YJIT Benchmarks

Details for Benchmarks at 2024-06-24 19:08:16 UTC

YJIT metrics from the yjit-bench suite using Ruby ae0c7faa79

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 72.0% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.3
On railsbench it is
  • 76.4% faster than CRuby 3.4.0dev
  • 2.2% slower than YJIT 3.3.3

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 3.3.3 warmups CRuby 3.3.3 iters CRuby 3.4.0dev warmups CRuby 3.4.0dev iters YJIT 3.3.3 warmups YJIT 3.3.3 iters YJIT 3.4.0dev warmups YJIT 3.4.0dev iters
activerecord 10 51 10 47 10 115 10 118
chunky-png 10 18 10 15 10 36 10 35
erubi-rails 10 10 10 10 10 20 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 352 10 334 10 504 10 477
liquid-compile 10 341 10 330 10 519 10 485
liquid-render 10 136 10 134 10 355 10 352
mail 10 162 10 148 10 238 10 217
psych-load 10 10 10 10 10 10 10 10
railsbench 10 10 10 10 10 10 10 10
rubocop 10 137 10 127 10 230 10 235
ruby-lsp 10 199 10 190 10 262 10 277
sequel 10 325 10 303 10 437 10 405
binarytrees 10 50 10 48 10 117 10 114
blurhash 10 62 10 57 10 118 10 144
erubi 10 83 10 82 10 102 10 103
etanni 10 59 10 57 10 68 10 67
fannkuchredux 10 10 10 10 10 18 10 16
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 34 10 34 10 39 10 39
lee 10 11 10 10 10 19 10 21
matmul 10 10 10 10 10 15 10 17
nbody 10 211 10 187 10 385 10 499
nqueens 10 115 10 95 10 114 10 441
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 189 10 172 10 680 10 667
rack 10 475 10 467 10 810 10 886
ruby-json 10 10 10 10 10 10 10 10
rubykon 10 10 10 10 10 10 10 10
sudoku 10 10 10 10 10 31 10 31
tinygql 10 24 10 22 10 51 10 49
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 257 10 235 10 1105 10 1210
fib 10 102 10 90 10 616 10 618
getivar 10 255 10 223 10 1280 10 1351
keyword_args 10 90 10 83 10 726 10 944
respond_to 10 89 10 84 10 1782 10 2146
ruby-xor 10 31 10 25 10 101 10 129
setivar 10 421 10 397 10 2357 10 3567
setivar_object 10 264 10 261 10 653 10 729
setivar_young 10 264 10 261 10 651 10 723
str_concat 10 327 10 282 10 593 10 526
throw 10 976 10 837 10 1275 10 1041

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) 1403568 1179877 214 2166 0 0% 0 0 76.153923
chunky-png (click) 331257 268947 82 1053 1 0% 0 0 33.906904
erubi-rails (click) 1676250 1422464 272 2887 6 0% 0 0 95.760515
hexapdf (click) 1288203 1105514 504 11684 41 0% 0 0 375.624344
liquid-c (click) 517841 425381 119 1761 5 0% 0 0 52.937677
liquid-compile (click) 440653 388069 151 2069 2 0% 0 0 69.647184
liquid-render (click) 612809 533640 136 2302 8 0% 0 0 70.39166
mail (click) 723226 644565 346 4881 14 0% 0 0 156.813725
psych-load (click) 293176 243984 61 594 3 0% 0 0 20.453134
railsbench (click) 2925338 2513998 1633 15909 57 0% 0 0 556.127273
rubocop (click) 5434535 4567813 2891 50369 110 0% 4 0 1782.352465
ruby-lsp (click) 635601 567796 159 2903 28 0% 0 0 90.178501
sequel (click) 488495 418196 16 117 0 0% 0 0 5.212416
binarytrees (click) 8756 7777 10 70 0 0% 0 0 2.968003
blurhash (click) 50429 43324 31 457 0 0% 0 0 17.047871
erubi (click) 270214 214579 10 112 0 0% 0 0 4.376659
etanni (click) 30236 28701 12 96 0 0% 0 0 3.451321
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.923931
fluentd (click) 375007 334610 4 28 0 0% 0 0 1.248622
graphql (click) 430898 361977 66 648 0 0% 0 0 22.19868
graphql-native (click) 402926 330696 42 278 0 0% 0 0 11.094572
lee (click) 293365 214005 34 531 0 0% 0 0 18.247874
matmul (click) 8315 983 8 86 0 0% 0 0 3.019812
nbody (click) 14798 17933 11 185 0 0% 0 0 5.568005
nqueens (click) 22145 28339 10 257 0 0% 0 0 8.997062
optcarrot (click) 304463 277860 188 4310 34 0% 0 0 109.149471
protoboeuf (click) 140419 133760 17 1349 0 0% 0 0 43.67266
rack (click) 275741 228654 37 408 0 0% 0 0 12.0043
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.197068
rubykon (click) 128391 79892 137 1484 3 0% 0 0 45.144238
sudoku (click) 41994 57542 8 473 0 0% 0 0 15.976428
tinygql (click) 307906 259268 58 734 5 0% 0 0 23.360094
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1907.828749
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 530.395706
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.322917
fib (click) 4970 5003 8 49 0 0% 0 0 1.986859
getivar (click) 5963 6375 8 74 0 0% 0 0 2.243783
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.58107
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.765722
ruby-xor (click) 5565 5673 5 62 0 0% 0 0 1.881169
setivar (click) 5102 5375 8 54 0 0% 0 0 1.921713
setivar_object (click) 5470 5395 8 54 0 0% 0 0 2.00839
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.218512
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.127118
throw (click) 7895 6377 10 69 0 0% 0 0 2.637991

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.