YJIT Benchmarks

Details for Benchmarks at 2024-02-22 19:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby a16fefcff5

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.5% faster than CRuby 3.4.0dev
On railsbench it is
  • 80.0% 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 30 519 30 519
chunky-png 30 30 30 30
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 352 30 352
liquid-compile 30 344 30 344
liquid-render 30 255 30 255
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 184 30 184
ruby-lsp 30 177 30 177
sequel 30 293 30 293
binarytrees 30 88 30 88
blurhash 30 102 30 102
erubi 30 77 30 77
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 30 333 30 333
nqueens 30 305 30 305
optcarrot 30 15 30 15
rack 30 178 30 178
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 30 416 30 416
getivar 30 939 30 939
keyword_args 30 592 30 592
respond_to 30 1480 30 1480
ruby-xor 30 87 30 87
setivar 30 2392 30 2392
setivar_object 30 488 30 488
setivar_young 30 506 30 506
str_concat 30 416 30 416
throw 30 784 30 784

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) 888150 769628 49 525 0 0% 0 0 15.936163
chunky-png (click) 337863 291403 87 1096 1 0% 0 0 32.497165
erubi-rails (click) 1721114 1414302 280 2907 6 0% 0 0 84.166543
hexapdf (click) 1428034 1261226 596 12668 38 0% 0 0 373.095864
liquid-c (click) 524878 448627 120 1753 5 0% 0 0 47.778865
liquid-compile (click) 448050 398944 151 2069 2 0% 0 0 63.027328
liquid-render (click) 626276 550937 144 2273 8 0% 0 0 63.580365
lobsters (click) 7912436 6598927 3218 50150 74 0% 0 0 1722.626347
mail (click) 732438 611730 346 4846 14 0% 0 0 142.919414
psych-load (click) 301391 253853 65 655 3 0% 0 0 20.411622
railsbench (click) 3014835 2612311 1643 15666 54 0% 0 0 453.952827
rubocop (click) 5362901 4602123 2902 47752 106 0% 4 0 1426.594411
ruby-lsp (click) 638849 554902 159 2793 14 0% 0 0 78.128718
sequel (click) 499807 423971 16 116 0 0% 0 0 3.999734
binarytrees (click) 9392 7588 11 75 0 0% 0 0 2.957026
blurhash (click) 52098 47218 32 461 0 0% 0 0 15.519308
erubi (click) 271414 222726 10 111 0 0% 0 0 3.865768
etanni (click) 31710 27867 12 96 0 0% 0 0 3.241749
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.886154
fluentd (click) 389820 321093 11 111 0 0% 0 0 3.619075
graphql (click) 443824 382807 70 673 0 0% 0 0 20.872467
graphql-native (click) 408948 344026 41 271 0 0% 0 0 9.239723
lee (click) 316023 278067 49 731 0 0% 0 0 23.076739
matmul (click) 12586 12175 12 126 0 0% 0 0 4.212306
nbody (click) 15103 7574 11 185 0 0% 0 0 5.069572
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.847114
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 104.856643
rack (click) 272700 235065 31 322 0 0% 0 0 9.40014
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.865496
rubykon (click) 133999 114882 143 1500 3 0% 0 0 42.164689
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.544607
tinygql (click) 313384 266366 63 788 5 0% 0 0 22.937142
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1504.782252
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 525.679949
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.230725
fib (click) 5017 4633 8 49 0 0% 0 0 1.770905
getivar (click) 6102 6023 8 74 0 0% 0 0 2.125786
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.560544
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.657674
ruby-xor (click) 8142 7087 9 87 0 0% 0 0 3.070011
setivar (click) 5193 4604 8 54 0 0% 0 0 1.757426
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.831282
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.043267
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.918307
throw (click) 7946 6065 10 69 0 0% 0 0 2.464841

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.