YJIT Benchmarks

Details for Benchmarks at 2024-03-13 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 42bfbe9aa6

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
  • 80.9% 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 30 532 30 532
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 350 30 350
liquid-compile 30 345 30 345
liquid-render 30 257 30 257
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 30 177 30 177
sequel 30 291 30 291
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 23 30 23
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 333 30 333
nqueens 30 304 30 304
optcarrot 30 15 30 15
rack 30 175 30 175
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 30 417 30 417
getivar 30 942 30 942
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 98 30 98
setivar 30 2392 30 2392
setivar_object 30 488 30 488
setivar_young 30 506 30 506
str_concat 30 444 30 444
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) 883826 758223 49 522 0 0% 0 0 15.929763
chunky-png (click) 337530 299786 87 1093 1 0% 0 0 32.631058
erubi-rails (click) 1711807 1449077 279 2916 6 0% 0 0 82.509494
hexapdf (click) 1418610 1251686 596 12570 38 0% 0 0 369.860271
liquid-c (click) 518184 459229 119 1754 5 0% 0 0 47.860462
liquid-compile (click) 447456 390164 151 2068 2 0% 0 0 63.20028
liquid-render (click) 623354 549204 136 2280 8 0% 0 0 63.110053
lobsters (click) 7890821 6595971 3219 50142 73 0% 0 0 1715.71709
mail (click) 732377 635986 346 4847 14 0% 0 0 143.086141
psych-load (click) 301197 253619 65 655 3 0% 0 0 20.558804
railsbench (click) 2998295 2582826 1638 15773 54 0% 0 0 454.924817
rubocop (click) 5371170 4570589 2901 47779 106 0% 4 0 1434.807263
ruby-lsp (click) 634003 557962 159 2735 14 0% 0 0 76.668859
sequel (click) 496402 428311 16 114 0 0% 0 0 4.083622
binarytrees (click) 9392 7588 11 75 0 0% 0 0 3.11109
blurhash (click) 52000 47236 32 461 0 0% 0 0 15.711683
erubi (click) 271196 230596 10 111 0 0% 0 0 3.920481
etanni (click) 31686 27819 12 96 0 0% 0 0 3.265674
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.88496
fluentd (click) 387855 311831 11 111 0 0% 0 0 3.708307
graphql (click) 442725 373961 70 673 0 0% 0 0 21.050414
graphql-native (click) 408277 343595 41 271 0 0% 0 0 9.197985
lee (click) 315831 277753 49 731 0 0% 0 0 22.992747
matmul (click) 12586 12175 12 126 0 0% 0 0 4.227242
nbody (click) 15103 7574 11 185 0 0% 0 0 5.055345
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.970799
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 104.087564
rack (click) 272079 234532 31 319 0 0% 0 0 9.242547
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.837796
rubykon (click) 133625 106471 143 1498 3 0% 0 0 42.009465
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.684384
tinygql (click) 313098 266157 63 787 5 0% 0 0 23.092233
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1495.899375
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 523.68976
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.278557
fib (click) 5017 4633 8 49 0 0% 0 0 1.802787
getivar (click) 6102 6023 8 74 0 0% 0 0 2.224676
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.571321
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.707856
ruby-xor (click) 8110 7110 9 87 0 0% 0 0 3.151411
setivar (click) 5193 4604 8 54 0 0% 0 0 1.801108
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.882958
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.096546
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.919737
throw (click) 7946 6065 10 69 0 0% 0 0 2.480184

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.