YJIT Benchmarks

Details for Benchmarks at 2021-11-02 07:09:59

Overall YJIT is 27.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 14.1% 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 MJIT3.0 warmups MJIT3.0 iters YJIT warmups YJIT iters
activerecord 10 127 10 120 10 177
hexapdf 10 10 10 10 10 10
liquid-render 10 106 10 112 10 163
mail 10 117 10 124 10 130
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 46 10 69 10 60
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 13 10 15
nbody 10 173 10 331 10 256
optcarrot 10 10 10 10 10 10
rubykon 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 53
30k_methods 10 10 10 10 10 17
cfunc_itself 10 209 10 339 10 470
fib 10 93 10 302 10 375
getivar 10 223 10 212 10 530
keyword_args 10 77 10 97 10 421
respond_to 10 75 10 90 10 120
setivar 10 257 10 265 10 492

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) 1116442 870066 185 1160 0 0% 0 0 0
hexapdf (click) 1089460 911753 603 7981 625 7% 0 0 320
liquid-render (click) 472385 386733 143 1408 96 6% 0 0 1
mail (click) 876980 680714 339 5430 124 2% 0 0 39
psych-load (click) 187626 151327 56 409 1 0% 0 0 0
railsbench (click) 2590257 2022059 1295 9493 263 2% 0 0 26
binarytrees (click) 114730 91314 9 48 0 0% 0 0 0
fannkuchredux (click) 130794 104939 6 202 0 0% 0 0 0
jekyll (click) 2013108 1673530 336 3831 177 4% 0 0 0
lee (click) 233066 180222 85 1062 110 10% 1 0 13
nbody (click) 123562 98650 8 148 0 0% 0 0 0
optcarrot (click) 460650 431214 196 3566 20 0% 0 0 0
rubykon (click) 260202 225568 138 1550 1 0% 0 0 0
30k_ifelse (click) 5562346 4892243 9261 57794 0 0% 0 0 0
30k_methods (click) 2118890 1818060 5780 19351 0 0% 0 0 0
cfunc_itself (click) 113194 89753 6 39 0 0% 0 0 0
fib (click) 111594 89326 6 28 0 0% 0 0 0
getivar (click) 113450 92167 6 55 0 0% 0 0 0
keyword_args (click) 114026 90509 7 41 0 0% 0 0 0
respond_to (click) 115370 91297 6 54 0 0% 0 0 0
setivar (click) 113450 90476 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.