YJIT Benchmarks

Details for Benchmarks at 2024-08-19 19:08:35 UTC

YJIT metrics from the yjit-bench suite using Ruby d1b2479b9f

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.9% faster than CRuby 3.4.0dev
  • 2.8% faster than YJIT 3.3.4
On railsbench it is
  • 79.3% 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 50 10 117 10 118
chunky-png 10 18 10 17 10 35 10 40
erubi-rails 10 10 10 10 10 21 10 20
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 341 10 349 10 488 10 510
liquid-compile 10 344 10 341 10 504 10 501
liquid-render 10 135 10 136 10 355 10 366
lobsters 10 14 10 13 10 25 10 23
mail 10 159 10 156 10 235 10 234
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 131 10 235 10 241
ruby-lsp 10 127 10 125 10 217 10 216
sequel 10 319 10 315 10 436 10 424
binarytrees 10 51 10 49 10 118 10 107
blurhash 10 62 10 64 10 120 10 147
erubi 10 83 10 95 10 104 10 123
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 28 10 31 10 32 10 34
lee 10 11 10 11 10 19 10 21
matmul 10 10 10 10 10 15 10 18
nbody 10 203 10 225 10 421 10 512
nqueens 10 112 10 114 10 113 10 428
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 180 10 184 10 572 10 686
protoboeuf-encode 10 125 10 159 10 283 10 642
rack 10 462 10 477 10 831 10 888
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 22 10 51 10 50
30k_ifelse 10 10 10 10 10 71 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 247 10 259 10 1108 10 1209
fib 10 102 10 100 10 616 10 618
getivar 10 214 10 234 10 1252 10 1743
keyword_args 10 90 10 89 10 729 10 945
object-new 10 230 10 210 10 309 10 272
respond_to 10 91 10 90 10 1784 10 2087
ruby-xor 10 30 10 32 10 92 10 174
setivar 10 348 10 411 10 2320 10 4875
setivar_object 10 216 10 244 10 536 10 606
setivar_young 10 216 10 247 10 528 10 603
str_concat 10 318 10 346 10 657 10 728
throw 10 973 10 862 10 1342 10 1138

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) 1361501 1213385 214 2169 0 0% 0 0 81.578269
chunky-png (click) 289629 259069 83 1054 1 0% 0 0 35.791139
erubi-rails (click) 1647343 1352588 274 2924 6 0% 0 0 102.929552
hexapdf (click) 1254571 1091773 505 11812 41 0% 0 0 412.901124
liquid-c (click) 461849 397501 119 1766 5 0% 0 0 58.101834
liquid-compile (click) 384077 330418 151 2078 2 0% 0 0 73.775944
liquid-render (click) 554297 499687 136 2323 8 0% 0 0 76.972571
lobsters (click) 7539241 6319690 3080 49557 81 0% 0 0 2242.600163
mail (click) 706596 672526 347 5554 14 0% 0 0 189.225716
psych-load (click) 236613 183256 61 594 3 0% 0 0 21.321144
railsbench (click) 2891913 2424485 1636 15970 57 0% 0 0 597.193535
rubocop (click) 5439339 4659177 2894 50963 114 0% 4 0 1937.271925
ruby-lsp (click) 787862 738525 309 4750 24 0% 0 0 160.16637
sequel (click) 433078 362741 16 118 0 0% 0 0 5.305621
binarytrees (click) 8404 7594 9 66 0 0% 0 0 2.970483
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.73541
erubi (click) 218766 210071 10 112 0 0% 0 0 4.431094
etanni (click) 24958 23898 11 92 0 0% 0 0 3.579382
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.671332
fluentd (click) 330842 284031 4 28 0 0% 0 0 1.337741
graphql (click) 391317 362764 66 650 0 0% 0 0 23.108244
graphql-native (click) 350979 318398 41 273 0 0% 0 0 10.649741
lee (click) 237800 190814 34 531 0 0% 0 0 19.566235
matmul (click) 7957 8968 7 82 0 0% 0 0 3.27527
nbody (click) 15014 19017 10 191 0 0% 0 0 6.189327
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.362189
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 119.796401
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.943224
protoboeuf-encode (click) 212046 158560 18 1189 0 0% 0 0 36.781761
rack (click) 239834 215783 37 408 0 0% 0 0 13.018719
ruby-json (click) 22286 19409 7 164 0 0% 0 0 5.424369
rubykon (click) 130437 109178 136 1500 3 0% 0 0 49.061195
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.256404
tinygql (click) 256226 223281 58 735 5 0% 0 0 24.290248
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1916.278709
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 537.056405
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.384266
fib (click) 4609 4792 7 45 0 0% 0 0 1.860998
getivar (click) 5575 6644 7 70 0 0% 0 0 2.321676
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.65737
object-new (click) 4039 4024 6 41 0 0% 0 0 1.816515
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.83845
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.967624
setivar (click) 4726 5320 7 50 0 0% 0 0 1.872816
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.95048
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.216506
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.231377
throw (click) 7538 6222 9 65 0 0% 0 0 2.676119

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.