<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Daft on 影神图</title><link>https://jiangxt2.github.io/topics/daft/</link><description>Recent content in Daft on 影神图</description><generator>Hugo</generator><language>zh-CN</language><lastBuildDate>Thu, 17 Sep 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jiangxt2.github.io/topics/daft/index.xml" rel="self" type="application/rss+xml"/><item><title>Daft</title><link>https://jiangxt2.github.io/docs/daft/</link><pubDate>Thu, 17 Sep 2026 00:00:00 +0000</pubDate><guid>https://jiangxt2.github.io/docs/daft/</guid><description>记录 DataFrame、物理执行计划和分布式数据处理之间的联系。</description></item><item><title>Spark vs Daft：数据处理模型的差异</title><link>https://jiangxt2.github.io/comparisons/spark-vs-daft/</link><pubDate>Thu, 17 Sep 2026 00:00:00 +0000</pubDate><guid>https://jiangxt2.github.io/comparisons/spark-vs-daft/</guid><description>比较 Spark 与 Daft 在数据抽象、执行计划、生态和适用场景上的差异。</description></item><item><title>什么是向量化执行</title><link>https://jiangxt2.github.io/concepts/vectorized-execution/</link><pubDate>Thu, 17 Sep 2026 00:00:00 +0000</pubDate><guid>https://jiangxt2.github.io/concepts/vectorized-execution/</guid><description>用批量处理而不是逐行处理理解向量化执行，以及它为什么常出现在 OLAP 系统中。</description></item></channel></rss>