YJIT Benchmarks

Details for Benchmarks at 2024-01-12 19:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby e59dd7094f

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 65.4% faster than CRuby 3.4.0dev
On railsbench it is
  • 66.9% 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 30 479 30 479
chunky-png 30 30 30 30
erubi-rails 30 15 30 15
hexapdf 30 15 30 15
liquid-c 30 350 30 350
liquid-compile 30 361 30 361
liquid-render 30 246 30 246
lobsters 30 23 30 23
mail 30 165 30 165
psych-load 30 15 30 15
railsbench 30 15 30 15
ruby-lsp 30 395 30 395
sequel 30 302 30 302
binarytrees 30 83 30 83
erubi 30 77 30 77
etanni 30 51 30 51
fannkuchredux 30 24 30 24
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 19 30 19
matmul 30 15 30 15
nbody 30 280 30 280
nqueens 30 104 30 104
optcarrot 30 15 30 15
rack 30 181 30 181
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 15 30 15
tinygql 30 41 30 41
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 750 30 750
fib 30 417 30 417
getivar 30 936 30 936
keyword_args 30 492 30 492
respond_to 30 1181 30 1181
setivar 30 1668 30 1668
setivar_object 30 471 30 471
setivar_young 30 470 30 470
str_concat 30 432 30 432
throw 30 828 30 828

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) 737613 669723 50 509 3 0% 0 0 0 15.135017
chunky-png (click) 306522 268800 87 1099 1 0% 0 0 0 33.21713
erubi-rails (click) 1613038 1401664 287 2937 1 0% 0 0 0 84.114466
hexapdf (click) 1332083 1150606 598 12097 36 0% 0 0 0 354.551628
liquid-c (click) 486333 452747 120 1701 5 0% 0 0 0 47.184126
liquid-compile (click) 348499 267340 150 2018 2 0% 0 0 0 61.949451
liquid-render (click) 520082 404623 143 2164 5 0% 0 0 0 60.619653
lobsters (click) 7407725 6366019 3182 48238 64 0% 0 0 0 1614.918867
mail (click) 683003 596344 345 4767 12 0% 0 0 0 140.344346
psych-load (click) 260898 211757 65 600 3 0% 0 0 0 18.840136
railsbench (click) 2461202 2129400 1357 12426 16 0% 0 0 0 366.795906
ruby-lsp (click) 5302877 4645127 3394 49739 398 0% 4 0 0 1527.1059
sequel (click) 453613 397007 16 117 0 0% 0 0 0 4.105004
binarytrees (click) 9306 8120 11 75 0 0% 0 0 0 2.95274
erubi (click) 232785 229083 10 95 0 0% 0 0 0 3.252055
etanni (click) 32063 22322 12 90 0 0% 0 0 0 3.078046
fannkuchredux (click) 22558 23293 9 233 0 0% 0 0 0 7.252404
fluentd (click) 332230 290845 12 104 0 0% 0 0 0 3.445891
graphql (click) 396988 350776 70 658 0 0% 0 0 0 20.275659
graphql-native (click) 362855 327738 42 264 0 0% 0 0 0 8.705671
lee (click) 281180 250100 49 691 0 0% 0 0 0 21.916772
matmul (click) 12919 12854 12 124 0 0% 0 0 0 4.258597
nbody (click) 18283 17348 11 189 0 0% 0 0 0 5.602953
nqueens (click) 19671 5668 10 206 0 0% 0 0 0 6.486339
optcarrot (click) 314630 260302 194 4242 32 0% 0 0 0 100.71827
rack (click) 239051 198091 31 304 0 0% 0 0 0 8.858759
ruby-json (click) 27788 25201 12 203 0 0% 0 0 0 6.196644
rubykon (click) 129011 102070 144 1473 3 0% 0 0 0 41.668305
sudoku (click) 46943 31883 10 515 0 0% 0 0 0 15.583642
tinygql (click) 277271 244800 63 773 5 0% 0 0 0 22.359718
30k_ifelse (click) 4909644 4374870 9264 50817 0 0% 0 0 0 1386.852944
30k_methods (click) 1850351 1594387 5782 19371 0 0% 0 0 0 496.797718
cfunc_itself (click) 7868 6931 9 73 0 0% 0 0 0 2.399396
fib (click) 5044 5012 8 49 0 0% 0 0 0 1.796108
getivar (click) 6179 6402 8 74 0 0% 0 0 0 2.261085
keyword_args (click) 8481 7140 10 75 0 0% 0 0 0 2.589947
respond_to (click) 8611 8551 9 88 0 0% 0 0 0 2.834792
setivar (click) 5330 4983 8 54 0 0% 0 0 0 1.82971
setivar_object (click) 5668 5003 8 54 0 0% 0 0 0 1.886371
setivar_young (click) 6435 5792 9 62 0 0% 0 0 0 2.135525
str_concat (click) 8079 7814 11 87 0 0% 0 0 0 2.837996
throw (click) 7723 6444 10 69 0 0% 0 0 0 2.360574

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.