YJIT Benchmarks

Details for Benchmarks at 2022-10-14 20:10:39

Overall YJIT is 38.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 29.9% 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 5 203 5 203
hexapdf 5 15 5 15
liquid-render 5 177 5 177
mail 5 127 5 127
psych-load 5 15 5 15
railsbench 5 15 5 15
binarytrees 5 86 5 86
chunky_png 5 31 5 31
erubi 5 67 5 67
erubi_rails 5 1066 5 1066
etanni 5 41 5 41
fannkuchredux 5 15 5 15
lee 5 21 5 21
nbody 5 244 5 244
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 56 5 56
30k_methods 5 24 5 24
cfunc_itself 5 484 5 484
fib 5 326 5 326
getivar 5 426 5 426
keyword_args 5 387 5 387
respond_to 5 716 5 716
setivar 5 425 5 425
str_concat 5 407 5 407

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) 2497041 1483480 23 280 6 2% 0 0 0
hexapdf (click) 1907603 1302381 818 9621 189 1% 0 0 0
liquid-render (click) 745363 488475 154 1737 34 1% 0 0 0
mail (click) 1484371 954292 371 4919 176 3% 0 0 0
psych-load (click) 951379 611919 68 490 19 3% 0 0 0
railsbench (click) 5421777 3314211 1777 12862 475 3% 0 0 0
binarytrees (click) 313107 194979 14 70 4 5% 0 0 0
chunky_png (click) 971923 630448 87 1032 31 3% 0 0 0
erubi (click) 899475 583871 11 78 4 5% 0 0 0
erubi_rails (click) 4492241 2661981 327 2466 107 4% 0 0 0
etanni (click) 318483 197774 11 38 4 10% 0 0 0
fannkuchredux (click) 330003 206998 11 200 4 2% 0 0 0
lee (click) 983315 639940 77 746 25 3% 0 0 0
nbody (click) 332179 207429 13 179 6 3% 0 0 0
optcarrot (click) 759443 545436 201 4001 93 2% 0 0 0
rubykon (click) 467347 311544 143 1561 32 2% 0 0 0
30k_ifelse (click) 5603155 4343885 9266 57127 4 0% 0 0 0
30k_methods (click) 2277011 1726096 5785 19356 4 0% 0 0 0
cfunc_itself (click) 315155 195756 11 53 4 7% 0 0 0
fib (click) 315155 196468 11 42 4 9% 0 0 0
getivar (click) 316947 198028 11 69 4 5% 0 0 0
keyword_args (click) 315603 196085 12 55 4 7% 0 0 0
respond_to (click) 314195 195879 11 55 5 9% 0 0 0
setivar (click) 317075 197298 11 42 4 9% 0 0 0
str_concat (click) 312595 195021 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.