<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>CUDA on Weile Luo&#39;s homepage</title>
    <link>https://lyleluo.github.io/tags/cuda/</link>
    <description>Recent content in CUDA on Weile Luo&#39;s homepage</description>
    <generator>Hugo</generator>
    <language>en</language>
    <lastBuildDate>Mon, 27 Apr 2026 12:00:00 +0800</lastBuildDate>
    <atom:link href="https://lyleluo.github.io/tags/cuda/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Breaking GPU Hardware Limits: Micro-benchmark Methodology, PTX Assembly, and Hopper Architecture</title>
      <link>https://lyleluo.github.io/posts/cuda-micro-benchmark-2/</link>
      <pubDate>Mon, 27 Apr 2026 12:00:00 +0800</pubDate>
      <guid>https://lyleluo.github.io/posts/cuda-micro-benchmark-2/</guid>
      <description></description>
    </item>
    <item>
      <title>CUDA Performance Profiling Cornerstone: Toolchains, Warp Scheduling, and Nsight Compute</title>
      <link>https://lyleluo.github.io/posts/cuda-micro-benchmark-1/</link>
      <pubDate>Sun, 26 Apr 2026 12:00:00 +0800</pubDate>
      <guid>https://lyleluo.github.io/posts/cuda-micro-benchmark-1/</guid>
      <description></description>
    </item>
  </channel>
</rss>
