YJIT Benchmarks

Details for Benchmarks at 2022-11-26 20:10:04

Overall YJIT is 33.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 35.8% 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 YJIT warmups YJIT iters
activerecord 5 213 5 213
hexapdf 5 15 5 15
liquid-render 5 155 5 155
mail 5 125 5 125
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 278 5 278
binarytrees 5 85 5 85
chunky_png 5 32 5 32
erubi 5 68 5 68
erubi_rails 5 1127 5 1127
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 22 5 22
nbody 5 244 5 244
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 50 5 50
30k_methods 5 20 5 20
cfunc_itself 5 496 5 496
fib 5 327 5 327
getivar 5 425 5 425
keyword_args 5 366 5 366
respond_to 5 688 5 688
setivar 5 385 5 385
str_concat 5 482 5 482

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) 2282287 2280380 25 376 6 1% 0 0 0
hexapdf (click) 1709606 1707825 820 9836 218 2% 0 0 0
liquid-render (click) 581598 581392 156 1804 34 1% 0 0 0
mail (click) 1315491 1313935 373 5101 176 3% 0 0 0
psych-load (click) 790799 789401 70 608 19 3% 0 0 0
railsbench (click) 5547572 5546221 1779 13664 483 3% 0 0 0
ruby-lsp (click) 5371122 5370815 6428 40280 1521 3% 14154 0 0
binarytrees (click) 134249 133123 16 139 4 2% 0 0 0
chunky_png (click) 809976 807860 89 1164 31 2% 0 0 0
erubi (click) 733804 732340 13 147 4 2% 0 0 0
erubi_rails (click) 4697331 4695708 329 2677 111 4% 0 0 0
etanni (click) 134966 133712 13 107 4 3% 0 0 0
fannkuchredux (click) 146146 144204 13 269 4 1% 0 0 0
lee (click) 813663 812684 79 804 25 3% 0 0 0
nbody (click) 143505 141839 15 203 6 2% 0 0 0
optcarrot (click) 549120 548791 203 4071 93 2% 0 0 0
rubykon (click) 277489 275348 146 1614 32 1% 0 0 0
30k_ifelse (click) 5403660 5403205 9268 57196 4 0% 0 0 0
30k_methods (click) 2086789 2084522 5787 19425 4 0% 0 0 0
cfunc_itself (click) 132151 131614 13 122 4 3% 0 0 0
fib (click) 130680 128334 13 111 4 3% 0 0 0
getivar (click) 134070 132892 13 138 4 2% 0 0 0
keyword_args (click) 125560 124538 14 124 4 3% 0 0 0
respond_to (click) 132616 132071 13 138 5 3% 0 0 0
setivar (click) 132926 132262 13 111 4 3% 0 0 0
str_concat (click) 132402 131875 15 137 6 4% 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.