YJIT Benchmarks

Details for Benchmarks at 2024-05-02 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby c681af3e5d

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 67.2% faster than CRuby 3.4.0dev
On railsbench it is
  • 77.4% 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 10 345 10 748
chunky-png 10 16 10 38
erubi-rails 10 10 10 19
hexapdf 10 10 10 10
liquid-c 10 351 10 509
liquid-compile 10 337 10 488
liquid-render 10 137 10 359
lobsters 10 12 10 23
mail 10 156 10 228
psych-load 10 10 10 10
railsbench 10 10 10 10
rubocop 10 132 10 223
ruby-lsp 10 180 10 247
sequel 10 316 10 417
binarytrees 10 50 10 117
blurhash 10 60 10 141
erubi 10 84 10 105
etanni 10 25 10 26
fannkuchredux 10 10 10 17
fluentd 10 10 10 10
graphql 10 10 10 10
graphql-native 10 34 10 40
lee 10 11 10 21
matmul 10 10 10 16
nbody 10 204 10 470
nqueens 10 114 10 460
optcarrot 10 10 10 10
protoboeuf 10 178 10 579
rack 10 208 10 257
ruby-json 10 10 10 10
rubykon 10 10 10 10
sudoku 10 10 10 31
tinygql 10 23 10 51
30k_ifelse 10 10 10 70
30k_methods 10 10 10 26
cfunc_itself 10 251 10 1212
fib 10 106 10 618
getivar 10 208 10 1339
keyword_args 10 89 10 945
respond_to 10 86 10 2148
ruby-xor 10 29 10 144
setivar 10 416 10 3578
setivar_object 10 233 10 592
setivar_young 10 236 10 608
str_concat 10 333 10 629
throw 10 949 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 Compile Time MS
activerecord (click) 885105 745890 49 526 0 0% 0 0 16.250718
chunky-png (click) 338761 273627 82 1048 1 0% 0 0 31.366552
erubi-rails (click) 1687988 1372224 272 2925 6 0% 0 0 84.112177
hexapdf (click) 1295549 1157596 505 11522 41 0% 0 0 340.153238
liquid-c (click) 525998 465202 119 1757 5 0% 0 0 49.711259
liquid-compile (click) 441229 399185 151 2078 2 0% 0 0 64.62786
liquid-render (click) 623962 512342 136 2292 8 0% 0 0 64.588725
lobsters (click) 7555997 6259080 3110 48994 91 0% 0 0 1662.69068
mail (click) 731588 642511 346 4865 14 0% 0 0 145.482949
psych-load (click) 303602 243969 61 615 3 0% 0 0 19.542361
railsbench (click) 2964173 2549410 1633 15945 57 0% 0 0 467.778483
rubocop (click) 5324917 4631621 2901 48250 112 0% 4 0 1472.596601
ruby-lsp (click) 634469 538199 159 2803 28 0% 0 0 79.927006
sequel (click) 492383 429256 16 119 0 0% 0 0 4.867939
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.905988
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.744654
erubi (click) 277116 235415 10 112 0 0% 0 0 3.881825
etanni (click) 29692 28216 11 91 0 0% 0 0 3.009162
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.638949
fluentd (click) 385230 320260 4 28 0 0% 0 0 1.204256
graphql (click) 439244 367926 66 644 0 0% 0 0 19.774336
graphql-native (click) 410453 352485 42 278 0 0% 0 0 9.441642
lee (click) 295449 273858 34 528 0 0% 0 0 17.068955
matmul (click) 8300 983 8 85 0 0% 0 0 3.025417
nbody (click) 14798 17933 11 185 0 0% 0 0 5.28673
nqueens (click) 22703 29059 10 260 0 0% 0 0 8.074056
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 103.047639
protoboeuf (click) 148013 144784 17 1378 0 0% 0 0 42.981274
rack (click) 278756 209179 31 323 0 0% 0 0 9.39401
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.05207
rubykon (click) 127405 128474 137 1461 3 0% 0 0 42.155986
sudoku (click) 42479 58142 8 475 0 0% 0 0 14.946206
tinygql (click) 315372 256249 58 741 5 0% 0 0 22.130741
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1521.217794
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 518.918617
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.540056
fib (click) 4970 5003 8 49 0 0% 0 0 1.993257
getivar (click) 5963 6375 8 74 0 0% 0 0 2.437671
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.747586
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.899882
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.840213
setivar (click) 5102 5375 8 54 0 0% 0 0 2.083847
setivar_object (click) 5470 5395 8 54 0 0% 0 0 2.355634
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.601251
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.074129
throw (click) 7895 6377 10 69 0 0% 0 0 2.46693

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.