YJIT Benchmarks

Details for Benchmarks at 2021-09-19 07:09:33

Overall YJIT is 23.0% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 18.5% 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 10 121 10 120 10 168
liquid-render 10 96 10 110 10 125
mail 10 118 10 124 10 127
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
binarytrees 10 43 10 69 10 58
fannkuchredux 10 10 10 10 10 10
jekyll 10 10 10 10 10 10
lee 10 10 10 13 10 15
nbody 10 173 10 324 10 268
optcarrot 10 10 10 10 10 10
30k_ifelse 10 10 10 10 10 51
30k_methods 10 10 10 10 10 19
cfunc_itself 10 211 10 329 10 481
fib 10 88 10 308 10 340
getivar 10 200 10 211 10 527
respond_to 10 75 10 89 10 114
setivar 10 293 10 262 10 444

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) 1077080 821871 185 1142 0 0% 0 0 0
liquid-render (click) 439634 352938 143 1239 92 7% 0 0 1
mail (click) 907224 694315 337 4563 125 2% 0 0 39
psych-load (click) 173415 136817 56 398 1 0% 0 0 0
railsbench (click) 5186028 3079110 1292 49181 40247 81% 0 0 26
binarytrees (click) 107130 82228 9 49 0 0% 0 0 0
fannkuchredux (click) 123194 95853 6 203 0 0% 0 0 0
jekyll (click) 2344920 1744976 335 9921 6515 65% 0 0 0
lee (click) 223975 169479 85 1045 111 10% 1 0 13
nbody (click) 116474 89958 8 149 0 0% 0 0 0
optcarrot (click) 641722 575657 286 5570 20 0% 0 0 0
30k_ifelse (click) 5527354 4883270 9261 57797 0 0% 0 0 0
30k_methods (click) 2099194 1808974 5780 19352 0 0% 0 0 0
cfunc_itself (click) 105338 80572 6 40 0 0% 0 0 0
fib (click) 104058 80240 6 29 0 0% 0 0 0
getivar (click) 106298 83327 6 56 0 0% 0 0 0
respond_to (click) 107642 82116 6 55 0 0% 0 0 0
setivar (click) 105722 81295 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.