YJIT Benchmarks

Details for Benchmarks at 2024-08-18 19:08:31 UTC

YJIT metrics from the yjit-bench suite using Ruby d450f9d6a2

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.4% faster than CRuby 3.4.0dev
  • 1.9% faster than YJIT 3.3.4
On railsbench it is
  • 78.2% 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 49 10 48 10 118 10 116
chunky-png 10 18 10 18 10 36 10 39
erubi-rails 10 10 10 10 10 21 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 340 10 347 10 486 10 506
liquid-compile 10 344 10 341 10 500 10 499
liquid-render 10 137 10 132 10 357 10 369
lobsters 10 14 10 13 10 24 10 23
mail 10 158 10 159 10 231 10 225
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 131 10 236 10 237
ruby-lsp 10 128 10 124 10 222 10 217
sequel 10 317 10 315 10 438 10 423
binarytrees 10 51 10 48 10 118 10 104
blurhash 10 63 10 63 10 120 10 149
erubi 10 83 10 96 10 105 10 124
etanni 10 60 10 64 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 29 10 29 10 32 10 36
lee 10 11 10 12 10 19 10 21
matmul 10 10 10 10 10 15 10 18
nbody 10 203 10 230 10 421 10 517
nqueens 10 113 10 112 10 113 10 448
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 181 10 181 10 572 10 679
protoboeuf-encode 10 125 10 163 10 283 10 646
rack 10 467 10 471 10 813 10 922
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 52 10 51
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 250 10 258 10 1108 10 1212
fib 10 101 10 98 10 616 10 618
getivar 10 214 10 230 10 1250 10 1738
keyword_args 10 90 10 88 10 729 10 947
object-new 10 230 10 207 10 309 10 275
respond_to 10 91 10 89 10 1786 10 2096
ruby-xor 10 30 10 29 10 92 10 158
setivar 10 348 10 391 10 2319 10 4859
setivar_object 10 216 10 241 10 536 10 607
setivar_young 10 216 10 247 10 528 10 602
str_concat 10 320 10 359 10 658 10 701
throw 10 971 10 908 10 1339 10 1180

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) 1353481 1164970 214 2169 0 0% 0 0 81.899745
chunky-png (click) 275970 246495 83 1054 1 0% 0 0 35.909102
erubi-rails (click) 1642283 1422703 274 2920 6 0% 0 0 101.529954
hexapdf (click) 1253661 1055182 505 11814 39 0% 0 0 413.513391
liquid-c (click) 460640 411694 119 1768 5 0% 0 0 58.211373
liquid-compile (click) 398705 363287 151 2073 2 0% 0 0 73.261131
liquid-render (click) 552404 491192 136 2323 8 0% 0 0 77.213968
lobsters (click) 7562262 6244483 3080 49742 81 0% 0 0 2255.363413
mail (click) 736483 674541 347 5554 14 0% 0 0 190.251034
psych-load (click) 236217 212010 61 594 3 0% 0 0 21.471183
railsbench (click) 2890890 2522512 1636 15966 57 0% 0 0 591.269534
rubocop (click) 5427782 4518640 2894 50954 114 0% 4 0 1934.185331
ruby-lsp (click) 787269 704383 309 4750 24 0% 0 0 160.841769
sequel (click) 432125 383087 16 115 0 0% 0 0 5.025293
binarytrees (click) 8404 7594 9 66 0 0% 0 0 2.981175
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.792569
erubi (click) 213427 189671 10 112 0 0% 0 0 4.487615
etanni (click) 24958 23898 11 92 0 0% 0 0 3.575172
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.743316
fluentd (click) 322858 276029 4 28 0 0% 0 0 1.339846
graphql (click) 375682 330234 66 650 0 0% 0 0 23.192692
graphql-native (click) 348383 305934 41 273 0 0% 0 0 10.145293
lee (click) 238354 179686 34 531 0 0% 0 0 19.592332
matmul (click) 7957 8968 7 82 0 0% 0 0 3.249487
nbody (click) 15014 19017 10 191 0 0% 0 0 6.179168
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.382062
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 119.158418
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.945468
protoboeuf-encode (click) 212046 158560 18 1189 0 0% 0 0 36.611349
rack (click) 226533 203458 37 413 0 0% 0 0 13.317289
ruby-json (click) 22523 19740 7 164 0 0% 0 0 5.426943
rubykon (click) 130437 109178 136 1500 3 0% 0 0 49.314768
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.302726
tinygql (click) 252538 244375 58 735 5 0% 0 0 24.246121
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1920.135095
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 534.965168
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.383642
fib (click) 4609 4792 7 45 0 0% 0 0 1.85236
getivar (click) 5575 6644 7 70 0 0% 0 0 2.309036
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.647593
object-new (click) 4039 4024 6 41 0 0% 0 0 1.860561
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.873775
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.96976
setivar (click) 4726 5320 7 50 0 0% 0 0 1.858639
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.962192
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.203147
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.204495
throw (click) 7538 6222 9 65 0 0% 0 0 2.650568

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.