YJIT Benchmarks

Details for Benchmarks at 2024-06-25 06:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 3b4ff810d2

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.4% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.3
On railsbench it is
  • 76.3% faster than CRuby 3.4.0dev
  • 2.0% slower than 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 10 115
chunky-png 10 18 10 15 10 36 10 35
erubi-rails 10 10 10 10 10 20 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 353 10 333 10 505 10 476
liquid-compile 10 340 10 329 10 489 10 481
liquid-render 10 136 10 135 10 355 10 351
mail 10 160 10 148 10 238 10 216
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 137 10 126 10 230 10 235
ruby-lsp 10 199 10 191 10 262 10 276
sequel 10 325 10 300 10 436 10 401
binarytrees 10 51 10 48 10 117 10 113
blurhash 10 61 10 58 10 118 10 145
erubi 10 83 10 83 10 102 10 107
etanni 10 58 10 58 10 68 10 67
fannkuchredux 10 10 10 10 10 18 10 16
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 34 10 33 10 39 10 39
lee 10 11 10 10 10 19 10 21
matmul 10 10 10 10 10 15 10 16
nbody 10 211 10 191 10 385 10 502
nqueens 10 115 10 100 10 114 10 423
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 189 10 172 10 680 10 662
rack 10 468 10 468 10 805 10 888
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 48
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 257 10 235 10 1104 10 1210
fib 10 103 10 100 10 616 10 618
getivar 10 255 10 243 10 1280 10 1366
keyword_args 10 90 10 82 10 726 10 944
respond_to 10 89 10 84 10 1782 10 2146
ruby-xor 10 31 10 25 10 100 10 130
setivar 10 427 10 405 10 2355 10 3573
setivar_object 10 265 10 265 10 653 10 734
setivar_young 10 264 10 265 10 650 10 738
str_concat 10 327 10 288 10 593 10 531
throw 10 974 10 836 10 1276 10 1032

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) 1403001 1138688 214 2166 0 0% 0 0 76.378867
chunky-png (click) 331257 268947 82 1053 1 0% 0 0 33.709811
erubi-rails (click) 1677596 1456748 272 2921 6 0% 0 0 97.036354
hexapdf (click) 1288056 1048093 504 11683 41 0% 0 0 375.235281
liquid-c (click) 518184 433903 120 1762 5 0% 0 0 53.674756
liquid-compile (click) 440747 379986 151 2070 2 0% 0 0 69.52743
liquid-render (click) 613161 509414 137 2303 8 0% 0 0 70.822271
mail (click) 723226 644565 346 4881 14 0% 0 0 157.015608
psych-load (click) 293176 243984 61 594 3 0% 0 0 20.511467
railsbench (click) 2931186 2503849 1634 15969 57 0% 0 0 556.724109
rubocop (click) 5435067 4576488 2891 50373 110 0% 4 0 1787.6671
ruby-lsp (click) 635601 567796 159 2903 28 0% 0 0 90.326381
sequel (click) 488715 402046 16 117 0 0% 0 0 5.237255
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.966489
blurhash (click) 50429 43324 31 457 0 0% 0 0 17.285752
erubi (click) 270214 214579 10 112 0 0% 0 0 4.379556
etanni (click) 30236 28701 12 96 0 0% 0 0 3.472588
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.93566
fluentd (click) 375007 342734 4 28 0 0% 0 0 1.257782
graphql (click) 430898 361981 66 648 0 0% 0 0 22.243884
graphql-native (click) 402926 330733 42 278 0 0% 0 0 10.748239
lee (click) 293365 214005 34 531 0 0% 0 0 18.238605
matmul (click) 8315 983 8 86 0 0% 0 0 3.029196
nbody (click) 14798 17933 11 185 0 0% 0 0 5.613288
nqueens (click) 22145 28339 10 257 0 0% 0 0 8.925518
optcarrot (click) 304463 277860 188 4310 34 0% 0 0 109.170857
protoboeuf (click) 140419 133760 17 1349 0 0% 0 0 43.182202
rack (click) 276092 228924 37 413 0 0% 0 0 12.263669
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.209333
rubykon (click) 128391 79892 137 1484 3 0% 0 0 45.350396
sudoku (click) 41994 57542 8 473 0 0% 0 0 16.038503
tinygql (click) 307906 259268 58 734 5 0% 0 0 23.302452
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1902.410199
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 531.994265
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.352134
fib (click) 4970 5003 8 49 0 0% 0 0 1.993627
getivar (click) 5963 6375 8 74 0 0% 0 0 2.243328
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.598587
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.774736
ruby-xor (click) 5565 5673 5 62 0 0% 0 0 1.871566
setivar (click) 5102 5375 8 54 0 0% 0 0 1.895458
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.988196
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.198179
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.101757
throw (click) 7895 6377 10 69 0 0% 0 0 2.622211

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.