YJIT Benchmarks

Details for Benchmarks at 2024-05-18 19:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby dbbaf871de

Overall YJIT is 71.0% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 78.3% faster than CRuby!

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 No JIT warmups No JIT iters YJIT 3.3 warmups YJIT 3.3 iters YJIT 3.4dev warmups YJIT 3.4dev iters
activerecord 10 50 10 102 10 115
chunky-png 10 16 10 34 10 37
erubi-rails 10 10 10 18 10 20
hexapdf 10 10 10 10 10 10
liquid-c 10 348 10 469 10 507
liquid-compile 10 338 10 465 10 498
liquid-render 10 133 10 331 10 358
lobsters 10 12 10 22 10 23
mail 10 155 10 211 10 227
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
rubocop 10 131 10 213 10 244
ruby-lsp 10 183 10 232 10 274
sequel 10 313 10 388 10 422
binarytrees 10 50 10 94 10 123
blurhash 10 57 10 126 10 143
erubi 10 85 10 97 10 107
etanni 10 25 10 62 10 27
fannkuchredux 10 10 10 14 10 16
fluentd 10 10 10 10 10 10
graphql 10 10 10 10 10 10
graphql-native 10 34 10 36 10 39
lee 10 11 10 16 10 20
matmul 10 10 10 15 10 15
nbody 10 199 10 454 10 468
nqueens 10 105 10 111 10 422
optcarrot 10 10 10 10 10 10
protoboeuf 10 177 10 540 10 763
rack 10 461 10 750 10 842
ruby-json 10 10 10 10 10 10
rubykon 10 10 10 10 10 10
sudoku 10 10 10 26 10 28
tinygql 10 22 10 45 10 51
30k_ifelse 10 10 10 70 10 71
30k_methods 10 10 10 26 10 26
cfunc_itself 10 249 10 1105 10 1212
fib 10 108 10 616 10 617
getivar 10 239 10 1280 10 1363
keyword_args 10 86 10 720 10 945
respond_to 10 93 10 1728 10 2149
ruby-xor 10 29 10 94 10 145
setivar 10 388 10 2351 10 3561
setivar_object 10 256 10 446 10 735
setivar_young 10 255 10 501 10 738
str_concat 10 345 10 638 10 610
throw 10 943 10 1164 10 1181

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
activerecord (click) 1427015 1213643 214 2184 0 0% 0 0
chunky-png (click) 333318 228906 82 1048 1 0% 0 0
erubi-rails (click) 1689396 1460853 272 2893 6 0% 0 0
hexapdf (click) 1294710 1140415 504 11516 41 0% 0 0
liquid-c (click) 526705 416464 119 1758 5 0% 0 0
liquid-compile (click) 450134 371667 151 2070 2 0% 0 0
liquid-render (click) 624424 496297 137 2296 8 0% 0 0
lobsters (click) 7570322 6389163 3109 48939 89 0% 0 0
mail (click) 732239 635060 346 4874 14 0% 0 0
psych-load (click) 303523 243898 61 615 3 0% 0 0
railsbench (click) 2954310 2594449 1633 15937 57 0% 0 0
rubocop (click) 5333851 4530593 2901 48288 112 0% 4 0
ruby-lsp (click) 634426 554494 159 2803 28 0% 0 0
sequel (click) 492077 420487 16 117 0 0% 0 0
binarytrees (click) 8756 7777 10 70 0 0% 0 0
blurhash (click) 50429 43273 31 455 0 0% 0 0
erubi (click) 277032 210763 10 112 0 0% 0 0
etanni (click) 29692 28216 11 91 0 0% 0 0
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0
fluentd (click) 385215 320289 4 28 0 0% 0 0
graphql (click) 438451 350855 66 644 0 0% 0 0
graphql-native (click) 410554 327786 42 278 0 0% 0 0
lee (click) 300558 275979 34 528 0 0% 0 0
matmul (click) 8300 983 8 85 0 0% 0 0
nbody (click) 14798 17933 11 185 0 0% 0 0
nqueens (click) 22703 29059 10 260 0 0% 0 0
optcarrot (click) 307949 264223 188 4285 34 0% 0 0
protoboeuf (click) 146719 143337 17 1366 0 0% 0 0
rack (click) 282506 208333 37 408 0 0% 0 0
ruby-json (click) 30222 27890 8 167 0 0% 0 0
rubykon (click) 127405 128474 137 1461 3 0% 0 0
sudoku (click) 42479 58142 8 475 0 0% 0 0
tinygql (click) 315294 264370 58 741 5 0% 0 0
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0
fib (click) 4970 5003 8 49 0 0% 0 0
getivar (click) 5963 6375 8 74 0 0% 0 0
keyword_args (click) 8409 6912 10 72 0 0% 0 0
respond_to (click) 8277 8274 9 85 0 0% 0 0
ruby-xor (click) 5593 5796 5 62 0 0% 0 0
setivar (click) 5102 5375 8 54 0 0% 0 0
setivar_object (click) 5470 5395 8 54 0 0% 0 0
setivar_young (click) 6182 6093 9 62 0 0% 0 0
str_concat (click) 7774 7946 11 85 0 0% 0 0
throw (click) 7895 6377 10 69 0 0% 0 0

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.