<?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>Comentários sobre: Playing with criterion</title>
	<atom:link href="http://marcotmarcot.wordpress.com/2010/05/23/playing-with-criterion/feed/" rel="self" type="application/rss+xml" />
	<link>http://marcotmarcot.wordpress.com/2010/05/23/playing-with-criterion/</link>
	<description></description>
	<lastBuildDate>Thu, 27 Oct 2011 14:34:27 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.com/</generator>
	<item>
		<title>Por: Twan van Laarhoven</title>
		<link>http://marcotmarcot.wordpress.com/2010/05/23/playing-with-criterion/#comment-54</link>
		<dc:creator><![CDATA[Twan van Laarhoven]]></dc:creator>
		<pubDate>Sun, 23 May 2010 19:25:48 +0000</pubDate>
		<guid isPermaLink="false">http://marcotmarcot.wordpress.com/?p=94#comment-54</guid>
		<description><![CDATA[You are missing a &quot;-O2&quot; in your invocation of Ghc, so these tests are run without optimizations.

The reason why more than 2 threads could be helpful is because the workloads are not balanced. With two threads, one does 1.618 times as much work as the others, since one is calculating &quot;fib 30&quot; and the other &quot;fib 31&quot;. With 4 threads one core will do only 1.118 times as much work as the other, it does &quot;fib 28&quot; and &quot;fib 30&quot;, while the other does &quot;fib 29&quot; twice.]]></description>
		<content:encoded><![CDATA[<p>You are missing a &#8220;-O2&#8243; in your invocation of Ghc, so these tests are run without optimizations.</p>
<p>The reason why more than 2 threads could be helpful is because the workloads are not balanced. With two threads, one does 1.618 times as much work as the others, since one is calculating &#8220;fib 30&#8243; and the other &#8220;fib 31&#8243;. With 4 threads one core will do only 1.118 times as much work as the other, it does &#8220;fib 28&#8243; and &#8220;fib 30&#8243;, while the other does &#8220;fib 29&#8243; twice.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
