YJIT Benchmarks

Details for Benchmarks at 2022-05-31 20:02:52

Overall YJIT is 31.7% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 27.1% 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 5 190 75 190 20 190
hexapdf 5 15 20 15
liquid-render 5 130 75 130 20 130
mail 5 108 75 108 20 108
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 67 75 67 20 67
chunky_png 5 29 75 29 20 29
discourse 5 32 75 32 20 32
erubi 5 49 75 49 20 49
erubi_rails 5 804 75 804 20 804
fannkuchredux 5 15 74 15 20 15
lee 5 22 75 22 20 22
nbody 5 275 75 275 20 275
optcarrot 5 15 75 15 20 15
rubykon 5 15 26 15 20 15
30k_ifelse 5 55 75 55 20 55
30k_methods 5 22 29 22 20 22
cfunc_itself 5 441 75 441 20 441
fib 5 320 75 320 20 320
getivar 5 758 75 758 20 758
keyword_args 5 378 75 378 20 378
respond_to 5 111 75 111 20 111
setivar 5 1859 75 1859 20 1859
str_concat 5 195 75 195 20 195

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) 1013019 752999 131 1241 0 0% 0 0 0
hexapdf (click) 1119643 878303 682 7744 9 0% 0 0 0
liquid-render (click) 509915 390573 150 1606 2 0% 0 0 0
mail (click) 898267 649181 374 5386 15 0% 0 0 0
psych-load (click) 339419 254774 68 457 1 0% 0 0 0
railsbench (click) 2637787 1927031 1436 9824 16 0% 0 0 0
binarytrees (click) 173915 130095 13 58 0 0% 0 0 0
chunky_png (click) 383835 285839 88 1033 0 0% 0 0 0
discourse (click) 5883419 4366874 3162 24965 82 0% 2 0 0
erubi (click) 317403 241400 10 79 0 0% 0 0 0
erubi_rails (click) 1951387 1403848 300 2012 4 0% 0 0 0
fannkuchredux (click) 187931 140793 10 188 0 0% 0 0 0
lee (click) 377947 283302 58 622 0 0% 0 0 0
nbody (click) 183387 137296 12 158 0 0% 0 0 0
optcarrot (click) 514587 442545 207 3571 20 0% 0 0 0
rubykon (click) 319515 251988 144 1540 1 0% 0 0 0
30k_ifelse (click) 5563291 4350797 9265 57804 0 0% 0 0 0
30k_methods (click) 2178459 1659259 5784 19361 0 0% 0 0 0
cfunc_itself (click) 172443 128724 10 49 0 0% 0 0 0
fib (click) 170907 128332 10 38 0 0% 0 0 0
getivar (click) 173019 131221 10 65 0 0% 0 0 0
keyword_args (click) 173275 129365 11 51 0 0% 0 0 0
respond_to (click) 173211 129317 10 64 0 0% 0 0 0
setivar (click) 172635 129367 10 38 0 0% 0 0 0
str_concat (click) 172955 130065 12 62 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.