YJIT Benchmarks

Details for Benchmarks at 2022-01-10 19:09:59

Overall YJIT is 29.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 27.8% 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 MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 184 20 184 75 184 20 184
hexapdf 5 15 20 15 20 15
liquid-render 5 156 20 156 75 156 20 156
mail 5 136 20 136 75 136 20 136
psych-load 5 15 20 15 75 15 20 15
railsbench 5 15 20 15 75 15 20 15
binarytrees 5 85 20 85 75 85 20 85
erubi 5 54 20 54 75 54 20 54
erubi_rails 5 977 20 977 75 977 20 977
fannkuchredux 5 15 20 15 54 15 20 15
lee 5 27 20 27 75 27 20 27
nbody 5 341 20 341 75 341 20 341
optcarrot 5 15 20 15 75 15 20 15
rubykon 5 15 20 15 43 15 20 15
30k_ifelse 5 62 20 62 66 62 20 62
30k_methods 5 27 20 27 43 27 20 27
cfunc_itself 5 511 20 511 75 511 20 511
fib 5 383 20 383 75 383 20 383
getivar 5 564 20 564 75 564 20 564
keyword_args 5 438 20 438 75 438 20 438
respond_to 5 121 20 121 75 121 20 121
setivar 5 454 20 454 75 454 20 454

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) 970705 743512 185 1198 0 0% 0 0 0
hexapdf (click) 1118481 916706 599 8165 613 7% 0 0 321
liquid-render (click) 478673 380880 144 1555 95 6% 0 0 1
mail (click) 870097 648159 325 5526 124 2% 0 0 39
psych-load (click) 302865 237215 59 433 1 0% 0 0 0
railsbench (click) 2514513 1912731 1297 9325 268 2% 0 0 26
binarytrees (click) 113745 87077 10 54 0 0% 0 0 0
erubi (click) 291985 231295 9 73 0 0% 0 0 0
erubi_rails (click) 1896849 1427235 261 1973 18 0% 0 0 3
fannkuchredux (click) 127505 97775 7 184 0 0% 0 0 0
lee (click) 333649 262779 45 586 72 12% 0 0 12
nbody (click) 123025 94278 9 154 0 0% 0 0 0
optcarrot (click) 450257 399908 197 3571 20 0% 0 0 0
rubykon (click) 255889 207934 139 1532 1 0% 0 0 0
30k_ifelse (click) 5503313 4307730 9262 57800 0 0% 0 0 0
30k_methods (click) 2117969 1615863 5781 19357 0 0% 0 0 0
cfunc_itself (click) 112209 85706 7 45 0 0% 0 0 0
fib (click) 110801 85314 7 34 0 0% 0 0 0
getivar (click) 112529 87825 7 61 0 0% 0 0 0
keyword_args (click) 113233 86460 8 47 0 0% 0 0 0
respond_to (click) 114385 87160 7 60 0 0% 0 0 0
setivar (click) 113041 86678 7 34 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.