YJIT Benchmarks

Details for Benchmarks at 2024-08-05 06:08:32 UTC

YJIT metrics from the yjit-bench suite using Ruby 5258e8b1cd

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 75.1% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.4
On railsbench it is
  • 79.4% faster than CRuby 3.4.0dev
  • 2.1% faster than 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 51 10 45 10 115 10 121
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 10 346 10 333 10 492 10 489
liquid-compile 10 349 10 329 10 479 10 487
liquid-render 10 137 10 132 10 351 10 365
lobsters 10 14 10 13 10 24 10 23
mail 10 161 10 150 10 233 10 219
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 136 10 128 10 230 10 235
ruby-lsp 10 130 10 121 10 213 10 205
sequel 10 322 10 303 10 428 10 406
binarytrees 10 51 10 48 10 120 10 113
blurhash 10 61 10 59 10 120 10 143
erubi 10 83 10 87 10 103 10 110
etanni 10 59 10 57 10 69 10 67
fannkuchredux 10 10 10 10 10 17 10 16
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 36 10 32 10 41 10 38
lee 10 11 10 10 10 20 10 19
matmul 10 10 10 10 10 15 10 15
nbody 10 208 10 196 10 407 10 464
nqueens 10 117 10 104 10 112 10 431
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 177 10 172 10 603 10 665
protoboeuf-encode 10 123 10 127 10 275 10 429
rack 10 458 10 459 10 792 10 919
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 31 10 28
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 10 238 10 1105 10 1212
fib 10 105 10 99 10 616 10 618
getivar 10 252 10 217 10 1277 10 1724
keyword_args 10 92 10 85 10 720 10 947
object-new 10 226 10 198 10 300 10 255
respond_to 10 94 10 86 10 1730 10 2094
ruby-xor 10 31 10 26 10 98 10 133
setivar 10 417 10 412 10 2348 10 4875
setivar_object 10 264 10 264 10 651 10 702
setivar_young 10 264 10 262 10 650 10 699
str_concat 10 327 10 300 10 592 10 521
throw 10 988 10 903 10 1289 10 1141

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) 1373107 1191552 214 2169 0 0% 0 0 85.605923
chunky-png (click) 298201 275553 83 1059 1 0% 0 0 38.727204
erubi-rails (click) 1651982 1390448 274 2933 6 0% 0 0 107.748851
hexapdf (click) 1266670 1135853 505 11812 39 0% 0 0 435.852001
liquid-c (click) 483833 427556 119 1768 5 0% 0 0 61.487544
liquid-compile (click) 406279 379526 151 2083 2 0% 0 0 77.466536
liquid-render (click) 580261 532273 136 2323 8 0% 0 0 82.089065
lobsters (click) 7558103 6316500 3081 49798 81 0% 0 0 2380.055503
mail (click) 746493 651086 347 5553 14 0% 0 0 203.01586
psych-load (click) 258568 248384 61 592 3 0% 0 0 22.432642
railsbench (click) 2903712 2459524 1636 15969 57 0% 0 0 623.327062
rubocop (click) 5443066 4687508 2892 50935 110 0% 4 0 2051.456764
ruby-lsp (click) 816997 692977 309 4750 24 0% 0 0 170.593538
sequel (click) 467798 377690 16 117 0 0% 0 0 5.497046
binarytrees (click) 8765 7825 10 70 0 0% 0 0 3.335341
blurhash (click) 50455 44132 31 457 0 0% 0 0 18.812837
erubi (click) 235903 210737 10 112 0 0% 0 0 4.663037
etanni (click) 28766 27121 12 95 0 0% 0 0 3.844434
fannkuchredux (click) 24067 31522 5 256 0 0% 0 0 10.486141
fluentd (click) 339957 308191 4 28 0 0% 0 0 1.420709
graphql (click) 398193 353062 66 650 0 0% 0 0 24.606399
graphql-native (click) 369097 311878 41 273 0 0% 0 0 11.178879
lee (click) 259547 227643 34 531 0 0% 0 0 20.965577
matmul (click) 8318 9199 8 86 0 0% 0 0 3.503819
nbody (click) 15375 19248 11 195 0 0% 0 0 6.637524
nqueens (click) 24183 24054 10 283 0 0% 0 0 11.207807
optcarrot (click) 309371 266843 188 4402 34 0% 0 0 126.008019
protoboeuf (click) 140353 122267 17 1368 0 0% 0 0 52.325043
protoboeuf-encode (click) 212407 175175 19 1193 0 0% 0 0 39.157942
rack (click) 241194 225389 37 414 0 0% 0 0 14.141616
ruby-json (click) 24603 21785 8 170 0 0% 0 0 5.942524
rubykon (click) 128584 123469 137 1484 3 0% 0 0 51.406411
sudoku (click) 45653 24997 8 520 0 0% 0 0 20.657084
tinygql (click) 273945 256442 58 735 5 0% 0 0 25.749387
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 2039.0499
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 572.285728
cfunc_itself (click) 7533 6248 9 70 0 0% 0 0 2.602413
fib (click) 4970 5023 8 49 0 0% 0 0 2.028634
getivar (click) 5936 6875 8 74 0 0% 0 0 2.55493
keyword_args (click) 8408 6980 10 72 0 0% 0 0 2.907096
object-new (click) 4400 4255 7 45 0 0% 0 0 2.204342
respond_to (click) 8276 8394 9 85 0 0% 0 0 3.191869
ruby-xor (click) 5580 6003 5 62 0 0% 0 0 2.166064
setivar (click) 5087 5551 8 54 0 0% 0 0 2.077448
setivar_object (click) 5470 5459 8 54 0 0% 0 0 2.167498
setivar_young (click) 6180 6181 9 62 0 0% 0 0 2.448088
str_concat (click) 7776 8178 11 85 0 0% 0 0 3.395091
throw (click) 7899 6453 10 69 0 0% 0 0 2.84285

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.