<?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: Back to some shader programming</title>
	<atom:link href="http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/feed/" rel="self" type="application/rss+xml" />
	<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/</link>
	<description>Random thoughts of a triangle pusher</description>
	<lastBuildDate>Thu, 09 Feb 2012 07:56:51 +0000</lastBuildDate>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=3.3.1</generator>
	<item>
		<title>By: NeARAZ</title>
		<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/comment-page-1/#comment-140</link>
		<dc:creator>NeARAZ</dc:creator>
		<pubDate>Sat, 27 May 2006 09:48:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=93#comment-140</guid>
		<description>ReJ/Ignacio: yeah, that&#039;s what my mean by &quot;let&#039;s oversimplify a bit&quot;.&lt;BR/&gt;Still, the nice thing about shaders is that you can profile fairly easily, and (another oversimplification here) they are quite independent from the rest of your &quot;stuff&quot;.</description>
		<content:encoded><![CDATA[<p>ReJ/Ignacio: yeah, that&#8217;s what my mean by &#8220;let&#8217;s oversimplify a bit&#8221;.<br />Still, the nice thing about shaders is that you can profile fairly easily, and (another oversimplification here) they are quite independent from the rest of your &#8220;stuff&#8221;.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ignacio</title>
		<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/comment-page-1/#comment-141</link>
		<dc:creator>Ignacio</dc:creator>
		<pubDate>Fri, 26 May 2006 20:27:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=93#comment-141</guid>
		<description>yeah. It&#039;s sad that programmers have so little insight about what happens in the hardware. We don&#039;t have to worry about threads, stalls, partial stalls, bypasses, load balancing, and all the schedulling problems that the compiler (assembler) solves for us.&lt;BR/&gt;&lt;BR/&gt;On one side, being isolated from those problems is nice, because the two major IHVs have very different architectures, and not exposing that information allows them to change the architecture from one generation to the next.&lt;BR/&gt;&lt;BR/&gt;However, I don&#039;t really like this situation. IHVs are monopolizing information that in the case of CPUs was public knowledge. On the days of the Pentium I used to know the uv pareability of every asm instruction and the number of cycles it took to execute. People could write compilers on their own! Today only IHVs can do that and if they don&#039;t support your favourite platform, (ie linux-ppc) you are screwed.&lt;BR/&gt;&lt;BR/&gt;In any case, I&#039;d recommend to use nvShaderPerf on nvidia hardware, sometimes you will get a surprise as shorter does not always mean faster.</description>
		<content:encoded><![CDATA[<p>yeah. It&#8217;s sad that programmers have so little insight about what happens in the hardware. We don&#8217;t have to worry about threads, stalls, partial stalls, bypasses, load balancing, and all the schedulling problems that the compiler (assembler) solves for us.</p>
<p>On one side, being isolated from those problems is nice, because the two major IHVs have very different architectures, and not exposing that information allows them to change the architecture from one generation to the next.</p>
<p>However, I don&#8217;t really like this situation. IHVs are monopolizing information that in the case of CPUs was public knowledge. On the days of the Pentium I used to know the uv pareability of every asm instruction and the number of cycles it took to execute. People could write compilers on their own! Today only IHVs can do that and if they don&#8217;t support your favourite platform, (ie linux-ppc) you are screwed.</p>
<p>In any case, I&#8217;d recommend to use nvShaderPerf on nvidia hardware, sometimes you will get a surprise as shorter does not always mean faster.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ReJ</title>
		<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/comment-page-1/#comment-142</link>
		<dc:creator>ReJ</dc:creator>
		<pubDate>Fri, 26 May 2006 13:36:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=93#comment-142</guid>
		<description>uhmm... except that it&#039;s becoming not so true this days ;)</description>
		<content:encoded><![CDATA[<p>uhmm&#8230; except that it&#8217;s becoming not so true this days ;)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: blackpawn</title>
		<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/comment-page-1/#comment-143</link>
		<dc:creator>blackpawn</dc:creator>
		<pubDate>Fri, 26 May 2006 05:13:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=93#comment-143</guid>
		<description>haha yeah i know this feeling exactly.    it&#039;s always nice too after some time to go back through some shaders and realize an optimization.  pixel shaders are great because you find a way to save a cycle or two then can multiply that by the number of pixels on the screen using that shader and feel very good about your even 1 cycle optimization.  :D</description>
		<content:encoded><![CDATA[<p>haha yeah i know this feeling exactly.    it&#8217;s always nice too after some time to go back through some shaders and realize an optimization.  pixel shaders are great because you find a way to save a cycle or two then can multiply that by the number of pixels on the screen using that shader and feel very good about your even 1 cycle optimization.  :D</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Anonymous</title>
		<link>http://aras-p.info/blog/2006/05/24/back-to-some-shader-programming/comment-page-1/#comment-144</link>
		<dc:creator>Anonymous</dc:creator>
		<pubDate>Thu, 25 May 2006 20:41:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=93#comment-144</guid>
		<description>Hurray for the simple yet powerful toys ;)&lt;BR/&gt;&lt;BR/&gt;Mav.</description>
		<content:encoded><![CDATA[<p>Hurray for the simple yet powerful toys ;)</p>
<p>Mav.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

