YJIT Benchmarks

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

YJIT metrics from the yjit-bench suite using Ruby c39c49cb24

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 64.7% faster than CRuby 3.4.0dev
On railsbench it is
  • 67.5% 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 30 480 30 480
chunky-png 30 30 30 30
erubi-rails 30 15 30 15
hexapdf 30 15 30 15
liquid-c 30 345 30 345
liquid-compile 30 332 30 332
liquid-render 30 243 30 243
lobsters 30 23 30 23
mail 30 163 30 163
psych-load 30 15 30 15
railsbench 30 15 30 15
ruby-lsp 30 390 30 390
sequel 30 298 30 298
binarytrees 30 82 30 82
erubi 30 76 30 76
etanni 30 51 30 51
fannkuchredux 30 23 30 23
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 19 30 19
matmul 15 15 15 15
nbody 30 276 30 276
nqueens 15 15 15 15
optcarrot 30 15 30 15
rack 30 178 30 178
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 15 15 15 15
tinygql 30 41 30 41
30k_ifelse 30 55 30 55
30k_methods 30 24 30 24
cfunc_itself 30 753 30 753
fib 30 416 30 416
getivar 30 942 30 942
keyword_args 30 493 30 493
respond_to 30 1172 30 1172
setivar 30 1668 30 1668
setivar_object 30 471 30 471
setivar_young 30 470 30 470
str_concat 30 405 30 405
throw 30 794 30 794

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) 736800 660703 50 509 3 0% 0 0 0 15.132674
chunky-png (click) 307325 261267 87 1104 1 0% 0 0 0 33.429437
erubi-rails (click) 1609855 1374833 287 2903 1 0% 0 0 0 82.963153
hexapdf (click) 1333229 1152251 598 12110 36 0% 0 0 0 360.336859
liquid-c (click) 486269 444484 120 1701 5 0% 0 0 0 47.51532
liquid-compile (click) 348568 259490 150 2026 2 0% 0 0 0 62.924427
liquid-render (click) 519570 379745 143 2163 5 0% 0 0 0 60.673052
lobsters (click) 7400690 6335939 3181 48163 64 0% 0 0 0 1625.319589
mail (click) 682842 628249 345 4760 12 0% 0 0 0 141.092046
psych-load (click) 260964 220020 65 600 3 0% 0 0 0 18.985138
railsbench (click) 2467118 2160298 1357 12473 16 0% 0 0 0 370.070142
ruby-lsp (click) 5310725 4657499 3395 49744 397 0% 4 0 0 1529.37444
sequel (click) 454917 414714 16 123 0 0% 0 0 0 4.767327
binarytrees (click) 9306 8120 11 75 0 0% 0 0 0 2.960174
erubi (click) 232785 229083 10 95 0 0% 0 0 0 3.275262
etanni (click) 32063 22322 12 90 0 0% 0 0 0 3.075563
fannkuchredux (click) 22558 23293 9 233 0 0% 0 0 0 7.208351
fluentd (click) 333189 275481 12 104 0 0% 0 0 0 3.359429
graphql (click) 397052 350820 70 658 0 0% 0 0 0 20.236211
graphql-native (click) 362855 319546 42 264 0 0% 0 0 0 8.715419
lee (click) 281180 250100 49 691 0 0% 0 0 0 22.268808
matmul (click) 14070 12895 17 122 0 0% 0 0 0 4.456562
nbody (click) 18283 17348 11 189 0 0% 0 0 0 5.73129
nqueens (click) 17996 20604 11 191 0 0% 0 0 0 5.985042
optcarrot (click) 314630 260302 194 4242 32 0% 0 0 0 100.868944
rack (click) 238781 205959 31 301 0 0% 0 0 0 8.857561
ruby-json (click) 27788 25201 12 203 0 0% 0 0 0 6.249013
rubykon (click) 129011 118454 144 1473 3 0% 0 0 0 41.94922
sudoku (click) 44938 40709 26 421 0 0% 0 0 0 13.131125
tinygql (click) 277335 244871 63 773 5 0% 0 0 0 22.500297
30k_ifelse (click) 4909644 4374870 9264 50817 0 0% 0 0 0 1400.282567
30k_methods (click) 1850351 1594387 5782 19371 0 0% 0 0 0 498.388354
cfunc_itself (click) 7868 6931 9 73 0 0% 0 0 0 2.450178
fib (click) 5044 5012 8 49 0 0% 0 0 0 1.805752
getivar (click) 6179 6402 8 74 0 0% 0 0 0 2.19268
keyword_args (click) 8481 7140 10 75 0 0% 0 0 0 2.606637
respond_to (click) 8611 8551 9 88 0 0% 0 0 0 2.766848
setivar (click) 5330 4983 8 54 0 0% 0 0 0 1.813667
setivar_object (click) 5668 5003 8 54 0 0% 0 0 0 1.882191
setivar_young (click) 6435 5792 9 62 0 0% 0 0 0 2.110132
str_concat (click) 8079 7814 11 87 0 0% 0 0 0 2.860279
throw (click) 7723 6444 10 69 0 0% 0 0 0 2.39745

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.