YJIT Benchmarks

Details for Benchmarks at 2025-04-25 03:48:47 UTC

YJIT metrics from the yjit-bench suite using Ruby 8e258af5b0.

Using the geomean of the headline benchmarks for x86 YJIT 3.5.0dev is
  • 86.2% faster than CRuby 3.5.0dev
  • 6.5% faster than YJIT 3.3.6
On railsbench it is
  • 98.1% faster than CRuby 3.5.0dev
  • 4.1% faster than YJIT 3.3.6
x86_64 runtime: 4 hours, 11 minutes
aarch64 runtime: 3 hours, 34 minutes

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 3.3.6 warmups CRuby 3.3.6 iters CRuby 3.5.0dev warmups CRuby 3.5.0dev iters YJIT 3.3.6 warmups YJIT 3.3.6 iters YJIT 3.5.0dev warmups YJIT 3.5.0dev iters
activerecord 5 83 5 83 50 158 50 159
chunky-png 5 32 5 34 50 16 50 33
hexapdf 5 10 5 10 50 10 50 10
liquid-c 5 420 5 431 50 589 50 640
liquid-compile 5 409 5 463 50 542 50 678
liquid-render 5 169 5 170 50 403 50 431
mail 5 189 5 177 50 239 50 208
psych-load 5 10 5 10 50 10 50 10
railsbench 5 10 5 10 50 10 50 10
rubocop 5 156 5 157 50 253 50 263
ruby-lsp 5 155 5 163 50 249 50 268
sequel 5 431 5 427 50 596 50 591
binarytrees 5 84 5 84 50 149 50 135
blurhash 5 82 5 88 50 127 50 145
erubi 5 117 5 142 50 99 50 127
etanni 5 90 5 100 50 54 50 68
fannkuchredux 5 52 5 57 50 99 50 107
fluentd 5 63 5 65 50 25 50 29
graphql 5 85 5 86 50 57 50 59
graphql-native 5 39 5 52 50 10 50 15
lee 5 22 5 25 50 10 50 10
matmul 5 51 5 61 50 85 50 96
nbody 5 248 5 339 50 577 50 703
nqueens 5 120 5 126 50 75 50 564
optcarrot 5 10 5 10 50 10 50 10
protoboeuf 5 175 5 180 50 620 50 716
protoboeuf-encode 5 179 5 210 50 327 50 840
rack 5 566 5 621 50 953 50 1042
ruby-json 5 84 5 82 50 50 50 47
rubyboy 5 10 5 10 50 10 50 10
rubykon 5 21 5 22 50 10 50 10
sudoku 5 48 5 51 50 164 50 158
tinygql 5 36 5 38 50 22 50 26
30k_ifelse 5 28 5 28 50 215 50 206
30k_methods 5 38 5 38 50 481 50 476
cfunc_itself 5 345 5 351 50 1147 50 1258
fib 5 127 5 144 50 909 50 933
getivar 5 207 5 317 50 2240 50 2753
keyword_args 5 107 5 110 50 1042 50 1243
loops-times 5 24 5 25 50 48 50 64
object-new 5 323 5 324 50 403 50 384
respond_to 5 133 5 139 50 3257 50 3979
ruby-xor 5 241 5 249 50 803 50 1372
setivar 5 364 5 595 50 3189 50 5905
setivar_object 5 355 5 482 50 700 50 811
setivar_young 5 365 5 480 50 756 50 817
str_concat 5 398 5 454 50 967 50 1159
throw 5 1266 5 1280 50 1770 50 1738

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) 1423663 1189946 209 2202 0 0% 0 0 63.609224
chunky-png (click) 303743 245886 84 1129 1 0% 0 0 33.651275
hexapdf (click) 1469190 1239528 595 13142 41 0% 0 0 376.181066
liquid-c (click) 508253 425031 115 1744 5 0% 0 0 49.007383
liquid-compile (click) 398359 344448 146 2080 2 0% 0 0 64.233733
liquid-render (click) 587661 532600 132 2310 8 0% 0 0 64.523977
mail (click) 735009 682072 342 5317 14 0% 0 0 155.710277
psych-load (click) 256900 235980 61 617 3 0% 0 0 19.462861
railsbench (click) 3252958 2780939 1645 16199 52 0% 0 0 467.819804
rubocop (click) 5689865 4973935 2887 50507 110 0% 4 0 1534.234703
ruby-lsp (click) 811194 700154 305 4732 24 0% 0 0 133.901645
sequel (click) 446681 399219 11 95 0 0% 0 0 3.920193
binarytrees (click) 7093 6143 6 52 0 0% 0 0 2.273276
blurhash (click) 50118 50863 27 438 0 0% 0 0 14.178672
erubi (click) 227667 192067 5 97 0 0% 0 0 3.182152
etanni (click) 30101 29597 8 88 0 0% 0 0 2.972421
fannkuchredux (click) 23031 13626 3 249 0 0% 0 0 7.328865
fluentd (click) 368955 319817 7 93 0 0% 0 0 3.186024
graphql (click) 430358 353445 66 676 0 0% 0 0 19.940529
graphql-native (click) 363446 335370 37 255 0 0% 0 0 8.695383
lee (click) 274716 248043 45 749 0 0% 0 0 23.624288
matmul (click) 10657 3512 8 109 0 0% 0 0 3.582141
nbody (click) 13050 17086 6 172 0 0% 0 0 4.381242
nqueens (click) 20163 27348 5 239 0 0% 0 0 6.825408
optcarrot (click) 318856 234467 188 4395 34 0% 0 0 101.084258
protoboeuf (click) 150678 129601 12 1479 0 0% 0 0 42.163013
protoboeuf-encode (click) 221062 212146 14 1220 0 0% 0 0 31.198303
rack (click) 242264 224790 32 385 0 0% 0 0 10.136321
ruby-json (click) 20219 17676 8 178 0 0% 0 0 5.002967
rubyboy (click) 663329 598168 177 5803 40 0% 0 0 143.764241
rubykon (click) 133501 111856 137 1482 3 0% 0 0 42.651742
sudoku (click) 45311 40871 7 516 0 0% 0 0 15.539047
tinygql (click) 275917 220223 58 762 5 0% 0 0 21.03951
30k_ifelse (click) 5658774 5284843 9259 51667 0 0% 0 0 1445.895673
30k_methods (click) 2234569 1592883 5778 19351 0 0% 0 0 456.72568
cfunc_itself (click) 5130 4086 4 47 0 0% 0 0 1.341006
fib (click) 2599 2861 3 26 0 0% 0 0 0.991368
getivar (click) 3501 4713 3 51 0 0% 0 0 1.34535
keyword_args (click) 6320 4813 5 49 0 0% 0 0 1.593137
loops-times (click) 6688 7405 5 70 0 0% 0 0 2.293565
object-new (click) 1918 2093 2 22 0 0% 0 0 0.822992
respond_to (click) 5868 6227 4 62 0 0% 0 0 1.758046
ruby-xor (click) 5331 6009 4 64 0 0% 0 0 1.886452
setivar (click) 2652 3389 3 31 0 0% 0 0 1.009954
setivar_object (click) 3181 3537 3 33 0 0% 0 0 1.125002
setivar_young (click) 3891 4259 4 41 0 0% 0 0 1.320252
str_concat (click) 5469 6016 6 62 0 0% 0 0 2.012878
throw (click) 5848 4291 5 46 0 0% 0 0 1.609617

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.