<?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: AMD Shanghai 45nm launch &#8211; Server benchmarks roundup</title>
	<atom:link href="http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/feed/" rel="self" type="application/rss+xml" />
	<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/</link>
	<description>Because technology isn&#039;t just for geeks</description>
	<lastBuildDate>Sat, 13 Mar 2010 16:13:01 +0000</lastBuildDate>
	<generator>http://wordpress.org/?v=2.9.2</generator>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
		<item>
		<title>By: Technology for Mortals &#187; Two AMD Shanghai processors beaten by a single Intel i7-965</title>
		<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/comment-page-1/#comment-1621</link>
		<dc:creator>Technology for Mortals &#187; Two AMD Shanghai processors beaten by a single Intel i7-965</dc:creator>
		<pubDate>Mon, 20 Jul 2009 00:04:48 +0000</pubDate>
		<guid isPermaLink="false">http://www.formortals.com/?p=136#comment-1621</guid>
		<description>[...] beat Intel&#8217;s Nehalem-EP to the mainstream two-socket server market with Shanghai.&#160; AMD took a lead in SPECjbb, SPECweb, SPECfp, and Virtualization Nested Paging for the server market and it looked [...]</description>
		<content:encoded><![CDATA[<p>[...] beat Intel&#8217;s Nehalem-EP to the mainstream two-socket server market with Shanghai.&nbsp; AMD took a lead in SPECjbb, SPECweb, SPECfp, and Virtualization Nested Paging for the server market and it looked [...]</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: George Ou</title>
		<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/comment-page-1/#comment-1207</link>
		<dc:creator>George Ou</dc:creator>
		<pubDate>Thu, 27 Nov 2008 18:32:16 +0000</pubDate>
		<guid isPermaLink="false">http://www.formortals.com/?p=136#comment-1207</guid>
		<description>First of all, I call it like I see it.  I&#039;ve given AMD praise on where they deserve it and criticize them where they deserve it.&lt;br&gt;&lt;br&gt;AMD has to fudge the results to claim a power advantage.&lt;br&gt;http://www.formortals.com/Home/tabid/36/EntryID/130/Default.aspx&lt;br&gt;&lt;br&gt;Single Nehalem beats two Shanghai&lt;br&gt;http://www.formortals.com/Home/tabid/36/EntryID/141/Default.aspx&lt;br&gt;&lt;br&gt;The truth about AMD&#039;s TDP rating&lt;br&gt;http://www.formortals.com/Home/tabid/36/EntryID/137/Default.aspx&lt;br&gt;&lt;br&gt;Lastly, 6-core Shanghai isn&#039;t here yet and when it does get here, it has to deal with 8-core Nehalem-EX.</description>
		<content:encoded><![CDATA[<p>First of all, I call it like I see it.  I&#8217;ve given AMD praise on where they deserve it and criticize them where they deserve it.</p>
<p>AMD has to fudge the results to claim a power advantage.<br /><a href="http://www.formortals.com/Home/tabid/36/EntryID/130/Default.aspx" rel="nofollow">http://www.formortals.com/Home/tabid/36/EntryID/130/Default.aspx</a></p>
<p>Single Nehalem beats two Shanghai<br /><a href="http://www.formortals.com/Home/tabid/36/EntryID/141/Default.aspx" rel="nofollow">http://www.formortals.com/Home/tabid/36/EntryID/141/Default.aspx</a></p>
<p>The truth about AMD&#8217;s TDP rating<br /><a href="http://www.formortals.com/Home/tabid/36/EntryID/137/Default.aspx" rel="nofollow">http://www.formortals.com/Home/tabid/36/EntryID/137/Default.aspx</a></p>
<p>Lastly, 6-core Shanghai isn&#8217;t here yet and when it does get here, it has to deal with 8-core Nehalem-EX.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Ciprian Mustiata</title>
		<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/comment-page-1/#comment-1206</link>
		<dc:creator>Ciprian Mustiata</dc:creator>
		<pubDate>Thu, 27 Nov 2008 18:21:12 +0000</pubDate>
		<guid isPermaLink="false">http://www.formortals.com/?p=136#comment-1206</guid>
		<description>George, are you a dealer of Intel? Or you think that only Intel do in all things in the right way? Integer performance matter on web servers, still AMD have other strong points (virtualization seems a strong point for me still). Your posts seems biased. &lt;br&gt;&lt;br&gt;I am not going to buy both Nehalem for server and Shanghai. Probably the next iteration which has 6 cores from AMD sounds more nicer (which is a Tick from Intel naming) and probably will match the quad Nehalem. &lt;br&gt;&lt;br&gt;What should I say, for sure I will buy the next CPU+Mainboard that offer the best for me on matter of what I use. And putting a biased conclusion on raw numbers seems inappropriate. Is right to say both on AMD achievements. In games (which Nehalem did not succed so great comparing with Peryn) Phenom II in early benchmarks match Peryn and probably is 10%-15% lower than Negaken. But putting the cheaper mainboard + DDR2 price, you can buy a nice video board and you can beat in any benchmark an Intel (in games). &lt;br&gt;&lt;br&gt;So please put all in equation seems a fair benchmark and comparison. Elsewhere seems as .NET beat always Java in a Microsoft benchmark, or C beats again Java in a XML processing. &lt;br&gt;&lt;br&gt;For now AMD seems very less power hungry and good (as were even the TLB free Barcelona) for server workloads and less powerful for games. Right now AMD have a bigger cache to achieve more for games and a bit lower power consumption. For me seems enough for a shrink. Intel did extend their power by offering a compatible by idea with AMD and 20% more in row numbers on bandwidth and frequency. Seems enough to beat AMD? Probably, but seems to not be enough on power consumption and virtualization.</description>
		<content:encoded><![CDATA[<p>George, are you a dealer of Intel? Or you think that only Intel do in all things in the right way? Integer performance matter on web servers, still AMD have other strong points (virtualization seems a strong point for me still). Your posts seems biased. </p>
<p>I am not going to buy both Nehalem for server and Shanghai. Probably the next iteration which has 6 cores from AMD sounds more nicer (which is a Tick from Intel naming) and probably will match the quad Nehalem. </p>
<p>What should I say, for sure I will buy the next CPU+Mainboard that offer the best for me on matter of what I use. And putting a biased conclusion on raw numbers seems inappropriate. Is right to say both on AMD achievements. In games (which Nehalem did not succed so great comparing with Peryn) Phenom II in early benchmarks match Peryn and probably is 10%-15% lower than Negaken. But putting the cheaper mainboard + DDR2 price, you can buy a nice video board and you can beat in any benchmark an Intel (in games). </p>
<p>So please put all in equation seems a fair benchmark and comparison. Elsewhere seems as .NET beat always Java in a Microsoft benchmark, or C beats again Java in a XML processing. </p>
<p>For now AMD seems very less power hungry and good (as were even the TLB free Barcelona) for server workloads and less powerful for games. Right now AMD have a bigger cache to achieve more for games and a bit lower power consumption. For me seems enough for a shrink. Intel did extend their power by offering a compatible by idea with AMD and 20% more in row numbers on bandwidth and frequency. Seems enough to beat AMD? Probably, but seems to not be enough on power consumption and virtualization.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: George Ou</title>
		<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/comment-page-1/#comment-1145</link>
		<dc:creator>George Ou</dc:creator>
		<pubDate>Fri, 14 Nov 2008 23:04:36 +0000</pubDate>
		<guid isPermaLink="false">http://www.formortals.com/?p=136#comment-1145</guid>
		<description>Slava, be prepared to watch the SPECfp lead change hands for 2 sockets or less in a few months.  If you&#039;re purchasing today and you only care about SPECfp, you&#039;re probably buying AMD.  However, note that SPECfp is an average of a larger set of applications.  A small percentage of those applications do work better on Intel CPUs.  Nehalem changes that of course.</description>
		<content:encoded><![CDATA[<p>Slava, be prepared to watch the SPECfp lead change hands for 2 sockets or less in a few months.  If you&#8217;re purchasing today and you only care about SPECfp, you&#8217;re probably buying AMD.  However, note that SPECfp is an average of a larger set of applications.  A small percentage of those applications do work better on Intel CPUs.  Nehalem changes that of course.</p>
]]></content:encoded>
	</item>
	<item>
		<title>By: Slava</title>
		<link>http://www.formortals.com/amd-shanghai-45nm-launch-server-benchmarks-roundup/comment-page-1/#comment-1144</link>
		<dc:creator>Slava</dc:creator>
		<pubDate>Fri, 14 Nov 2008 23:01:56 +0000</pubDate>
		<guid isPermaLink="false">http://www.formortals.com/?p=136#comment-1144</guid>
		<description>AMD still leads by huge margin in FP, almost 50% if compare clock-by-clock and 26% at the clocks mentioned above. That&#039;s like one generation ahead. For my science only FP matter   </description>
		<content:encoded><![CDATA[<p>AMD still leads by huge margin in FP, almost 50% if compare clock-by-clock and 26% at the clocks mentioned above. That&#8217;s like one generation ahead. For my science only FP matter</p>
]]></content:encoded>
	</item>
</channel>
</rss>
