YJIT Benchmarks

Details for Benchmarks at 2022-10-11 20:10:53

Overall YJIT is 35.2% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 28.0% 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 5 187 5 187
hexapdf 5 15 5 15
liquid-render 5 175 5 175
mail 5 127 5 127
psych-load 5 15 5 15
railsbench 5 15 5 15
binarytrees 5 88 5 88
chunky_png 5 30 5 30
erubi 5 67 5 67
erubi_rails 5 980 5 980
etanni 15 15 15 15
fannkuchredux 5 15 5 15
lee 5 20 5 20
nbody 5 226 5 226
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 57 5 57
30k_methods 5 24 5 24
cfunc_itself 5 475 5 475
fib 5 323 5 323
getivar 5 467 5 467
keyword_args 5 373 5 373
respond_to 5 668 5 668
setivar 5 491 5 491
str_concat 5 409 5 409

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) 2459985 1456984 23 250 6 2% 0 0 0
hexapdf (click) 1883219 1286524 872 9510 182 1% 0 0 0
liquid-render (click) 742739 486387 154 1719 34 1% 0 0 0
mail (click) 1479315 951285 385 4957 176 3% 0 0 0
psych-load (click) 937171 601864 68 440 19 4% 0 0 0
railsbench (click) 5360657 3267260 1784 12675 475 3% 0 0 0
binarytrees (click) 313491 195886 14 70 4 5% 0 0 0
chunky_png (click) 960211 622038 87 1025 31 3% 0 0 0
erubi (click) 889235 577747 11 78 4 5% 0 0 0
erubi_rails (click) 4440145 2621826 327 2460 107 4% 0 0 0
etanni (click) 314259 195756 11 38 4 10% 0 0 0
fannkuchredux (click) 326291 205539 11 200 4 2% 0 0 0
lee (click) 974483 634603 80 746 25 3% 0 0 0
nbody (click) 331091 207151 13 179 6 3% 0 0 0
optcarrot (click) 741651 532957 201 3905 93 2% 0 0 0
rubykon (click) 468051 312382 143 1559 32 2% 0 0 0
30k_ifelse (click) 5599251 4342179 9266 57127 4 0% 0 0 0
30k_methods (click) 2274131 1724477 5785 19356 4 0% 0 0 0
cfunc_itself (click) 313747 195166 11 53 4 7% 0 0 0
fib (click) 312275 194849 11 42 4 9% 0 0 0
getivar (click) 311827 195575 11 69 4 5% 0 0 0
keyword_args (click) 311699 194379 12 55 4 7% 0 0 0
respond_to (click) 313171 195601 11 55 5 9% 0 0 0
setivar (click) 311955 194845 11 42 4 9% 0 0 0
str_concat (click) 314003 196015 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.