YJIT Benchmarks

Details for Benchmarks at 2024-05-28 06:08:17 UTC

YJIT metrics from the yjit-bench suite using Ruby ca2d229e6b

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 69.8% faster than CRuby 3.4.0dev
  • 9.3% faster than YJIT 3.3.1
On railsbench it is
  • 77.3% faster than CRuby 3.4.0dev
  • 7.4% faster than YJIT 3.3.1

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 3.3.1 warmups CRuby 3.3.1 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.1 warmups YJIT 3.3.1 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 44 10 48 10 103 10 113
chunky-png 10 17 10 15 10 33 10 35
erubi-rails 10 10 10 10 10 17 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 332 10 336 10 470 10 486
liquid-compile 10 327 10 338 10 465 10 491
liquid-render 10 129 10 134 10 331 10 349
lobsters 10 13 10 12 10 22 10 23
mail 10 149 10 150 10 211 10 218
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 128 10 131 10 212 10 246
ruby-lsp 10 167 10 196 10 232 10 283
sequel 10 299 10 305 10 388 10 399
binarytrees 10 47 10 48 10 94 10 115
blurhash 10 58 10 56 10 126 10 144
erubi 10 78 10 83 10 97 10 103
etanni 10 53 10 24 10 62 10 26
fannkuchredux 10 10 10 10 10 14 10 17
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 31 10 34 10 36 10 38
lee 10 10 10 11 10 16 10 20
matmul 10 10 10 10 10 15 10 17
nbody 10 203 10 200 10 454 10 503
nqueens 10 109 10 104 10 110 10 442
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 165 10 177 10 540 10 632
rack 10 420 10 483 10 759 10 870
ruby-json 10 10 10 10 10 10 10 10
rubykon 10 10 10 10 10 10 10 10
sudoku 10 10 10 10 10 26 10 30
tinygql 10 21 10 23 10 45 10 52
30k_ifelse 10 10 10 10 10 70 10 70
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 251 10 253 10 1105 10 1212
fib 10 106 10 106 10 616 10 618
getivar 10 257 10 221 10 1283 10 1349
keyword_args 10 86 10 86 10 720 10 945
respond_to 10 85 10 94 10 1728 10 2149
ruby-xor 10 30 10 28 10 94 10 131
setivar 10 412 10 397 10 2352 10 3567
setivar_object 10 226 10 243 10 472 10 731
setivar_young 10 229 10 242 10 501 10 729
str_concat 10 328 10 296 10 639 10 522
throw 10 914 10 816 10 1164 10 1004

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) 1421093 1227337 214 2184 0 0% 0 0 66.833689
chunky-png (click) 332335 254130 82 1044 1 0% 0 0 31.27106
erubi-rails (click) 1686026 1411117 272 2905 6 0% 0 0 82.241949
hexapdf (click) 1290294 1130625 504 11518 41 0% 0 0 338.265646
liquid-c (click) 521560 406158 119 1757 5 0% 0 0 49.154662
liquid-compile (click) 445351 386582 151 2078 2 0% 0 0 64.7102
liquid-render (click) 618663 526446 136 2292 8 0% 0 0 64.292786
lobsters (click) 7563379 6337344 3110 48985 92 0% 0 0 1656.451114
mail (click) 725573 615353 346 4860 14 0% 0 0 146.48541
psych-load (click) 298636 233756 61 617 3 0% 0 0 19.892295
railsbench (click) 2947440 2574499 1633 15931 57 0% 0 0 466.591648
rubocop (click) 5328288 4413372 2901 48280 112 0% 4 0 1455.549804
ruby-lsp (click) 629149 560406 159 2818 28 0% 0 0 79.995553
sequel (click) 485514 441258 16 118 0 0% 0 0 4.354539
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.832397
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.638321
erubi (click) 271818 208559 10 112 0 0% 0 0 4.005671
etanni (click) 29692 28216 11 91 0 0% 0 0 2.992864
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.351645
fluentd (click) 379866 326186 4 28 0 0% 0 0 1.143712
graphql (click) 433463 373609 66 644 0 0% 0 0 20.472854
graphql-native (click) 404732 333251 41 273 0 0% 0 0 9.505106
lee (click) 295280 249128 34 528 0 0% 0 0 16.876602
matmul (click) 8300 983 8 85 0 0% 0 0 2.906717
nbody (click) 14798 17933 11 185 0 0% 0 0 5.378223
nqueens (click) 22703 29059 10 260 0 0% 0 0 7.95448
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 102.705735
protoboeuf (click) 146719 135165 17 1366 0 0% 0 0 42.53036
rack (click) 281029 218898 37 455 0 0% 0 0 12.374746
ruby-json (click) 30222 27890 8 167 0 0% 0 0 4.866143
rubykon (click) 127405 128474 137 1461 3 0% 0 0 42.178079
sudoku (click) 42479 58142 8 475 0 0% 0 0 15.008934
tinygql (click) 310335 278970 58 741 5 0% 0 0 22.30096
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1506.841854
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 515.225002
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.21381
fib (click) 4970 5003 8 49 0 0% 0 0 1.785359
getivar (click) 5963 6375 8 74 0 0% 0 0 2.220476
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.499079
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.63361
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.755971
setivar (click) 5102 5375 8 54 0 0% 0 0 1.850429
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.870983
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.093073
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.037325
throw (click) 7895 6377 10 69 0 0% 0 0 2.600941

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.