fact: if you want to run it on ~500 machines to impress your ISMIR colleagues but you&#039;re an AWS newbie, you&#039;re limited to 20 EC2 instances; still cool, but less &quot;pazzaz&quot;. Also AWS EMR takes about 3 min to actually start.]]></description>
		<content:encoded><![CDATA[<p>Fun fact: if you want to run it on ~500 machines to impress your ISMIR colleagues but you&#8217;re an AWS newbie, you&#8217;re limited to 20 EC2 instances; still cool, but less &#8220;pazzaz&#8221;. Also AWS EMR takes about 3 min to actually start.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: tanjk</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-13355</link>
		<dc:creator><![CDATA[tanjk]]></dc:creator>
		<pubDate>Thu, 08 Sep 2011 15:48:53 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-13355</guid>
		<description><![CDATA[drums play notes.]]></description>
		<content:encoded><![CDATA[<p>drums play notes.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: test</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-13249</link>
		<dc:creator><![CDATA[test]]></dc:creator>
		<pubDate>Wed, 07 Sep 2011 20:34:04 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-13249</guid>
		<description><![CDATA[I think the difference between musical notes and drum hits should be made here---those &quot;dense&quot; tracks are just a bunch of repetitive drum hits.]]></description>
		<content:encoded><![CDATA[<p>I think the difference between musical notes and drum hits should be made here&#8212;those &#8220;dense&#8221; tracks are just a bunch of repetitive drum hits.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Twirrim</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-13135</link>
		<dc:creator><![CDATA[Twirrim]]></dc:creator>
		<pubDate>Wed, 07 Sep 2011 06:02:07 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-13135</guid>
		<description><![CDATA[Arthur: Not true, Jeffrey Dean and Sanjay Ghemawat of Google were the creators of MapReduce.  The concepts of mapping and reducing weren&#039;t novel, but MapReduce is the name of Google&#039;s implementation of the process, done in a way to suit clustering on their scale. You can read their paper here: http://static.googleusercontent.com/external_content/untrusted_dlcp/labs.google.com/en/us/papers/mapreduce-osdi04.pdf]]></description>
		<content:encoded><![CDATA[<p>Arthur: Not true, Jeffrey Dean and Sanjay Ghemawat of Google were the creators of MapReduce.  The concepts of mapping and reducing weren&#8217;t novel, but MapReduce is the name of Google&#8217;s implementation of the process, done in a way to suit clustering on their scale. You can read their paper here: <a href="http://static.googleusercontent.com/external_content/untrusted_dlcp/labs.google.com/en/us/papers/mapreduce-osdi04.pdf" rel="nofollow">http://static.googleusercontent.com/external_content/untrusted_dlcp/labs.google.com/en/us/papers/mapreduce-osdi04.pdf</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Arthur Ice</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-13049</link>
		<dc:creator><![CDATA[Arthur Ice]]></dc:creator>
		<pubDate>Tue, 06 Sep 2011 20:36:06 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-13049</guid>
		<description><![CDATA[Google popularized map reduce, they did not invent it.]]></description>
		<content:encoded><![CDATA[<p>Google popularized map reduce, they did not invent it.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ashwiniyer</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-12970</link>
		<dc:creator><![CDATA[ashwiniyer]]></dc:creator>
		<pubDate>Tue, 06 Sep 2011 14:15:22 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-12970</guid>
		<description><![CDATA[Why Do I get the feeling that spotify has a similar technology in play?]]></description>
		<content:encoded><![CDATA[<p>Why Do I get the feeling that spotify has a similar technology in play?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Eugenio Tacchini</title>
		<link>http://musicmachinery.com/2011/09/04/how-to-process-a-million-songs-in-20-minutes/#comment-12794</link>
		<dc:creator><![CDATA[Eugenio Tacchini]]></dc:creator>
		<pubDate>Sun, 04 Sep 2011 22:28:18 +0000</pubDate>
		<guid isPermaLink="false">http://musicmachinery.com/?p=3557#comment-12794</guid>
		<description><![CDATA[Very interesting approach, thanks for sharing!]]></description>
		<content:encoded><![CDATA[<p>Very interesting approach, thanks for sharing!</p>
]]></content:encoded>
	</item>
</channel>
</rss>
