<?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: ARM compiler shoot-out</title>
	<atom:link href="http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/feed/" rel="self" type="application/rss+xml" />
	<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/</link>
	<description>Everything is broken</description>
	<lastBuildDate>Tue, 15 May 2012 02:38:01 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.2</generator>
	<item>
		<title>By: A few things iOS developers ought to know about the ARM architecture &#171; AVATAR.Dev - iOS Developer Tips, Tricks and Tutorials.</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-1377</link>
		<dc:creator>A few things iOS developers ought to know about the ARM architecture &#171; AVATAR.Dev - iOS Developer Tips, Tricks and Tutorials.</dc:creator>
		<pubDate>Mon, 23 Jan 2012 07:41:36 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-1377</guid>
		<description>[...] While I’ve not tested it much, I have at least seen nice improvements on 64-bit integer code (a particularly weak point of GCC on ARM) when using LLVM. Hopefully, LLVM will prove to be an improvement over GCC in all domains. [...]</description>
		<content:encoded><![CDATA[<p>[...] While I’ve not tested it much, I have at least seen nice improvements on 64-bit integer code (a particularly weak point of GCC on ARM) when using LLVM. Hopefully, LLVM will prove to be an improvement over GCC in all domains. [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-1253</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Fri, 19 Nov 2010 08:39:29 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-1253</guid>
		<description>Video codecs never use floating-point. Audio codecs can be either fixed-point or floating-point.</description>
		<content:encoded><![CDATA[<p>Video codecs never use floating-point. Audio codecs can be either fixed-point or floating-point.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: salixman</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-1251</link>
		<dc:creator>salixman</dc:creator>
		<pubDate>Thu, 18 Nov 2010 11:13:49 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-1251</guid>
		<description>How do I know what codec uses integer or float? Is this documented somewhere?</description>
		<content:encoded><![CDATA[<p>How do I know what codec uses integer or float? Is this documented somewhere?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-178</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Wed, 19 Aug 2009 12:37:28 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-178</guid>
		<description>I measured the CPU time needed to decode the samples.</description>
		<content:encoded><![CDATA[<p>I measured the CPU time needed to decode the samples.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Fredrik</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-175</link>
		<dc:creator>Fredrik</dc:creator>
		<pubDate>Wed, 19 Aug 2009 11:06:58 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-175</guid>
		<description>Hi,
How did you measure the performance?</description>
		<content:encoded><![CDATA[<p>Hi,<br />
How did you measure the performance?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-88</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Wed, 12 Aug 2009 14:02:06 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-88</guid>
		<description>Yes, I&#039;m running Linux on the board.</description>
		<content:encoded><![CDATA[<p>Yes, I&#8217;m running Linux on the board.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: asn</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-87</link>
		<dc:creator>asn</dc:creator>
		<pubDate>Wed, 12 Aug 2009 13:38:28 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-87</guid>
		<description>Hi,
How did you measure the performance ? Have you put any Linux distro on the board ?</description>
		<content:encoded><![CDATA[<p>Hi,<br />
How did you measure the performance ? Have you put any Linux distro on the board ?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-85</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Tue, 11 Aug 2009 02:26:42 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-85</guid>
		<description>I enabled gcc compatibility in RVCT so those options are exactly what I used. I&#039;m not sure what RVCT-native options they map to.

I did not use --vectorize for the simple reason that it fails to compile FFmpeg with vectorisation enabled.</description>
		<content:encoded><![CDATA[<p>I enabled gcc compatibility in RVCT so those options are exactly what I used. I&#8217;m not sure what RVCT-native options they map to.</p>
<p>I did not use &#8211;vectorize for the simple reason that it fails to compile FFmpeg with vectorisation enabled.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: mh</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-84</link>
		<dc:creator>mh</dc:creator>
		<pubDate>Tue, 11 Aug 2009 02:12:55 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-84</guid>
		<description>I doubt that the RVCT options you quoted were the same you actually used. Looks more like a copy paste issue to me.

Did you use --vectorize with RVCT? Otherwise you might not be able to take full advantage of NEON. The capability of the compiler to vectorize code depends quite a bit on the C code structure, though.</description>
		<content:encoded><![CDATA[<p>I doubt that the RVCT options you quoted were the same you actually used. Looks more like a copy paste issue to me.</p>
<p>Did you use &#8211;vectorize with RVCT? Otherwise you might not be able to take full advantage of NEON. The capability of the compiler to vectorize code depends quite a bit on the C code structure, though.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: kert</title>
		<link>http://hardwarebug.org/2009/08/05/arm-compiler-shoot-out/comment-page-1/#comment-82</link>
		<dc:creator>kert</dc:creator>
		<pubDate>Wed, 05 Aug 2009 15:22:44 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=150#comment-82</guid>
		<description>Does anyone know if any other optflags beyond -Os now work reliably in ARM code ?
A year or so back, -O2 produced very weird assembler-level mess here and there in the code ( a large c++ lib ) and from newsgroups i basically got this: dont use anything beyond -Os</description>
		<content:encoded><![CDATA[<p>Does anyone know if any other optflags beyond -Os now work reliably in ARM code ?<br />
A year or so back, -O2 produced very weird assembler-level mess here and there in the code ( a large c++ lib ) and from newsgroups i basically got this: dont use anything beyond -Os</p>
]]></content:encoded>
	</item>
</channel>
</rss>

