YJIT Benchmarks

Details for Benchmarks at 2024-08-25 19:08:26 UTC

YJIT metrics from the yjit-bench suite using Ruby 76e0ea28ea

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 74.9% faster than CRuby 3.4.0dev
  • 3.4% faster than YJIT 3.3.4
On railsbench it is
  • 79.8% faster than CRuby 3.4.0dev
  • 1.3% faster than YJIT 3.3.4

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 3.3.4 warmups CRuby 3.3.4 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.4 warmups YJIT 3.3.4 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 49 10 47 10 115 10 120
chunky-png 10 18 10 18 10 36 10 39
erubi-rails 10 10 10 10 10 21 10 20
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 348 10 349 10 498 10 516
liquid-compile 10 345 10 344 10 504 10 502
liquid-render 10 138 10 134 10 357 10 374
lobsters 10 14 10 13 10 24 10 23
mail 10 159 10 156 10 231 10 228
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 130 10 235 10 239
ruby-lsp 10 127 10 124 10 209 10 217
sequel 10 318 10 319 10 438 10 432
binarytrees 10 51 10 51 10 118 10 107
blurhash 10 62 10 62 10 120 10 147
erubi 10 78 10 98 10 105 10 124
etanni 10 60 10 65 10 69 10 76
fannkuchredux 10 10 10 10 10 17 10 18
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 30 10 31 10 34 10 39
lee 10 11 10 12 10 19 10 21
matmul 10 10 10 10 10 15 10 18
nbody 10 203 10 215 10 421 10 514
nqueens 10 114 10 113 10 113 10 442
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 182 10 185 10 572 10 685
protoboeuf-encode 10 125 10 163 10 283 10 636
rack 10 455 10 471 10 838 10 885
ruby-json 10 10 10 10 10 10 10 10
rubykon 10 10 10 10 10 10 10 10
sudoku 10 10 10 10 10 28 10 32
tinygql 10 23 10 22 10 51 10 53
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 249 10 247 10 1108 10 1213
fib 10 102 10 103 10 616 10 618
getivar 10 214 10 241 10 1247 10 1748
keyword_args 10 89 10 86 10 729 10 947
object-new 10 229 10 217 10 308 10 287
respond_to 10 91 10 92 10 1787 10 2095
ruby-xor 10 30 10 24 10 92 10 165
setivar 10 348 10 360 10 2320 10 4824
setivar_object 10 216 10 227 10 536 10 518
setivar_young 10 216 10 225 10 529 10 534
str_concat 10 320 10 357 10 658 10 683
throw 10 970 10 909 10 1344 10 1211

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) 1351950 1156066 214 2169 0 0% 0 0 81.085137
chunky-png (click) 264698 253740 83 1054 1 0% 0 0 35.793406
erubi-rails (click) 1636700 1426509 275 2924 6 0% 0 0 102.657686
hexapdf (click) 1251829 1089123 505 11812 40 0% 0 0 411.294005
liquid-c (click) 454633 416692 119 1768 5 0% 0 0 58.601749
liquid-compile (click) 387181 311839 151 2082 2 0% 0 0 73.520117
liquid-render (click) 571472 516170 136 2323 8 0% 0 0 76.662952
lobsters (click) 7522605 6237531 3081 49838 81 0% 0 0 2250.195202
mail (click) 718263 674868 347 5554 14 0% 0 0 189.813617
psych-load (click) 231182 191337 61 594 3 0% 0 0 21.260822
railsbench (click) 2902919 2418700 1637 15977 57 0% 0 0 592.614854
rubocop (click) 5448357 4724880 2894 50958 114 0% 4 0 1939.137979
ruby-lsp (click) 788609 731026 309 4745 24 0% 0 0 161.01337
sequel (click) 430024 352782 16 116 0 0% 0 0 4.952206
binarytrees (click) 8404 7594 9 66 0 0% 0 0 3.004639
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.672577
erubi (click) 209467 187238 10 112 0 0% 0 0 4.531262
etanni (click) 28405 26890 11 91 0 0% 0 0 3.484218
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.730161
fluentd (click) 324356 293594 4 28 0 0% 0 0 1.341128
graphql (click) 382139 345394 66 650 0 0% 0 0 22.754158
graphql-native (click) 361439 329233 41 273 0 0% 0 0 10.483795
lee (click) 249524 210620 34 531 0 0% 0 0 19.501345
matmul (click) 7957 8968 7 82 0 0% 0 0 3.215354
nbody (click) 15014 19017 10 191 0 0% 0 0 6.208411
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.36824
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 118.891671
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.560193
protoboeuf-encode (click) 212046 174944 18 1189 0 0% 0 0 36.659946
rack (click) 230316 215840 37 445 0 0% 0 0 14.57293
ruby-json (click) 24237 21549 7 166 0 0% 0 0 5.506444
rubykon (click) 128223 123238 136 1480 3 0% 0 0 48.467239
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.166271
tinygql (click) 241266 210631 58 735 5 0% 0 0 24.142772
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1937.687422
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 533.39054
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.321453
fib (click) 4609 4792 7 45 0 0% 0 0 1.841989
getivar (click) 5575 6644 7 70 0 0% 0 0 2.398389
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.636718
object-new (click) 4039 4024 6 41 0 0% 0 0 1.976268
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.871145
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.944128
setivar (click) 4726 5320 7 50 0 0% 0 0 1.907699
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.944072
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.188635
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.234632
throw (click) 7538 6222 9 65 0 0% 0 0 2.688767

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.