<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
<title>Intel Software Network Blogs</title>
<link>http://software.intel.com/en-us/blogs</link>
<description>[full-text feed from fivefilters.org]: </description>
<item>
<title>MSDN Subscriber Downloads - Visual Studio 2010 Release Candidate</title>
<link>http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/teHM6jmWDFY/</link>
<guid isPermaLink="true" >http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/teHM6jmWDFY/</guid>
<description>&lt;p&gt;&lt;em&gt;Message from fivefilters.org: If you can, please &lt;a href=&quot;http://fivefilters.org/content-only/#donate&quot;&gt;donate to the full-text RSS service&lt;/a&gt; so we can continue developing it.&lt;/em&gt;&lt;/p&gt;&lt;div&gt;&lt;div id=&quot;right&quot; readability=&quot;5&quot;&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/&quot;&gt;English&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/zh-cn/&quot;&gt;中文&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/ru-ru/&quot;&gt;Русский&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/fr-fr/&quot;&gt;Français&lt;/a&gt;&lt;/p&gt;


     &lt;p&gt;2,852 Posts served&lt;/p&gt;
     &lt;p&gt;8,602 Conversations started&lt;/p&gt;
	
	
	
&lt;!--
commented out, since comments come from another place
	&lt;div class=&quot;box&quot;&gt;
		&lt;div class=&quot;boxHeader&quot;&gt;Recent Comments &lt;a href=&quot;http://software.intel.com/en-us/blogs/comments/feed/&quot;&gt;&lt;img height=&quot;16&quot; alt=&quot;RSS&quot; class=&quot;rss&quot; src=&quot;/common/images/icons/rss.gif&quot; width=&quot;16&quot; border=&quot;0&quot; /&gt;&lt;/a&gt;&lt;/div&gt;
		&lt;div class=&quot;boxBody&quot;&gt;
			&lt;div class=&quot;rbc2&quot;&gt;
				&lt;ul&gt;
									&lt;/ul&gt;
			&lt;/div&gt;
		&lt;/div&gt;
	&lt;/div&gt;
--&gt;
        
&lt;/div&gt;&lt;/div&gt;&lt;p&gt;&lt;em&gt;&lt;a href=&quot;http://fivefilters.org&quot;&gt;Five Filters&lt;/a&gt; featured article: &lt;a href=&quot;http://medialens.org/alerts/09/091216_chilcot_inquiry_the.php&quot;&gt;Chilcot Inquiry&lt;/a&gt;. Available tools: &lt;a href=&quot;http://fivefilters.org/pdf-newspaper/&quot;&gt;PDF Newspaper&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/content-only/&quot;&gt;Full Text RSS&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/term-extraction/&quot;&gt;Term Extraction&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;</description>
<pubDate>Tue, 09 Feb 2010 00:45:41 +0000</pubDate>
<dc:creator>Doug Holland (Intel)</dc:creator>
</item>
<item>
<title>n-bodies: a parallel TBB solution: parallel code: first runs</title>
<link>http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/4BVkCnuyY2U/</link>
<guid isPermaLink="true" >http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/4BVkCnuyY2U/</guid>
<description>&lt;p&gt;&lt;em&gt;Message from fivefilters.org: If you can, please &lt;a href=&quot;http://fivefilters.org/content-only/#donate&quot;&gt;donate to the full-text RSS service&lt;/a&gt; so we can continue developing it.&lt;/em&gt;&lt;/p&gt;&lt;div&gt;&lt;div id=&quot;body&quot; readability=&quot;28&quot;&gt;
     
 
 &lt;h3&gt;
   By &lt;a href=&quot;http://software.intel.com/en-us/blogs/author/robert-reed/&quot;&gt;Robert Reed (Intel)&lt;/a&gt; (26 posts)
 on February 8, 2010 at 3:23 pm &lt;/h3&gt;
 &lt;p&gt;Shortly after Thanksgiving I started experimenting with the &lt;a href=&quot;http://software.intel.com/en-us/blogs/2009/11/13/n-bodies-a-parallel-tbb-solution-parallel-code-a-first-attempt/&quot;&gt;ideas for some parallel code&lt;/a&gt; to replace &lt;a href=&quot;http://software.intel.com/en-us/blogs/2009/10/14/n-bodies-a-parallel-tbb-solution-serial-body-drill-down/&quot;&gt;the serial code&lt;/a&gt; I’d previously optimized.  However, exceeding my goal of stepping into every hole I could find along the way, I hit a doozy: a case of modified source in a function not executed affecting the execution performance of another function!  After passing the code around among some compiler guys and taking the holiday hit, as I get back to this project it appears to be a case of aggressive optimizers in the compiler. I’m still working on some experiments to understand the interactions of inter-procedural optimization and function inlining, but as those efforts continue to percolate, I’m overdue to take the next step—run this parallel version.&lt;/p&gt;
&lt;p&gt;But first, because I’ve made some serial code optimizations and now I’m using Intel® Parallel Composer update 4, I want to take more samples of the serial kernel with the improved &lt;em&gt;addAcc()&lt;/em&gt; function.  Using the command, “select serial” I collected several runs of data and took their averages (first column is the number of bodies):&lt;br /&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-01.png&quot;&gt;&lt;img class=&quot;alignnone size-full wp-image-13821&quot; src=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-01.png&quot; alt=&quot;&quot; width=&quot;332&quot; height=&quot;242&quot; /&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;Then I did the same thing with the command, “select par” to get the basic parallel kernels for interactions and dynamics discussed previously.  To compare against the serial, first I color-coded the averages (I’m a sucker for Excel conditional formatting): parallel runs that are faster get the green—if they’re more than 10% slower, they see red.&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-02.png&quot;&gt;&lt;img class=&quot;alignnone size-full wp-image-13818&quot; src=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-02.png&quot; alt=&quot;&quot; width=&quot;592&quot; height=&quot;242&quot; /&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;OOOooooo…, that’s way more red than I expected.  Plotting a log-log graph of these data:&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-03.png&quot;&gt;&lt;img class=&quot;alignnone size-full wp-image-13819&quot; src=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-03.png&quot; alt=&quot;&quot; width=&quot;659&quot; height=&quot;311&quot; /&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;That’s not very impressive parallelism.  It takes around 2048 bodies interacting for my simple parallel kernel to beat the serial code.  But wasn’t like this six months ago when I compared these kernels:&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-04.png&quot;&gt;&lt;img class=&quot;alignnone size-full wp-image-13820&quot; src=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-04.png&quot; alt=&quot;&quot; width=&quot;698&quot; height=&quot;337&quot; /&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;This is an image of the performance of these same kernels from a presentation I put together last summer.  Here the simple parallel kernel looks impressive, sweeping under the serial kernel albeit stuck on the same n-squared growth curve.  What happened?  Serial optimization.  I pulled the data for those serial runs and added it to my previous graph of the new results:&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-05.png&quot;&gt;&lt;img class=&quot;alignnone size-full wp-image-13821&quot; src=&quot;http://software.intel.com/en-us/blogs/wordpress/wp-content/uploads/2010/02/B100207-05.png&quot; alt=&quot;&quot; width=&quot;660&quot; height=&quot;312&quot; /&gt;&lt;/a&gt;&lt;/p&gt;
&lt;p&gt;As you can see, the old serial code was quite a bit slower and the crossover point for the parallel runs was down around 64 bodies (the new parallel results are a little better than the old: the old 4096 bodies number was around 288 seconds, versus 277 here).  So, even as I was preaching about doing serial code optimization first, the serial code I was using for the previous graph lulled me into a false sense of accomplishment.  No wonder I was disappointed!&lt;/p&gt;
&lt;p&gt;But it’s even worse, though this twist I was expecting.  This parallel kernel that is struggling to beat its serial cousin has a fatal flaw, which I’ll explore next time.&lt;/p&gt;
&lt;p&gt;Next time: parallel code: first run’s fatal flaw&lt;/p&gt;
 &lt;h5&gt;
  Categories: &lt;a href=&quot;http://software.intel.com/en-us/blogs/category/parallel/&quot; title=&quot;View all posts in Parallel Programming&quot; rel=&quot;category tag&quot;&gt;Parallel Programming&lt;/a&gt;,  &lt;a href=&quot;http://software.intel.com/en-us/blogs/category/intel-threading-building-blocks/&quot; title=&quot;View all posts in Threading Building Blocks&quot; rel=&quot;category tag&quot;&gt;Threading Building Blocks&lt;/a&gt; &lt;/h5&gt;
 
&lt;style type=&quot;text/css&quot;&gt;&lt;![CDATA[.dp-highlighter { width: 525px; }]]&gt;&lt;/style&gt;&lt;h3 class=&quot;pagesection&quot;&gt;Comments (0)&lt;/h3&gt;
&lt;h3 class=&quot;pagesection&quot;&gt;Trackbacks (1)&lt;/h3&gt;&lt;ul&gt;&lt;li&gt;&lt;a href=&quot;http://software.intel.com/en-us/blogs/2009/11/13/n-bodies-a-parallel-tbb-solution-parallel-code-a-first-attempt/&quot; rel=&quot;nofollow&quot; target=&quot;_blank&quot;&gt;Intel Software Network Blogs » n-bodies: a parallel TBB solution: parallel code, a first attempt&lt;/a&gt;&lt;br /&gt;
February 8, 2010 3:26 PM PST
&lt;/li&gt;&lt;/ul&gt;&lt;br /&gt;&lt;h3 class=&quot;pagesection&quot;&gt;Leave a comment  &lt;a target=&quot;_blank&quot; href=&quot;http://software.intel.com/en-us/articles/comments-help-guide/&quot;&gt;&lt;img src=&quot;/media/images/help.gif&quot; border=&quot;0&quot; /&gt;&lt;/a&gt;&lt;/h3&gt;

   &lt;/div&gt;&lt;/div&gt;&lt;p&gt;&lt;em&gt;&lt;a href=&quot;http://fivefilters.org&quot;&gt;Five Filters&lt;/a&gt; featured article: &lt;a href=&quot;http://medialens.org/alerts/09/091216_chilcot_inquiry_the.php&quot;&gt;Chilcot Inquiry&lt;/a&gt;. Available tools: &lt;a href=&quot;http://fivefilters.org/pdf-newspaper/&quot;&gt;PDF Newspaper&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/content-only/&quot;&gt;Full Text RSS&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/term-extraction/&quot;&gt;Term Extraction&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;</description>
<pubDate>Mon, 08 Feb 2010 23:23:48 +0000</pubDate>
<dc:creator>Robert Reed (Intel)</dc:creator>
</item>
<item>
<title>My Netbook Journey – Life in Eden with my Atom</title>
<link>http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/cxaZVHCyuQ8/</link>
<guid isPermaLink="true" >http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/cxaZVHCyuQ8/</guid>
<description>&lt;p&gt;&lt;em&gt;Message from fivefilters.org: If you can, please &lt;a href=&quot;http://fivefilters.org/content-only/#donate&quot;&gt;donate to the full-text RSS service&lt;/a&gt; so we can continue developing it.&lt;/em&gt;&lt;/p&gt;&lt;div&gt;&lt;div id=&quot;body&quot; readability=&quot;35&quot;&gt;
     
 
 &lt;h3&gt;
   By &lt;a href=&quot;http://software.intel.com/en-us/blogs/author/darla-worden/&quot;&gt;Darla Worden (Intel)&lt;/a&gt; (1 posts)
 on February 8, 2010 at 2:21 pm &lt;/h3&gt;
 &lt;p&gt;I am NOT an engineer. I am an admin to engineers and, more importantly, I am an end user.  I am the one who benefits from all the hard work Intel (and other) engineers and developers do.  My life, both at work and at home has been enormously improved by the hard work of hardware and software engineers and developers.  You Guys Rock!&lt;/p&gt;
&lt;p&gt;That said, I thought there might be a niche that I could fill for all my creative, hard working benefactors out there, sort of a pay it forward for all the great things you’ve done for me.  I’d like to give you a view from the cheap seats; feedback from the lowly end user who does not have a degree in computer science.  So here goes, my thoughts on netbooks.&lt;/p&gt;
&lt;p&gt;It has been almost a year since I was a winner in a contest that Intel sponsored and I became the owner of an Acer netbook.  At first I was delighted to win, especially after all the excitement surrounding the Atom processor launch. And let’s face it, we females love cute little gadgets.  (Can’t you almost hear my high pitched squeal?)  Then I powered up my cute new toy and thought, “OK, now what?”  &lt;/p&gt;
&lt;p&gt;Sure, I could surf the web, but I already have a MacBook and a Sony VAIO (yes, I’m computer bilingual), in addition to my work laptop, so I do not lack access to the internet. The netbook did not have a DVD so I could not watch my movies or load games I already own. Drat!  So for most of 2009 my netbook was unused other than some “test drives” by my sons who wanted to try a netbook before buying one of their own.  I figured it would be used only for trips when I did not want to lug my laptop.&lt;/p&gt;
&lt;p&gt;Then I learned about the new Intel App store that would be launching (in Beta form) at CES.  This really grabbed my interest.  A way to get apps on my netbook?  Cool!  From someone I already felt a great deal of trust?  Even better!  I could hardly wait for CES when I would learn the name of the store and how to get on the bandwagon.&lt;/p&gt;
&lt;p&gt;Long story short, I am now a registered user of AppUp.  I have downloaded 9 apps so far and have only had one issue - an app for weight loss that was listed as free took me to a site that wanted money to continue.  It should have been listed as free trial, not a free app.  &lt;/p&gt;
&lt;p&gt;On the whole, I like AppUp and am looking forward to seeing it grow into the wonderful site the team envisioned.  Having tried it out now, I have several suggested improvements for the site.  I would love to be able to see a demo of an app (as opposed to just screen shots) before I commit to buying.  Descriptions can be unclear and ratings only tell you what others think, not what your experience will be.  (i.e WOW gets really high ratings from my family, but World of Warcraft leaves me yawning, not my cup of tea.)  Another cool thing would be a user “wish list” we could use to encourage developers to create apps we end users really want to see.&lt;/p&gt;
&lt;p&gt;So, after almost a year with my netbook, I am beginning to really like this different format.  I still want to add my favorite Hoyle card games to it without having to pay for it again and I don’t have an external DVD so does anyone have suggestions on how to get it loaded on my netbook?&lt;/p&gt;
&lt;p&gt;I am also open to testing new software on my netbook so if that would be helpful to anyone, please contact me.  All comments/suggestions on improving my netbook experience are welcome and please check back for updates as my adventures continue.&lt;/p&gt;
 &lt;h5&gt;
  Categories: &lt;a href=&quot;http://software.intel.com/en-us/blogs/category/appdeveloper/&quot; title=&quot;View all posts in Intel® Atom™ Developer Program&quot; rel=&quot;category tag&quot;&gt;Intel® Atom™ Developer Program&lt;/a&gt;,  &lt;a href=&quot;http://software.intel.com/en-us/blogs/category/isn/&quot; title=&quot;View all posts in Intel® Software Network 2.0&quot; rel=&quot;category tag&quot;&gt;Intel® Software Network 2.0&lt;/a&gt; &lt;/h5&gt;
 
&lt;style type=&quot;text/css&quot;&gt;&lt;![CDATA[.dp-highlighter { width: 525px; }]]&gt;&lt;/style&gt;&lt;h3 class=&quot;pagesection&quot;&gt;Comments (0)&lt;/h3&gt;
&lt;h3 class=&quot;pagesection&quot;&gt;Trackbacks (0)&lt;/h3&gt;&lt;br /&gt;&lt;h3 class=&quot;pagesection&quot;&gt;Leave a comment  &lt;a target=&quot;_blank&quot; href=&quot;http://software.intel.com/en-us/articles/comments-help-guide/&quot;&gt;&lt;img src=&quot;/media/images/help.gif&quot; border=&quot;0&quot; /&gt;&lt;/a&gt;&lt;/h3&gt;

   &lt;/div&gt;&lt;/div&gt;&lt;p&gt;&lt;em&gt;&lt;a href=&quot;http://fivefilters.org&quot;&gt;Five Filters&lt;/a&gt; featured article: &lt;a href=&quot;http://medialens.org/alerts/09/091216_chilcot_inquiry_the.php&quot;&gt;Chilcot Inquiry&lt;/a&gt;. Available tools: &lt;a href=&quot;http://fivefilters.org/pdf-newspaper/&quot;&gt;PDF Newspaper&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/content-only/&quot;&gt;Full Text RSS&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/term-extraction/&quot;&gt;Term Extraction&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;</description>
<pubDate>Mon, 08 Feb 2010 22:21:02 +0000</pubDate>
<dc:creator>Darla Worden (Intel)</dc:creator>
</item>
<item>
<title>Video on Optimizing MID Performance With VTune Performance Analyzer</title>
<link>http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/g64VORFFdqQ/</link>
<guid isPermaLink="true" >http://feedproxy.google.com/~r/IntelSoftwareNetworkBlog/~3/g64VORFFdqQ/</guid>
<description>&lt;p&gt;&lt;em&gt;Message from fivefilters.org: If you can, please &lt;a href=&quot;http://fivefilters.org/content-only/#donate&quot;&gt;donate to the full-text RSS service&lt;/a&gt; so we can continue developing it.&lt;/em&gt;&lt;/p&gt;&lt;div&gt;&lt;div id=&quot;right&quot; readability=&quot;5&quot;&gt;
&lt;p&gt;&lt;a href=&quot;http://software.intel.com/en-us/&quot;&gt;English&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/zh-cn/&quot;&gt;中文&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/ru-ru/&quot;&gt;Русский&lt;/a&gt; | &lt;a href=&quot;http://software.intel.com/fr-fr/&quot;&gt;Français&lt;/a&gt;&lt;/p&gt;


     &lt;p&gt;2,852 Posts served&lt;/p&gt;
     &lt;p&gt;8,602 Conversations started&lt;/p&gt;
	
	
	
&lt;!--
commented out, since comments come from another place
	&lt;div class=&quot;box&quot;&gt;
		&lt;div class=&quot;boxHeader&quot;&gt;Recent Comments &lt;a href=&quot;http://software.intel.com/en-us/blogs/comments/feed/&quot;&gt;&lt;img height=&quot;16&quot; alt=&quot;RSS&quot; class=&quot;rss&quot; src=&quot;/common/images/icons/rss.gif&quot; width=&quot;16&quot; border=&quot;0&quot; /&gt;&lt;/a&gt;&lt;/div&gt;
		&lt;div class=&quot;boxBody&quot;&gt;
			&lt;div class=&quot;rbc2&quot;&gt;
				&lt;ul&gt;
									&lt;/ul&gt;
			&lt;/div&gt;
		&lt;/div&gt;
	&lt;/div&gt;
--&gt;
        
&lt;/div&gt;&lt;/div&gt;&lt;p&gt;&lt;em&gt;&lt;a href=&quot;http://fivefilters.org&quot;&gt;Five Filters&lt;/a&gt; featured article: &lt;a href=&quot;http://medialens.org/alerts/09/091216_chilcot_inquiry_the.php&quot;&gt;Chilcot Inquiry&lt;/a&gt;. Available tools: &lt;a href=&quot;http://fivefilters.org/pdf-newspaper/&quot;&gt;PDF Newspaper&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/content-only/&quot;&gt;Full Text RSS&lt;/a&gt;, &lt;a href=&quot;http://fivefilters.org/term-extraction/&quot;&gt;Term Extraction&lt;/a&gt;.&lt;/em&gt;&lt;/p&gt;</description>
<pubDate>Mon, 08 Feb 2010 21:43:13 +0000</pubDate>
<dc:creator>Jon Bullinger (Intel)</dc:creator>
</item>
</channel>
</rss>