YJIT Benchmarks

Details for Benchmarks at 2021-11-28 19:09:59

Overall YJIT is 29.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 27.1% 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 5 186 20 186 75 186 20 186
hexapdf 5 15 20 15 20 15
liquid-render 5 170 20 170 75 170 20 170
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 49 20 49 75 49 20 49
erubi_rails 5 601 20 601 75 601 20 601
fannkuchredux 5 15 20 15 54 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 65 20 65 74 65 20 65
30k_methods 5 26 20 26 43 26 20 26
cfunc_itself 5 502 20 502 75 502 20 502
fib 5 384 20 384 75 384 20 384
getivar 5 563 20 563 75 563 20 563
keyword_args 5 429 20 429 75 429 20 429
respond_to 5 127 20 127 75 127 20 127
setivar 5 512 20 512 75 512 20 512

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) 971242 730066 185 1188 0 0% 0 0 0
hexapdf (click) 1076138 857425 595 7996 616 7% 0 0 321
liquid-render (click) 469879 364768 143 1437 96 6% 0 0 1
mail (click) 853098 628994 325 5241 124 2% 0 0 39
psych-load (click) 290913 225786 57 423 1 0% 0 0 0
railsbench (click) 2570530 1918463 1293 9677 263 2% 0 0 26
binarytrees (click) 112293 85408 9 48 0 0% 0 0 0
erubi (click) 269153 208860 8 35 0 0% 0 0 0
erubi_rails (click) 2398818 1724133 260 1983 16 0% 0 0 3
fannkuchredux (click) 128293 97418 6 202 0 0% 0 0 0
jekyll (click) 1887530 1499587 336 3977 179 4% 0 0 0
lee (click) 330218 256770 44 562 67 11% 0 0 12
nbody (click) 122021 92707 8 148 0 0% 0 0 0
optcarrot (click) 450853 392113 196 3566 20 0% 0 0 0
rubykon (click) 255781 205420 138 1550 1 0% 0 0 0
30k_ifelse (click) 5501797 4306060 9261 57794 0 0% 0 0 0
30k_methods (click) 2117157 1614543 5780 19351 0 0% 0 0 0
cfunc_itself (click) 111461 84386 6 39 0 0% 0 0 0
fib (click) 109669 83973 6 28 0 0% 0 0 0
getivar (click) 111397 86484 6 55 0 0% 0 0 0
keyword_args (click) 111909 84811 7 41 0 0% 0 0 0
respond_to (click) 113317 85819 6 54 0 0% 0 0 0
setivar (click) 111333 85008 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.