YJIT Benchmarks

Details for Benchmarks at 2021-12-23 19:11:11

Overall YJIT is 32.7% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 36.3% 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 MJIT3.0 warmups MJIT3.0 iters MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 181 20 181 75 181 20 181
hexapdf 5 15 20 15 20 15
liquid-render 5 174 20 174 75 174 20 174
mail 5 139 20 139 75 139 20 139
psych-load 5 15 20 15 75 15 20 15
railsbench 5 15 20 15 75 15 20 15
binarytrees 5 88 20 88 75 88 20 88
erubi 5 51 20 51 75 51 20 51
erubi_rails 5 576 20 576 75 576 20 576
fannkuchredux 5 15 20 15 55 15 20 15
jekyll 5 15 20 15 36 15 20 15
lee 5 26 20 26 75 26 20 26
nbody 5 343 20 343 75 343 20 343
optcarrot 5 15 20 15 75 15 20 15
rubykon 5 15 20 15 43 15 20 15
30k_ifelse 5 62 20 62 65 62 20 62
30k_methods 5 26 20 26 44 26 20 26
cfunc_itself 5 508 20 508 75 508 20 508
fib 5 383 20 383 75 383 20 383
getivar 5 563 20 563 75 563 20 563
keyword_args 5 416 20 416 75 416 20 416
respond_to 5 121 20 121 75 121 20 121
setivar 5 478 20 478 75 478 20 478

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) 974826 743573 185 1193 0 0% 0 0 0
hexapdf (click) 1120362 914745 599 8109 620 7% 0 0 321
liquid-render (click) 466359 368906 143 1419 95 6% 0 0 1
mail (click) 847850 629876 325 5231 124 2% 0 0 39
psych-load (click) 298465 234475 57 440 1 0% 0 0 0
railsbench (click) 2514530 1901321 1295 9284 266 2% 0 0 26
binarytrees (click) 113253 86834 9 48 0 0% 0 0 0
erubi (click) 276065 216938 8 35 0 0% 0 0 0
erubi_rails (click) 2414498 1747662 260 1993 16 0% 0 0 3
fannkuchredux (click) 128869 98628 6 202 0 0% 0 0 0
jekyll (click) 1849002 1485831 338 3761 185 4% 0 0 0
lee (click) 334817 263366 43 557 66 11% 0 0 12
nbody (click) 122661 94035 8 148 0 0% 0 0 0
optcarrot (click) 451877 399847 196 3566 20 0% 0 0 0
rubykon (click) 255013 207408 138 1531 1 0% 0 0 0
30k_ifelse (click) 5502309 4307158 9261 57794 0 0% 0 0 0
30k_methods (click) 2117477 1615620 5780 19351 0 0% 0 0 0
cfunc_itself (click) 111781 85463 6 39 0 0% 0 0 0
fib (click) 110245 85071 6 28 0 0% 0 0 0
getivar (click) 112037 87582 6 55 0 0% 0 0 0
keyword_args (click) 112613 86104 7 41 0 0% 0 0 0
respond_to (click) 113957 86917 6 54 0 0% 0 0 0
setivar (click) 111589 85890 6 28 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.