<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"
	xmlns:content="http://purl.org/rss/1.0/modules/content/"
	xmlns:wfw="http://wellformedweb.org/CommentAPI/"
	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/"
	xmlns:slash="http://purl.org/rss/1.0/modules/slash/"
			xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd"
		>

<channel>
	<title>Gigaom Search &#187; Technologies and Products &#187; graphic processing units (GPUs)</title>
	<atom:link href="http://search.gigaom.com/technology/graphic-processing-units-gpus/feed/" rel="self" type="application/rss+xml" />
	<link>http://search.gigaom.com</link>
	<description></description>
	<lastBuildDate>Wed, 11 Mar 2015 13:08:37 +0000</lastBuildDate>
	<language>en-US</language>
	<sy:updatePeriod>hourly</sy:updatePeriod>
	<sy:updateFrequency>1</sy:updateFrequency>
	<generator>http://wordpress.org/?v=4.1</generator>
	<item>
		<title>Microsoft is building fast, low-power neural networks with FPGAs</title>
		<link>http://gigaom.com/2015/02/23/microsoft-is-building-fast-low-power-neural-networks-with-fpgas/</link>
		<comments>http://gigaom.com/2015/02/23/microsoft-is-building-fast-low-power-neural-networks-with-fpgas/#comments</comments>
		<pubDate>Mon, 23 Feb 2015 17:28:12 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Altera]]></category>
		<category><![CDATA[FPGAs]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[Microsoft Research]]></category>
		<category><![CDATA[neural networks]]></category>
		<category><![CDATA[object recognition]]></category>
		<category><![CDATA[processor architecture]]></category>
		<category><![CDATA[web scale]]></category>
		<category><![CDATA[webscale infrastructure]]></category>
<category domain="http://search.gigaom.com/stock/"><![CDATA[NASDAQ:MSFT]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:MSFT]]></category>
		
		<guid isPermaLink="false">http://gigaom.com/?p=916437</guid>
		<description><![CDATA[Microsoft on Monday released a white paper explaining a current effort to run convolutional neural networks -- the deep learning technique responsible for record-setting computer vision algorithms -- on FPGAs rather&#8230;]]></description>
		<wfw:commentRss>http://gigaom.com/2015/02/23/microsoft-is-building-fast-low-power-neural-networks-with-fpgas/feed/</wfw:commentRss>
		<slash:comments>1</slash:comments>
		</item>
		<item>
		<title>PhotoTime is a deep learning application for the rest of us</title>
		<link>https://gigaom.com/2015/02/06/phototime-is-a-deep-learning-application-for-the-rest-of-us/</link>
		<comments>https://gigaom.com/2015/02/06/phototime-is-a-deep-learning-application-for-the-rest-of-us/#comments</comments>
		<pubDate>Fri, 06 Feb 2015 20:23:58 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[object recognition]]></category>
		<category><![CDATA[Orbeus]]></category>
		<category><![CDATA[photo tagging]]></category>
		<category><![CDATA[PhotoTime]]></category>

		<guid isPermaLink="false">http://gigaom.com/?p=913150</guid>
		<description><![CDATA[A Sunnyvale, California, startup called Orbeus has developed what could be the best application yet for letting everyday consumers benefit from advances in deep learning. It's called PhotoTime and, yes, it's&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2015/02/06/phototime-is-a-deep-learning-application-for-the-rest-of-us/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>ARM launches a faster, more efficient chip design for smartphones</title>
		<link>https://gigaom.com/2015/02/03/arm-launches-a-faster-more-efficient-chip-design-for-smartphones/</link>
		<comments>https://gigaom.com/2015/02/03/arm-launches-a-faster-more-efficient-chip-design-for-smartphones/#comments</comments>
		<pubDate>Tue, 03 Feb 2015 19:58:47 +0000</pubDate>
		<dc:creator><![CDATA[Kif Leswing]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[ARM architecture]]></category>
		<category><![CDATA[chips]]></category>
		<category><![CDATA[Cortex]]></category>
		<category><![CDATA[Exynos]]></category>
		<category><![CDATA[microprocessor]]></category>

		<guid isPermaLink="false">http://gigaom.com/?p=912134</guid>
		<description><![CDATA[Nearly every single smartphone sold last year uses a processor originally designed by ARM. On Tuesday, the British company announced new processor designs that will likely end up in devices in 2016&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2015/02/03/arm-launches-a-faster-more-efficient-chip-design-for-smartphones/feed/</wfw:commentRss>
		<slash:comments>2</slash:comments>
		</item>
		<item>
		<title>Facebook open sources tools for bigger, faster deep learning models</title>
		<link>https://gigaom.com/2015/01/16/facebook-open-sources-tools-for-bigger-faster-deep-learning-models/</link>
		<comments>https://gigaom.com/2015/01/16/facebook-open-sources-tools-for-bigger-faster-deep-learning-models/#comments</comments>
		<pubDate>Fri, 16 Jan 2015 16:10:58 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[neural networks]]></category>
		<category><![CDATA[open source]]></category>
<category domain="http://search.gigaom.com/stock/"><![CDATA[NASDAQ:FB]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:FB]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:NVDA]]></category>
		
		<guid isPermaLink="false">http://gigaom.com/?p=907116</guid>
		<description><![CDATA[Facebook on Friday open sourced a handful of software libraries that it claims will help users build bigger, faster deep learning models than existing tools allow. The libraries, which  is&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2015/01/16/facebook-open-sources-tools-for-bigger-faster-deep-learning-models/feed/</wfw:commentRss>
		<slash:comments>5</slash:comments>
		</item>
		<item>
		<title>5 things to expect from Qualcomm&#8217;s flagship mobile chip in 2015</title>
		<link>https://gigaom.com/2014/12/12/5-things-to-expect-from-qualcomms-flagship-mobile-chip-in-2015/</link>
		<comments>https://gigaom.com/2014/12/12/5-things-to-expect-from-qualcomms-flagship-mobile-chip-in-2015/#comments</comments>
		<pubDate>Fri, 12 Dec 2014 14:00:39 +0000</pubDate>
		<dc:creator><![CDATA[Kif Leswing]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[chips]]></category>
		<category><![CDATA[Snapdragon 810]]></category>
<category domain="http://search.gigaom.com/stock/"><![CDATA[NASDAQ:GOOG]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:GOOG]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:QCOM]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NYSE:MMI]]></category>
		
		<guid isPermaLink="false">http://gigaom.com/?p=899947</guid>
		<description><![CDATA[This past week, Qualcomm's been beginning to reveal what its new flagship smartphone and tablet chip can do. If you're buying a new phone in the next year, pay attention: There's&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2014/12/12/5-things-to-expect-from-qualcomms-flagship-mobile-chip-in-2015/feed/</wfw:commentRss>
		<slash:comments>1</slash:comments>
		</item>
		<item>
		<title>Baidu is trying to speed up image search using FPGAs</title>
		<link>https://gigaom.com/2014/09/22/baidu-is-trying-to-speed-up-image-search-using-fpgas/</link>
		<comments>https://gigaom.com/2014/09/22/baidu-is-trying-to-speed-up-image-search-using-fpgas/#comments</comments>
		<pubDate>Mon, 22 Sep 2014 18:46:50 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Altera]]></category>
		<category><![CDATA[FPGAs]]></category>
		<category><![CDATA[web infrastructure]]></category>

		<guid isPermaLink="false">http://gigaom.com/?p=875013</guid>
		<description><![CDATA[Chinese search engine Baidu is trying to speed the performance of its deep learning models for image search using field programmable gate arrays, or FPGAs, made by Altera. Baidu has been experimenting&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2014/09/22/baidu-is-trying-to-speed-up-image-search-using-fpgas/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Nvidia stakes its claim in deep learning by making its GPUs easier to program</title>
		<link>https://gigaom.com/2014/09/08/nvidia-stakes-its-claim-in-deep-learning-by-making-its-gpus-easier-to-program/</link>
		<comments>https://gigaom.com/2014/09/08/nvidia-stakes-its-claim-in-deep-learning-by-making-its-gpus-easier-to-program/#comments</comments>
		<pubDate>Mon, 08 Sep 2014 20:21:07 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[parallel programming]]></category>

		<guid isPermaLink="false">http://gigaom.com/?p=871242</guid>
		<description><![CDATA[Nvidia is fully embracing the effectiveness of GPUs for running deep learning algorithms, releasing over the weekend a new set of libraries designed to let researchers experience the performance boost of&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2014/09/08/nvidia-stakes-its-claim-in-deep-learning-by-making-its-gpus-easier-to-program/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
		<item>
		<title>Baidu says its massive deep-learning system is nearly complete</title>
		<link>https://gigaom.com/2014/09/04/baidu-says-its-massive-deep-learning-system-is-nearly-complete/</link>
		<comments>https://gigaom.com/2014/09/04/baidu-says-its-massive-deep-learning-system-is-nearly-complete/#comments</comments>
		<pubDate>Thu, 04 Sep 2014 23:17:43 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Baidu Eye]]></category>
		<category><![CDATA[machine learning]]></category>
		<category><![CDATA[object recognition]]></category>
		<category><![CDATA[text analysis]]></category>
<category domain="http://search.gigaom.com/stock/"><![CDATA[NASDAQ:GOOG]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:GOOG]]></category>
		
		<guid isPermaLink="false">http://gigaom.com/?p=870370</guid>
		<description><![CDATA[Baidu says its 100-billion-neuron deep learning system will be complete within six months, powering a fast transition away from text as the dominant search input. Thanks to smartphones and its new&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2014/09/04/baidu-says-its-massive-deep-learning-system-is-nearly-complete/feed/</wfw:commentRss>
		<slash:comments>6</slash:comments>
		</item>
		<item>
		<title>Nvidia launches patent war against Samsung and Qualcomm over graphic chips</title>
		<link>https://gigaom.com/2014/09/04/nvidia-launches-patent-war-against-samsung-and-qualcomm-over-graphic-chips/</link>
		<comments>https://gigaom.com/2014/09/04/nvidia-launches-patent-war-against-samsung-and-qualcomm-over-graphic-chips/#comments</comments>
		<pubDate>Thu, 04 Sep 2014 22:05:34 +0000</pubDate>
		<dc:creator><![CDATA[Jeff Roberts]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:NVDA]]></category>
		<category domain="http://search.gigaom.com/stock/"><![CDATA[NSDQ:QCOM]]></category>
		
		<guid isPermaLink="false">http://gigaom.com/?p=870341</guid>
		<description><![CDATA[Patent lawsuits are common in Silicon Valley, but the one that NVIDIA filed over graphics technology will make many in the smartphone and gaming industry take notice.]]></description>
		<wfw:commentRss>https://gigaom.com/2014/09/04/nvidia-launches-patent-war-against-samsung-and-qualcomm-over-graphic-chips/feed/</wfw:commentRss>
		<slash:comments>7</slash:comments>
		</item>
		<item>
		<title>Nervana Systems raises $3.3M to build hardware designed for deep learning</title>
		<link>https://gigaom.com/2014/08/21/nervana-systems-raises-3-3m-to-build-hardware-designed-for-deep-learning/</link>
		<comments>https://gigaom.com/2014/08/21/nervana-systems-raises-3-3m-to-build-hardware-designed-for-deep-learning/#comments</comments>
		<pubDate>Thu, 21 Aug 2014 12:48:34 +0000</pubDate>
		<dc:creator><![CDATA[Derrick Harris]]></dc:creator>
				<category><![CDATA[Uncategorized]]></category>
		<category><![CDATA[Neuromorphic engineering]]></category>

		<guid isPermaLink="false">http://gigaom.com/?p=866795</guid>
		<description><![CDATA[A San Diego-based startup called Nervana Systems has raised a series A round for its specialized deep learning computing system. It's a smart move given the hype and legitimate promise of&#8230;]]></description>
		<wfw:commentRss>https://gigaom.com/2014/08/21/nervana-systems-raises-3-3m-to-build-hardware-designed-for-deep-learning/feed/</wfw:commentRss>
		<slash:comments>0</slash:comments>
		</item>
	</channel>
</rss>
