YJIT Benchmarks

Details for Benchmarks at 2024-03-08 06:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby 86ce78d73a

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 72.4% faster than CRuby 3.4.0dev
On railsbench it is
  • 81.5% 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 30 517 30 517
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 345 30 345
liquid-compile 30 341 30 341
liquid-render 30 254 30 254
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 30 176 30 176
sequel 30 290 30 290
binarytrees 30 87 30 87
blurhash 30 101 30 101
erubi 30 78 30 78
etanni 30 52 30 52
fannkuchredux 30 24 30 24
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 22 30 22
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 325 30 325
nqueens 30 304 30 304
optcarrot 30 15 30 15
rack 30 185 30 185
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 26 30 26
tinygql 30 42 30 42
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 417 30 417
getivar 30 942 30 942
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 102 30 102
setivar 30 2391 30 2391
setivar_object 30 488 30 488
setivar_young 30 505 30 505
str_concat 30 451 30 451
throw 30 759 30 759

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) 883844 758151 49 522 0 0% 0 0 16.103461
chunky-png (click) 337548 299786 87 1093 1 0% 0 0 32.481266
erubi-rails (click) 1713948 1442943 279 2937 6 0% 0 0 82.646758
hexapdf (click) 1417475 1242297 596 12557 38 0% 0 0 366.376317
liquid-c (click) 518202 459229 119 1754 5 0% 0 0 47.281514
liquid-compile (click) 447563 390273 151 2069 2 0% 0 0 62.425502
liquid-render (click) 624107 549653 136 2282 8 0% 0 0 62.469381
lobsters (click) 7890308 6621839 3217 50064 73 0% 0 0 1710.720806
mail (click) 732395 635986 346 4847 14 0% 0 0 142.730552
psych-load (click) 301646 262081 65 655 3 0% 0 0 20.376679
railsbench (click) 2996989 2573369 1638 15764 54 0% 0 0 452.744117
rubocop (click) 5371106 4562385 2901 47769 106 0% 4 0 1419.118781
ruby-lsp (click) 634011 541545 159 2735 14 0% 0 0 76.332753
sequel (click) 498328 429440 16 118 0 0% 0 0 4.304977
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.083046
blurhash (click) 52000 47236 32 461 0 0% 0 0 15.481132
erubi (click) 271214 230596 10 111 0 0% 0 0 3.878049
etanni (click) 31686 27819 12 96 0 0% 0 0 3.252628
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.831969
fluentd (click) 387873 311831 11 111 0 0% 0 0 3.580015
graphql (click) 443736 382897 70 673 0 0% 0 0 21.056627
graphql-native (click) 409288 344309 41 271 0 0% 0 0 9.315075
lee (click) 315849 277753 49 731 0 0% 0 0 22.826456
matmul (click) 12586 12175 12 126 0 0% 0 0 4.208602
nbody (click) 15103 7574 11 185 0 0% 0 0 5.038592
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.84538
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 104.955991
rack (click) 272097 234532 31 319 0 0% 0 0 9.16197
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.838316
rubykon (click) 135895 124742 143 1518 3 0% 0 0 42.696894
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.478646
tinygql (click) 313116 266157 63 787 5 0% 0 0 22.936485
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1475.615452
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 518.964462
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.239081
fib (click) 5017 4633 8 49 0 0% 0 0 1.777137
getivar (click) 6102 6023 8 74 0 0% 0 0 2.182071
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.52514
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.656043
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.151762
setivar (click) 5193 4604 8 54 0 0% 0 0 1.74646
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.844937
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.045755
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.886392
throw (click) 7946 6065 10 69 0 0% 0 0 2.500943

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.