YJIT Benchmarks

Details for Benchmarks at 2024-03-09 19:08:17 UTC

YJIT metrics from the yjit-bench suite using Ruby d94ad00252

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.5% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.4% 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 30 526 30 526
chunky-png 30 32 30 32
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 351 30 351
liquid-compile 30 338 30 338
liquid-render 30 257 30 257
lobsters 30 23 30 23
mail 30 160 30 160
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 183 30 183
ruby-lsp 30 173 30 173
sequel 30 290 30 290
binarytrees 30 81 30 81
blurhash 30 99 30 99
erubi 30 76 30 76
etanni 30 51 30 51
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 30 302 30 302
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 41 30 41
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 417 30 417
getivar 30 946 30 946
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 122 30 122
setivar 30 2393 30 2393
setivar_object 30 477 30 477
setivar_young 30 508 30 508
str_concat 30 396 30 396
throw 30 746 30 746

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 758191 49 522 0 0% 0 0 15.996111
chunky-png (click) 337548 299786 87 1093 1 0% 0 0 32.833397
erubi-rails (click) 1711776 1449157 280 2921 6 0% 0 0 83.033962
hexapdf (click) 1419168 1243777 595 12571 38 0% 0 0 370.917301
liquid-c (click) 519073 435374 119 1754 5 0% 0 0 47.94734
liquid-compile (click) 447474 390164 151 2068 2 0% 0 0 63.009328
liquid-render (click) 623835 541382 136 2284 8 0% 0 0 63.186927
lobsters (click) 7888714 6607996 3217 50073 73 0% 0 0 1727.421281
mail (click) 732395 635954 346 4847 14 0% 0 0 143.672947
psych-load (click) 301215 253619 65 655 3 0% 0 0 20.544938
railsbench (click) 2998729 2566409 1638 15773 54 0% 0 0 453.264979
rubocop (click) 5367946 4510590 2901 47760 106 0% 4 0 1424.977074
ruby-lsp (click) 634011 533353 159 2735 14 0% 0 0 77.219812
sequel (click) 496306 428609 16 119 0 0% 0 0 4.53529
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.222163
blurhash (click) 52000 47236 32 461 0 0% 0 0 15.573227
erubi (click) 271214 230596 10 111 0 0% 0 0 3.83269
etanni (click) 31686 27819 12 96 0 0% 0 0 3.233856
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.845195
fluentd (click) 387873 311763 11 111 0 0% 0 0 3.610747
graphql (click) 443736 382893 70 673 0 0% 0 0 21.071978
graphql-native (click) 409288 344342 41 271 0 0% 0 0 9.483365
lee (click) 315849 277753 49 731 0 0% 0 0 22.958573
matmul (click) 12586 12175 12 126 0 0% 0 0 4.201046
nbody (click) 15103 7574 11 185 0 0% 0 0 5.03439
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.898746
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 104.536624
rack (click) 272097 234532 31 319 0 0% 0 0 9.252604
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.881365
rubykon (click) 133625 106471 143 1498 3 0% 0 0 41.939733
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.532912
tinygql (click) 313116 266157 63 787 5 0% 0 0 22.929406
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1506.332869
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 528.801659
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.236518
fib (click) 5017 4633 8 49 0 0% 0 0 1.790413
getivar (click) 6102 6023 8 74 0 0% 0 0 2.130009
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.556062
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.672135
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.183352
setivar (click) 5193 4604 8 54 0 0% 0 0 1.777698
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.865746
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.046613
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.880019
throw (click) 7946 6065 10 69 0 0% 0 0 2.508125

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.