YJIT Benchmarks

Details for Benchmarks at 2022-01-17 19:12:04

Overall YJIT is 32.1% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 28.8% 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 5 184 20 184 75 184 20 184
hexapdf 5 15 20 15 20 15
liquid-render 5 182 20 182 75 182 20 182
mail 5 144 20 144 75 144 20 144
psych-load 5 15 20 15 75 15 20 15
railsbench 5 15 20 15 75 15 20 15
binarytrees 5 85 20 85 75 85 20 85
erubi 5 56 20 56 75 56 20 56
erubi_rails 5 1000 20 1000 75 1000 20 1000
fannkuchredux 5 15 20 15 75 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 44 15 20 15
30k_ifelse 5 65 20 65 68 65 20 65
30k_methods 5 27 20 27 43 27 20 27
cfunc_itself 5 507 20 507 75 507 20 507
fib 5 383 20 383 75 383 20 383
getivar 5 965 20 965 75 965 20 965
keyword_args 5 446 20 446 75 446 20 446
respond_to 5 127 20 127 75 127 20 127
setivar 5 2216 20 2216 75 2216 20 2216

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) 965841 740438 185 1198 0 0% 0 0 0
hexapdf (click) 1095121 897149 599 8171 614 7% 0 0 321
liquid-render (click) 478289 380523 143 1572 95 6% 0 0 1
mail (click) 860369 643861 325 5342 124 2% 0 0 39
psych-load (click) 297745 234717 58 445 1 0% 0 0 0
railsbench (click) 2503697 1906971 1297 9255 268 2% 0 0 26
binarytrees (click) 112465 86374 10 54 0 0% 0 0 0
erubi (click) 294673 234301 9 73 0 0% 0 0 0
erubi_rails (click) 1887505 1421217 261 1889 18 0% 0 0 3
fannkuchredux (click) 126225 97072 7 184 0 0% 0 0 0
lee (click) 336977 265264 45 586 72 12% 0 0 12
nbody (click) 121745 93575 9 154 0 0% 0 0 0
optcarrot (click) 448977 399205 197 3571 20 0% 0 0 0
rubykon (click) 253713 206764 140 1529 1 0% 0 0 0
30k_ifelse (click) 5501521 4306698 9262 57800 0 0% 0 0 0
30k_methods (click) 2116689 1615160 5781 19357 0 0% 0 0 0
cfunc_itself (click) 110929 85003 7 45 0 0% 0 0 0
fib (click) 109521 84611 7 34 0 0% 0 0 0
getivar (click) 111249 87122 7 61 0 0% 0 0 0
keyword_args (click) 111825 85644 8 47 0 0% 0 0 0
respond_to (click) 113105 86457 7 60 0 0% 0 0 0
setivar (click) 111249 85646 7 34 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.