<?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>RTL-Generation on 兜忆轩 | Cedric's Compiler Notes</title><link>https://douyixuan.github.io/tags/rtl-generation/</link><description>Recent content in RTL-Generation 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>Mon, 21 Sep 2026 12:22:00 +0800</lastBuildDate><atom:link href="https://douyixuan.github.io/tags/rtl-generation/index.xml" rel="self" type="application/rss+xml"/><item><title>008 · 过了编译，为何长 RTL 仍几乎全错？</title><link>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-21/</link><pubDate>Mon, 21 Sep 2026 12:22:00 +0800</pubDate><guid>https://douyixuan.github.io/posts/ai-silicon-papers/2026-09-21/</guid><description>ChipVerilog 把 RTL 生成评测推进到长模块和跨模块层级：强模型大多能生成可编译代码，但功能正确率随规模与层级迅速下降；这也暴露了规格来源和验证口径的边界。</description></item></channel></rss>