YJIT Benchmarks

Details for Benchmarks at 2022-04-28 19:12:49

Overall YJIT is 33.7% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 35.6% faster than CRuby!
The basic "faster" measurement is the geomean of all "headlining" x86 benchmarks on this page.

Headlining Benchmarks

These are "headlining" because the "overall" speedup above is based on these benchmarks specifically.

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Other Benchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

MicroBenchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

Benchmark Memory Usage Details

Number of Iterations and Warmups Tested

bench No JIT warmups No JIT iters MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 189 75 189 20 189
hexapdf 5 15 20 15
liquid-render 5 158 75 158 20 158
mail 5 125 75 125 20 125
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 66 75 66 20 66
chunky_png 5 28 75 28 20 28
discourse 5 39 75 39 20 39
erubi 5 48 75 48 20 48
erubi_rails 5 997 75 997 20 997
fannkuchredux 5 15 75 15 20 15
lee 5 21 75 21 20 21
nbody 5 274 75 274 20 274
optcarrot 5 15 75 15 20 15
rubykon 5 15 27 15 20 15
30k_ifelse 5 56 75 56 20 56
30k_methods 5 22 29 22 20 22
cfunc_itself 5 426 75 426 20 426
fib 5 320 75 320 20 320
getivar 5 777 75 777 20 777
keyword_args 5 378 75 378 20 378
respond_to 5 100 75 100 20 100
setivar 5 1789 75 1789 20 1789
str_concat 5 181 75 181 20 181

Different Ruby configurations want different amounts of warmup. With no JIT, CRuby needs hardly any. YJIT and MJIT 3.0 both warm up quite quickly, while MJIT in 3.1 often slows down for a time as it compiles, after an unpredictable delay.

Benchmark YJIT Stats

Hover your cursor over the benchmark names for descriptions of each benchmark.

bench Exit Report Inline Outlined Comp iSeqs Comp Blocks Inval Inval Ratio Bind Alloc Bind Set Const Bumps
activerecord (click) 1005275 746912 131 1228 0 0% 0 0 0
hexapdf (click) 1091419 854065 682 7443 9 0% 0 0 0
liquid-render (click) 509467 390317 150 1619 2 0% 0 0 0
mail (click) 714907 536357 374 3383 15 0% 0 0 0
psych-load (click) 338715 254660 68 457 1 0% 0 0 0
railsbench (click) 2614107 1908327 1435 9784 16 0% 0 0 0
binarytrees (click) 171611 128872 13 54 0 0% 0 0 0
chunky_png (click) 368667 275664 88 903 0 0% 0 0 0
discourse (click) 5902491 4372179 3222 25443 84 0% 2 0 0
erubi (click) 321307 241803 10 79 0 0% 0 0 0
erubi_rails (click) 1925083 1384771 300 1978 4 0% 0 0 0
fannkuchredux (click) 186331 139968 10 188 0 0% 0 0 0
lee (click) 376987 282780 58 618 0 0% 0 0 0
nbody (click) 180571 135641 12 146 0 0% 0 0 0
optcarrot (click) 460379 395526 207 3017 20 0% 0 0 0
rubykon (click) 280795 220258 144 1148 0 0% 0 0 0
30k_ifelse (click) 5561435 4349594 9265 57804 0 0% 0 0 0
30k_methods (click) 2181339 1659826 5784 19391 0 0% 0 0 0
cfunc_itself (click) 170843 127899 10 49 0 0% 0 0 0
fib (click) 169307 127507 10 38 0 0% 0 0 0
getivar (click) 169179 127593 10 34 0 0% 0 0 0
keyword_args (click) 171675 128540 11 51 0 0% 0 0 0
respond_to (click) 172955 129353 10 64 0 0% 0 0 0
setivar (click) 171035 128542 10 38 0 0% 0 0 0
str_concat (click) 169563 127596 12 43 0 0% 0 0 0

YJIT stats correspond to the YJIT stats exit report.

Note: currently, all stats are collected on x86_64, not ARM.

Raw JSON data files

All graphs and table data in this page comes from processing these data files, which come from benchmark runs.