YJIT Benchmarks

Details for Benchmarks at 2024-04-28 19:08:14 UTC

YJIT metrics from the yjit-bench suite using Ruby 29aaf4abe6

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 69.7% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.4% 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 30 493 30 493
chunky-png 30 32 30 32
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 344 30 344
liquid-compile 30 339 30 339
liquid-render 30 247 30 247
lobsters 30 22 30 22
mail 30 161 30 161
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 180 30 180
ruby-lsp 30 167 30 167
sequel 30 285 30 285
binarytrees 30 88 30 88
blurhash 30 101 30 101
erubi 30 76 30 76
etanni 30 24 30 24
fannkuchredux 30 25 30 25
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 19 30 19
matmul 30 17 30 17
nbody 30 320 30 320
nqueens 30 329 30 329
optcarrot 30 15 30 15
protoboeuf 30 407 30 407
rack 30 178 30 178
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 27 30 27
tinygql 30 38 30 38
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 826 30 826
fib 30 418 30 418
getivar 30 1013 30 1013
keyword_args 30 646 30 646
respond_to 30 1462 30 1462
ruby-xor 30 109 30 109
setivar 30 2546 30 2546
setivar_object 30 415 30 415
setivar_young 30 431 30 431
str_concat 30 422 30 422
throw 30 786 30 786

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) 881754 761002 49 528 0 0% 0 0 16.288747
chunky-png (click) 333979 274395 87 1094 1 0% 0 0 32.861773
erubi-rails (click) 1691969 1484054 277 2973 6 0% 0 0 85.041557
hexapdf (click) 1405948 1124784 597 12705 41 0% 0 0 376.575574
liquid-c (click) 516808 404212 119 1757 5 0% 0 0 49.32416
liquid-compile (click) 441723 385632 151 2081 2 0% 0 0 64.765313
liquid-render (click) 615301 541938 136 2294 8 0% 0 0 64.72036
lobsters (click) 7792881 6511271 3211 51058 89 0% 0 0 1737.273873
mail (click) 722587 631023 346 4865 14 0% 0 0 146.125934
psych-load (click) 298270 277006 65 656 3 0% 0 0 20.845439
railsbench (click) 2962379 2532177 1634 15934 57 0% 0 0 467.449984
rubocop (click) 5321213 4622073 2901 48252 109 0% 4 0 1459.047944
ruby-lsp (click) 625503 518561 159 2803 28 0% 0 0 78.891155
sequel (click) 489509 425393 16 117 0 0% 0 0 4.340141
binarytrees (click) 9300 8262 11 75 0 0% 0 0 3.097201
blurhash (click) 50973 43758 32 460 0 0% 0 0 15.985481
erubi (click) 268015 240244 10 112 0 0% 0 0 3.889109
etanni (click) 29692 28216 11 91 0 0% 0 0 2.99178
fannkuchredux (click) 23856 29309 9 257 0 0% 0 0 8.486039
fluentd (click) 382136 331435 11 111 0 0% 0 0 3.718953
graphql (click) 433879 351541 70 685 0 0% 0 0 21.194903
graphql-native (click) 401449 340681 42 278 0 0% 0 0 9.519506
lee (click) 313294 278323 49 737 0 0% 0 0 23.605995
matmul (click) 12453 4981 12 126 0 0% 0 0 4.490548
nbody (click) 14798 17933 11 185 0 0% 0 0 5.247289
nqueens (click) 22703 29059 10 260 0 0% 0 0 8.007285
optcarrot (click) 311581 267827 192 4326 34 0% 0 0 103.824541
protoboeuf (click) 148013 144784 17 1378 0 0% 0 0 42.856148
rack (click) 269664 213977 31 323 0 0% 0 0 9.601299
ruby-json (click) 32870 30395 12 196 0 0% 0 0 6.017876
rubykon (click) 131218 132129 143 1501 3 0% 0 0 43.189342
sudoku (click) 45463 61097 11 507 0 0% 0 0 16.033992
tinygql (click) 310457 273364 63 787 5 0% 0 0 23.260005
30k_ifelse (click) 5137861 4732461 9264 50813 0 0% 0 0 1507.546746
30k_methods (click) 2019563 1594382 5782 19369 0 0% 0 0 524.821434
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.422649
fib (click) 4970 5003 8 49 0 0% 0 0 2.018714
getivar (click) 5963 6375 8 74 0 0% 0 0 2.435215
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.756365
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.871952
ruby-xor (click) 7891 7863 9 87 0 0% 0 0 2.888114
setivar (click) 5102 5375 8 54 0 0% 0 0 2.130507
setivar_object (click) 5470 5395 8 54 0 0% 0 0 2.368677
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.577866
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.041379
throw (click) 7895 6377 10 69 0 0% 0 0 2.424452

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.