YJIT Benchmarks

Details for Benchmarks at 2024-06-19 06:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby ed2f8ea62e

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.7% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.3
On railsbench it is
  • 76.0% faster than CRuby 3.4.0dev
  • 2.1% slower than YJIT 3.3.3

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 3.3.3 warmups CRuby 3.3.3 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.3 warmups YJIT 3.3.3 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 51 10 47 10 116 10 118
chunky-png 10 18 10 15 10 36 10 36
erubi-rails 10 10 10 10 10 21 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 352 10 333 10 505 10 472
liquid-compile 10 341 10 331 10 489 10 487
liquid-render 10 137 10 134 10 353 10 350
mail 10 162 10 147 10 238 10 218
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 137 10 127 10 229 10 235
ruby-lsp 10 193 10 191 10 262 10 279
sequel 10 324 10 302 10 437 10 405
binarytrees 10 51 10 47 10 117 10 112
blurhash 10 62 10 56 10 118 10 143
erubi 10 83 10 82 10 103 10 103
etanni 10 58 10 57 10 68 10 67
fannkuchredux 10 10 10 10 10 18 10 16
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 34 10 33 10 39 10 38
lee 10 11 10 10 10 19 10 21
matmul 10 10 10 10 10 15 10 16
nbody 10 211 10 187 10 385 10 470
nqueens 10 115 10 101 10 114 10 449
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 189 10 170 10 681 10 658
rack 10 469 10 469 10 812 10 881
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 31 10 31
tinygql 10 24 10 22 10 52 10 50
30k_ifelse 10 10 10 10 10 70 10 70
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 257 10 235 10 1105 10 1211
fib 10 103 10 94 10 616 10 618
getivar 10 250 10 223 10 1284 10 1353
keyword_args 10 90 10 84 10 726 10 944
respond_to 10 87 10 84 10 1782 10 2148
ruby-xor 10 31 10 25 10 100 10 131
setivar 10 424 10 396 10 2353 10 3567
setivar_object 10 264 10 269 10 654 10 737
setivar_young 10 265 10 269 10 651 10 729
str_concat 10 327 10 280 10 592 10 528
throw 10 974 10 817 10 1275 10 1028

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) 1403105 1122243 214 2166 0 0% 0 0 76.233528
chunky-png (click) 331257 268947 82 1053 1 0% 0 0 33.846773
erubi-rails (click) 1676303 1430664 272 2899 6 0% 0 0 96.065797
hexapdf (click) 1288403 1081135 504 11685 41 0% 0 0 376.533636
liquid-c (click) 517841 425381 119 1761 5 0% 0 0 53.220887
liquid-compile (click) 441050 388479 151 2075 2 0% 0 0 69.559359
liquid-render (click) 612809 533640 136 2302 8 0% 0 0 70.723283
mail (click) 723221 636316 346 4881 14 0% 0 0 156.749291
psych-load (click) 293176 243984 61 594 3 0% 0 0 20.612276
railsbench (click) 2924358 2545328 1633 15912 57 0% 0 0 558.317996
rubocop (click) 5430855 4630057 2891 50362 110 0% 4 0 1783.405743
ruby-lsp (click) 636016 518939 159 2903 28 0% 0 0 90.195202
sequel (click) 485894 416151 16 117 0 0% 0 0 5.309941
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.973397
blurhash (click) 50429 43324 31 457 0 0% 0 0 17.12297
erubi (click) 270214 214579 10 112 0 0% 0 0 4.435964
etanni (click) 30236 28701 12 96 0 0% 0 0 3.501326
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.929984
fluentd (click) 375007 342734 4 28 0 0% 0 0 1.269787
graphql (click) 430898 362014 66 648 0 0% 0 0 22.486455
graphql-native (click) 402926 330770 42 278 0 0% 0 0 10.771131
lee (click) 293365 214005 34 531 0 0% 0 0 18.187632
matmul (click) 8315 983 8 86 0 0% 0 0 3.005981
nbody (click) 14798 17933 11 185 0 0% 0 0 5.575691
nqueens (click) 22145 28339 10 257 0 0% 0 0 8.914599
optcarrot (click) 304463 277860 188 4310 34 0% 0 0 108.660004
protoboeuf (click) 140419 133760 17 1349 0 0% 0 0 43.364121
rack (click) 278736 232128 37 445 0 0% 0 0 13.200409
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.23906
rubykon (click) 128391 79892 137 1484 3 0% 0 0 45.38541
sudoku (click) 41994 57542 8 473 0 0% 0 0 16.047666
tinygql (click) 307906 259268 58 734 5 0% 0 0 23.258461
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1898.991658
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 535.43855
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.338214
fib (click) 4970 5003 8 49 0 0% 0 0 1.973609
getivar (click) 5963 6375 8 74 0 0% 0 0 2.253538
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.597843
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.784093
ruby-xor (click) 5565 5673 5 62 0 0% 0 0 1.865039
setivar (click) 5102 5375 8 54 0 0% 0 0 1.928063
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.996407
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.22894
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.063701
throw (click) 7895 6377 10 69 0 0% 0 0 2.635617

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.