YJIT Benchmarks

Details for Benchmarks at 2024-09-30 04:00:18 UTC

YJIT metrics from the yjit-bench suite using Ruby 3fe59b04d6

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.1% faster than CRuby 3.4.0dev
  • 5.1% faster than YJIT 3.3.4
On railsbench it is
  • 75.4% 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 58 10 59 10 143 10 153
chunky-png 10 18 10 17 10 35 10 39
erubi-rails 10 10 10 10 10 22 10 22
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 350 10 349 10 487 10 517
liquid-compile 10 347 10 357 10 499 10 511
liquid-render 10 139 10 136 10 355 10 370
lobsters 10 13 10 13 10 24 10 23
mail 10 159 10 163 10 232 10 236
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 134 10 235 10 240
ruby-lsp 10 127 10 128 10 184 10 219
sequel 10 324 10 322 10 429 10 445
binarytrees 10 51 10 51 10 118 10 115
blurhash 10 62 10 62 10 120 10 143
erubi 10 83 10 102 10 104 10 131
etanni 10 60 10 69 10 69 10 81
fannkuchredux 10 59 10 59 10 123 10 135
fluentd 10 38 10 37 10 42 10 46
graphql 10 60 10 61 10 75 10 76
graphql-native 10 29 10 40 10 32 10 47
lee 10 11 10 12 10 19 10 21
matmul 10 38 10 44 10 72 10 81
nbody 10 203 10 217 10 421 10 515
nqueens 10 114 10 110 10 113 10 452
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 159 10 159 10 583 10 635
protoboeuf-encode 10 133 10 167 10 293 10 661
rack 10 465 10 500 10 835 10 937
ruby-json 10 64 10 66 10 76 10 78
rubykon 10 13 10 13 10 38 10 38
sudoku 10 48 10 49 10 139 10 159
tinygql 10 23 10 23 10 51 10 52
30k_ifelse 10 26 10 26 10 230 10 206
30k_methods 10 32 10 32 10 341 10 343
cfunc_itself 10 249 10 252 10 1108 10 1212
fib 10 98 10 100 10 616 10 623
getivar 10 215 10 230 10 1247 10 1738
keyword_args 10 90 10 89 10 730 10 947
object-new 10 228 10 187 10 307 10 236
respond_to 10 91 10 89 10 1784 10 2220
ruby-xor 10 186 10 189 10 497 10 880
setivar 10 348 10 411 10 2320 10 3122
setivar_object 10 216 10 234 10 536 10 491
setivar_young 10 216 10 235 10 528 10 494
str_concat 10 319 10 347 10 658 10 656
throw 10 948 10 816 10 1347 10 1053

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) 1448803 1219154 214 2301 0 0% 0 0 75.035834
chunky-png (click) 321331 273869 82 1090 1 0% 0 0 35.378635
erubi-rails (click) 1947683 1662249 245 2806 8 0% 0 0 84.984002
hexapdf (click) 1368280 1206008 507 12572 40 0% 0 0 399.764363
liquid-c (click) 487192 444295 119 1859 5 0% 0 0 57.270004
liquid-compile (click) 409589 320683 150 2187 2 0% 0 0 73.397959
liquid-render (click) 605200 518320 136 2473 12 0% 0 0 75.930408
lobsters (click) 8070491 6723587 3087 51908 182 0% 0 0 1920.142341
mail (click) 775537 712786 346 5489 16 0% 0 0 176.431274
psych-load (click) 253179 238770 60 615 3 0% 0 0 21.349758
railsbench (click) 3312963 2870739 1631 16663 41 0% 0 0 528.271584
rubocop (click) 5841418 5146512 2892 52160 110 0% 4 0 1702.995242
ruby-lsp (click) 847125 803283 308 4986 26 0% 0 0 157.458102
sequel (click) 460090 391148 15 125 0 0% 0 0 5.216603
binarytrees (click) 9627 8546 8 75 0 0% 0 0 3.366825
blurhash (click) 57136 49713 29 501 0 0% 0 0 18.745915
erubi (click) 226538 214824 9 108 0 0% 0 0 4.124668
etanni (click) 28241 26371 10 86 0 0% 0 0 3.250536
fannkuchredux (click) 24582 31311 6 262 0 0% 0 0 8.838581
fluentd (click) 344594 325633 11 114 0 0% 0 0 5.006798
graphql (click) 429135 382591 70 700 0 0% 0 0 23.770117
graphql-native (click) 363754 326277 41 275 0 0% 0 0 9.964313
lee (click) 284398 253991 33 567 0 0% 0 0 19.582819
matmul (click) 7323 8338 6 76 0 0% 0 0 2.918308
nbody (click) 15428 19810 9 201 0 0% 0 0 6.033036
nqueens (click) 21699 28649 8 252 0 0% 0 0 8.730081
optcarrot (click) 324183 308580 186 4508 34 0% 0 0 114.324844
protoboeuf (click) 163936 155521 15 1615 0 0% 0 0 53.02855
protoboeuf-encode (click) 235128 231105 17 1254 0 0% 0 0 36.996848
rack (click) 233871 205696 36 417 0 0% 0 0 12.415086
ruby-json (click) 21877 19055 11 192 0 0% 0 0 6.272343
rubykon (click) 135726 115935 132 1521 3 0% 0 0 48.552523
sudoku (click) 44908 40454 6 507 0 0% 0 0 17.151749
tinygql (click) 272594 231079 57 743 5 0% 0 0 23.570957
30k_ifelse (click) 6316209 5792190 9262 56478 0 0% 0 0 1846.524813
30k_methods (click) 2236110 1594189 5781 19364 0 0% 0 0 531.679152
cfunc_itself (click) 6912 5554 7 62 0 0% 0 0 2.304259
fib (click) 4585 4605 6 42 0 0% 0 0 1.863004
getivar (click) 5037 6014 6 64 0 0% 0 0 2.046891
keyword_args (click) 8181 6507 8 65 0 0% 0 0 2.565721
object-new (click) 3469 3394 5 35 0 0% 0 0 1.638602
respond_to (click) 9866 2524 7 100 0 0% 0 0 3.406977
ruby-xor (click) 6981 7365 7 77 0 0% 0 0 2.827867
setivar (click) 4188 4690 6 44 0 0% 0 0 1.702572
setivar_object (click) 4717 4838 6 46 0 0% 0 0 1.940356
setivar_young (click) 5427 5560 7 54 0 0% 0 0 2.162685
str_concat (click) 7646 7893 9 81 0 0% 0 0 3.274057
throw (click) 7384 5592 8 59 0 0% 0 0 2.384951

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.