YJIT Benchmarks

Details for Benchmarks at 2024-08-17 06:08:31 UTC

YJIT metrics from the yjit-bench suite using Ruby d56470a27c

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.7% faster than CRuby 3.4.0dev
  • 2.4% 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 49 10 117 10 118
chunky-png 10 18 10 18 10 36 10 40
erubi-rails 10 10 10 10 10 22 10 20
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 349 10 348 10 487 10 510
liquid-compile 10 344 10 339 10 503 10 499
liquid-render 10 139 10 137 10 357 10 373
lobsters 10 14 10 13 10 24 10 23
mail 10 159 10 155 10 234 10 227
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 131 10 233 10 240
ruby-lsp 10 127 10 125 10 209 10 212
sequel 10 319 10 315 10 437 10 424
binarytrees 10 51 10 49 10 118 10 107
blurhash 10 62 10 64 10 120 10 148
erubi 10 84 10 94 10 104 10 121
etanni 10 60 10 63 10 69 10 74
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 20
matmul 10 10 10 10 10 15 10 19
nbody 10 203 10 232 10 421 10 511
nqueens 10 111 10 114 10 112 10 441
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 182 10 183 10 572 10 681
protoboeuf-encode 10 125 10 159 10 283 10 638
rack 10 461 10 472 10 835 10 916
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 23 10 51 10 50
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 246 10 255 10 1108 10 1210
fib 10 102 10 99 10 616 10 618
getivar 10 214 10 228 10 1251 10 1735
keyword_args 10 89 10 88 10 729 10 946
object-new 10 230 10 209 10 309 10 269
respond_to 10 90 10 92 10 1786 10 2089
ruby-xor 10 30 10 30 10 92 10 173
setivar 10 347 10 405 10 2319 10 4869
setivar_object 10 216 10 244 10 536 10 606
setivar_young 10 216 10 248 10 528 10 603
str_concat 10 319 10 338 10 658 10 722
throw 10 972 10 885 10 1342 10 1171

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) 1350225 1219609 214 2169 0 0% 0 0 81.189244
chunky-png (click) 273148 244536 83 1054 1 0% 0 0 36.056574
erubi-rails (click) 1635344 1408956 274 2920 6 0% 0 0 102.907969
hexapdf (click) 1255643 1050851 505 11812 40 0% 0 0 415.857244
liquid-c (click) 463400 355595 119 1768 5 0% 0 0 57.816035
liquid-compile (click) 387759 352349 151 2072 2 0% 0 0 73.585909
liquid-render (click) 560122 494037 136 2325 8 0% 0 0 77.222554
lobsters (click) 7547561 6311596 3081 49676 81 0% 0 0 2247.764828
mail (click) 738431 692945 347 5554 14 0% 0 0 190.157168
psych-load (click) 229970 206214 61 594 3 0% 0 0 21.713087
railsbench (click) 2890272 2439725 1636 15972 57 0% 0 0 590.677476
rubocop (click) 5432133 4595254 2894 50983 114 0% 4 0 1936.749279
ruby-lsp (click) 786675 726208 309 4744 24 0% 0 0 160.710114
sequel (click) 432349 383071 16 116 0 0% 0 0 5.077054
binarytrees (click) 8404 7594 9 66 0 0% 0 0 3.013925
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.7562
erubi (click) 211440 170125 10 112 0 0% 0 0 4.632036
etanni (click) 28405 26890 11 91 0 0% 0 0 3.513492
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.715097
fluentd (click) 328951 264408 4 28 0 0% 0 0 1.316901
graphql (click) 370101 319946 66 650 0 0% 0 0 22.888297
graphql-native (click) 343174 321193 41 273 0 0% 0 0 10.547984
lee (click) 235745 220431 34 531 0 0% 0 0 19.661645
matmul (click) 7957 8968 7 82 0 0% 0 0 3.252775
nbody (click) 15014 19017 10 191 0 0% 0 0 6.185733
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.381382
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 119.419192
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.954848
protoboeuf-encode (click) 212046 158560 18 1189 0 0% 0 0 36.811637
rack (click) 223353 193032 37 408 0 0% 0 0 13.044625
ruby-json (click) 22939 19989 7 164 0 0% 0 0 5.419419
rubykon (click) 130437 109178 136 1500 3 0% 0 0 49.344152
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.375759
tinygql (click) 252299 216131 58 735 5 0% 0 0 24.559255
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1927.874983
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 537.127824
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.38048
fib (click) 4609 4792 7 45 0 0% 0 0 1.856511
getivar (click) 5575 6644 7 70 0 0% 0 0 2.330001
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.669402
object-new (click) 4039 4024 6 41 0 0% 0 0 1.836326
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.853466
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.947864
setivar (click) 4726 5320 7 50 0 0% 0 0 1.859554
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.955778
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.216954
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.204307
throw (click) 7538 6222 9 65 0 0% 0 0 2.667368

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.