YJIT Benchmarks

Details for Benchmarks at 2022-10-05 20:10:39

Overall YJIT is 34.4% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 31.3% 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 YJIT warmups YJIT iters
activerecord 5 196 20 196
hexapdf 5 15 20 15
liquid-render 5 171 20 171
mail 5 129 20 129
psych-load 5 15 20 15
railsbench 5 15 20 15
binarytrees 5 84 20 84
chunky_png 5 29 20 29
erubi 5 67 20 67
erubi_rails 5 1053 20 1053
fannkuchredux 5 15 20 15
lee 5 20 20 20
nbody 5 262 20 262
optcarrot 5 15 20 15
rubykon 5 15 20 15
30k_ifelse 5 55 20 55
30k_methods 5 25 20 25
cfunc_itself 5 428 20 428
fib 5 313 20 313
getivar 5 467 20 467
keyword_args 5 359 20 359
respond_to 5 632 20 632
setivar 5 490 20 490
str_concat 5 492 20 492

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) 2479249 1541491 23 265 6 2% 0 0 0
hexapdf (click) 1885843 1383816 872 9370 181 1% 0 0 0
liquid-render (click) 749139 518218 154 1661 34 2% 0 0 0
mail (click) 1474131 988667 385 4880 174 3% 0 0 0
psych-load (click) 938771 627550 68 434 18 4% 0 0 0
railsbench (click) 5391889 3446330 1784 12528 470 3% 0 0 0
binarytrees (click) 318163 203226 14 70 4 5% 0 0 0
chunky_png (click) 946515 638244 87 1047 31 2% 0 0 0
erubi (click) 886931 598234 11 76 4 5% 0 0 0
erubi_rails (click) 4477393 2771066 327 2431 104 4% 0 0 0
fannkuchredux (click) 327123 210333 11 200 4 2% 0 0 0
lee (click) 971347 657920 80 744 25 3% 0 0 0
nbody (click) 329427 213015 13 179 6 3% 0 0 0
optcarrot (click) 752787 591545 201 3773 93 2% 0 0 0
rubykon (click) 475731 334750 143 1572 32 2% 0 0 0
30k_ifelse (click) 5624979 4414714 9266 57127 4 0% 0 0 0
30k_methods (click) 2275987 1730454 5785 19356 4 0% 0 0 0
cfunc_itself (click) 316115 201407 11 53 4 7% 0 0 0
fib (click) 309971 198133 11 42 4 9% 0 0 0
getivar (click) 317011 203612 11 69 4 5% 0 0 0
keyword_args (click) 316883 202048 12 55 4 7% 0 0 0
respond_to (click) 314963 201513 11 55 5 9% 0 0 0
setivar (click) 312211 199275 11 42 4 9% 0 0 0
str_concat (click) 315859 201927 13 68 6 8% 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.