<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>Researches on Siho Shin</title>
    <link>https://www.siho-shin.life/researches/</link>
    <description>Recent content in Researches on Siho Shin</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>Seung-ri Shin</copyright>
    <lastBuildDate>Thu, 23 Apr 2026 17:53:38 +0000</lastBuildDate>
    <atom:link href="https://www.siho-shin.life/researches/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Learning NVIDIA DOCA [2]</title>
      <link>https://www.siho-shin.life/researches/learning-nvidia-doca-2/</link>
      <pubDate>Thu, 23 Apr 2026 17:53:38 +0000</pubDate>
      <guid>https://www.siho-shin.life/researches/learning-nvidia-doca-2/</guid>
      <description>In this post, I&amp;rsquo;ll be discussing how I utilized the accelerators of the BlueField device, using doca_compress.&#xA;Understand the architecture DOCA Core primitives Device enumerations with doca_devinfo Run sample applications Regex offload sample Compression sample: doca_compress First, our program opens a device capable of supporting hardware compression engine. The device here means PF, VF, or SF in the BlueField device, and it is stored into struct doca_dev object.&#xA;Next, the compression context doca_compress is created, and the progress engine (PE) is also created.</description>
    </item>
    <item>
      <title>Learning NVIDIA DOCA [1]</title>
      <link>https://www.siho-shin.life/researches/learning-nvidia-doca-1/</link>
      <pubDate>Sun, 19 Apr 2026 23:09:36 +0000</pubDate>
      <guid>https://www.siho-shin.life/researches/learning-nvidia-doca-1/</guid>
      <description>Today, I used doca_dev.h API to enumerate PCI functions of the BlueField device.&#xA;Understand the architecture DOCA Core primitives Device enumerations with doca_devinfo Run sample applications Regex offload sample Compression sample: doca_compress To acquire the information of each interface of the device, first I had to call the function doca_devinfo_create_list. It creates an array of struct doca_devinfo. Then, while iterating through the array, I called doca_dev_open function to retrieve struct doca_dev of the device.</description>
    </item>
    <item>
      <title>Learning NVIDIA DOCA [0]</title>
      <link>https://www.siho-shin.life/researches/learning-nvidia-doca-0/</link>
      <pubDate>Mon, 13 Apr 2026 12:00:05 +0000</pubDate>
      <guid>https://www.siho-shin.life/researches/learning-nvidia-doca-0/</guid>
      <description>Since I am assigned to research SmartNICs, I also have to learn NVIDIA DOCA. Here is the roadmap that Claude made for me:&#xA;Understand the architecture DOCA Core primitives Device enumerations with doca_devinfo Run sample applications Regex offload sample Compression sample: doca_compress In this short series, I&amp;rsquo;ll go through this roadmap and document my journey on this blog.&#xA;Stay tuned!</description>
    </item>
  </channel>
</rss>
