YJIT Benchmarks

Details for Benchmarks at 2024-05-04 06:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby bd42f0898d

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 68.5% faster than CRuby 3.4.0dev
On railsbench it is
  • 77.2% faster than CRuby 3.4.0dev

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 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 346 10 736
chunky-png 10 17 10 38
erubi-rails 10 10 10 19
hexapdf 10 10 10 10
liquid-c 10 349 10 501
liquid-compile 10 338 10 497
liquid-render 10 136 10 360
lobsters 10 13 10 23
mail 10 156 10 227
psych-load 10 10 10 10
railsbench 10 10 10 10
rubocop 10 132 10 246
ruby-lsp 10 176 10 236
sequel 10 314 10 415
binarytrees 10 51 10 118
blurhash 10 59 10 141
erubi 10 84 10 106
etanni 10 25 10 27
fannkuchredux 10 10 10 17
fluentd 10 10 10 10
graphql 10 10 10 10
graphql-native 10 35 10 41
lee 10 11 10 21
matmul 10 10 10 16
nbody 10 204 10 471
nqueens 10 113 10 460
optcarrot 10 10 10 10
protoboeuf 10 180 10 721
rack 10 202 10 256
ruby-json 10 10 10 10
rubykon 10 10 10 10
sudoku 10 10 10 31
tinygql 10 23 10 52
30k_ifelse 10 10 10 70
30k_methods 10 10 10 26
cfunc_itself 10 250 10 1211
fib 10 107 10 618
getivar 10 216 10 1344
keyword_args 10 86 10 945
respond_to 10 87 10 2149
ruby-xor 10 29 10 145
setivar 10 416 10 3578
setivar_object 10 201 10 503
setivar_young 10 198 10 529
str_concat 10 338 10 623
throw 10 942 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) 890316 756063 49 526 0 0% 0 0 16.711121
chunky-png (click) 338761 273627 82 1048 1 0% 0 0 31.376887
erubi-rails (click) 1689966 1461292 272 2898 6 0% 0 0 82.445715
hexapdf (click) 1295445 1141010 504 11519 41 0% 0 0 339.101094
liquid-c (click) 525796 464965 119 1758 5 0% 0 0 49.74171
liquid-compile (click) 450491 372298 151 2077 2 0% 0 0 65.26768
liquid-render (click) 623897 495887 136 2292 8 0% 0 0 64.416195
lobsters (click) 7551559 6281545 3110 48879 89 0% 0 0 1658.722574
mail (click) 731588 642511 346 4865 14 0% 0 0 146.037076
psych-load (click) 303929 244228 61 617 3 0% 0 0 19.817614
railsbench (click) 2954122 2479654 1633 15943 57 0% 0 0 467.244787
rubocop (click) 5331920 4504539 2901 48274 112 0% 4 0 1464.923734
ruby-lsp (click) 622665 530329 159 2808 28 0% 0 0 80.365218
sequel (click) 489237 417861 16 118 0 0% 0 0 4.317525
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.81072
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.505738
erubi (click) 277116 235415 10 112 0 0% 0 0 3.902329
etanni (click) 29692 28216 11 91 0 0% 0 0 3.003893
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.233151
fluentd (click) 385230 320292 4 28 0 0% 0 0 1.120153
graphql (click) 427888 327896 66 644 0 0% 0 0 20.227986
graphql-native (click) 410104 360421 42 278 0 0% 0 0 9.443355
lee (click) 300573 267787 34 528 0 0% 0 0 17.168078
matmul (click) 8300 983 8 85 0 0% 0 0 2.960844
nbody (click) 14798 17933 11 185 0 0% 0 0 5.22321
nqueens (click) 22703 29059 10 260 0 0% 0 0 8.037858
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 103.186502
protoboeuf (click) 146719 143337 17 1366 0 0% 0 0 42.009954
rack (click) 269048 196187 31 345 0 0% 0 0 9.975249
ruby-json (click) 30222 27890 8 167 0 0% 0 0 4.930337
rubykon (click) 127771 104177 137 1463 3 0% 0 0 42.64067
sudoku (click) 42479 58142 8 475 0 0% 0 0 15.230468
tinygql (click) 315372 264441 58 741 5 0% 0 0 21.8892
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1520.657167
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 520.405261
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.271312
fib (click) 4970 5003 8 49 0 0% 0 0 1.790269
getivar (click) 5963 6375 8 74 0 0% 0 0 2.158867
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.55384
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.66553
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.783427
setivar (click) 5102 5375 8 54 0 0% 0 0 1.828546
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.906351
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.109394
str_concat (click) 7774 7946 11 85 0 0% 0 0 2.894382
throw (click) 7895 6377 10 69 0 0% 0 0 2.647489

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.