YJIT Benchmarks

Details for Benchmarks at 2022-11-16 20:10:21

Overall YJIT is 31.4% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 37.7% 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 YJIT warmups YJIT iters
activerecord 5 205 5 205
hexapdf 5 15 5 15
liquid-render 5 171 5 171
mail 5 122 5 122
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 272 5 272
binarytrees 5 78 5 78
chunky_png 5 32 5 32
erubi 5 68 5 68
erubi_rails 5 1121 5 1121
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 21 5 21
nbody 5 234 5 234
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 50 5 50
30k_methods 5 20 5 20
cfunc_itself 5 487 5 487
fib 5 327 5 327
getivar 5 426 5 426
keyword_args 5 387 5 387
respond_to 5 699 5 699
setivar 5 359 5 359
str_concat 5 456 5 456

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) 2331896 2329820 25 375 6 1% 0 0 0
hexapdf (click) 1809265 1809174 819 10313 218 2% 0 0 0
liquid-render (click) 604963 602693 156 1843 34 1% 0 0 0
mail (click) 1350090 1348023 373 5168 176 3% 0 0 0
psych-load (click) 801304 799325 70 636 19 2% 0 0 0
railsbench (click) 5687509 5685840 1779 13933 484 3% 0 0 0
ruby-lsp (click) 5542831 5542487 6425 40582 1522 3% 12354 0 0
binarytrees (click) 135642 134004 16 137 4 2% 0 0 0
chunky_png (click) 830270 829149 89 1171 31 2% 0 0 0
erubi (click) 753570 753298 13 145 4 2% 0 0 0
erubi_rails (click) 4779313 4777405 329 2666 111 4% 0 0 0
etanni (click) 136490 134707 13 105 4 3% 0 0 0
fannkuchredux (click) 147681 147534 13 267 4 1% 0 0 0
lee (click) 838439 837267 79 802 25 3% 0 0 0
nbody (click) 150291 149264 15 246 6 2% 0 0 0
optcarrot (click) 576933 575593 203 4131 93 2% 0 0 0
rubykon (click) 279582 279155 146 1656 32 1% 0 0 0
30k_ifelse (click) 5427259 5424754 9268 57194 4 0% 0 0 0
30k_methods (click) 2088065 2087759 5787 19423 4 0% 0 0 0
cfunc_itself (click) 133540 132581 13 120 4 3% 0 0 0
fib (click) 132078 131639 13 109 4 3% 0 0 0
getivar (click) 134164 132917 13 136 4 2% 0 0 0
keyword_args (click) 134328 133148 14 122 4 3% 0 0 0
respond_to (click) 134057 132917 13 136 5 3% 0 0 0
setivar (click) 126843 125607 13 109 4 3% 0 0 0
str_concat (click) 133784 132749 15 135 6 4% 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.