YJIT Benchmarks

Details for Benchmarks at 2024-05-20 06:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby 0b38403328

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.4% faster than CRuby 3.4.0dev
  • 11.8% faster than YJIT 3.3.1
On railsbench it is
  • 78.1% faster than CRuby 3.4.0dev
  • 6.9% faster than YJIT 3.3.1

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 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.1 warmups YJIT 3.3.1 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 49 10 101 10 118
chunky-png 10 17 10 33 10 38
erubi-rails 10 10 10 18 10 21
hexapdf 10 10 10 10 10 10
liquid-c 10 345 10 469 10 503
liquid-compile 10 341 10 465 10 499
liquid-render 10 133 10 332 10 356
lobsters 10 13 10 22 10 23
mail 10 156 10 211 10 226
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
rubocop 10 129 10 213 10 247
ruby-lsp 10 186 10 233 10 277
sequel 10 315 10 388 10 421
binarytrees 10 51 10 94 10 124
blurhash 10 59 10 126 10 145
erubi 10 85 10 97 10 106
etanni 10 25 10 62 10 27
fannkuchredux 10 10 10 14 10 17
fluentd 10 10 10 10 10 10
graphql 10 10 10 10 10 10
graphql-native 10 35 10 36 10 40
lee 10 11 10 16 10 20
matmul 10 10 10 15 10 17
nbody 10 201 10 454 10 503
nqueens 10 110 10 111 10 447
optcarrot 10 10 10 10 10 10
protoboeuf 10 179 10 540 10 771
rack 10 458 10 762 10 799
ruby-json 10 10 10 10 10 10
rubykon 10 10 10 10 10 10
sudoku 10 10 10 26 10 31
tinygql 10 23 10 45 10 52
30k_ifelse 10 10 10 70 10 70
30k_methods 10 10 10 26 10 26
cfunc_itself 10 260 10 1105 10 1212
fib 10 108 10 616 10 618
getivar 10 238 10 1279 10 1362
keyword_args 10 87 10 720 10 945
respond_to 10 92 10 1727 10 2150
ruby-xor 10 30 10 94 10 157
setivar 10 366 10 2353 10 3541
setivar_object 10 235 10 472 10 706
setivar_young 10 234 10 501 10 730
str_concat 10 334 10 639 10 632
throw 10 948 10 1165 10 1166

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) 1427015 1213679 214 2184 0 0% 0 0 66.442392
chunky-png (click) 338682 273556 82 1048 1 0% 0 0 31.134862
erubi-rails (click) 1689484 1469121 272 2894 6 0% 0 0 82.029571
hexapdf (click) 1295781 1141269 504 11521 41 0% 0 0 337.11122
liquid-c (click) 526617 416355 119 1757 5 0% 0 0 49.155683
liquid-compile (click) 450041 371552 151 2069 2 0% 0 0 63.800834
liquid-render (click) 624424 496297 137 2296 8 0% 0 0 64.030847
lobsters (click) 7585943 6387817 3109 49107 89 0% 0 0 1649.004434
mail (click) 731575 634037 346 4865 14 0% 0 0 144.406833
psych-load (click) 303523 243898 61 615 3 0% 0 0 19.373824
railsbench (click) 2953549 2536150 1633 15933 57 0% 0 0 460.509271
rubocop (click) 5332053 4537545 2901 48278 112 0% 4 0 1450.130642
ruby-lsp (click) 634421 521746 159 2803 28 0% 0 0 78.913375
sequel (click) 489585 426229 16 119 0 0% 0 0 4.645276
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.771181
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.52187
erubi (click) 277032 210763 10 112 0 0% 0 0 3.806787
etanni (click) 29692 28216 11 91 0 0% 0 0 2.963048
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.098779
fluentd (click) 385215 328545 4 28 0 0% 0 0 1.112405
graphql (click) 438485 383623 66 644 0 0% 0 0 19.946182
graphql-native (click) 410520 344150 42 278 0 0% 0 0 9.272687
lee (click) 300558 275979 34 528 0 0% 0 0 17.060212
matmul (click) 8300 983 8 85 0 0% 0 0 2.922252
nbody (click) 14798 17933 11 185 0 0% 0 0 5.115431
nqueens (click) 22703 29059 10 260 0 0% 0 0 7.911635
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 102.625295
protoboeuf (click) 146719 143337 17 1366 0 0% 0 0 41.975509
rack (click) 282506 208301 37 408 0 0% 0 0 10.95674
ruby-json (click) 30222 27890 8 167 0 0% 0 0 4.938726
rubykon (click) 127405 128474 137 1461 3 0% 0 0 41.672713
sudoku (click) 42479 58142 8 475 0 0% 0 0 14.991264
tinygql (click) 315294 264370 58 741 5 0% 0 0 22.062807
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1515.861398
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 520.564703
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.218558
fib (click) 4970 5003 8 49 0 0% 0 0 1.751641
getivar (click) 5963 6375 8 74 0 0% 0 0 2.115413
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.506081
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.61678
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.726642
setivar (click) 5102 5375 8 54 0 0% 0 0 1.790332
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.862164
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.062867
str_concat (click) 7774 7946 11 85 0 0% 0 0 2.812463
throw (click) 7895 6377 10 69 0 0% 0 0 2.558042

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.