YJIT Benchmarks

Details for Benchmarks at 2024-08-25 06:08:30 UTC

YJIT metrics from the yjit-bench suite using Ruby 76e0ea28ea

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 74.3% faster than CRuby 3.4.0dev
  • 3.1% faster than YJIT 3.3.4
On railsbench it is
  • 80.2% 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 50 10 50 10 118 10 118
chunky-png 10 18 10 18 10 35 10 39
erubi-rails 10 10 10 10 10 21 10 21
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 347 10 353 10 498 10 518
liquid-compile 10 344 10 342 10 501 10 531
liquid-render 10 139 10 135 10 356 10 374
lobsters 10 14 10 13 10 25 10 23
mail 10 159 10 156 10 238 10 226
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 135 10 132 10 234 10 240
ruby-lsp 10 127 10 125 10 217 10 215
sequel 10 323 10 318 10 424 10 428
binarytrees 10 51 10 50 10 118 10 107
blurhash 10 62 10 62 10 120 10 147
erubi 10 83 10 98 10 105 10 125
etanni 10 60 10 65 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 28 10 31 10 32 10 35
lee 10 11 10 12 10 20 10 21
matmul 10 10 10 10 10 15 10 18
nbody 10 202 10 215 10 421 10 514
nqueens 10 113 10 114 10 111 10 442
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 181 10 183 10 572 10 685
protoboeuf-encode 10 126 10 164 10 283 10 636
rack 10 457 10 481 10 831 10 884
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 52
30k_ifelse 10 10 10 10 10 71 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 250 10 246 10 1108 10 1213
fib 10 101 10 98 10 616 10 618
getivar 10 214 10 240 10 1249 10 1748
keyword_args 10 89 10 85 10 729 10 947
object-new 10 230 10 217 10 308 10 287
respond_to 10 90 10 91 10 1785 10 2094
ruby-xor 10 30 10 25 10 92 10 165
setivar 10 348 10 360 10 2319 10 4824
setivar_object 10 216 10 226 10 536 10 518
setivar_young 10 216 10 227 10 528 10 534
str_concat 10 321 10 357 10 658 10 684
throw 10 973 10 909 10 1342 10 1214

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) 1372643 1198876 214 2169 0 0% 0 0 81.255086
chunky-png (click) 270433 258469 83 1054 1 0% 0 0 35.758794
erubi-rails (click) 1647558 1370263 275 2924 6 0% 0 0 101.776375
hexapdf (click) 1248093 1084429 505 11812 40 0% 0 0 411.245779
liquid-c (click) 463372 421187 119 1765 5 0% 0 0 57.251843
liquid-compile (click) 398730 363359 151 2070 2 0% 0 0 73.08009
liquid-render (click) 573747 468380 136 2323 8 0% 0 0 76.744587
lobsters (click) 7532935 6396797 3081 49712 81 0% 0 0 2247.947
mail (click) 717020 674593 347 5554 14 0% 0 0 188.829649
psych-load (click) 231366 190663 61 594 3 0% 0 0 21.268223
railsbench (click) 2894548 2493046 1637 15959 57 0% 0 0 591.740763
rubocop (click) 5431085 4479769 2893 50949 114 0% 4 0 1936.291522
ruby-lsp (click) 792086 659497 309 4745 24 0% 0 0 161.124453
sequel (click) 424652 355847 16 117 0 0% 0 0 5.105624
binarytrees (click) 8404 7594 9 66 0 0% 0 0 2.997205
blurhash (click) 50094 43901 30 453 0 0% 0 0 17.72223
erubi (click) 228155 203188 10 112 0 0% 0 0 4.518856
etanni (click) 28405 26890 11 91 0 0% 0 0 3.515568
fannkuchredux (click) 23706 31291 4 252 0 0% 0 0 9.661334
fluentd (click) 331804 301047 4 28 0 0% 0 0 1.273805
graphql (click) 389008 336865 66 650 0 0% 0 0 23.187935
graphql-native (click) 361439 329196 41 273 0 0% 0 0 10.205701
lee (click) 251804 195538 34 531 0 0% 0 0 19.527365
matmul (click) 7957 8968 7 82 0 0% 0 0 3.221204
nbody (click) 15014 19017 10 191 0 0% 0 0 6.11664
nqueens (click) 23822 23823 9 279 0 0% 0 0 10.342589
optcarrot (click) 309010 266612 187 4398 34 0% 0 0 119.156375
protoboeuf (click) 139992 122036 16 1364 0 0% 0 0 48.377379
protoboeuf-encode (click) 212046 174944 18 1189 0 0% 0 0 36.707644
rack (click) 231441 207114 37 408 0 0% 0 0 12.861036
ruby-json (click) 24237 21549 7 166 0 0% 0 0 5.590574
rubykon (click) 128223 123238 136 1480 3 0% 0 0 48.224594
sudoku (click) 45292 24766 7 516 0 0% 0 0 19.067726
tinygql (click) 247001 231749 58 735 5 0% 0 0 24.066029
30k_ifelse (click) 5134313 4729205 9258 50774 0 0% 0 0 1925.640947
30k_methods (click) 2016559 1591611 5777 19335 0 0% 0 0 535.475667
cfunc_itself (click) 7172 6017 8 66 0 0% 0 0 2.346936
fib (click) 4609 4792 7 45 0 0% 0 0 1.856036
getivar (click) 5575 6644 7 70 0 0% 0 0 2.338871
keyword_args (click) 8042 6744 9 68 0 0% 0 0 2.631995
object-new (click) 4039 4024 6 41 0 0% 0 0 1.938334
respond_to (click) 7910 8158 8 81 0 0% 0 0 2.888331
ruby-xor (click) 5219 5772 4 58 0 0% 0 0 1.94204
setivar (click) 4726 5320 7 50 0 0% 0 0 1.891487
setivar_object (click) 5109 5228 7 50 0 0% 0 0 1.968855
setivar_young (click) 5819 5950 8 58 0 0% 0 0 2.205309
str_concat (click) 7415 7947 10 81 0 0% 0 0 3.198517
throw (click) 7538 6222 9 65 0 0% 0 0 2.703711

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.