YJIT Benchmarks

Details for Benchmarks at 2024-03-24 19:08:18 UTC

YJIT metrics from the yjit-bench suite using Ruby 5e4b4d6674

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 74.4% faster than CRuby 3.4.0dev
On railsbench it is
  • 80.1% 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 30 531 30 531
chunky-png 30 31 30 31
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 349 30 349
liquid-compile 30 339 30 339
liquid-render 30 253 30 253
lobsters 30 23 30 23
mail 30 160 30 160
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 185 30 185
ruby-lsp 30 205 30 205
sequel 30 286 30 286
binarytrees 30 84 30 84
blurhash 30 101 30 101
erubi 30 76 30 76
etanni 30 24 30 24
fannkuchredux 30 24 30 24
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 31 30 31
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 331 30 331
nqueens 30 296 30 296
optcarrot 30 15 30 15
protoboeuf 30 447 30 447
rack 30 179 30 179
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 25 30 25
tinygql 30 41 30 41
30k_ifelse 30 55 30 55
30k_methods 30 24 30 24
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 944 30 944
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 110 30 110
setivar 30 2391 30 2391
setivar_object 30 488 30 488
setivar_young 30 503 30 503
str_concat 30 418 30 418
throw 30 754 30 754

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) 884764 766544 49 522 0 0% 0 0 15.783629
chunky-png (click) 338152 291620 87 1093 1 0% 0 0 32.562025
erubi-rails (click) 1709805 1413185 279 2903 6 0% 0 0 84.463409
hexapdf (click) 1419746 1202543 595 12571 38 0% 0 0 371.239285
liquid-c (click) 524560 439464 119 1754 5 0% 0 0 47.543205
liquid-compile (click) 449584 391279 151 2078 2 0% 0 0 64.705225
liquid-render (click) 624105 549265 136 2280 8 0% 0 0 62.540767
lobsters (click) 7882304 6603184 3219 50076 73 0% 0 0 1726.619636
mail (click) 733001 627912 346 4847 14 0% 0 0 145.132558
psych-load (click) 301941 253685 65 655 3 0% 0 0 20.796334
railsbench (click) 2998938 2605586 1638 15764 54 0% 0 0 456.293819
rubocop (click) 5370718 4544442 2901 47764 106 0% 4 0 1447.860063
ruby-lsp (click) 634719 549782 159 2720 14 0% 0 0 76.488127
sequel (click) 498968 421807 16 117 0 0% 0 0 4.233019
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.044418
blurhash (click) 52005 47236 32 461 0 0% 0 0 15.581707
erubi (click) 271828 214258 10 111 0 0% 0 0 3.872839
etanni (click) 31211 27374 11 91 0 0% 0 0 3.050864
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.896594
fluentd (click) 388649 328272 11 111 0 0% 0 0 3.624898
graphql (click) 444946 383184 70 673 0 0% 0 0 20.857368
graphql-native (click) 410622 344869 42 276 0 0% 0 0 9.137209
lee (click) 316673 261419 49 732 0 0% 0 0 22.992612
matmul (click) 12586 12175 12 126 0 0% 0 0 4.188578
nbody (click) 15103 7574 11 185 0 0% 0 0 5.041651
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.855481
optcarrot (click) 317102 278432 192 4342 34 0% 0 0 104.934179
protoboeuf (click) 159155 142916 17 1422 0 0% 0 0 44.30077
rack (click) 272701 234526 31 319 0 0% 0 0 9.25565
ruby-json (click) 28200 23070 12 198 0 0% 0 0 5.869237
rubykon (click) 135895 124742 143 1518 3 0% 0 0 42.876791
sudoku (click) 47017 45195 11 507 0 0% 0 0 15.611302
tinygql (click) 313454 265632 63 780 2 0% 0 0 23.24435
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1485.042608
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 531.490745
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.248017
fib (click) 5017 4633 8 49 0 0% 0 0 1.775224
getivar (click) 6102 6023 8 74 0 0% 0 0 2.214502
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.549983
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.70144
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.172252
setivar (click) 5193 4604 8 54 0 0% 0 0 1.760276
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.843817
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.074317
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.873008
throw (click) 7946 6065 10 69 0 0% 0 0 2.502275

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.