<?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: Speculation: pipelining geometry shaders</title>
	<atom:link href="http://aras-p.info/blog/2005/12/22/speculation-pipelining-geometry-shaders/feed/" rel="self" type="application/rss+xml" />
	<link>http://aras-p.info/blog/2005/12/22/speculation-pipelining-geometry-shaders/</link>
	<description>Random thoughts of a triangle pusher</description>
	<lastBuildDate>Fri, 10 Feb 2012 03:15:49 +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/2005/12/22/speculation-pipelining-geometry-shaders/comment-page-1/#comment-111</link>
		<dc:creator>NeARAZ</dc:creator>
		<pubDate>Thu, 22 Dec 2005 19:06:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=82#comment-111</guid>
		<description>Yeah, I know &lt;I&gt;(=heard :))&lt;/I&gt; that Xenos has unified shader pipes, with dynamic allocation happening somehow. In fact, both MS and ATI had stated that multiple times.&lt;BR/&gt;&lt;BR/&gt;The future hardware also seems to be going in that direction, as most of &quot;stuff&quot; in the shaders will be of the same capabilities (with some exceptions: break/emit is GS only; derivatives/automaticmiplevel is PS only). Maybe the hardware is just a big array of &quot;computation/sampling units&quot;, and someone &quot;from above&quot; allocates them on demand.&lt;BR/&gt;&lt;BR/&gt;Speculating is fun :)</description>
		<content:encoded><![CDATA[<p>Yeah, I know <i>(=heard :))</i> that Xenos has unified shader pipes, with dynamic allocation happening somehow. In fact, both MS and ATI had stated that multiple times.</p>
<p>The future hardware also seems to be going in that direction, as most of &#8220;stuff&#8221; in the shaders will be of the same capabilities (with some exceptions: break/emit is GS only; derivatives/automaticmiplevel is PS only). Maybe the hardware is just a big array of &#8220;computation/sampling units&#8221;, and someone &#8220;from above&#8221; allocates them on demand.</p>
<p>Speculating is fun :)</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: ReJ</title>
		<link>http://aras-p.info/blog/2005/12/22/speculation-pipelining-geometry-shaders/comment-page-1/#comment-112</link>
		<dc:creator>ReJ</dc:creator>
		<pubDate>Thu, 22 Dec 2005 17:05:00 +0000</pubDate>
		<guid isPermaLink="false">http://aras-p.info/blog/?p=82#comment-112</guid>
		<description>cite from the same Beyond3DL: &lt;I&gt;Unlike ATI&#039;s Xenos graphics processors for the XBOX 360, the R520 architecture is a little more traditional in that it doesn&#039;t make use of a unified architecture and hence has distinct vertex shader and pixel shader processors.&lt;/I&gt; Probably can be used as a bit of a hint.</description>
		<content:encoded><![CDATA[<p>cite from the same Beyond3DL: <i>Unlike ATI&#8217;s Xenos graphics processors for the XBOX 360, the R520 architecture is a little more traditional in that it doesn&#8217;t make use of a unified architecture and hence has distinct vertex shader and pixel shader processors.</i> Probably can be used as a bit of a hint.</p>
]]></content:encoded>
	</item>
</channel>
</rss>

