YJIT Benchmarks

Details for Benchmarks at 2024-08-20 06:08:31 UTC

YJIT metrics from the yjit-bench suite using Ruby f73d435262

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 74.4% faster than CRuby 3.4.0dev
  • 2.8% faster than YJIT 3.3.4
On railsbench it is
  • 79.6% faster than CRuby 3.4.0dev
  • the same speed as 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 48 10 49 10 117 10 117
chunky-png 10 18 10 18 10 36 10 41
erubi-rails 10 10 10 10 10 21 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 341 10 349 10 497 10 515
liquid-compile 10 344 10 342 10 502 10 501
liquid-render 10 138 10 136 10 354 10 372
lobsters 10 14 10 13 10 24 10 23
mail 10 159 10 155 10 238 10 234
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 136 10 131 10 235 10 240
ruby-lsp 10 127 10 125 10 215 10 216
sequel 10 319 10 316 10 430 10 432
binarytrees 10 51 10 48 10 118 10 105
blurhash 10 62 10 63 10 120 10 148
erubi 10 78 10 94 10 100 10 124
etanni 10 60 10 64 10 69 10 75
fannkuchredux 10 10 10 10 10 17 10 19
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 29 10 30 10 32 10 34
lee 10 11 10 12 10 19 10 21
matmul 10 10 10 10 10 15 10 18
nbody 10 203 10 213 10 421 10 512
nqueens 10 112 10 114 10 113 10 432
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 179 10 179 10 572 10 686
protoboeuf-encode 10 125 10 159 10 283 10 643
rack 10 455 10 476 10 833 10 920
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 33
tinygql 10 23 10 23 10 52 10 52
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 247 10 263 10 1108 10 1211
fib 10 100 10 102 10 616 10 617
getivar 10 214 10 228 10 1249 10 1735
keyword_args 10 90 10 88 10 730 10 946
object-new 10 230 10 215 10 308 10 275
respond_to 10 90 10 91 10 1785 10 2092
ruby-xor 10 30 10 31 10 92 10 171
setivar 10 349 10 406 10 2319 10 4871
setivar_object 10 217 10 244 10 536 10 607
setivar_young 10 216 10 246 10 528 10 602
str_concat 10 319 10 326 10 659 10 737
throw 10 969 10 880 10 1343 10 1176

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) 1362591 1172827 214 2169 0 0% 0 0 81.263343
chunky-png (click) 272574 226822 83 1054 1 0% 0 0 35.62711
erubi-rails (click) 1640397 1396540 274 2937 6 0% 0 0 102.37696
hexapdf (click) 1262272 1058599 505 11812 37 0% 0 0 410.643945
liquid-c (click) 476187 411491 119 1768 5 0% 0 0 58.406731
liquid-compile (click) 380034 323419 151 2086 2 0% 0 0 73.421774
liquid-render (click) 571472 516170 136 2323 8 0% 0 0 76.798008
lobsters (click) 7532805 6316482 3082 49706 81 0% 0 0 2236.012391
mail (click) 710135 658826 347 5554 14 0% 0 0 188.298702
psych-load (click) 241842 182841 61 594 3 0% 0 0 21.366706
railsbench (click) 2890021 2438659 1636 15968 57 0% 0 0 588.887657
rubocop (click) 5440094 4651548 2894 50973 114 0% 4 0 1926.750369
ruby-lsp (click) 788781 686742 309 4745 24 0% 0 0 159.220094
sequel (click) 434545 361359 16 116 0 0% 0 0 4.995278
binarytrees (click) 8404 7594 9 66 0 0% 0 0 2.939295
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.600207
erubi (click) 220585 195739 10 112 0 0% 0 0 4.397765
etanni (click) 24958 23898 11 92 0 0% 0 0 3.578979
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.616401
fluentd (click) 331141 292987 4 28 0 0% 0 0 1.266884
graphql (click) 388330 336188 66 650 0 0% 0 0 23.160958
graphql-native (click) 359703 312076 42 278 0 0% 0 0 10.849401
lee (click) 239090 200734 34 531 0 0% 0 0 19.361929
matmul (click) 7957 8968 7 82 0 0% 0 0 3.189626
nbody (click) 15014 19017 10 191 0 0% 0 0 6.198751
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.302359
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 119.555603
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.775779
protoboeuf-encode (click) 212046 174944 18 1189 0 0% 0 0 36.385201
rack (click) 234709 211017 37 413 0 0% 0 0 13.009715
ruby-json (click) 24237 21549 7 166 0 0% 0 0 5.443498
rubykon (click) 128223 123238 136 1480 3 0% 0 0 48.170396
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.131064
tinygql (click) 263922 239355 58 735 5 0% 0 0 24.251782
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1896.766205
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 531.65086
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.329282
fib (click) 4609 4792 7 45 0 0% 0 0 1.850669
getivar (click) 5575 6644 7 70 0 0% 0 0 2.315812
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.606898
object-new (click) 4039 4024 6 41 0 0% 0 0 1.975551
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.805632
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.942894
setivar (click) 4726 5320 7 50 0 0% 0 0 1.873735
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.938716
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.178106
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.196025
throw (click) 7538 6222 9 65 0 0% 0 0 2.626978

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.