YJIT Benchmarks

Details for Benchmarks at 2021-11-10 19:11:23

Overall YJIT is 30.4% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 20.5% 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 MJIT3.0 warmups MJIT3.0 iters YJIT warmups YJIT iters
activerecord 10 125 10 118 10 180
hexapdf 10 10 10 10 10 10
liquid-render 10 104 10 111 10 164
mail 10 118 10 121 10 130
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 44 10 70 10 58
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 14 10 15
nbody 10 171 10 324 10 255
optcarrot 10 10 10 10 10 10
rubykon 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 52
30k_methods 10 10 10 10 10 17
cfunc_itself 10 205 10 339 10 504
fib 10 94 10 308 10 375
getivar 10 209 10 211 10 540
keyword_args 10 76 10 97 10 428
respond_to 10 77 10 90 10 122
setivar 10 293 10 265 10 461

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) 968938 678279 184 1164 0 0% 0 0 0
hexapdf (click) 1087658 812997 604 8072 647 8% 0 0 320
liquid-render (click) 467447 341077 143 1426 95 6% 0 0 1
mail (click) 872618 600871 339 5407 124 2% 0 0 39
psych-load (click) 296673 211303 57 423 1 0% 0 0 0
railsbench (click) 2591010 1800326 1295 9717 263 2% 0 0 26
binarytrees (click) 112741 80259 9 48 0 0% 0 0 0
fannkuchredux (click) 129317 92618 6 202 0 0% 0 0 0
jekyll (click) 1886634 1392372 336 3907 180 4% 0 0 0
lee (click) 344810 239379 44 566 70 12% 0 0 12
nbody (click) 122725 87443 8 148 0 0% 0 0 0
optcarrot (click) 451685 381143 196 3566 20 0% 0 0 0
rubykon (click) 255013 196966 138 1526 1 0% 0 0 0
30k_ifelse (click) 5502501 4300932 9261 57794 0 0% 0 0 0
30k_methods (click) 2117221 1609178 5780 19351 0 0% 0 0 0
cfunc_itself (click) 111909 79237 6 39 0 0% 0 0 0
fib (click) 109797 78496 6 28 0 0% 0 0 0
getivar (click) 112101 81356 6 55 0 0% 0 0 0
keyword_args (click) 112741 79878 7 41 0 0% 0 0 0
respond_to (click) 113445 80222 6 54 0 0% 0 0 0
setivar (click) 112037 79880 6 28 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.