YJIT Benchmarks

Details for Benchmarks at 2024-03-26 19:08:15 UTC

YJIT metrics from the yjit-bench suite using Ruby 4a78d75213

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.7% faster than CRuby 3.4.0dev
On railsbench it is
  • 78.9% 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 30 528 30 528
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 348 30 348
liquid-compile 30 354 30 354
liquid-render 30 253 30 253
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 181 30 181
ruby-lsp 30 203 30 203
sequel 30 290 30 290
binarytrees 30 83 30 83
blurhash 30 102 30 102
erubi 30 75 30 75
etanni 30 24 30 24
fannkuchredux 30 23 30 23
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 325 30 325
nqueens 30 303 30 303
optcarrot 30 15 30 15
protoboeuf 30 416 30 416
rack 30 182 30 182
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 24 30 24
tinygql 30 39 30 39
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 417 30 417
getivar 30 945 30 945
keyword_args 30 592 30 592
respond_to 30 1480 30 1480
ruby-xor 30 104 30 104
setivar 30 2391 30 2391
setivar_object 30 481 30 481
setivar_young 30 506 30 506
str_concat 30 411 30 411
throw 30 760 30 760

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) 883290 773258 49 522 0 0% 0 0 15.888465
chunky-png (click) 337917 299285 87 1093 1 0% 0 0 32.51378
erubi-rails (click) 1705542 1441010 276 2889 6 0% 0 0 80.855911
hexapdf (click) 1418748 1192219 596 12574 38 0% 0 0 368.900691
liquid-c (click) 524422 446803 119 1754 5 0% 0 0 47.939168
liquid-compile (click) 447400 397216 151 2064 2 0% 0 0 63.104133
liquid-render (click) 623922 564499 136 2285 8 0% 0 0 62.441152
lobsters (click) 7871325 6583835 3211 49963 73 0% 0 0 1702.41521
mail (click) 732129 617905 346 4847 14 0% 0 0 141.284379
psych-load (click) 301724 253180 65 655 3 0% 0 0 20.58868
railsbench (click) 2990654 2541076 1634 15757 54 0% 0 0 455.235846
rubocop (click) 5370611 4567105 2901 47766 106 0% 4 0 1422.220621
ruby-lsp (click) 633106 539707 159 2725 14 0% 0 0 76.675611
sequel (click) 495948 435236 16 118 0 0% 0 0 4.239484
binarytrees (click) 9384 7556 11 75 0 0% 0 0 2.9465
blurhash (click) 51966 47132 32 461 0 0% 0 0 15.600248
erubi (click) 271655 230266 10 111 0 0% 0 0 3.834414
etanni (click) 31131 27054 11 91 0 0% 0 0 3.029059
fannkuchredux (click) 24443 9175 9 257 0 0% 0 0 7.758405
fluentd (click) 388157 327764 11 111 0 0% 0 0 3.577232
graphql (click) 444060 381559 70 673 0 0% 0 0 20.148084
graphql-native (click) 411115 345097 42 276 0 0% 0 0 9.277095
lee (click) 316577 269356 49 732 0 0% 0 0 22.922954
matmul (click) 12555 12107 12 126 0 0% 0 0 4.222631
nbody (click) 15072 7506 11 185 0 0% 0 0 4.988181
nqueens (click) 23509 25983 10 261 0 0% 0 0 7.852578
optcarrot (click) 316603 318930 192 4342 34 0% 0 0 104.002073
protoboeuf (click) 157753 136477 17 1422 0 0% 0 0 42.773187
rack (click) 272835 234522 31 322 0 0% 0 0 9.412363
ruby-json (click) 34095 28619 12 196 0 0% 0 0 5.75176
rubykon (click) 133943 122908 143 1500 3 0% 0 0 42.011703
sudoku (click) 46892 53197 11 507 0 0% 0 0 15.487593
tinygql (click) 313520 265883 63 787 5 0% 0 0 23.139023
30k_ifelse (click) 5222589 4374204 9264 50813 0 0% 0 0 1449.850719
30k_methods (click) 2019606 1594020 5782 19369 0 0% 0 0 522.212543
cfunc_itself (click) 7581 5778 9 70 0 0% 0 0 2.228466
fib (click) 5009 4601 8 49 0 0% 0 0 1.779006
getivar (click) 6094 5991 8 74 0 0% 0 0 2.135362
keyword_args (click) 8464 6470 10 72 0 0% 0 0 2.56815
respond_to (click) 8333 7728 9 85 0 0% 0 0 2.641017
ruby-xor (click) 8062 6902 9 87 0 0% 0 0 3.115767
setivar (click) 5185 4572 8 54 0 0% 0 0 1.752571
setivar_object (click) 5553 4592 8 54 0 0% 0 0 1.845382
setivar_young (click) 6276 5242 9 62 0 0% 0 0 2.047648
str_concat (click) 7876 7217 11 85 0 0% 0 0 2.861127
throw (click) 7938 6033 10 69 0 0% 0 0 2.475808

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.