<?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: CCL on x8632: more registers, please</title>
	<atom:link href="http://www.thoughtstuff.com/rme/weblog/?feed=rss2&#038;p=16" rel="self" type="application/rss+xml" />
	<link>http://www.thoughtstuff.com/rme/weblog/?p=16</link>
	<description>Matters of minor import</description>
	<lastBuildDate>Sat, 20 Sep 2008 03:46:26 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: wolf550e</title>
		<link>http://www.thoughtstuff.com/rme/weblog/?p=16&#038;cpage=1#comment-24567</link>
		<dc:creator>wolf550e</dc:creator>
		<pubDate>Sat, 20 Sep 2008 03:46:26 +0000</pubDate>
		<guid isPermaLink="false">http://www.thoughtstuff.com/rme/weblog/?p=16#comment-24567</guid>
		<description>Very interesting.
Win32 uses FS for thread local storage. Did you take the idea from there?
What about doing what GCC does when you specify -fomit-frame-pointer? That should give you a register. Or if you can&#039;t use if, please write another post about it.
Re: presumably cheaper instruction pair. Benchmark! Some legacy x86 instructions are quite slow on modern cpus (core2). The Intel docs are good, but I&#039;d benchmark and possibly even see what the Intel compilers generate to find out what&#039;s best practice for today&#039;s chips.</description>
		<content:encoded><![CDATA[<p>Very interesting.<br />
Win32 uses FS for thread local storage. Did you take the idea from there?<br />
What about doing what GCC does when you specify -fomit-frame-pointer? That should give you a register. Or if you can&#8217;t use if, please write another post about it.<br />
Re: presumably cheaper instruction pair. Benchmark! Some legacy x86 instructions are quite slow on modern cpus (core2). The Intel docs are good, but I&#8217;d benchmark and possibly even see what the Intel compilers generate to find out what&#8217;s best practice for today&#8217;s chips.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
