<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Parallel Computing | Xuanhao</title><link>https://www.xh-zhang.com/tags/parallel-computing/</link><atom:link href="https://www.xh-zhang.com/tags/parallel-computing/index.xml" rel="self" type="application/rss+xml"/><description>Parallel Computing</description><generator>Source Themes Academic (https://sourcethemes.com/academic/)</generator><language>en-us</language><lastBuildDate>Mon, 01 Oct 2018 16:40:57 -0400</lastBuildDate><image><url>https://www.xh-zhang.com/img/icon-192.png</url><title>Parallel Computing</title><link>https://www.xh-zhang.com/tags/parallel-computing/</link></image><item><title>Pictures Histogram Accelerating based on CUDA</title><link>https://www.xh-zhang.com/project/histogram/</link><pubDate>Mon, 01 Oct 2018 16:40:57 -0400</pubDate><guid>https://www.xh-zhang.com/project/histogram/</guid><description>
&lt;h2 id=&#34;pictures-histogram-accelerating-based-on-cuda&#34;&gt;Pictures Histogram Accelerating based on CUDA&lt;/h2&gt;
&lt;p&gt;Implemented a histogram equalization algorithm based on CUDA, where the benchmark of GPU was Nvidia Kepler 10. To optimize, I downsampled 16 pixels (144 bits) as a block to the kernel at a time, which was a tradeoff between accuracy and efficiency. Also, I pinned-memory on the host side and optimized the blocks with a one-dimensional block design.&lt;/p&gt;</description></item></channel></rss>