YJIT Benchmarks

Details for Benchmarks at 2024-03-01 19:08:14 UTC

YJIT metrics from the yjit-bench suite using Ruby 6f31dd495c

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 70.4% faster than CRuby 3.4.0dev
On railsbench it is
  • 78.6% faster than CRuby 3.4.0dev

Performance on Headline Benchmarks

Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on Headline Benchmarks

Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Performance on Other Benchmarks

Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on Other Benchmarks

Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Performance on MicroBenchmarks

Speed of each Ruby implementation relative to the baseline CRuby measurement. Higher is better.

Memory Usage on MicroBenchmarks

Memory usage of each Ruby implementation relative to the baseline CRuby measurement. Lower is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

Benchmark Memory Usage Details

Number of Iterations and Warmups Tested

bench CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 30 512 30 512
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 352 30 352
liquid-compile 30 342 30 342
liquid-render 30 252 30 252
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 180 30 180
ruby-lsp 30 181 30 181
sequel 30 289 30 289
binarytrees 30 87 30 87
blurhash 30 101 30 101
erubi 30 77 30 77
etanni 30 51 30 51
fannkuchredux 30 23 30 23
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 22 30 22
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 330 30 330
nqueens 30 297 30 297
optcarrot 30 15 30 15
rack 30 180 30 180
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 24 30 24
tinygql 30 41 30 41
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 417 30 417
getivar 30 943 30 943
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 105 30 105
setivar 30 2391 30 2391
setivar_object 30 488 30 488
setivar_young 30 505 30 505
str_concat 30 403 30 403
throw 30 747 30 747

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 Compile Time MS
activerecord (click) 884206 758777 49 526 0 0% 0 0 15.499605
chunky-png (click) 337170 299401 87 1096 1 0% 0 0 32.692164
erubi-rails (click) 1715273 1452682 279 2989 6 0% 0 0 85.146733
hexapdf (click) 1418729 1251614 595 12574 38 0% 0 0 370.609333
liquid-c (click) 524945 456571 119 1751 5 0% 0 0 47.343921
liquid-compile (click) 447877 390531 151 2074 2 0% 0 0 62.836443
liquid-render (click) 623835 541382 136 2284 8 0% 0 0 62.692495
lobsters (click) 7880779 6636320 3217 50018 73 0% 0 0 1710.691637
mail (click) 732395 635986 346 4847 14 0% 0 0 142.961851
psych-load (click) 301215 253619 65 655 3 0% 0 0 20.542999
railsbench (click) 2998969 2574670 1638 15780 54 0% 0 0 455.104221
rubocop (click) 5368258 4595062 2901 47784 106 0% 4 0 1423.84714
ruby-lsp (click) 634011 541609 159 2735 14 0% 0 0 76.626664
sequel (click) 494350 426154 16 119 0 0% 0 0 4.412072
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.125713
blurhash (click) 52000 47236 32 461 0 0% 0 0 15.44346
erubi (click) 271214 230596 10 111 0 0% 0 0 3.85564
etanni (click) 31686 27819 12 96 0 0% 0 0 3.225965
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.900444
fluentd (click) 387873 311831 11 111 0 0% 0 0 3.594864
graphql (click) 443736 382893 70 673 0 0% 0 0 21.011515
graphql-native (click) 409288 344342 41 271 0 0% 0 0 9.237092
lee (click) 315883 277753 49 731 0 0% 0 0 22.961585
matmul (click) 12586 12175 12 126 0 0% 0 0 4.214615
nbody (click) 15103 7574 11 185 0 0% 0 0 5.013624
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.804922
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 105.07775
rack (click) 272794 235029 31 325 0 0% 0 0 9.517771
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.860886
rubykon (click) 133999 114882 143 1500 3 0% 0 0 42.23257
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.556196
tinygql (click) 313012 266151 63 788 5 0% 0 0 22.935159
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1482.502473
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 524.100994
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.246255
fib (click) 5017 4633 8 49 0 0% 0 0 1.785487
getivar (click) 6102 6023 8 74 0 0% 0 0 2.200492
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.544813
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.671751
ruby-xor (click) 7940 7126 9 87 0 0% 0 0 3.128197
setivar (click) 5193 4604 8 54 0 0% 0 0 1.750748
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.844521
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.065864
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.911767
throw (click) 7946 6065 10 69 0 0% 0 0 2.468894

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.