YJIT Benchmarks

Details for Benchmarks at 2021-10-01 19:09:23

Overall YJIT is 23.5% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 16.2% 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 10 117 10 114 10 161
liquid-render 10 98 10 103 10 118
mail 10 115 10 117 10 126
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 41 10 68 10 56
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 13 10 15
nbody 10 173 10 331 10 264
optcarrot 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 52
30k_methods 10 10 10 10 10 16
cfunc_itself 10 221 10 329 10 490
fib 10 89 10 307 10 375
getivar 10 200 10 211 10 527
keyword_args 10 72 10 98 10 73
respond_to 10 73 10 88 10 106
setivar 10 290 10 265 10 491

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) 1085850 839333 185 1168 0 0% 0 0 0
liquid-render (click) 436244 354247 143 1206 92 7% 0 0 1
mail (click) 949274 730939 337 4947 129 2% 0 0 39
psych-load (click) 175530 139624 56 408 1 0% 0 0 0
railsbench (click) 2500465 1933246 1293 9394 255 2% 0 0 26
binarytrees (click) 107069 83422 9 49 0 0% 0 0 0
fannkuchredux (click) 122557 96653 6 203 0 0% 0 0 0
jekyll (click) 1936922 1607946 336 3728 174 4% 0 0 0
lee (click) 223402 169914 85 1043 111 10% 1 0 13
nbody (click) 116029 90906 8 149 0 0% 0 0 0
optcarrot (click) 643069 577712 286 5575 20 0% 0 0 0
30k_ifelse (click) 5554109 4883957 9261 57795 0 0% 0 0 0
30k_methods (click) 2110781 1809922 5780 19352 0 0% 0 0 0
cfunc_itself (click) 105533 81808 6 40 0 0% 0 0 0
fib (click) 103997 81434 6 29 0 0% 0 0 0
getivar (click) 105213 83881 6 56 0 0% 0 0 0
keyword_args (click) 102909 80368 7 22 0 0% 0 0 0
respond_to (click) 107197 83011 6 55 0 0% 0 0 0
setivar (click) 105597 82383 6 29 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.