YJIT Benchmarks

Details for Benchmarks at 2021-10-20 07:10:11

Overall YJIT is 27.8% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 22.2% 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 10 129 10 120 10 179
hexapdf 10 10 10 10 10 10
liquid-render 10 107 10 114 10 151
mail 10 119 10 125 10 134
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 44 10 66 10 57
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 13 10 16
nbody 10 175 10 331 10 256
optcarrot 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 10 505
fib 10 93 10 308 10 375
getivar 10 212 10 211 10 529
keyword_args 10 73 10 96 10 429
respond_to 10 78 10 89 10 112
setivar 10 272 10 259 10 459

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) 1110938 865733 185 1153 0 0% 0 0 0
hexapdf (click) 1066932 892739 604 7831 619 7% 0 0 320
liquid-render (click) 458900 375190 143 1288 94 7% 0 0 1
mail (click) 995418 769536 337 5192 129 2% 0 0 39
psych-load (click) 185066 149179 56 409 1 0% 0 0 0
railsbench (click) 2567921 2000866 1293 9611 262 2% 0 0 26
binarytrees (click) 113405 89958 9 49 0 0% 0 0 0
fannkuchredux (click) 129597 103451 6 203 0 0% 0 0 0
jekyll (click) 1960090 1631036 336 3763 173 4% 0 0 0
lee (click) 235306 181797 85 1091 114 10% 1 0 13
nbody (click) 122685 97540 8 149 0 0% 0 0 0
optcarrot (click) 459773 430104 196 3567 20 0% 0 0 0
30k_ifelse (click) 5561149 4890755 9261 57795 0 0% 0 0 0
30k_methods (click) 2117117 1816178 5780 19352 0 0% 0 0 0
cfunc_itself (click) 111997 88265 6 40 0 0% 0 0 0
fib (click) 110845 88216 6 29 0 0% 0 0 0
getivar (click) 112253 90679 6 56 0 0% 0 0 0
keyword_args (click) 112765 89021 7 42 0 0% 0 0 0
respond_to (click) 114557 90187 6 55 0 0% 0 0 0
setivar (click) 112573 89366 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.