YJIT Benchmarks

Details for Benchmarks at 2022-11-21 04:12:26

Overall YJIT is 32.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 35.7% 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 5 204 5 204
hexapdf 5 15 5 15
liquid-render 5 179 5 179
mail 5 124 5 124
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 276 5 276
binarytrees 5 85 5 85
chunky_png 5 32 5 32
erubi 5 67 5 67
erubi_rails 5 1124 5 1124
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 22 5 22
nbody 5 232 5 232
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 50 5 50
30k_methods 5 20 5 20
cfunc_itself 5 495 5 495
fib 5 326 5 326
getivar 5 427 5 427
keyword_args 5 384 5 384
respond_to 5 702 5 702
setivar 5 362 5 362
str_concat 5 446 5 446

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) 2306273 2304679 25 388 6 1% 0 0 0
hexapdf (click) 1770978 1770135 820 10296 218 2% 0 0 0
liquid-render (click) 588259 586323 156 1828 34 1% 0 0 0
mail (click) 1330233 1329014 373 5168 176 3% 0 0 0
psych-load (click) 800941 799204 70 639 19 2% 0 0 0
railsbench (click) 5610110 5609516 1779 13894 484 3% 0 0 0
ruby-lsp (click) 5421024 5420553 6425 40524 1522 3% 14104 0 0
binarytrees (click) 127222 125888 16 139 4 2% 0 0 0
chunky_png (click) 822805 821715 89 1180 31 2% 0 0 0
erubi (click) 745506 745230 13 147 4 2% 0 0 0
erubi_rails (click) 4728216 4727034 329 2694 111 4% 0 0 0
etanni (click) 135393 133981 13 107 4 3% 0 0 0
fannkuchredux (click) 146649 144465 13 269 4 1% 0 0 0
lee (click) 826531 824400 79 804 25 3% 0 0 0
nbody (click) 148318 147793 15 248 6 2% 0 0 0
optcarrot (click) 556602 554056 203 4133 93 2% 0 0 0
rubykon (click) 272336 271517 146 1645 31 1% 0 0 0
30k_ifelse (click) 5395552 5395019 9268 57196 4 0% 0 0 0
30k_methods (click) 2094588 2092547 5787 19425 4 0% 0 0 0
cfunc_itself (click) 132545 132096 13 122 4 3% 0 0 0
fib (click) 131088 131044 13 111 4 3% 0 0 0
getivar (click) 132937 132287 13 138 4 2% 0 0 0
keyword_args (click) 125903 124731 14 124 4 3% 0 0 0
respond_to (click) 133068 132355 13 138 5 3% 0 0 0
setivar (click) 133337 132513 13 111 4 3% 0 0 0
str_concat (click) 125355 124395 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.


Far Too Many Details

These are links to HTML reports on GitHub with far, far too much detail about the benchmarking runs per-platform.


Autogenerated by continuous_reporting/generate_and_upload_reports.rb script.