YJIT Benchmarks

Details for Benchmarks at 2022-07-03 20:14:18

Overall YJIT is 36.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 33.0% 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 MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 190 75 190 20 190
hexapdf 5 15 20 15
liquid-render 5 157 75 157 20 157
mail 5 124 75 124 20 124
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 64 75 64 20 64
chunky_png 5 30 75 30 20 30
erubi 5 53 75 53 20 53
erubi_rails 5 981 75 981 20 981
fannkuchredux 5 15 57 15 20 15
lee 5 21 75 21 20 21
nbody 5 273 75 273 20 273
optcarrot 5 15 75 15 20 15
rubykon 5 15 34 15 20 15
30k_ifelse 5 54 75 54 20 54
30k_methods 5 22 29 22 20 22
cfunc_itself 5 447 75 447 20 447
fib 5 311 75 311 20 311
getivar 5 771 75 771 20 771
keyword_args 5 373 75 373 20 373
respond_to 5 108 75 108 20 108
setivar 5 1849 75 1849 20 1849
str_concat 5 379 75 379 20 379

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) 1029083 764323 131 1259 0 0% 0 0 0
hexapdf (click) 1123803 881709 683 7758 9 0% 0 0 0
liquid-render (click) 512347 392909 150 1637 2 0% 0 0 0
mail (click) 900827 650371 374 5322 15 0% 0 0 0
psych-load (click) 344731 258430 68 457 1 0% 0 0 0
railsbench (click) 2638875 1929323 1436 9929 16 0% 0 0 0
binarytrees (click) 173083 129563 13 58 0 0% 0 0 0
chunky_png (click) 384347 286533 88 996 0 0% 0 0 0
erubi (click) 321499 244026 10 79 0 0% 0 0 0
erubi_rails (click) 1942171 1397395 300 1974 4 0% 0 0 0
fannkuchredux (click) 186459 139852 10 188 0 0% 0 0 0
lee (click) 382235 286006 58 623 0 0% 0 0 0
nbody (click) 181915 136355 12 158 0 0% 0 0 0
optcarrot (click) 514395 442558 207 3585 20 0% 0 0 0
rubykon (click) 319259 251653 144 1549 1 0% 0 0 0
30k_ifelse (click) 5562523 4350103 9265 57804 0 0% 0 0 0
30k_methods (click) 2176987 1658101 5784 19361 0 0% 0 0 0
cfunc_itself (click) 170971 127783 10 49 0 0% 0 0 0
fib (click) 169435 127391 10 38 0 0% 0 0 0
getivar (click) 171227 129902 10 65 0 0% 0 0 0
keyword_args (click) 172827 129049 11 51 0 0% 0 0 0
respond_to (click) 173083 129237 10 64 0 0% 0 0 0
setivar (click) 171163 128426 10 38 0 0% 0 0 0
str_concat (click) 171099 128801 12 62 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.