<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Msvc on icyveins7's blog</title><link>https://icyveins7.github.io/tags/msvc/</link><description>Recent content in Msvc on icyveins7's blog</description><generator>Hugo</generator><language>en-us</language><copyright>This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.</copyright><lastBuildDate>Sat, 24 Feb 2024 20:00:00 +0800</lastBuildDate><atom:link href="https://icyveins7.github.io/tags/msvc/index.xml" rel="self" type="application/rss+xml"/><item><title>MSVC's terrible auto-vectoriser for AVX</title><link>https://icyveins7.github.io/posts/2024/02/msvcs-terrible-auto-vectoriser-for-avx/</link><pubDate>Sat, 24 Feb 2024 20:00:00 +0800</pubDate><guid>https://icyveins7.github.io/posts/2024/02/msvcs-terrible-auto-vectoriser-for-avx/</guid><description>&lt;blockquote&gt;&#10;&lt;p&gt;MSVC has extremely lackluster auto-vectorisation, so I handrolled intrinsic calls by backtranslating GCC&amp;rsquo;s output.&lt;/p&gt;&#10;&lt;/blockquote&gt;&#10;&lt;h1 id="the-motivation"&gt;The Motivation&lt;/h1&gt;&#10;&lt;p&gt;I recently decided I wanted to spend some time understanding intrinsics and SIMD at a deeper level.&lt;/p&gt;&#10;&lt;p&gt;In developing code for my project &lt;a href="https://github.com/icyveins7/ffs"&gt;&lt;code&gt;ffs&lt;/code&gt;&lt;/a&gt;, I wanted to make sure that the code was running with at least AVX instructions (because that&amp;rsquo;s my target architecture, and honestly very few computers don&amp;rsquo;t have AVX these days..).&lt;/p&gt;&#10;&lt;p&gt;This led me down a path of discovery; first I discovered the amazing-ness that is &lt;a href="https://godbolt.org"&gt;godbolt.org&lt;/a&gt;, then I joined their discord, where I then asked for some help with understanding basic .asm compiler output.&lt;/p&gt;</description></item></channel></rss>