<?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: LSI Releases PCIe 3.0 MegaRAID and HBA Portfolio &#8211; 4.1GB/s Reached With New PCIe Gen 3 HBA	</title>
	<atom:link href="https://www.thessdreview.com/daily-news/latest-buzz/lsi-releases-pcie-3-0-megaraid-hba-portfolio-4-1gbs-reached-with-new-pcie-gen-3-hba/feed/" rel="self" type="application/rss+xml" />
	<link>https://www.thessdreview.com/daily-news/latest-buzz/lsi-releases-pcie-3-0-megaraid-hba-portfolio-4-1gbs-reached-with-new-pcie-gen-3-hba/</link>
	<description>The Worlds Dedicated SSD Education and Review Resource &#124;</description>
	<lastBuildDate>Fri, 15 Feb 2013 04:16:00 +0000</lastBuildDate>
	<sy:updatePeriod>
	hourly	</sy:updatePeriod>
	<sy:updateFrequency>
	1	</sy:updateFrequency>
	
	<item>
		<title>
		By: zachariah		</title>
		<link>https://www.thessdreview.com/daily-news/latest-buzz/lsi-releases-pcie-3-0-megaraid-hba-portfolio-4-1gbs-reached-with-new-pcie-gen-3-hba/#comment-14826</link>

		<dc:creator><![CDATA[zachariah]]></dc:creator>
		<pubDate>Fri, 15 Feb 2013 04:16:00 +0000</pubDate>
		<guid isPermaLink="false">https://thessdreview.com/?p=53275#comment-14826</guid>

					<description><![CDATA[I haven&#039;t found any decent information anywhere between the 2308 and the 2208 chips; this article is similarly vague. Any ideas where to find the differences?]]></description>
			<content:encoded><![CDATA[<p>I haven&#8217;t found any decent information anywhere between the 2308 and the 2208 chips; this article is similarly vague. Any ideas where to find the differences?</p>
]]></content:encoded>
		
			</item>
		<item>
		<title>
		By: MRFS		</title>
		<link>https://www.thessdreview.com/daily-news/latest-buzz/lsi-releases-pcie-3-0-megaraid-hba-portfolio-4-1gbs-reached-with-new-pcie-gen-3-hba/#comment-10988</link>

		<dc:creator><![CDATA[MRFS]]></dc:creator>
		<pubDate>Tue, 26 Jun 2012 17:04:00 +0000</pubDate>
		<guid isPermaLink="false">https://thessdreview.com/?p=53275#comment-10988</guid>

					<description><![CDATA[&#062;  PCIe Gen 2 devices are being replaced by PCIe Gen 3

We need to reiterate 2 key features of PCIe Gen 3:
8 GHz clock rate AND 130b/128b &quot;jumbo frames&quot;.

By design, these 2 features result in 8G / 8b = ~1.0 GB/second throughput
at the chipset level, for a single x1 PCIe &quot;lane&quot;.

However, current 6G SSDs remain limited by
6 GHz clock rates AND 10b/8b &quot;legacy frames&quot;,
and the best are now bumping against this
&quot;glass ceiling&quot; e.g. 550 MB/second READS.

So, we can raise the ceiling by increasing the
clock rate to 8G (at least) or 12G and
keeping legacy frames, like this:

8G / 10b  = 800 MB/second
12G / 10b  =  1,200 MB/second

But, the PCIe Gen3 spec offers a wonderful opportunity
to &quot;sync&quot; it with all future SATA standards, i.e. by also adding
the 130b/128b &quot;jumbo frame&quot; to the SATA standard e.g.:

8G / 8b  =  ~1.0 GB/second per channel
12G / 8b  =  ~1.5 GB/second per channel
16G / 8b  =  ~2.0 GB/second per channel
... and so on.

Dropping 2 extra bits from every byte transmitted
should also eliminate a lot of overhead in
controllers at both ends of the data cables!

FYI:  More details are at the Forums here:
&quot;SATA-IV&quot; Proposal: A Flexible Topology for PCIe 3.0


MRFS]]></description>
			<content:encoded><![CDATA[<p>&gt;  PCIe Gen 2 devices are being replaced by PCIe Gen 3</p>
<p>We need to reiterate 2 key features of PCIe Gen 3:<br />
8 GHz clock rate AND 130b/128b &#8220;jumbo frames&#8221;.</p>
<p>By design, these 2 features result in 8G / 8b = ~1.0 GB/second throughput<br />
at the chipset level, for a single x1 PCIe &#8220;lane&#8221;.</p>
<p>However, current 6G SSDs remain limited by<br />
6 GHz clock rates AND 10b/8b &#8220;legacy frames&#8221;,<br />
and the best are now bumping against this<br />
&#8220;glass ceiling&#8221; e.g. 550 MB/second READS.</p>
<p>So, we can raise the ceiling by increasing the<br />
clock rate to 8G (at least) or 12G and<br />
keeping legacy frames, like this:</p>
<p>8G / 10b  = 800 MB/second<br />
12G / 10b  =  1,200 MB/second</p>
<p>But, the PCIe Gen3 spec offers a wonderful opportunity<br />
to &#8220;sync&#8221; it with all future SATA standards, i.e. by also adding<br />
the 130b/128b &#8220;jumbo frame&#8221; to the SATA standard e.g.:</p>
<p>8G / 8b  =  ~1.0 GB/second per channel<br />
12G / 8b  =  ~1.5 GB/second per channel<br />
16G / 8b  =  ~2.0 GB/second per channel<br />
&#8230; and so on.</p>
<p>Dropping 2 extra bits from every byte transmitted<br />
should also eliminate a lot of overhead in<br />
controllers at both ends of the data cables!</p>
<p>FYI:  More details are at the Forums here:<br />
&#8220;SATA-IV&#8221; Proposal: A Flexible Topology for PCIe 3.0</p>
<p>MRFS</p>
]]></content:encoded>
		
			</item>
	</channel>
</rss>
