<?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, round 2</title>
	<atom:link href="http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/feed/" rel="self" type="application/rss+xml" />
	<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/</link>
	<description>Everything is broken</description>
	<lastBuildDate>Mon, 30 Aug 2010 09:33:38 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.0.1</generator>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-479</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Wed, 18 Nov 2009 12:25:00 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-479</guid>
		<description>I already said I&#039;m using --translate_gcc which maps -O3 to -O3 -Otime.</description>
		<content:encoded><![CDATA[<p>I already said I&#8217;m using &#8211;translate_gcc which maps -O3 to -O3 -Otime.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Marcus Harnisch</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-478</link>
		<dc:creator>Marcus Harnisch</dc:creator>
		<pubDate>Wed, 18 Nov 2009 09:19:12 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-478</guid>
		<description>Just as a reminder: Unlike gcc, armcc optimizes for space by default. Please also specify -Otime to make sure it directs its effort to execution time. Please check this out, too. No guarantees, though.</description>
		<content:encoded><![CDATA[<p>Just as a reminder: Unlike gcc, armcc optimizes for space by default. Please also specify -Otime to make sure it directs its effort to execution time. Please check this out, too. No guarantees, though.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Korobeynikov</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-477</link>
		<dc:creator>Anton Korobeynikov</dc:creator>
		<pubDate>Fri, 13 Nov 2009 13:12:39 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-477</guid>
		<description>Sorry, I really have no idea what you&#039;ve downloaded. Release tarballs contains all the code from the SVN repository. For ARM stuff you might really want do checkout code from SVN, since after the 2.6 release bunch of stuff was fixed / improved.</description>
		<content:encoded><![CDATA[<p>Sorry, I really have no idea what you&#8217;ve downloaded. Release tarballs contains all the code from the SVN repository. For ARM stuff you might really want do checkout code from SVN, since after the 2.6 release bunch of stuff was fixed / improved.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-476</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Thu, 12 Nov 2009 21:27:30 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-476</guid>
		<description>That is most definitely not what was in a tarball I downloaded.  The only instructions I found involved a complicated procedure combining parts from an llvm base tarball with some llvm-gcc bits, and none of it made much sense, so I gave up.</description>
		<content:encoded><![CDATA[<p>That is most definitely not what was in a tarball I downloaded.  The only instructions I found involved a complicated procedure combining parts from an llvm base tarball with some llvm-gcc bits, and none of it made much sense, so I gave up.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Korobeynikov</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-475</link>
		<dc:creator>Anton Korobeynikov</dc:creator>
		<pubDate>Thu, 12 Nov 2009 21:19:10 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-475</guid>
		<description>Huh, how so? There is definitely one:
http://llvm.org/viewvc/llvm-project/llvm-gcc-4.2/trunk/configure

Make sure you checked out stuff properly. README.LLVM is also a good thing to read before building.

There is a script for almost automatic build of cross-compilers. See http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/crosstool/ARM/README</description>
		<content:encoded><![CDATA[<p>Huh, how so? There is definitely one:<br />
<a href="http://llvm.org/viewvc/llvm-project/llvm-gcc-4.2/trunk/configure" rel="nofollow">http://llvm.org/viewvc/llvm-project/llvm-gcc-4.2/trunk/configure</a></p>
<p>Make sure you checked out stuff properly. README.LLVM is also a good thing to read before building.</p>
<p>There is a script for almost automatic build of cross-compilers. See <a href="http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/crosstool/ARM/README" rel="nofollow">http://llvm.org/viewvc/llvm-project/llvm/trunk/utils/crosstool/ARM/README</a></p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-474</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Thu, 12 Nov 2009 13:36:18 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-474</guid>
		<description>I see nothing usual about building llvm-gcc.  There isn&#039;t even a configure script.</description>
		<content:encoded><![CDATA[<p>I see nothing usual about building llvm-gcc.  There isn&#8217;t even a configure script.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Korobeynikov</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-473</link>
		<dc:creator>Anton Korobeynikov</dc:creator>
		<pubDate>Thu, 12 Nov 2009 13:18:09 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-473</guid>
		<description>Build llvm-gcc as usual gcc. There is even script to use codesourcery-provided binutils as a &quot;bootstrap&quot; toolchain.</description>
		<content:encoded><![CDATA[<p>Build llvm-gcc as usual gcc. There is even script to use codesourcery-provided binutils as a &#8220;bootstrap&#8221; toolchain.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Mans</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-472</link>
		<dc:creator>Mans</dc:creator>
		<pubDate>Tue, 10 Nov 2009 13:08:32 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-472</guid>
		<description>Most of the compilers support only softfp ABI.  I compared soft and hard with gcc-csl 2009q1, and there was very little difference.  FFmpeg passes floats as arguments or return values in very few places.

I&#039;m planning a new round soon, and I&#039;d be happy to include LLVM, if only I could figure out how to configure it as a cross-compiler.</description>
		<content:encoded><![CDATA[<p>Most of the compilers support only softfp ABI.  I compared soft and hard with gcc-csl 2009q1, and there was very little difference.  FFmpeg passes floats as arguments or return values in very few places.</p>
<p>I&#8217;m planning a new round soon, and I&#8217;d be happy to include LLVM, if only I could figure out how to configure it as a cross-compiler.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anton Korobeynikov</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-471</link>
		<dc:creator>Anton Korobeynikov</dc:creator>
		<pubDate>Tue, 10 Nov 2009 12:57:51 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-471</guid>
		<description>Why are you using softfp ABI for the benchmarks? Hardware FP ABI is much better suited for such of applications and might yield a noticeable speedup.

PS: Could you please also include LLVM for the tests?</description>
		<content:encoded><![CDATA[<p>Why are you using softfp ABI for the benchmarks? Hardware FP ABI is much better suited for such of applications and might yield a noticeable speedup.</p>
<p>PS: Could you please also include LLVM for the tests?</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Reimar</title>
		<link>http://hardwarebug.org/2009/08/20/arm-compiler-shoot-out-round-2/comment-page-1/#comment-262</link>
		<dc:creator>Reimar</dc:creator>
		<pubDate>Tue, 25 Aug 2009 13:01:41 +0000</pubDate>
		<guid isPermaLink="false">http://hardwarebug.org/?p=204#comment-262</guid>
		<description>s/incredibly bad/useless/
Really, you just &lt;u&gt;can&#039;t&lt;/u&gt; use gcc to do multiplications larger than the native size if speed or code size are in any way relevant.</description>
		<content:encoded><![CDATA[<p>s/incredibly bad/useless/<br />
Really, you just <u>can&#8217;t</u> use gcc to do multiplications larger than the native size if speed or code size are in any way relevant.</p>
]]></content:encoded>
	</item>
</channel>
</rss>
