YJIT Benchmarks

Details for Benchmarks at 2022-11-17 20:10:29

Overall YJIT is 30.9% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 36.1% 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 5 206 5 206
hexapdf 5 15 5 15
liquid-render 5 178 5 178
mail 5 122 5 122
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 241 5 241
binarytrees 5 81 5 81
chunky_png 5 32 5 32
erubi 5 66 5 66
erubi_rails 5 1129 5 1129
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 21 5 21
nbody 5 231 5 231
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 49 5 49
30k_methods 5 20 5 20
cfunc_itself 5 480 5 480
fib 5 327 5 327
getivar 5 426 5 426
keyword_args 5 386 5 386
respond_to 5 709 5 709
setivar 5 407 5 407
str_concat 5 424 5 424

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) 2323889 2321822 25 383 6 1% 0 0 0
hexapdf (click) 1806695 1804977 820 10296 218 2% 0 0 0
liquid-render (click) 597237 594838 156 1843 34 1% 0 0 0
mail (click) 1338909 1337576 373 5174 176 3% 0 0 0
psych-load (click) 815003 813773 70 639 19 2% 0 0 0
railsbench (click) 5684077 5683190 1779 13966 484 3% 0 0 0
ruby-lsp (click) 5539210 5537542 6425 40533 1521 3% 13954 0 0
binarytrees (click) 135848 134192 16 139 4 2% 0 0 0
chunky_png (click) 839248 838062 89 1226 31 2% 0 0 0
erubi (click) 756850 755663 13 147 4 2% 0 0 0
erubi_rails (click) 4783614 4782730 329 2693 111 4% 0 0 0
etanni (click) 136696 134895 13 107 4 3% 0 0 0
fannkuchredux (click) 147888 147627 13 269 4 1% 0 0 0
lee (click) 838680 837523 79 804 25 3% 0 0 0
nbody (click) 150498 149289 15 248 6 2% 0 0 0
optcarrot (click) 569217 567839 203 4133 93 2% 0 0 0
rubykon (click) 286950 286696 146 1654 32 1% 0 0 0
30k_ifelse (click) 5427477 5427386 9268 57196 4 0% 0 0 0
30k_methods (click) 2095813 2095684 5787 19425 4 0% 0 0 0
cfunc_itself (click) 133742 132749 13 122 4 3% 0 0 0
fib (click) 132282 131832 13 111 4 3% 0 0 0
getivar (click) 134370 133148 13 138 4 2% 0 0 0
keyword_args (click) 134534 133336 14 124 4 3% 0 0 0
respond_to (click) 126777 125526 13 138 5 3% 0 0 0
setivar (click) 134524 133336 13 111 4 3% 0 0 0
str_concat (click) 126494 125338 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.