YJIT Benchmarks

Details for Benchmarks at 2021-10-07 07:10:05

Overall YJIT is 24.7% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 20.8% 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 10 123 10 117 10 178
hexapdf 10 10 10 10 10 10
liquid-render 10 108 10 113 10 129
mail 10 123 10 124 10 138
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 44 10 69 10 59
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 13 10 15
nbody 10 172 10 331 10 262
optcarrot 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 53
30k_methods 10 10 10 10 10 17
cfunc_itself 10 214 10 336 10 487
fib 10 89 10 307 10 375
getivar 10 223 10 211 10 530
keyword_args 10 77 10 96 10 74
respond_to 10 77 10 90 10 107
setivar 10 293 10 265 10 458

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) 1111386 864607 185 1158 0 0% 0 0 0
hexapdf (click) 974017 812748 602 7852 675 8% 0 0 320
liquid-render (click) 452692 369339 143 1224 94 7% 0 0 1
mail (click) 987546 763418 337 5188 129 2% 0 0 39
psych-load (click) 184938 148953 56 408 1 0% 0 0 0
railsbench (click) 2560497 1992613 1293 9525 262 2% 0 0 26
binarytrees (click) 113085 89467 9 49 0 0% 0 0 0
fannkuchredux (click) 128957 102944 6 203 0 0% 0 0 0
jekyll (click) 1957274 1626330 336 3737 173 4% 0 0 0
lee (click) 234602 180481 85 1083 114 10% 1 0 13
nbody (click) 122813 97443 8 149 0 0% 0 0 0
optcarrot (click) 649277 583958 286 5575 20 0% 0 0 0
30k_ifelse (click) 5561085 4890642 9261 57795 0 0% 0 0 0
30k_methods (click) 2117053 1816065 5780 19352 0 0% 0 0 0
cfunc_itself (click) 111357 87758 6 40 0 0% 0 0 0
fib (click) 109821 87331 6 29 0 0% 0 0 0
getivar (click) 112189 90566 6 56 0 0% 0 0 0
keyword_args (click) 109373 86659 7 22 0 0% 0 0 0
respond_to (click) 114493 89889 6 55 0 0% 0 0 0
setivar (click) 111741 88629 6 29 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.