The following is a chronicle of implementing a general purpose zero-instrumentation BPF based profiler for LuaJIT. Some assumptions are made about what this entails and it may be helpful to read some of our other work in this area. One major change from prior efforts is that instead of working with the original Parca unwinder we are now working with the OpenTelemetry eBPF profiler. If you missed t
Welcome to the LuaJIT blog series. In this one, we will go over some basic introduction, stuff like the motivation behind this research, setup notes, etc. Table of Contents LuaJIT Internals(Pt. 0/3): Intro / This post LuaJIT Internals(Pt. 1/3): Stepping into the VM LuaJIT Internals(Pt. 2/3): Fighting the JIT Compiler LuaJIT Internals(Pt. 3/3): Crafting Shellcodes (Bonus!) LuaJIT Sandbox Escape: Th
This is the Part 2 of a series. Feel free to read the prequel for more context: Building the fastest Lua interpreter automatically Building a good VM for a dynamic language takes a ton of engineering. The best-performing VMs (e.g., JavaScriptCore, V8, SpiderMonkey) employ at least 3 VM tiers (interpreter, baseline JIT[1] and optimizing JIT), and pervasively use hand-coded assembly in every VM tier
LuaJIT is a high-performance virtual machine for Lua. I've recently started playing with it and this blog post talks about what I've discovered so far. LuaJIT is a tracing JIT as opposed to a method JIT -- it works not by discovering and optimizing hot methods as a whole but by discovering and optimizing hot traces or paths of execution. LuaJIT has a rather interesting interpreter as well, but I w
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
処理を実行中です
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
