YJIT Benchmarks

Details for Benchmarks at 2024-04-11 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby cd516ebd20

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.3% 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 30 519 30 519
chunky-png 30 31 30 31
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 344 30 344
liquid-compile 30 357 30 357
liquid-render 30 252 30 252
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 30 206 30 206
sequel 30 287 30 287
binarytrees 30 83 30 83
blurhash 30 102 30 102
erubi 30 76 30 76
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 17 30 17
nbody 30 328 30 328
nqueens 30 278 30 278
optcarrot 30 15 30 15
protoboeuf 30 414 30 414
rack 30 176 30 176
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 23 30 23
tinygql 30 39 30 39
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 946 30 946
keyword_args 30 592 30 592
respond_to 30 1480 30 1480
ruby-xor 30 107 30 107
setivar 30 2394 30 2394
setivar_object 30 477 30 477
setivar_young 30 505 30 505
str_concat 30 417 30 417
throw 30 766 30 766

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) 882084 747851 49 524 0 0% 0 0 15.879737
chunky-png (click) 333598 289724 87 1087 1 0% 0 0 32.509954
erubi-rails (click) 1707195 1426093 276 2907 6 0% 0 0 81.879526
hexapdf (click) 1413686 1197968 595 12559 38 0% 0 0 370.806518
liquid-c (click) 523492 437995 119 1754 5 0% 0 0 48.184859
liquid-compile (click) 445247 379062 151 2055 2 0% 0 0 63.21002
liquid-render (click) 622750 547264 136 2285 8 0% 0 0 62.660957
lobsters (click) 7865390 6549903 3211 50012 73 0% 0 0 1719.823179
mail (click) 727006 624166 346 4833 14 0% 0 0 142.89338
psych-load (click) 297392 251760 65 653 3 0% 0 0 20.497642
railsbench (click) 2994432 2575157 1634 15758 54 0% 0 0 456.531673
rubocop (click) 5365500 4628192 2901 47724 106 0% 4 0 1428.135291
ruby-lsp (click) 628740 538361 159 2735 14 0% 0 0 77.610258
sequel (click) 494058 435886 16 119 0 0% 0 0 4.79828
binarytrees (click) 9384 7556 11 75 0 0% 0 0 2.972664
blurhash (click) 51809 46977 32 459 0 0% 0 0 15.500017
erubi (click) 266531 228209 10 111 0 0% 0 0 3.902822
etanni (click) 30003 26174 11 90 0 0% 0 0 2.993387
fannkuchredux (click) 24443 9175 9 257 0 0% 0 0 7.897
fluentd (click) 377109 329405 11 111 0 0% 0 0 3.602273
graphql (click) 438473 379259 70 673 0 0% 0 0 20.255899
graphql-native (click) 405528 342788 42 276 0 0% 0 0 9.274105
lee (click) 316481 277419 49 732 0 0% 0 0 22.935765
matmul (click) 12555 12107 12 126 0 0% 0 0 4.240734
nbody (click) 15072 7506 11 185 0 0% 0 0 4.977044
nqueens (click) 23358 17741 10 260 0 0% 0 0 7.780094
optcarrot (click) 313814 260221 192 4322 34 0% 0 0 104.152733
protoboeuf (click) 153256 132318 17 1378 0 0% 0 0 42.253526
rack (click) 272332 234206 31 319 0 0% 0 0 9.183118
ruby-json (click) 33300 28167 12 196 0 0% 0 0 5.847288
rubykon (click) 135132 132229 143 1512 3 0% 0 0 42.67562
sudoku (click) 46892 53197 11 507 0 0% 0 0 15.551937
tinygql (click) 309412 256441 63 786 5 0% 0 0 23.157254
30k_ifelse (click) 5222589 4374204 9264 50813 0 0% 0 0 1477.665926
30k_methods (click) 2019606 1594020 5782 19369 0 0% 0 0 530.931723
cfunc_itself (click) 7581 5778 9 70 0 0% 0 0 2.256963
fib (click) 5009 4601 8 49 0 0% 0 0 1.757553
getivar (click) 6094 5991 8 74 0 0% 0 0 2.14499
keyword_args (click) 8464 6470 10 72 0 0% 0 0 2.513217
respond_to (click) 8333 7728 9 85 0 0% 0 0 2.651517
ruby-xor (click) 8062 6902 9 87 0 0% 0 0 2.760549
setivar (click) 5185 4572 8 54 0 0% 0 0 1.740729
setivar_object (click) 5553 4592 8 54 0 0% 0 0 1.851706
setivar_young (click) 6276 5242 9 62 0 0% 0 0 2.043469
str_concat (click) 7876 7217 11 85 0 0% 0 0 2.820006
throw (click) 7938 6033 10 69 0 0% 0 0 2.366751

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.