YJIT Benchmarks

Details for Benchmarks at 2024-06-26 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 43d7db3828

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 72.3% faster than CRuby 3.4.0dev
  • the same speed as YJIT 3.3.3
On railsbench it is
  • 76.8% faster than CRuby 3.4.0dev
  • 1.9% 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 10 117
chunky-png 10 18 10 15 10 36 10 36
erubi-rails 10 10 10 10 10 20 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 353 10 333 10 504 10 481
liquid-compile 10 341 10 331 10 489 10 482
liquid-render 10 137 10 135 10 354 10 351
mail 10 162 10 149 10 237 10 219
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 10 204 10 190 10 262 10 276
sequel 10 324 10 307 10 436 10 413
binarytrees 10 51 10 48 10 117 10 113
blurhash 10 61 10 59 10 118 10 145
erubi 10 83 10 84 10 103 10 105
etanni 10 59 10 58 10 68 10 68
fannkuchredux 10 10 10 10 10 18 10 17
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 11 10 19 10 21
matmul 10 10 10 10 10 15 10 17
nbody 10 211 10 191 10 385 10 502
nqueens 10 115 10 102 10 114 10 433
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 189 10 170 10 680 10 657
rack 10 474 10 469 10 811 10 889
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 29
tinygql 10 24 10 22 10 51 10 49
30k_ifelse 10 10 10 10 10 70 10 70
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 257 10 231 10 1105 10 1210
fib 10 103 10 100 10 617 10 618
getivar 10 255 10 243 10 1279 10 1366
keyword_args 10 90 10 83 10 726 10 944
respond_to 10 89 10 83 10 1781 10 2145
ruby-xor 10 31 10 26 10 100 10 133
setivar 10 424 10 406 10 2353 10 3573
setivar_object 10 265 10 265 10 654 10 734
setivar_young 10 263 10 265 10 651 10 738
str_concat 10 326 10 288 10 593 10 520
throw 10 974 10 838 10 1276 10 1034

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) 1404697 1148515 214 2166 0 0% 0 0 76.403896
chunky-png (click) 331257 268947 82 1053 1 0% 0 0 34.059347
erubi-rails (click) 1676414 1447659 272 2904 6 0% 0 0 96.794576
hexapdf (click) 1288198 1097277 504 11684 41 0% 0 0 376.700022
liquid-c (click) 518410 434198 120 1762 5 0% 0 0 53.508236
liquid-compile (click) 441048 388479 151 2075 2 0% 0 0 69.984521
liquid-render (click) 613161 509414 137 2303 8 0% 0 0 70.456872
mail (click) 723226 644565 346 4881 14 0% 0 0 156.887864
psych-load (click) 293176 243984 61 594 3 0% 0 0 20.406676
railsbench (click) 2925680 2521775 1634 15923 57 0% 0 0 556.790889
rubocop (click) 5431408 4638658 2891 50374 110 0% 4 0 1792.914158
ruby-lsp (click) 635601 567796 159 2903 28 0% 0 0 91.293812
sequel (click) 488148 418373 16 116 0 0% 0 0 4.706839
binarytrees (click) 8756 7777 10 70 0 0% 0 0 3.008892
blurhash (click) 50429 43324 31 457 0 0% 0 0 17.116985
erubi (click) 270214 214579 10 112 0 0% 0 0 4.374914
etanni (click) 30236 28701 12 96 0 0% 0 0 3.456132
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0 7.915427
fluentd (click) 375259 336801 4 28 0 0% 0 0 1.369875
graphql (click) 430898 361944 66 648 0 0% 0 0 22.118139
graphql-native (click) 402926 330733 42 278 0 0% 0 0 10.968679
lee (click) 293772 238942 34 531 0 0% 0 0 18.186897
matmul (click) 8315 983 8 86 0 0% 0 0 3.09022
nbody (click) 14798 17933 11 185 0 0% 0 0 5.608633
nqueens (click) 22145 28339 10 257 0 0% 0 0 8.988633
optcarrot (click) 304463 277860 188 4310 34 0% 0 0 109.368591
protoboeuf (click) 140419 133760 17 1349 0 0% 0 0 43.242157
rack (click) 275741 228622 37 408 0 0% 0 0 12.076092
ruby-json (click) 30222 27890 8 167 0 0% 0 0 5.203884
rubykon (click) 129933 122375 137 1498 3 0% 0 0 46.084286
sudoku (click) 41994 57542 8 473 0 0% 0 0 16.112893
tinygql (click) 302478 255453 58 734 5 0% 0 0 23.357988
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0 1910.847055
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0 532.219128
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0 2.439774
fib (click) 4970 5003 8 49 0 0% 0 0 2.04608
getivar (click) 5963 6375 8 74 0 0% 0 0 2.298719
keyword_args (click) 8409 6912 10 72 0 0% 0 0 2.666514
respond_to (click) 8277 8274 9 85 0 0% 0 0 2.778977
ruby-xor (click) 5565 5673 5 62 0 0% 0 0 1.929495
setivar (click) 5102 5375 8 54 0 0% 0 0 1.981201
setivar_object (click) 5470 5395 8 54 0 0% 0 0 2.039771
setivar_young (click) 6182 6093 9 62 0 0% 0 0 2.225021
str_concat (click) 7774 7946 11 85 0 0% 0 0 3.198952
throw (click) 7895 6377 10 69 0 0% 0 0 2.608612

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.