YJIT Benchmarks

Details for Benchmarks at 2024-07-30 19:08:36 UTC

YJIT metrics from the yjit-bench suite using Ruby 91bb6afa75

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 74.2% faster than CRuby 3.4.0dev
  • 1.0% faster than YJIT 3.3.3
On railsbench it is
  • 80.2% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.3

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 3.3.3 warmups CRuby 3.3.3 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.3 warmups YJIT 3.3.3 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 51 10 47 10 115 10 113
chunky-png 10 18 10 15 10 36 10 36
erubi-rails 10 10 10 10 10 20 10 18
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 347 10 336 10 494 10 492
liquid-compile 10 336 10 331 10 478 10 491
liquid-render 10 137 10 132 10 355 10 360
lobsters 10 14 10 13 10 24 10 23
mail 10 159 10 151 10 233 10 219
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 129 10 227 10 237
ruby-lsp 10 130 10 120 10 214 10 211
sequel 10 318 10 307 10 427 10 409
binarytrees 10 51 10 49 10 118 10 118
blurhash 10 61 10 55 10 119 10 144
erubi 10 64 10 87 10 74 10 110
etanni 10 58 10 58 10 68 10 67
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 35 10 33 10 38 10 38
lee 10 11 10 10 10 19 10 20
matmul 10 10 10 10 10 15 10 17
nbody 10 213 10 200 10 410 10 468
nqueens 10 115 10 104 10 113 10 458
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 184 10 177 10 603 10 693
protoboeuf-encode 10 124 10 130 10 268 10 361
rack 10 452 10 488 10 790 10 918
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 27 10 34
tinygql 10 24 10 22 10 51 10 51
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 256 10 236 10 1100 10 1213
fib 10 107 10 91 10 616 10 618
getivar 10 247 10 238 10 1272 10 1746
keyword_args 10 90 10 83 10 720 10 947
object-new 10 225 10 200 10 292 10 258
respond_to 10 92 10 84 10 1738 10 2095
ruby-xor 10 31 10 26 10 100 10 132
setivar 10 372 10 398 10 2328 10 4866
setivar_object 10 240 10 264 10 647 10 702
setivar_young 10 241 10 264 10 643 10 699
str_concat 10 337 10 312 10 604 10 534
throw 10 948 10 902 10 1244 10 1144

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) 1353397 1166222 214 2169 0 0% 0 0 81.463875
chunky-png (click) 280779 252402 83 1054 1 0% 0 0 36.246776
erubi-rails (click) 1632680 1365663 274 2920 6 0% 0 0 102.825742
hexapdf (click) 1243872 1074527 505 11812 34 0% 0 0 412.391278
liquid-c (click) 479910 382324 119 1768 5 0% 0 0 58.616285
liquid-compile (click) 388089 314776 151 2087 2 0% 0 0 74.167099
liquid-render (click) 576662 512336 136 2323 8 0% 0 0 76.9408
lobsters (click) 7560285 6329714 3081 49795 81 0% 0 0 2238.912355
mail (click) 744723 706437 347 5553 14 0% 0 0 188.462028
psych-load (click) 258568 248384 61 592 3 0% 0 0 21.441305
railsbench (click) 2903812 2435125 1636 15971 57 0% 0 0 591.102946
rubocop (click) 5449368 4618874 2892 50933 110 0% 4 0 1934.56389
ruby-lsp (click) 798501 666472 309 4750 24 0% 0 0 163.036737
sequel (click) 467171 376565 16 116 0 0% 0 0 5.239746
binarytrees (click) 8765 7825 10 70 0 0% 0 0 3.131556
blurhash (click) 50455 44132 31 457 0 0% 0 0 17.717965
erubi (click) 235903 210737 10 112 0 0% 0 0 4.410893
etanni (click) 25319 24129 12 96 0 0% 0 0 3.736959
fannkuchredux (click) 24067 31522 5 256 0 0% 0 0 9.876484
fluentd (click) 329108 282861 4 28 0 0% 0 0 1.414743
graphql (click) 385830 333876 66 650 0 0% 0 0 23.38987
graphql-native (click) 357278 309631 42 278 0 0% 0 0 10.718167
lee (click) 259547 227643 34 531 0 0% 0 0 19.8725
matmul (click) 8318 9199 8 86 0 0% 0 0 3.293004
nbody (click) 15375 19248 11 195 0 0% 0 0 6.383586
nqueens (click) 24183 24054 10 283 0 0% 0 0 10.734965
optcarrot (click) 309371 266843 188 4402 34 0% 0 0 118.804939
protoboeuf (click) 140353 122267 17 1368 0 0% 0 0 50.348614
protoboeuf-encode (click) 221090 228639 19 1172 0 0% 0 0 37.79921
rack (click) 229915 190681 37 413 0 0% 0 0 13.791713
ruby-json (click) 24603 21785 8 170 0 0% 0 0 5.632413
rubykon (click) 128584 123469 137 1484 3 0% 0 0 49.315462
sudoku (click) 45653 24997 8 520 0 0% 0 0 19.377226
tinygql (click) 262749 238050 58 735 5 0% 0 0 24.461182
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1949.954181
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 550.468693
cfunc_itself (click) 7533 6248 9 70 0 0% 0 0 2.51543
fib (click) 4970 5023 8 49 0 0% 0 0 2.016968
getivar (click) 5936 6875 8 74 0 0% 0 0 2.466141
keyword_args (click) 8408 6980 10 72 0 0% 0 0 2.780433
object-new (click) 4400 4255 7 45 0 0% 0 0 2.129697
respond_to (click) 8276 8394 9 85 0 0% 0 0 3.036927
ruby-xor (click) 5580 6003 5 62 0 0% 0 0 2.099465
setivar (click) 5087 5551 8 54 0 0% 0 0 2.014954
setivar_object (click) 5470 5459 8 54 0 0% 0 0 2.113211
setivar_young (click) 6180 6181 9 62 0 0% 0 0 2.380648
str_concat (click) 7776 8178 11 85 0 0% 0 0 3.32796
throw (click) 7899 6453 10 69 0 0% 0 0 2.824757

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.