YJIT Benchmarks

Details for Benchmarks at 2024-05-08 19:08:14 UTC

YJIT metrics from the yjit-bench suite using Ruby 442e398e62

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 70.0% faster than CRuby 3.4.0dev
On railsbench it is
  • 78.2% 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 19
hexapdf 10 10 10 10
liquid-c 10 346 10 496
liquid-compile 10 338 10 501
liquid-render 10 133 10 360
lobsters 10 12 10 23
mail 10 156 10 228
psych-load 10 10 10 10
railsbench 10 10 10 10
rubocop 10 131 10 242
ruby-lsp 10 175 10 242
sequel 10 311 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 10 201 10 468
nqueens 10 108 10 454
optcarrot 10 10 10 10
protoboeuf 10 181 10 725
rack 10 454 10 834
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 10 256 10 1374
keyword_args 10 88 10 945
respond_to 10 90 10 2150
ruby-xor 10 30 10 144
setivar 10 373 10 3549
setivar_object 10 176 10 501
setivar_young 10 177 10 517
str_concat 10 335 10 614
throw 10 939 10 1151

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) 1443878 1200065 224 2320 0 0% 0 0 69.554601
chunky-png (click) 327754 258461 82 1048 1 0% 0 0 31.150421
erubi-rails (click) 1690046 1420506 272 2893 6 0% 0 0 81.11037
hexapdf (click) 1290318 1130677 504 11519 41 0% 0 0 334.238486
liquid-c (click) 525934 456939 119 1757 5 0% 0 0 48.919483
liquid-compile (click) 450648 380676 151 2078 2 0% 0 0 64.571136
liquid-render (click) 623961 528746 136 2292 8 0% 0 0 63.614669
lobsters (click) 7561954 6389366 3110 48952 89 0% 0 0 1638.333144
mail (click) 720578 651844 346 4865 14 0% 0 0 143.171191
psych-load (click) 303929 244228 61 617 3 0% 0 0 19.64275
railsbench (click) 2955104 2530107 1633 15939 57 0% 0 0 457.142573
rubocop (click) 5329996 4551533 2901 48241 111 0% 4 0 1441.842181
ruby-lsp (click) 633774 553812 159 2808 28 0% 0 0 77.577334
sequel (click) 489103 425981 16 118 0 0% 0 0 4.339975
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.785901
blurhash (click) 50429 43273 31 455 0 0% 0 0 15.221834
erubi (click) 266104 220212 10 112 0 0% 0 0 3.805902
etanni (click) 29692 28216 11 91 0 0% 0 0 2.989708
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.201454
fluentd (click) 385230 320328 4 28 0 0% 0 0 1.123213
graphql (click) 427888 327929 66 644 0 0% 0 0 19.769357
graphql-native (click) 410104 360421 42 278 0 0% 0 0 9.365961
lee (click) 300573 267787 34 528 0 0% 0 0 16.954931
matmul (click) 8300 983 8 85 0 0% 0 0 2.932072
nbody (click) 14798 17933 11 185 0 0% 0 0 5.190274
nqueens (click) 22703 29059 10 260 0 0% 0 0 7.887831
optcarrot (click) 307949 264223 188 4285 34 0% 0 0 101.917031
protoboeuf (click) 146719 135165 17 1366 0 0% 0 0 41.767047
rack (click) 280500 209886 37 445 0 0% 0 0 12.258366
ruby-json (click) 30222 27890 8 167 0 0% 0 0 4.888177
rubykon (click) 127405 128474 137 1461 3 0% 0 0 41.359593
sudoku (click) 42479 58142 8 475 0 0% 0 0 14.800061
tinygql (click) 315372 264441 58 741 5 0% 0 0 21.384809
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1496.579691
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 512.433337
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.221204
fib (click) 4970 5003 8 49 0 0% 0 0 1.751287
getivar (click) 5963 6375 8 74 0 0% 0 0 2.106858
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.497736
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.626538
ruby-xor (click) 5593 5796 5 62 0 0% 0 0 1.727185
setivar (click) 5102 5375 8 54 0 0% 0 0 1.772311
setivar_object (click) 5470 5395 8 54 0 0% 0 0 1.858548
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.062025
str_concat (click) 7774 7946 11 85 0 0% 0 0 2.881249
throw (click) 7895 6377 10 69 0 0% 0 0 2.589193

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.