TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Why LuaJIT's interpreter is written in assembly

81 pointsby oblover 4 years ago

4 comments

newobjover 4 years ago
Is LuaJIT still under active development? I thought the developer had walked away. With Torch also looking dead, that use case is gone, too. Roblox has their own Lua VM now.<p>I love Lua and code in it almost every day for fun, but yeah I&#x27;m pretty sure LuaJIT is just &quot;done&quot; now?
评论 #26107969 未加载
评论 #26108137 未加载
评论 #26107191 未加载
评论 #26108134 未加载
评论 #26121056 未加载
pansa2over 4 years ago
Relevant:<p>&gt; &gt; <i>Threaded code should have better branch prediction behavior than a jump table with a single dispatch point</i><p>&gt; <i>This is not the case anymore, at least for modern Intel processors. Starting with the Haswell micro-architecture, the indirect branch predictor got much better and a plain switch statement is just as fast as the &quot;computed goto&quot; equivalent. Be wary of any references about this that are from before 2013.</i><p><a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=15396761" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=15396761</a>
评论 #26107721 未加载
评论 #26108490 未加载
guenthertover 4 years ago
That needs an 2011 tag.
remexreover 4 years ago
I wonder if Clang can do better these days; I noticed that it seems to merge computed gotos to normal-looking control-flow (I suppose this is necessary for alias analysis).
评论 #26107965 未加载