YJIT Benchmarks

Details for Benchmarks at 2021-09-30 19:11:50

Overall YJIT is 26.1% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 20.3% 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 10 116 10 117 10 168
liquid-render 10 103 10 109 10 136
mail 10 118 10 120 10 132
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 42 10 69 10 56
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 10 264
optcarrot 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 51
30k_methods 10 10 10 10 10 17
cfunc_itself 10 221 10 337 10 490
fib 10 90 10 308 10 375
getivar 10 193 10 211 10 527
keyword_args 10 71 10 98 10 73
respond_to 10 73 10 90 10 105
setivar 10 290 10 265 10 490

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) 1083226 837598 185 1147 0 0% 0 0 0
liquid-render (click) 438996 356312 143 1240 92 7% 0 0 1
mail (click) 953370 733347 337 4975 129 2% 0 0 39
psych-load (click) 174954 139230 56 408 1 0% 0 0 0
railsbench (click) 2496369 1930536 1293 9363 255 2% 0 0 26
binarytrees (click) 107069 83422 9 49 0 0% 0 0 0
fannkuchredux (click) 123133 97047 6 203 0 0% 0 0 0
jekyll (click) 1936602 1607031 336 3728 174 4% 0 0 0
lee (click) 223530 170062 85 1043 111 10% 1 0 13
nbody (click) 115901 90758 8 149 0 0% 0 0 0
optcarrot (click) 643261 577913 286 5575 20 0% 0 0 0
30k_ifelse (click) 5554301 4884105 9261 57795 0 0% 0 0 0
30k_methods (click) 2110653 1809774 5780 19352 0 0% 0 0 0
cfunc_itself (click) 104957 81467 6 40 0 0% 0 0 0
fib (click) 103549 81188 6 29 0 0% 0 0 0
getivar (click) 105405 84029 6 56 0 0% 0 0 0
keyword_args (click) 102973 80368 7 22 0 0% 0 0 0
respond_to (click) 107197 83011 6 55 0 0% 0 0 0
setivar (click) 105213 82190 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.