<?xml version="1.0" encoding="UTF-8" ?>
<rss version="2.0">
<channel>
	<title>IfThen Software LLC</title>
	<link><![CDATA[http://www.gamedev.net/index.php?app=blog&module=showblog&blogid=706]]></link>
	<description>IfThen Software LLC Syndication</description>
	<pubDate>Sat, 01 Oct 2011 02:39:38 +0000</pubDate>
	<webMaster>support@gamedev.net (GameDev.net)</webMaster>
	<generator>IP.Blog</generator>
	<ttl>60</ttl>
	<item>
		<title>DDR SDRAM Memory Bank</title>
		<link>http://www.gamedev.net/blog/706/entry-2250702-ddr-sdram-memory-bank/</link>
		<category></category>
		<description><![CDATA[Because I'm getting into the section on memory (and some parts of   yesterday's example made me curious, particularly the RAS-to-CAS delay) I   have decided to research RAM again.  I did quite a bit of research in   this area about a month ago, so a lot of this is review and should go  by  relatively quickly.<br />
 <br />
 Data is stored in RAM in an...]]></description>
		<pubDate>Thu, 29 Sep 2011 01:31:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250702-ddr-sdram-memory-bank/</guid>
	</item>
	<item>
		<title>Memory Access Latency</title>
		<link>http://www.gamedev.net/blog/706/entry-2250696-memory-access-latency/</link>
		<category></category>
		<description><![CDATA[A predicated instruction is an instruction whose execution depends on  the result of a true/false test.  Another way to look at it is a single  instruction for code like the following:<br />
<br />
<span style='font-family: Courier New'>if (a &gt; b) c = 6;</span><br />
<br />
Predicated instructions can help to reduce the number of branches in  your code, which may increase how...]]></description>
		<pubDate>Wed, 28 Sep 2011 01:05:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250696-memory-access-latency/</guid>
	</item>
	<item>
		<title>VLIW and Researching Interlocks</title>
		<link>http://www.gamedev.net/blog/706/entry-2250695-vliw-and-researching-interlocks/</link>
		<category></category>
		<description><![CDATA[Trying out a different work schedule, so my blog entries may be a little  erratic while I work out some of the kinks.  So anyways, this blog post  is for yesterday.<br />
<br />
Today I learned about a couple new techniques.  The first one is  something called "very long instruction word" (VLIW).  In VLIW, a single  instruction is actually composed...]]></description>
		<pubDate>Tue, 27 Sep 2011 15:03:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250695-vliw-and-researching-interlocks/</guid>
	</item>
	<item>
		<title>Instruction Throughput Decides All</title>
		<link>http://www.gamedev.net/blog/706/entry-2250660-instruction-throughput-decides-all/</link>
		<category></category>
		<description><![CDATA[I finally have an answer to my question!  PleasingFungus from the  #tigIRC channel on Esper discussed the question with me for two hours  straight today and this is the answer I ended up with:<br />
<br />
[b]If a scalar (not superscalar) processor has multiple nonredundant  functional units (a single FPU and a single ALU for example) and it  issues an...]]></description>
		<pubDate>Wed, 21 Sep 2011 04:49:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250660-instruction-throughput-decides-all/</guid>
	</item>
	<item>
		<title>Scalar But Multiple Functional Units?</title>
		<link>http://www.gamedev.net/blog/706/entry-2250658-scalar-but-multiple-functional-units/</link>
		<category></category>
		<description><![CDATA[I spent most of the day trying to find the answer to the following question:<br />
<br />
If a scalar (not superscalar) processor has multiple nonredundant  functional units (a single FPU and a single ALU for example) and it  issues an instruction to the FPU at a certain clock tick, could it issue  another instruction to the ALU at the next clock tick so that...]]></description>
		<pubDate>Tue, 20 Sep 2011 03:57:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250658-scalar-but-multiple-functional-units/</guid>
	</item>
	<item>
		<title><![CDATA[Researching Thornton's Algorithm]]></title>
		<link>http://www.gamedev.net/blog/706/entry-2250644-researching-thorntons-algorithm/</link>
		<category></category>
		<description><![CDATA["Scoreboarding" is also called "Thornton's Algorithm".  Tomasulo's  Algorithm and Thornton's Algorithm were developed around the same time  with roughly the same goals.<br />
[list][*]They are both dynamic scheduling methods.[*]They both resolve dependencies (RAW, WAR, and WAW).[*]They are both pipelined.[*]They both have...]]></description>
		<pubDate>Sat, 17 Sep 2011 05:39:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250644-researching-thorntons-algorithm/</guid>
	</item>
	<item>
		<title>Forwarding and Out-of-Order Scalar Trouble</title>
		<link>http://www.gamedev.net/blog/706/entry-2250637-forwarding-and-out-of-order-scalar-trouble/</link>
		<category></category>
		<description>Welp, I am still trying to figure out how an out-of-order scalar  processor would work.  The out-of-order execution part is easy enough,  but I am having trouble figuring out how in-order completion would  work.  To this end, I am currently researching scoreboarding in the  hopes of gleaning some hint as to how such a processor would work.  If ...</description>
		<pubDate>Fri, 16 Sep 2011 03:49:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250637-forwarding-and-out-of-order-scalar-trouble/</guid>
	</item>
	<item>
		<title>OOO Execution with In-Order Completion?</title>
		<link>http://www.gamedev.net/blog/706/entry-2250634-ooo-execution-with-in-order-completion/</link>
		<category></category>
		<description><![CDATA[Today I was able to find an answer to the following research question:<br />
<br />
<strong class='bbc'>Can a processor have out-of-order execution and in-order completion?</strong><br />
Yes; with one pipeline per active instruction.  In other words, for  every instruction in the active instruction window (every instruction  which can be selected for execution) there needs to be a...]]></description>
		<pubDate>Thu, 15 Sep 2011 05:12:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250634-ooo-execution-with-in-order-completion/</guid>
	</item>
	<item>
		<title>Reorder Buffer, Public Project Tracking</title>
		<link>http://www.gamedev.net/blog/706/entry-2250629-reorder-buffer-public-project-tracking/</link>
		<category></category>
		<description><![CDATA[Today I was able to find answers to the following questions:<br />
<br />
<strong class='bbc'>What is the reorder buffer?</strong><br />
<strong class='bbc'> </strong>It is a buffer which is used to ensure that instructions commit  in-order.  It is also used in one method of register renaming.  There is  one entry for every <strong class='bbc'>active instruction</strong>.  An instruction is <strong class='bbc'>active</strong>  after it has been...]]></description>
		<pubDate>Wed, 14 Sep 2011 04:30:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250629-reorder-buffer-public-project-tracking/</guid>
	</item>
	<item>
		<title>Execution Scheduling and Memory Disambiguation</title>
		<link>http://www.gamedev.net/blog/706/entry-2250608-execution-scheduling-and-memory-disambiguation/</link>
		<category></category>
		<description><![CDATA[Unfortunately I was unable to get much research done today.  However, I did learn a few things.<br />
<br />
A processor can be either <strong class='bbc'>statically scheduled</strong> or <strong class='bbc'>dynamically scheduled</strong>.<br />
<br />
A statically scheduled processor depends on the compiler to create the  execution schedule.  I am guessing this is either through hints or by  actually reordering...]]></description>
		<pubDate>Sat, 10 Sep 2011 05:51:00 +0000</pubDate>
		<guid>http://www.gamedev.net/blog/706/entry-2250608-execution-scheduling-and-memory-disambiguation/</guid>
	</item>
</channel>
</rss>
