YJIT Benchmarks

Details for Benchmarks at 2024-03-20 06:08:15 UTC

YJIT metrics from the yjit-bench suite using Ruby e5b585ba90

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.0% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.9% 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 30 528 30 528
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 30 342 30 342
liquid-render 30 253 30 253
lobsters 30 23 30 23
mail 30 161 30 161
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 184 30 184
ruby-lsp 30 206 30 206
sequel 30 289 30 289
binarytrees 30 85 30 85
blurhash 30 101 30 101
erubi 30 76 30 76
etanni 30 24 30 24
fannkuchredux 30 23 30 23
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 30 326 30 326
nqueens 30 300 30 300
optcarrot 30 15 30 15
protoboeuf 30 454 30 454
rack 30 177 30 177
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 30 940 30 940
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 102 30 102
setivar 30 2392 30 2392
setivar_object 30 492 30 492
setivar_young 30 504 30 504
str_concat 30 421 30 421
throw 30 735 30 735

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) 885233 766756 49 525 0 0% 0 0 15.603272
chunky-png (click) 338152 291620 87 1093 1 0% 0 0 32.765578
erubi-rails (click) 1713910 1409293 280 2955 6 0% 0 0 83.92418
hexapdf (click) 1417954 1217516 595 12554 38 0% 0 0 368.853725
liquid-c (click) 524790 431507 119 1754 5 0% 0 0 47.402868
liquid-compile (click) 448301 390359 151 2069 2 0% 0 0 63.570784
liquid-render (click) 624105 549265 136 2280 8 0% 0 0 62.156167
lobsters (click) 7891124 6565981 3219 50137 73 0% 0 0 1717.373833
mail (click) 733001 627880 346 4847 14 0% 0 0 142.61257
psych-load (click) 301941 253685 65 655 3 0% 0 0 20.559461
railsbench (click) 2998502 2605852 1638 15764 54 0% 0 0 454.64471
rubocop (click) 5370976 4544661 2901 47759 106 0% 4 0 1428.308072
ruby-lsp (click) 634719 533430 159 2735 14 0% 0 0 77.873871
sequel (click) 497202 420455 16 117 0 0% 0 0 4.114576
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.03158
blurhash (click) 52005 47236 32 461 0 0% 0 0 15.44272
erubi (click) 271828 214258 10 111 0 0% 0 0 3.877456
etanni (click) 31211 27374 11 91 0 0% 0 0 3.05366
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 8.038021
fluentd (click) 388649 328236 11 111 0 0% 0 0 3.625043
graphql (click) 444836 374797 70 673 0 0% 0 0 20.898282
graphql-native (click) 410941 344921 42 276 0 0% 0 0 9.249495
lee (click) 316673 261419 49 732 0 0% 0 0 23.044218
matmul (click) 12586 12175 12 126 0 0% 0 0 4.21033
nbody (click) 15103 7574 11 185 0 0% 0 0 5.0408
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.875898
optcarrot (click) 317102 278432 192 4342 34 0% 0 0 104.14639
protoboeuf (click) 159155 142916 17 1422 0 0% 0 0 43.896995
rack (click) 272971 234810 31 322 0 0% 0 0 9.417062
ruby-json (click) 28200 23070 12 198 0 0% 0 0 5.87732
rubykon (click) 135895 124742 143 1518 3 0% 0 0 42.719831
sudoku (click) 47017 45195 11 507 0 0% 0 0 15.519207
tinygql (click) 313454 265632 63 780 2 0% 0 0 22.77234
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1462.58367
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 523.862001
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.259078
fib (click) 5017 4633 8 49 0 0% 0 0 1.807631
getivar (click) 6102 6023 8 74 0 0% 0 0 2.168197
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.542681
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.658455
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.125182
setivar (click) 5193 4604 8 54 0 0% 0 0 1.758919
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.868679
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.05458
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.902795
throw (click) 7946 6065 10 69 0 0% 0 0 2.469764

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.