Comment by shakna | Hacker News Reader

Comment by shakna | Hacker News Reader

Parent Full thread

It depends. In Debian's [0][1] benchmarks, JS is clearly ahead in a handful of the benchmarks, but in the rest, Lua is either on-par or faster. They're within a shout of each other.

There are some places where Lua has surprisingly poor performance. However, in almost everything else, it's one of the fastest around. Luajit is still one of the fastest JITs in existence.

In the real world, rather than constraints of a benchmark, Lua tends to be on-par from what I've seen. When you're not cold-cacheing everything, its memory use is lower. But it's standard library is ISO-C, and that's about it. No batteries. And the others beat it soundly there, whilst being close to the same performance. Which will mean they will just about always win out.

[0] https://benchmarksgame-team.pages.debian.net/benchmarksgame/...

[1] https://benchmarksgame-team.pages.debian.net/benchmarksgame/...

> a handful of the benchmarks

Now made a little easier for your comparison

https://benchmarksgame-team.pages.debian.net/benchmarksgame/...

Thanks. I calculated the geomean of the speed-up factors based on the average results (cpu secs) per benchmark. Overall, Lua 5.4.6 is factor 5.1 slower than V8 v23. Only in k-nucleotide Lua is slightly faster than V8, but in n-body Lua is even factor 26 slower.

Btw. it seems notable that Lua 5.4.6 is about 40% slower than Lua 5.4.1, see http://software.rochus-keller.ch/are-we-fast-yet_Lua_results....

Mind you its a bit unfair to compare nodejs with lua, a better example is luajit.

See https://news.ycombinator.com/item?id=42518508. LuaJIT was about factor two slower than the V8 in 2020.

Of course, it doesn't have millions of dollars thrown at it.

It's also a completely different approach. Probably additional performance could be gained by implementing JIT support for additional LuaJIT bytecodes. But we cannot predict how significant this gain would be. If the concept has limitations, more money likely doesn't change much. We can also compare with the old Mono 3 version developed by a rather small company (Xamarin, before they were bought by MS), which follows yet another approach than V8 or LuaJIT, and which achieves about the same performance as V8; see https://github.com/rochus-keller/Oberon/blob/master/testcase....

Unfortunately, the comparison pages don't actually show every test, or even the same run, as the main pages. You'll find a lot of differences between what I linked, and what is linked here.

Reply on news.ycombinator.com