YJIT Benchmarks

Details for Benchmarks at 2022-12-01 04:10:33

Overall YJIT is 35.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 34.9% 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 5 208 5 208
hexapdf 5 15 5 15
liquid-render 5 153 5 153
mail 5 123 5 123
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 277 5 277
binarytrees 5 84 5 84
chunky_png 5 30 5 30
erubi 5 70 5 70
erubi_rails 5 1138 5 1138
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 22 5 22
nbody 5 254 5 254
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 50 5 50
30k_methods 5 20 5 20
cfunc_itself 5 477 5 477
fib 5 331 5 331
getivar 5 425 5 425
keyword_args 5 384 5 384
respond_to 5 707 5 707
setivar 5 410 5 410
str_concat 5 433 5 433

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) 2244534 2243991 25 382 6 1% 0 0 0
hexapdf (click) 1688531 1688024 820 9814 216 2% 0 0 0
liquid-render (click) 570669 568846 156 1791 33 1% 0 0 0
mail (click) 1262589 1262236 373 5074 176 3% 0 0 0
psych-load (click) 768197 766435 70 607 19 3% 0 0 0
railsbench (click) 5476861 5476750 1779 13741 482 3% 0 0 0
ruby-lsp (click) 5279796 5277702 6428 40177 1522 3% 14104 0 0
binarytrees (click) 131788 131305 16 139 4 2% 0 0 0
chunky_png (click) 800722 799106 89 1172 31 2% 0 0 0
erubi (click) 711849 709771 13 147 4 2% 0 0 0
erubi_rails (click) 4629794 4628777 329 2678 111 4% 0 0 0
etanni (click) 130731 128334 13 107 4 3% 0 0 0
fannkuchredux (click) 143687 142260 13 269 4 1% 0 0 0
lee (click) 790129 789117 79 804 25 3% 0 0 0
nbody (click) 144336 142840 15 235 6 2% 0 0 0
optcarrot (click) 540937 540605 203 4071 93 2% 0 0 0
rubykon (click) 272028 271424 146 1605 31 1% 0 0 0
30k_ifelse (click) 5281090 5280608 9268 57196 4 0% 0 0 0
30k_methods (click) 2028974 2027034 5787 19425 4 0% 0 0 0
cfunc_itself (click) 129977 128000 13 122 4 3% 0 0 0
fib (click) 128278 126684 13 111 4 3% 0 0 0
getivar (click) 130091 128068 13 138 4 2% 0 0 0
keyword_args (click) 130486 128284 14 124 4 3% 0 0 0
respond_to (click) 130206 128068 13 138 5 3% 0 0 0
setivar (click) 130511 128284 13 111 4 3% 0 0 0
str_concat (click) 129964 128000 15 137 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.