YJIT Benchmarks

Details for Benchmarks at 2024-05-12 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby b911d2222f

Overall YJIT is 69.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 80.3% 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 10 116
chunky-png 10 16 10 34 10 38
erubi-rails 10 10 10 18 10 19
hexapdf 10 10 10 10 10 10
liquid-c 10 346 10 471 10 507
liquid-compile 10 337 10 464 10 496
liquid-render 10 134 10 330 10 357
lobsters 10 12 10 22 10 23
mail 10 155 10 212 10 228
psych-load 10 10 10 10 10 10
railsbench 10 10 10 10 10 10
rubocop 10 131 10 212 10 245
ruby-lsp 10 179 10 235 10 236
sequel 10 315 10 385 10 418
binarytrees 10 49 10 94 10 121
blurhash 10 57 10 126 10 143
erubi 10 83 10 97 10 106
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 35 10 36 10 40
lee 10 11 10 16 10 20
matmul 10 10 10 15 10 15
nbody 10 198 10 454 10 468
nqueens 10 105 10 110 10 422
optcarrot 10 10 10 10 10 10
protoboeuf 10 180 10 541 10 722
rack 10 456 10 765 10 829
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 48
30k_ifelse 10 10 10 70 10 70
30k_methods 10 10 10 26 10 26
cfunc_itself 10 252 10 1105 10 1212
fib 10 95 10 616 10 618
getivar 10 253 10 1282 10 1370
keyword_args 10 85 10 720 10 945
respond_to 10 89 10 1727 10 2149
ruby-xor 10 29 10 94 10 144
setivar 10 388 10 2351 10 3561
setivar_object 10 178 10 472 10 508
setivar_young 10 182 10 501 10 509
str_concat 10 342 10 639 10 614
throw 10 942 10 1164 10 1162

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) 1426454 1246012 214 2184 0 0% 0 0
chunky-png (click) 327754 258461 82 1048 1 0% 0 0
erubi-rails (click) 1689945 1395958 272 2893 6 0% 0 0
hexapdf (click) 1295792 1124905 504 11521 41 0% 0 0
liquid-c (click) 525708 456664 119 1757 5 0% 0 0
liquid-compile (click) 451043 389278 151 2084 2 0% 0 0
liquid-render (click) 623961 512342 136 2292 8 0% 0 0
lobsters (click) 7570741 6236416 3110 49038 89 0% 0 0
mail (click) 720578 651844 346 4865 14 0% 0 0
psych-load (click) 303929 244228 61 617 3 0% 0 0
railsbench (click) 2954298 2512845 1633 15945 57 0% 0 0
rubocop (click) 5330553 4593085 2901 48252 112 0% 4 0
ruby-lsp (click) 633673 586499 159 2808 28 0% 0 0
sequel (click) 488822 417124 16 118 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) 271987 233309 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) 385166 328413 4 28 0 0% 0 0
graphql (click) 427888 327896 66 644 0 0% 0 0
graphql-native (click) 410118 327675 42 278 0 0% 0 0
lee (click) 300573 267787 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) 281198 218988 37 455 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) 315372 264441 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.