YJIT Benchmarks

Details for Benchmarks at 2024-04-24 19:09:24 UTC

YJIT metrics from the yjit-bench suite using Ruby 4349c7909f

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.0% faster than CRuby 3.4.0dev
On railsbench it is
  • 78.8% 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 30 518 30 518
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 345 30 345
liquid-compile 30 359 30 359
liquid-render 30 247 30 247
lobsters 30 23 30 23
mail 30 163 30 163
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 182 30 182
ruby-lsp 30 180 30 180
sequel 30 291 30 291
binarytrees 30 84 30 84
blurhash 30 101 30 101
erubi 30 75 30 75
etanni 30 24 30 24
fannkuchredux 30 23 30 23
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 336 30 336
nqueens 30 311 30 311
optcarrot 30 15 30 15
protoboeuf 30 389 30 389
rack 30 182 30 182
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 23 30 23
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 944 30 944
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 103 30 103
setivar 30 2392 30 2392
setivar_object 30 384 30 384
setivar_young 30 412 30 412
str_concat 30 428 30 428
throw 30 776 30 776

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) 885787 770119 49 526 0 0% 0 0 15.793099
chunky-png (click) 337053 281985 87 1094 1 0% 0 0 31.992198
erubi-rails (click) 1701124 1395767 276 2968 6 0% 0 0 83.366974
hexapdf (click) 1415252 1224016 595 12692 38 0% 0 0 364.735024
liquid-c (click) 522192 445366 119 1757 5 0% 0 0 47.435967
liquid-compile (click) 439738 374589 151 2069 2 0% 0 0 62.036634
liquid-render (click) 616435 542255 136 2292 8 0% 0 0 62.000513
lobsters (click) 7865325 6564585 3212 51252 73 0% 0 0 1703.319582
mail (click) 734452 619806 346 4899 14 0% 0 0 143.066022
psych-load (click) 301454 252936 65 658 3 0% 0 0 20.369419
railsbench (click) 2988383 2569816 1634 15922 54 0% 0 0 450.770036
rubocop (click) 5373339 4591217 2901 48282 109 0% 4 0 1423.920611
ruby-lsp (click) 630782 554588 159 2794 14 0% 0 0 75.595164
sequel (click) 495973 418902 16 117 0 0% 0 0 4.11761
binarytrees (click) 9384 7556 11 75 0 0% 0 0 3.006711
blurhash (click) 51756 46977 32 460 0 0% 0 0 15.536791
erubi (click) 270262 237443 10 112 0 0% 0 0 3.792772
etanni (click) 29895 26052 11 91 0 0% 0 0 2.942286
fannkuchredux (click) 24443 9175 9 257 0 0% 0 0 8.279001
fluentd (click) 377946 329497 11 111 0 0% 0 0 3.667891
graphql (click) 438187 370080 70 685 0 0% 0 0 20.190929
graphql-native (click) 405240 341780 42 278 0 0% 0 0 9.072815
lee (click) 316265 260791 49 737 0 0% 0 0 22.800914
matmul (click) 12555 12107 12 126 0 0% 0 0 4.276146
nbody (click) 15072 7506 11 185 0 0% 0 0 5.056412
nqueens (click) 23358 17741 10 260 0 0% 0 0 8.196324
optcarrot (click) 313653 276483 192 4326 34 0% 0 0 102.499047
protoboeuf (click) 153148 132196 17 1378 0 0% 0 0 41.554257
rack (click) 272129 233969 31 323 0 0% 0 0 9.268935
ruby-json (click) 33192 28025 12 196 0 0% 0 0 5.780192
rubykon (click) 133902 123073 143 1507 3 0% 0 0 41.360733
sudoku (click) 46784 53075 11 507 0 0% 0 0 15.17754
tinygql (click) 313143 257403 63 787 5 0% 0 0 22.864611
30k_ifelse (click) 5222589 4374204 9264 50813 0 0% 0 0 1447.900002
30k_methods (click) 2019606 1594020 5782 19369 0 0% 0 0 515.584061
cfunc_itself (click) 7581 5778 9 70 0 0% 0 0 2.710697
fib (click) 5009 4601 8 49 0 0% 0 0 2.259854
getivar (click) 6094 5991 8 74 0 0% 0 0 2.607627
keyword_args (click) 8464 6470 10 72 0 0% 0 0 2.961272
respond_to (click) 8333 7728 9 85 0 0% 0 0 3.120756
ruby-xor (click) 8062 6902 9 87 0 0% 0 0 2.789392
setivar (click) 5185 4572 8 54 0 0% 0 0 2.217416
setivar_object (click) 5553 4592 8 54 0 0% 0 0 2.182053
setivar_young (click) 6276 5242 9 62 0 0% 0 0 2.398408
str_concat (click) 7876 7217 11 85 0 0% 0 0 2.919608
throw (click) 7938 6033 10 69 0 0% 0 0 2.404316

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.