<?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>Synthesis on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/synthesis/</link><description>Recent content in Synthesis on 兜忆轩 | Cedric's Compiler Notes</description><image><title>兜忆轩 | Cedric's Compiler Notes</title><url>https://douyixuan.github.io/images/papermod-cover.png</url><link>https://douyixuan.github.io/images/papermod-cover.png</link></image><generator>Hugo -- 0.146.0</generator><language>en-us</language><lastBuildDate>Fri, 13 Nov 2026 10:15:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/synthesis/index.xml" rel="self" type="application/rss+xml"/><item><title>059 · 综合器越强，RTL 优化的收益越真实吗？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-11-13/</link><pubDate>Fri, 13 Nov 2026 10:15:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-11-13/</guid><description>RTL 改写的价值取决于下游综合器还没有完成什么。这篇研究把起始设计、综合流程与等价检查放回评测中心，追问一次显著改善究竟发现了新机会，还是恢复了人为注入的低效。</description></item></channel></rss>