YJIT Benchmarks

Details for Benchmarks at 2021-11-08 19:16:12

Overall YJIT is 31.8% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 28.2% 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 YJIT warmups YJIT iters
activerecord 10 122 10 115 10 179
hexapdf 10 10 10 10 10 10
liquid-render 10 107 10 112 10 164
mail 10 118 10 122 10 126
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 46 10 69 10 61
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 14 10 15
nbody 10 170 10 331 10 264
optcarrot 10 10 10 10 10 10
rubykon 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 52
30k_methods 10 10 10 10 10 17
cfunc_itself 10 214 10 324 10 498
fib 10 95 10 308 10 374
getivar 10 220 10 211 10 541
keyword_args 10 75 10 97 10 427
respond_to 10 76 10 90 10 113
setivar 10 281 10 256 10 498

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) 969258 678799 184 1169 0 0% 0 0 0
hexapdf (click) 1087402 812976 604 8071 647 8% 0 0 320
liquid-render (click) 466807 340804 143 1415 95 6% 0 0 1
mail (click) 871210 600394 339 5401 124 2% 0 0 39
psych-load (click) 296545 211258 57 423 1 0% 0 0 0
railsbench (click) 2589154 1799042 1295 9705 263 2% 0 0 26
binarytrees (click) 113317 80608 9 48 0 0% 0 0 0
fannkuchredux (click) 129253 92593 6 202 0 0% 0 0 0
jekyll (click) 1889578 1393809 336 3956 179 4% 0 0 0
lee (click) 345194 239795 44 566 70 12% 0 0 12
nbody (click) 122661 87555 8 148 0 0% 0 0 0
optcarrot (click) 451685 381143 196 3566 20 0% 0 0 0
rubykon (click) 255909 197814 139 1534 1 0% 0 0 0
30k_ifelse (click) 5502437 4300932 9261 57794 0 0% 0 0 0
30k_methods (click) 2117605 1609394 5780 19351 0 0% 0 0 0
cfunc_itself (click) 111909 79237 6 39 0 0% 0 0 0
fib (click) 110309 78845 6 28 0 0% 0 0 0
getivar (click) 112037 81356 6 55 0 0% 0 0 0
keyword_args (click) 112677 79878 7 41 0 0% 0 0 0
respond_to (click) 113957 80683 6 54 0 0% 0 0 0
setivar (click) 111973 79992 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.