<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Parallelism on Pi Stack</title>
    <link>https://www.pistack.xyz/tags/parallelism/</link>
    <description>Recent content in Parallelism on Pi Stack</description>
    <generator>Hugo</generator>
    <language>en-us</language>
    <lastBuildDate>Sun, 21 Jun 2026 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://www.pistack.xyz/tags/parallelism/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Self-Hosted C&#43;&#43; Task Parallelism: Taskflow vs oneTBB vs BS::thread_pool</title>
      <link>https://www.pistack.xyz/posts/2026-06-21-cpp-task-parallelism-libraries-taskflow-onetbb-threadpool/</link>
      <pubDate>Sun, 21 Jun 2026 00:00:00 +0000</pubDate>
      <guid>https://www.pistack.xyz/posts/2026-06-21-cpp-task-parallelism-libraries-taskflow-onetbb-threadpool/</guid>
      <description>&lt;h2 id=&#34;introduction&#34;&gt;Introduction&lt;/h2&gt;&#xA;&lt;p&gt;Writing correct, efficient parallel C++ code remains one of the hardest challenges in systems programming. Raw &lt;code&gt;std::thread&lt;/code&gt; and manual mutex management lead to deadlocks, race conditions, and suboptimal CPU utilization. Modern task parallelism libraries abstract thread management behind high-level APIs — you describe &lt;em&gt;what&lt;/em&gt; work needs to be done and &lt;em&gt;which tasks depend on each other&lt;/em&gt;, while the runtime handles thread pools, work stealing, and load balancing automatically.&lt;/p&gt;</description>
    </item>
  </channel>
</rss>
