YJIT Benchmarks

Details for Benchmarks at 2024-04-19 06:08:12 UTC

YJIT metrics from the yjit-bench suite using Ruby 662ce928a7

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 71.3% faster than CRuby 3.4.0dev
On railsbench it is
  • 80.7% 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 30 508 30 508
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 30 356 30 356
liquid-render 30 253 30 253
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 181 30 181
ruby-lsp 30 173 30 173
sequel 30 290 30 290
binarytrees 30 86 30 86
blurhash 30 103 30 103
erubi 30 76 30 76
etanni 30 23 30 23
fannkuchredux 30 25 30 25
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 20 30 20
matmul 30 17 30 17
nbody 30 337 30 337
nqueens 30 315 30 315
optcarrot 30 15 30 15
protoboeuf 30 402 30 402
rack 30 179 30 179
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 30 418 30 418
getivar 30 1013 30 1013
keyword_args 30 646 30 646
respond_to 30 1462 30 1462
ruby-xor 30 105 30 105
setivar 30 2546 30 2546
setivar_object 30 417 30 417
setivar_young 30 431 30 431
str_concat 30 412 30 412
throw 30 762 30 762

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) 877950 751404 49 526 0 0% 0 0 17.031091
chunky-png (click) 333979 258011 87 1094 1 0% 0 0 33.650544
erubi-rails (click) 1692652 1479920 276 2954 6 0% 0 0 86.214455
hexapdf (click) 1409217 1142710 597 12725 41 0% 0 0 384.88242
liquid-c (click) 516860 404212 119 1757 5 0% 0 0 50.26436
liquid-compile (click) 441591 385402 151 2077 2 0% 0 0 66.350078
liquid-render (click) 615258 525780 136 2292 8 0% 0 0 65.550069
lobsters (click) 7805716 6508080 3212 51172 89 0% 0 0 1768.914267
mail (click) 722587 614595 346 4865 14 0% 0 0 149.08749
psych-load (click) 298270 268834 65 656 3 0% 0 0 21.434029
railsbench (click) 2968573 2604689 1634 15925 57 0% 0 0 473.513723
rubocop (click) 5317539 4620887 2901 48242 109 0% 4 0 1484.823097
ruby-lsp (click) 624746 558731 159 2808 28 0% 0 0 81.069912
sequel (click) 492230 428274 16 118 0 0% 0 0 4.54724
binarytrees (click) 9300 8262 11 75 0 0% 0 0 3.071958
blurhash (click) 50973 43758 32 460 0 0% 0 0 16.425341
erubi (click) 268015 223860 10 112 0 0% 0 0 4.034676
etanni (click) 29692 28216 11 91 0 0% 0 0 3.068384
fannkuchredux (click) 23856 29309 9 257 0 0% 0 0 8.625168
fluentd (click) 383973 349329 11 111 0 0% 0 0 3.860255
graphql (click) 436081 343759 70 685 0 0% 0 0 21.635838
graphql-native (click) 404100 325031 42 278 0 0% 0 0 9.625175
lee (click) 313294 278323 49 737 0 0% 0 0 23.986599
matmul (click) 12453 4981 12 126 0 0% 0 0 4.506095
nbody (click) 14798 17933 11 185 0 0% 0 0 5.402578
nqueens (click) 22703 29059 10 260 0 0% 0 0 8.722011
optcarrot (click) 311581 267827 192 4326 34 0% 0 0 105.876319
protoboeuf (click) 148013 144784 17 1378 0 0% 0 0 43.650574
rack (click) 271234 224640 31 348 0 0% 0 0 10.499162
ruby-json (click) 32870 30395 12 196 0 0% 0 0 5.993533
rubykon (click) 131584 107832 143 1503 3 0% 0 0 44.74282
sudoku (click) 45463 61097 11 507 0 0% 0 0 16.099202
tinygql (click) 310457 273364 63 787 5 0% 0 0 24.058547
30k_ifelse (click) 5137861 4732461 9264 50813 0 0% 0 0 1541.075117
30k_methods (click) 2019563 1594382 5782 19369 0 0% 0 0 531.951006
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.796065
fib (click) 4970 5003 8 49 0 0% 0 0 2.41749
getivar (click) 5963 6375 8 74 0 0% 0 0 2.629505
keyword_args (click) 8409 6912 10 72 0 0% 0 0 3.083297
respond_to (click) 8277 8274 9 85 0 0% 0 0 3.240197
ruby-xor (click) 7891 7863 9 87 0 0% 0 0 2.9666
setivar (click) 5102 5375 8 54 0 0% 0 0 2.373034
setivar_object (click) 5470 5395 8 54 0 0% 0 0 2.368377
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.565633
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.09178
throw (click) 7895 6377 10 69 0 0% 0 0 2.537945

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.