Hacker News new | ask | show | jobs
by azakai 4213 days ago
Yet in the other latency test in Octane, MandreelLatency, Firefox does about 50% better than Chrome.

Perceived performance depends on a lot of things, not just JS speed and consistency - also graphics, UI responsiveness, etc. Chrome has had an advantage in some of those areas, but the difference is pretty small at this point, especially if you are on Firefox Nightly.

1 comments

Isn't Mandreel just another Emscripten style test that avoids the garbage collector in favor of typed arrays?

I think we definitely need some GC throughput/latency benchmarks in the standard suites.

Mandreel doesn't avoid garbage as much as emscripten output does, but it does create less than "typical" JS, most likely. However, it still can create plenty of doubles as garbage on the heap, on JS engines without nanboxing, such as v8, which is a factor in why v8 loses here.