YJIT Benchmarks

Details for Benchmarks at 2022-11-24 20:10:07

Overall YJIT is 35.1% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 37.1% 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 5 210 5 210
hexapdf 5 15 5 15
liquid-render 5 154 5 154
mail 5 124 5 124
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 281 5 281
binarytrees 5 83 5 83
chunky_png 5 31 5 31
erubi 5 69 5 69
erubi_rails 5 1131 5 1131
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 21 5 21
nbody 5 251 5 251
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 50 5 50
30k_methods 5 20 5 20
cfunc_itself 5 482 5 482
fib 5 326 5 326
getivar 5 426 5 426
keyword_args 5 385 5 385
respond_to 5 703 5 703
setivar 5 422 5 422
str_concat 5 506 5 506

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) 2287962 2286729 25 393 6 1% 0 0 0
hexapdf (click) 1717829 1716011 819 9866 218 2% 0 0 0
liquid-render (click) 581731 581485 156 1809 34 1% 0 0 0
mail (click) 1311384 1311063 373 5073 176 3% 0 0 0
psych-load (click) 793172 791302 70 607 19 3% 0 0 0
railsbench (click) 5557635 5555725 1779 13761 484 3% 0 0 0
ruby-lsp (click) 5342227 5340867 6425 40145 1519 3% 14104 0 0
binarytrees (click) 126551 125338 16 139 4 2% 0 0 0
chunky_png (click) 816704 814848 89 1199 31 2% 0 0 0
erubi (click) 740613 739617 13 147 4 2% 0 0 0
erubi_rails (click) 4688851 4687311 329 2647 111 4% 0 0 0
etanni (click) 127271 125888 13 107 4 3% 0 0 0
fannkuchredux (click) 145882 143945 13 269 4 1% 0 0 0
lee (click) 816101 814589 79 804 25 3% 0 0 0
nbody (click) 146950 144656 15 235 6 2% 0 0 0
optcarrot (click) 548357 545827 203 4071 93 2% 0 0 0
rubykon (click) 276384 274529 145 1609 32 1% 0 0 0
30k_ifelse (click) 5403340 5403064 9268 57196 4 0% 0 0 0
30k_methods (click) 2086458 2084429 5787 19425 4 0% 0 0 0
cfunc_itself (click) 131837 131421 13 122 4 3% 0 0 0
fib (click) 130362 128068 13 111 4 3% 0 0 0
getivar (click) 124802 124076 13 138 4 2% 0 0 0
keyword_args (click) 132616 132071 14 124 4 3% 0 0 0
respond_to (click) 124919 124144 13 138 5 3% 0 0 0
setivar (click) 132610 132071 13 111 4 3% 0 0 0
str_concat (click) 124701 124076 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.