YJIT Benchmarks

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

YJIT metrics from the yjit-bench suite using Ruby b4b39a6199

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 70.5% faster than CRuby 3.4.0dev
On railsbench it is
  • 78.4% 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 53 10 135
chunky-png 10 17 10 38
erubi-rails 10 10 10 20
hexapdf 10 10 10 10
liquid-c 10 345 10 497
liquid-compile 10 338 10 493
liquid-render 10 133 10 357
lobsters 10 12 10 23
mail 10 155 10 228
psych-load 10 10 10 10
railsbench 10 10 10 10
rubocop 10 131 10 241
ruby-lsp 10 175 10 242
sequel 10 310 10 420
binarytrees 10 50 10 120
blurhash 10 57 10 142
erubi 10 84 10 105
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 20
matmul 10 10 10 16
nbody 10 200 10 468
nqueens 10 108 10 454
optcarrot 10 10 10 10
protoboeuf 10 181 10 725
rack 10 457 10 826
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 10 261 10 1212
fib 10 102 10 618
getivar 10 249 10 1369
keyword_args 10 86 10 945
respond_to 10 91 10 2150
ruby-xor 10 30 10 144
setivar 10 363 10 3542
setivar_object 10 177 10 501
setivar_young 10 176 10 516
str_concat 10 334 10 615
throw 10 938 10 1150

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) 1444008 1257849 224 2320 0 0% 0 0 69.174979
chunky-png (click) 327754 258461 82 1048 1 0% 0 0 30.966358
erubi-rails (click) 1690046 1436758 272 2893 6 0% 0 0 80.887473
hexapdf (click) 1290427 1130879 505 11522 41 0% 0 0 333.681047
liquid-c (click) 525934 465131 119 1757 5 0% 0 0 48.901461
liquid-compile (click) 450648 380676 151 2078 2 0% 0 0 64.758101
liquid-render (click) 623961 528746 136 2292 8 0% 0 0 63.543227
lobsters (click) 7573361 6321978 3110 49075 89 0% 0 0 1646.60158
mail (click) 720578 651844 346 4865 14 0% 0 0 143.792174
psych-load (click) 303929 244228 61 617 3 0% 0 0 19.805052
railsbench (click) 2953605 2511990 1633 15935 57 0% 0 0 459.120923
rubocop (click) 5329322 4567374 2901 48240 112 0% 4 0 1443.454409
ruby-lsp (click) 633673 578275 159 2808 28 0% 0 0 78.779255
sequel (click) 488984 409611 16 117 0 0% 0 0 4.260701
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.812585
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.23708
erubi (click) 266104 220212 10 112 0 0% 0 0 3.803898
etanni (click) 29692 28216 11 91 0 0% 0 0 2.967918
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.242453
fluentd (click) 385230 328452 4 28 0 0% 0 0 1.161012
graphql (click) 427888 327933 66 644 0 0% 0 0 19.800151
graphql-native (click) 410040 360440 42 278 0 0% 0 0 9.36941
lee (click) 300573 267787 34 528 0 0% 0 0 16.897054
matmul (click) 8300 983 8 85 0 0% 0 0 2.933292
nbody (click) 14798 17933 11 185 0 0% 0 0 5.223431
nqueens (click) 22703 29059 10 260 0 0% 0 0 7.883433
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 101.92348
protoboeuf (click) 146719 135165 17 1366 0 0% 0 0 41.781093
rack (click) 277544 214515 37 409 0 0% 0 0 11.297266
ruby-json (click) 30222 27890 8 167 0 0% 0 0 4.842662
rubykon (click) 127405 128474 137 1461 3 0% 0 0 42.051871
sudoku (click) 42479 58142 8 475 0 0% 0 0 14.842323
tinygql (click) 315372 264441 58 741 5 0% 0 0 21.461474
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1495.477124
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 511.45877
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.227501
fib (click) 4970 5003 8 49 0 0% 0 0 1.767531
getivar (click) 5963 6375 8 74 0 0% 0 0 2.124206
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.522726
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.605895
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.75976
setivar (click) 5102 5375 8 54 0 0% 0 0 1.792114
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.8711
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.084307
str_concat (click) 7774 7946 11 85 0 0% 0 0 2.895811
throw (click) 7895 6377 10 69 0 0% 0 0 2.569427

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.