YJIT Benchmarks

Details for Benchmarks at 2022-04-29 07:13:52

Overall YJIT is 33.5% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 31.7% 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 MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 190 75 190 20 190
hexapdf 5 15 20 15
liquid-render 5 158 75 158 20 158
mail 5 125 75 125 20 125
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 64 75 64 20 64
chunky_png 5 28 75 28 20 28
discourse 5 41 75 41 20 41
erubi 5 47 75 47 20 47
erubi_rails 5 994 75 994 20 994
fannkuchredux 5 15 73 15 20 15
lee 5 21 75 21 20 21
nbody 5 274 75 274 20 274
optcarrot 5 15 75 15 20 15
rubykon 5 15 28 15 20 15
30k_ifelse 5 56 75 56 20 56
30k_methods 5 22 29 22 20 22
cfunc_itself 5 442 75 442 20 442
fib 5 318 75 318 20 318
getivar 5 769 75 769 20 769
keyword_args 5 373 75 373 20 373
respond_to 5 100 75 100 20 100
setivar 5 1845 75 1845 20 1845
str_concat 5 201 75 201 20 201

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) 1009243 749378 131 1251 0 0% 0 0 0
hexapdf (click) 1092507 855341 682 7460 10 0% 0 0 0
liquid-render (click) 508763 389899 150 1613 2 0% 0 0 0
mail (click) 727771 547660 374 3517 15 0% 0 0 0
psych-load (click) 338139 254331 68 457 1 0% 0 0 0
railsbench (click) 2615195 1908796 1435 9792 16 0% 0 0 0
binarytrees (click) 171611 128872 13 54 0 0% 0 0 0
chunky_png (click) 370971 277147 88 929 0 0% 0 0 0
discourse (click) 5870683 4351325 3196 25168 83 0% 2 0 0
erubi (click) 321563 242231 10 79 0 0% 0 0 0
erubi_rails (click) 1924443 1384305 300 1974 4 0% 0 0 0
fannkuchredux (click) 186331 139968 10 188 0 0% 0 0 0
lee (click) 376987 282755 58 618 0 0% 0 0 0
nbody (click) 180507 135641 12 146 0 0% 0 0 0
optcarrot (click) 460315 395526 207 3017 20 0% 0 0 0
rubykon (click) 282331 221416 144 1163 0 0% 0 0 0
30k_ifelse (click) 5561307 4349594 9265 57804 0 0% 0 0 0
30k_methods (click) 2178395 1658764 5784 19373 0 0% 0 0 0
cfunc_itself (click) 170779 127764 10 49 0 0% 0 0 0
fib (click) 169243 127507 10 38 0 0% 0 0 0
getivar (click) 168667 127129 10 34 0 0% 0 0 0
keyword_args (click) 171611 128540 11 51 0 0% 0 0 0
respond_to (click) 172891 129353 10 64 0 0% 0 0 0
setivar (click) 170971 128542 10 38 0 0% 0 0 0
str_concat (click) 169563 127596 12 43 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.