YJIT Benchmarks

Details for Benchmarks at 2024-03-18 06:08:17 UTC

YJIT metrics from the yjit-bench suite using Ruby 0ff2c7fe6f

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.2% faster than CRuby 3.4.0dev
On railsbench it is
  • 80.4% 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 30 525 30 525
chunky-png 30 32 30 32
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 348 30 348
liquid-compile 30 342 30 342
liquid-render 30 254 30 254
lobsters 30 23 30 23
mail 30 163 30 163
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 183 30 183
ruby-lsp 30 206 30 206
sequel 30 290 30 290
binarytrees 30 84 30 84
blurhash 30 100 30 100
erubi 30 79 30 79
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 19 30 19
matmul 30 18 30 18
nbody 30 316 30 316
nqueens 30 305 30 305
optcarrot 30 15 30 15
protoboeuf 30 444 30 444
rack 30 181 30 181
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 26 30 26
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 30 945 30 945
keyword_args 30 592 30 592
respond_to 30 1480 30 1480
ruby-xor 30 125 30 125
setivar 30 2393 30 2393
setivar_object 30 477 30 477
setivar_young 30 506 30 506
str_concat 30 406 30 406
throw 30 734 30 734

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) 883948 766538 49 522 0 0% 0 0 15.828681
chunky-png (click) 337530 299786 87 1093 1 0% 0 0 32.573932
erubi-rails (click) 1709477 1447468 279 2920 6 0% 0 0 84.00735
hexapdf (click) 1417343 1250250 595 12554 38 0% 0 0 368.752534
liquid-c (click) 518923 443332 119 1754 5 0% 0 0 47.739501
liquid-compile (click) 448779 391246 151 2081 2 0% 0 0 63.720956
liquid-render (click) 623584 557611 136 2280 8 0% 0 0 62.259183
lobsters (click) 7888040 6600398 3220 50112 73 0% 0 0 1710.798082
mail (click) 732377 635954 346 4847 14 0% 0 0 143.025579
psych-load (click) 300866 253380 65 653 3 0% 0 0 20.184971
railsbench (click) 2997148 2589521 1638 15761 54 0% 0 0 451.971504
rubocop (click) 5365118 4590250 2901 47778 106 0% 4 0 1424.451507
ruby-lsp (click) 633123 516056 159 2757 14 0% 0 0 76.531133
sequel (click) 493284 425274 16 118 0 0% 0 0 4.46067
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.092843
blurhash (click) 52000 47236 32 461 0 0% 0 0 15.486383
erubi (click) 271201 230576 10 111 0 0% 0 0 3.848425
etanni (click) 31686 27819 12 96 0 0% 0 0 3.225697
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.834472
fluentd (click) 387855 311763 11 111 0 0% 0 0 3.609087
graphql (click) 442725 374031 70 673 0 0% 0 0 21.012087
graphql-native (click) 408277 343628 41 271 0 0% 0 0 9.181665
lee (click) 315831 277753 49 731 0 0% 0 0 22.866782
matmul (click) 12586 12175 12 126 0 0% 0 0 4.179078
nbody (click) 15103 7574 11 185 0 0% 0 0 5.008322
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.891228
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 104.902283
protoboeuf (click) 159155 142916 17 1422 0 0% 0 0 43.634412
rack (click) 272349 234720 31 322 0 0% 0 0 9.298648
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.807366
rubykon (click) 133999 114882 143 1500 3 0% 0 0 41.724706
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.481057
tinygql (click) 313098 266157 63 787 5 0% 0 0 23.134962
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1501.301434
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 521.244957
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.23179
fib (click) 5017 4633 8 49 0 0% 0 0 1.7829
getivar (click) 6102 6023 8 74 0 0% 0 0 2.178509
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.543954
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.644829
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.149193
setivar (click) 5193 4604 8 54 0 0% 0 0 1.731368
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.831804
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.034304
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.790859
throw (click) 7946 6065 10 69 0 0% 0 0 2.519729

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.