YJIT Benchmarks

Details for Benchmarks at 2024-02-22 06:08:14 UTC

YJIT metrics from the yjit-bench suite using Ruby 7acc8bbea5

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 69.5% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.1% 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 30 514 30 514
chunky-png 30 32 30 32
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 351 30 351
liquid-compile 30 344 30 344
liquid-render 30 251 30 251
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 184 30 184
ruby-lsp 30 186 30 186
sequel 30 290 30 290
binarytrees 30 85 30 85
blurhash 30 101 30 101
erubi 30 77 30 77
etanni 30 52 30 52
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 30 331 30 331
nqueens 30 295 30 295
optcarrot 30 15 30 15
rack 30 177 30 177
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 25 30 25
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 30 940 30 940
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 99 30 99
setivar 30 2393 30 2393
setivar_object 30 492 30 492
setivar_young 30 507 30 507
str_concat 30 414 30 414
throw 30 808 30 808

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) 890594 774820 49 569 0 0% 0 0 16.165069
chunky-png (click) 336858 293597 87 1092 1 0% 0 0 31.593837
erubi-rails (click) 1720690 1435006 281 2926 6 0% 0 0 83.051282
hexapdf (click) 1416772 1191435 596 12588 37 0% 0 0 363.386978
liquid-c (click) 523305 458654 120 1753 5 0% 0 0 47.637837
liquid-compile (click) 440710 395449 151 2062 2 0% 0 0 61.096142
liquid-render (click) 617891 554755 144 2272 8 0% 0 0 62.71541
lobsters (click) 7895615 6576199 3219 50084 73 0% 0 0 1687.575463
mail (click) 733538 631695 346 4858 14 0% 0 0 141.152968
psych-load (click) 299787 255776 65 649 3 0% 0 0 19.518674
railsbench (click) 3014388 2639971 1643 15648 54 0% 0 0 447.004203
rubocop (click) 5360312 4570593 2902 47736 106 0% 4 0 1404.977085
ruby-lsp (click) 638918 557701 159 2793 14 0% 0 0 76.948907
sequel (click) 500069 434617 16 116 0 0% 0 0 4.167951
binarytrees (click) 9392 7588 11 75 0 0% 0 0 2.905259
blurhash (click) 52098 47218 32 461 0 0% 0 0 15.166205
erubi (click) 271442 225424 10 111 0 0% 0 0 3.837373
etanni (click) 31710 27867 12 96 0 0% 0 0 3.203352
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.781546
fluentd (click) 389833 323832 11 111 0 0% 0 0 3.557578
graphql (click) 443389 385315 70 673 0 0% 0 0 20.52239
graphql-native (click) 408976 346647 41 271 0 0% 0 0 9.131879
lee (click) 316051 280725 49 731 0 0% 0 0 22.524226
matmul (click) 12586 12175 12 126 0 0% 0 0 4.154223
nbody (click) 15103 7574 11 185 0 0% 0 0 4.94942
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.788995
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 102.62067
rack (click) 273643 239300 31 341 0 0% 0 0 9.544508
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.754592
rubykon (click) 133999 114902 143 1500 3 0% 0 0 41.466497
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.282752
tinygql (click) 313412 269044 63 788 5 0% 0 0 22.539668
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1455.240432
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 515.483742
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.199564
fib (click) 5017 4633 8 49 0 0% 0 0 1.753999
getivar (click) 6102 6023 8 74 0 0% 0 0 2.14166
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.490783
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.624418
ruby-xor (click) 8142 7087 9 87 0 0% 0 0 3.019328
setivar (click) 5193 4604 8 54 0 0% 0 0 1.730691
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.832383
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.023792
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.776339
throw (click) 7946 6065 10 69 0 0% 0 0 2.440975

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.