YJIT Benchmarks

Details for Benchmarks at 2024-10-07 04:00:07 UTC

YJIT metrics from the yjit-bench suite using Ruby 773d140f65

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.4% faster than CRuby 3.4.0dev
  • 3.3% faster than YJIT 3.3.4
On railsbench it is
  • 76.5% faster than CRuby 3.4.0dev
  • 1.6% 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 56 10 59 10 145 10 154
chunky-png 10 18 10 17 10 36 10 40
erubi-rails 10 10 10 10 10 22 10 22
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 349 10 353 10 487 10 526
liquid-compile 10 345 10 348 10 500 10 532
liquid-render 10 139 10 137 10 354 10 375
lobsters 10 13 10 13 10 24 10 24
mail 10 161 10 162 10 238 10 232
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 134 10 234 10 239
ruby-lsp 10 129 10 115 10 215 10 183
sequel 10 325 10 325 10 428 10 445
binarytrees 10 51 10 51 10 118 10 112
blurhash 10 62 10 62 10 120 10 147
erubi 10 80 10 95 10 100 10 124
etanni 10 60 10 69 10 69 10 81
fannkuchredux 10 59 10 59 10 123 10 137
fluentd 10 38 10 42 10 42 10 48
graphql 10 62 10 61 10 75 10 75
graphql-native 10 29 10 40 10 32 10 46
lee 10 11 10 12 10 19 10 21
matmul 10 38 10 45 10 72 10 87
nbody 10 203 10 228 10 421 10 529
nqueens 10 113 10 113 10 113 10 469
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 158 10 158 10 582 10 641
protoboeuf-encode 10 132 10 169 10 293 10 662
rack 10 459 10 494 10 838 10 913
ruby-json 10 64 10 66 10 76 10 78
rubykon 10 13 10 13 10 37 10 39
sudoku 10 48 10 49 10 139 10 167
tinygql 10 23 10 24 10 51 10 53
30k_ifelse 10 26 10 26 10 231 10 208
30k_methods 10 32 10 32 10 343 10 343
cfunc_itself 10 250 10 256 10 1108 10 1212
fib 10 102 10 99 10 616 10 623
getivar 10 215 10 258 10 1251 10 1757
keyword_args 10 89 10 88 10 729 10 948
object-new 10 230 10 188 10 309 10 236
respond_to 10 91 10 89 10 1785 10 2219
ruby-xor 10 186 10 191 10 497 10 842
setivar 10 348 10 405 10 2319 10 3123
setivar_object 10 216 10 232 10 536 10 488
setivar_young 10 216 10 234 10 528 10 494
str_concat 10 320 10 344 10 658 10 684
throw 10 970 10 837 10 1340 10 1036

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) 1481982 1250381 214 2301 0 0% 0 0 73.631602
chunky-png (click) 292861 278908 82 1095 1 0% 0 0 35.294045
erubi-rails (click) 1952239 1625753 245 2806 8 0% 0 0 83.959179
hexapdf (click) 1363662 1218938 507 12566 40 0% 0 0 393.46096
liquid-c (click) 522376 432904 119 1859 5 0% 0 0 56.036268
liquid-compile (click) 446535 344438 150 2223 2 0% 0 0 74.923496
liquid-render (click) 603583 524335 136 2473 12 0% 0 0 75.211615
lobsters (click) 8045852 6655543 3087 51775 182 0% 0 0 1887.945714
mail (click) 778010 706974 346 5481 16 0% 0 0 174.535558
psych-load (click) 246053 213624 60 615 3 0% 0 0 21.09852
railsbench (click) 3310717 2788545 1631 16677 41 0% 0 0 521.587054
rubocop (click) 5812610 4892696 2892 52166 110 0% 4 0 1667.333114
ruby-lsp (click) 847040 775536 308 4991 26 0% 0 0 155.215904
sequel (click) 491472 446118 15 120 0 0% 0 0 4.790881
binarytrees (click) 9627 8546 8 75 0 0% 0 0 3.358488
blurhash (click) 57136 49713 29 501 0 0% 0 0 18.416558
erubi (click) 254580 246442 9 108 0 0% 0 0 4.153059
etanni (click) 24711 23355 10 87 0 0% 0 0 3.222554
fannkuchredux (click) 24582 31311 6 262 0 0% 0 0 8.826749
fluentd (click) 345524 293016 11 114 0 0% 0 0 4.319317
graphql (click) 428176 373728 70 700 0 0% 0 0 23.54245
graphql-native (click) 364053 315699 41 275 0 0% 0 0 9.786719
lee (click) 250060 215173 33 567 0 0% 0 0 19.254047
matmul (click) 7323 8338 6 76 0 0% 0 0 2.861214
nbody (click) 15428 19810 9 201 0 0% 0 0 5.972943
nqueens (click) 21699 28649 8 252 0 0% 0 0 8.629829
optcarrot (click) 324183 308580 186 4508 34 0% 0 0 112.589823
protoboeuf (click) 163936 155521 15 1615 0 0% 0 0 52.506564
protoboeuf-encode (click) 235128 231105 17 1254 0 0% 0 0 36.217505
rack (click) 236535 205978 36 417 0 0% 0 0 12.024244
ruby-json (click) 27649 24400 11 194 0 0% 0 0 6.274458
rubykon (click) 135726 115935 132 1521 3 0% 0 0 47.652314
sudoku (click) 44908 40454 6 507 0 0% 0 0 16.945408
tinygql (click) 266197 230539 57 743 5 0% 0 0 23.462916
30k_ifelse (click) 6316209 5792190 9262 56478 0 0% 0 0 1828.768189
30k_methods (click) 2236110 1594189 5781 19364 0 0% 0 0 522.845424
cfunc_itself (click) 6912 5554 7 62 0 0% 0 0 2.243827
fib (click) 4585 4605 6 42 0 0% 0 0 1.792096
getivar (click) 5037 6014 6 64 0 0% 0 0 2.038604
keyword_args (click) 8181 6507 8 65 0 0% 0 0 2.501469
object-new (click) 3469 3394 5 35 0 0% 0 0 1.607048
respond_to (click) 9866 2524 7 100 0 0% 0 0 3.358707
ruby-xor (click) 6981 7365 7 77 0 0% 0 0 2.79501
setivar (click) 4188 4690 6 44 0 0% 0 0 1.743301
setivar_object (click) 4717 4838 6 46 0 0% 0 0 1.930805
setivar_young (click) 5427 5560 7 54 0 0% 0 0 2.155454
str_concat (click) 7646 7893 9 81 0 0% 0 0 3.227139
throw (click) 7384 5592 8 59 0 0% 0 0 2.329863

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.