<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by Matthew Kieber-Emmons on Medium]]></title>
        <description><![CDATA[Stories by Matthew Kieber-Emmons on Medium]]></description>
        <link>https://medium.com/@kieber-emmons?source=rss-74de02236c0f------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*Exat_W_zcAZ3pcuAUCUdDg.jpeg</url>
            <title>Stories by Matthew Kieber-Emmons on Medium</title>
            <link>https://medium.com/@kieber-emmons?source=rss-74de02236c0f------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Thu, 19 Nov 2026 06:08:08 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@kieber-emmons/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Application of Statistical Process Control to Performance Testing in Swift]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://levelup.gitconnected.com/application-of-statistical-process-control-to-performance-testing-in-swift-95a90c4df900?source=rss-74de02236c0f------2"><img src="https://cdn-images-1.medium.com/max/1106/1*3BfB-I8JM0oMWQ21P6HueQ.png" width="1106"></a></p><p class="medium-feed-snippet">Reliable regression detection when performance differences are on the order of the measurement variance.</p><p class="medium-feed-link"><a href="https://levelup.gitconnected.com/application-of-statistical-process-control-to-performance-testing-in-swift-95a90c4df900?source=rss-74de02236c0f------2">Continue reading on Level Up Coding »</a></p></div>]]></description>
            <link>https://levelup.gitconnected.com/application-of-statistical-process-control-to-performance-testing-in-swift-95a90c4df900?source=rss-74de02236c0f------2</link>
            <guid isPermaLink="false">https://medium.com/p/95a90c4df900</guid>
            <category><![CDATA[control-chart]]></category>
            <category><![CDATA[regression-testing]]></category>
            <category><![CDATA[swift-testing]]></category>
            <category><![CDATA[swift-benchmark]]></category>
            <category><![CDATA[performance-testing]]></category>
            <dc:creator><![CDATA[Matthew Kieber-Emmons]]></dc:creator>
            <pubDate>Sun, 25 Jan 2026 23:37:56 GMT</pubDate>
            <atom:updated>2026-02-23T16:52:52.808Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Design of Shader and Associated Host Class for Performance Optimization of Metal Compute Kernels]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://kieber-emmons.medium.com/design-of-shader-and-associated-host-class-for-performance-optimization-of-metal-compute-kernels-449a14089080?source=rss-74de02236c0f------2"><img src="https://cdn-images-1.medium.com/max/2600/0*J1k4Ns7EXGcKL5rh" width="6000"></a></p><p class="medium-feed-snippet">Optimize compute performance with kernels that are fine-tuned for the unique characteristics of each Metal GPU family.</p><p class="medium-feed-link"><a href="https://kieber-emmons.medium.com/design-of-shader-and-associated-host-class-for-performance-optimization-of-metal-compute-kernels-449a14089080?source=rss-74de02236c0f------2">Continue reading on Medium »</a></p></div>]]></description>
            <link>https://kieber-emmons.medium.com/design-of-shader-and-associated-host-class-for-performance-optimization-of-metal-compute-kernels-449a14089080?source=rss-74de02236c0f------2</link>
            <guid isPermaLink="false">https://medium.com/p/449a14089080</guid>
            <category><![CDATA[apple-silicon]]></category>
            <category><![CDATA[gpu-computing]]></category>
            <category><![CDATA[swift]]></category>
            <category><![CDATA[metal]]></category>
            <category><![CDATA[parallel-reduce]]></category>
            <dc:creator><![CDATA[Matthew Kieber-Emmons]]></dc:creator>
            <pubDate>Tue, 03 Sep 2024 07:31:50 GMT</pubDate>
            <atom:updated>2024-09-03T16:10:12.668Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Memory Bandwidth Optimized Parallel Radix Sort in Metal for Apple M1 and Beyond]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/better-programming/memory-bandwidth-optimized-parallel-radix-sort-in-metal-for-apple-m1-and-beyond-4f4590cfd5d3?source=rss-74de02236c0f------2"><img src="https://cdn-images-1.medium.com/max/1960/1*VUcUbvjBdg8RU2c3Qq9o4w.jpeg" width="1960"></a></p><p class="medium-feed-snippet">A sort shader in Metal for use on primitive data types</p><p class="medium-feed-link"><a href="https://medium.com/better-programming/memory-bandwidth-optimized-parallel-radix-sort-in-metal-for-apple-m1-and-beyond-4f4590cfd5d3?source=rss-74de02236c0f------2">Continue reading on Better Programming »</a></p></div>]]></description>
            <link>https://medium.com/better-programming/memory-bandwidth-optimized-parallel-radix-sort-in-metal-for-apple-m1-and-beyond-4f4590cfd5d3?source=rss-74de02236c0f------2</link>
            <guid isPermaLink="false">https://medium.com/p/4f4590cfd5d3</guid>
            <category><![CDATA[algorithms]]></category>
            <category><![CDATA[data-science]]></category>
            <category><![CDATA[gpu-computing]]></category>
            <category><![CDATA[metal]]></category>
            <category><![CDATA[apple-silicon]]></category>
            <dc:creator><![CDATA[Matthew Kieber-Emmons]]></dc:creator>
            <pubDate>Sat, 17 Sep 2022 23:07:10 GMT</pubDate>
            <atom:updated>2023-03-03T00:31:59.019Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Efficient Parallel Prefix Sum in Metal for Apple M1]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/better-programming/efficient-parallel-prefix-sum-in-metal-for-apple-m1-9e60b974d62?source=rss-74de02236c0f------2"><img src="https://cdn-images-1.medium.com/max/2600/0*GGva7d88yFrwE4c9" width="4608"></a></p><p class="medium-feed-snippet">Comparison of optimal M1 GPU scan primitives to vectorized CPU performance</p><p class="medium-feed-link"><a href="https://medium.com/better-programming/efficient-parallel-prefix-sum-in-metal-for-apple-m1-9e60b974d62?source=rss-74de02236c0f------2">Continue reading on Better Programming »</a></p></div>]]></description>
            <link>https://medium.com/better-programming/efficient-parallel-prefix-sum-in-metal-for-apple-m1-9e60b974d62?source=rss-74de02236c0f------2</link>
            <guid isPermaLink="false">https://medium.com/p/9e60b974d62</guid>
            <category><![CDATA[parallel-primitive]]></category>
            <category><![CDATA[metal]]></category>
            <category><![CDATA[optimization]]></category>
            <category><![CDATA[apple-m1]]></category>
            <category><![CDATA[prefix-sum]]></category>
            <dc:creator><![CDATA[Matthew Kieber-Emmons]]></dc:creator>
            <pubDate>Thu, 09 Sep 2021 18:01:02 GMT</pubDate>
            <atom:updated>2023-03-28T19:42:41.681Z</atom:updated>
        </item>
        <item>
            <title><![CDATA[Optimizing Parallel Reduction in Metal for Apple M1]]></title>
            <description><![CDATA[<div class="medium-feed-item"><p class="medium-feed-image"><a href="https://medium.com/better-programming/optimizing-parallel-reduction-in-metal-for-apple-m1-8e8677b49b01?source=rss-74de02236c0f------2"><img src="https://cdn-images-1.medium.com/max/766/1*Eo_SSRLKe4fA_u9QFxz7Qg.png" width="766"></a></p><p class="medium-feed-snippet">Exploring how an optimal implementation should approach the memory bandwidth of the architecture</p><p class="medium-feed-link"><a href="https://medium.com/better-programming/optimizing-parallel-reduction-in-metal-for-apple-m1-8e8677b49b01?source=rss-74de02236c0f------2">Continue reading on Better Programming »</a></p></div>]]></description>
            <link>https://medium.com/better-programming/optimizing-parallel-reduction-in-metal-for-apple-m1-8e8677b49b01?source=rss-74de02236c0f------2</link>
            <guid isPermaLink="false">https://medium.com/p/8e8677b49b01</guid>
            <category><![CDATA[apple-silicon]]></category>
            <category><![CDATA[metal]]></category>
            <category><![CDATA[gpu]]></category>
            <category><![CDATA[m1]]></category>
            <category><![CDATA[parallel-reduce]]></category>
            <dc:creator><![CDATA[Matthew Kieber-Emmons]]></dc:creator>
            <pubDate>Mon, 15 Mar 2021 06:40:21 GMT</pubDate>
            <atom:updated>2023-03-28T18:29:27.438Z</atom:updated>
        </item>
    </channel>
</rss>