<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Amd on KSTRLWORKS | Linux Made Easy</title><link>https://www.kstrlworks.com/tags/amd/</link><description>Recent content in Amd on KSTRLWORKS | Linux Made Easy</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Fri, 20 Nov 2026 19:15:36 -0500</lastBuildDate><atom:link href="https://www.kstrlworks.com/tags/amd/index.xml" rel="self" type="application/rss+xml"/><item><title>Oh, the States You'll Go To: The AMD GPU Reset Bug and Everything It Isn't</title><link>https://www.kstrlworks.com/blog/amd-gpu-reset-bug-vendor-reset/</link><pubDate>Sat, 14 Nov 2026 00:00:00 +0000</pubDate><guid>https://www.kstrlworks.com/blog/amd-gpu-reset-bug-vendor-reset/</guid><description>&lt;p&gt;&lt;img src="https://www.kstrlworks.com/images/amd-rx5700xt-exploded.avif" alt="An exploded view of a reference Radeon RX 5700 XT"&gt;&lt;/p&gt;&#10;&lt;h1 id="most-people-do-not-have-a-reset-bug-at-all"&gt;Most people do not have a reset bug at all&lt;/h1&gt;&#10;&lt;p&gt;they have one of several different problems that look identical from the onset. Black screens, Windows code 43, libvirt coughing up &lt;code&gt;Unknown PCI header type '127'&lt;/code&gt; or &lt;code&gt;lspci&lt;/code&gt; saying your card is revision &lt;code&gt;ff&lt;/code&gt;. All of which can be explained with:&lt;/p&gt;&#10;&lt;p&gt;&lt;strong&gt;Reset gap (a precondition)&lt;/strong&gt;: the device holds state that nothing in the PCIe reset path can see or clear, and the resets available to whatever driver owns the card next don&amp;rsquo;t touch it either. Every consumer AMD card from Polaris on has this, the RX 9000 included.&lt;/p&gt;</description></item></channel></rss>