<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/">
  <channel>
    <title>algorithm on The Site of laekov</title>
    <link>/tags/algorithm/</link>
    <description>Recent content in algorithm on The Site of laekov</description>
    <generator>Hugo -- gohugo.io</generator>
    <language>en</language>
    <copyright>&amp;copy; laekov</copyright>
    <lastBuildDate>Sun, 22 Apr 2018 17:59:13 +0000</lastBuildDate><atom:link href="/tags/algorithm/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>LIRS Plus</title>
      <link>/technical/3e470a/</link>
      <pubDate>Sun, 22 Apr 2018 17:59:13 +0000</pubDate>
      
      <guid>/technical/3e470a/</guid>
      <description>最近在做一个 Cache 替换算法的 PA. 系统结构课.
给的 Baseline 是 2010 年的一个 championship.
看了看现在用得比较多的通用算法叫 LIRS.
在 LIRS 基础上想方法优化.
瞎搞的东西把单核 miss 率降低得有点 surprising.
还没有更多的 benchmark 测试.
感觉有点意思.</description>
    </item>
    
  </channel>
</rss>
