YJIT Benchmarks

Details for Benchmarks at 2024-02-20 06:08:17 UTC

YJIT metrics from the yjit-bench suite using Ruby f75b9dbf7d

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 67.1% faster than CRuby 3.4.0dev
On railsbench it is
  • 75.7% 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 30 524 30 524
chunky-png 30 31 30 31
erubi-rails 30 19 30 19
hexapdf 30 15 30 15
liquid-c 30 353 30 353
liquid-compile 30 334 30 334
liquid-render 30 250 30 250
lobsters 30 23 30 23
mail 30 160 30 160
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 184 30 184
ruby-lsp 30 173 30 173
sequel 30 290 30 290
binarytrees 30 83 30 83
blurhash 30 100 30 100
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 22 30 22
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 314 30 314
nqueens 30 305 30 305
optcarrot 30 15 30 15
rack 30 174 30 174
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 26 30 26
tinygql 30 40 30 40
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 942 30 942
keyword_args 30 592 30 592
respond_to 30 1480 30 1480
ruby-xor 30 108 30 108
setivar 30 2392 30 2392
setivar_object 30 358 30 358
setivar_young 30 371 30 371
str_concat 30 432 30 432
throw 30 843 30 843

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) 884113 777870 49 522 0 0% 0 0 16.018027
chunky-png (click) 333600 291081 87 1092 1 0% 0 0 31.798076
erubi-rails (click) 1711705 1438648 280 2964 6 0% 0 0 84.849249
hexapdf (click) 1417050 1192952 597 12629 37 0% 0 0 370.517057
liquid-c (click) 519610 464075 120 1750 5 0% 0 0 47.862001
liquid-compile (click) 443111 381628 151 2062 2 0% 0 0 63.226416
liquid-render (click) 620370 532546 144 2271 8 0% 0 0 62.932856
lobsters (click) 7866352 6618588 3219 49827 73 0% 0 0 1696.817838
mail (click) 719380 614552 346 4846 14 0% 0 0 141.43297
psych-load (click) 296529 261452 65 649 3 0% 0 0 20.005469
railsbench (click) 3000411 2581269 1643 15661 54 0% 0 0 453.330433
rubocop (click) 5360572 4577166 2902 47738 106 0% 4 0 1414.819156
ruby-lsp (click) 625014 524371 159 2816 14 0% 0 0 78.091579
sequel (click) 492370 427788 16 118 0 0% 0 0 4.409239
binarytrees (click) 9392 7588 11 75 0 0% 0 0 2.97375
blurhash (click) 52098 47218 32 461 0 0% 0 0 15.490987
erubi (click) 258400 217372 10 111 0 0% 0 0 3.781727
etanni (click) 31710 27867 12 96 0 0% 0 0 3.254115
fannkuchredux (click) 24912 17701 9 257 0 0% 0 0 7.789288
fluentd (click) 386575 321304 11 111 0 0% 0 0 3.607407
graphql (click) 430381 369031 70 673 0 0% 0 0 20.337325
graphql-native (click) 396367 338937 41 271 0 0% 0 0 9.019387
lee (click) 312793 278189 49 731 0 0% 0 0 22.688875
matmul (click) 12586 12175 12 126 0 0% 0 0 4.265776
nbody (click) 15103 7574 11 185 0 0% 0 0 5.00153
nqueens (click) 23609 17866 10 261 0 0% 0 0 7.694115
optcarrot (click) 317087 278432 192 4342 34 0% 0 0 103.47745
rack (click) 260601 223076 31 341 0 0% 0 0 9.551237
ruby-json (click) 28135 23070 12 198 0 0% 0 0 5.892156
rubykon (click) 133625 106471 143 1498 3 0% 0 0 41.689647
sudoku (click) 47007 45195 11 507 0 0% 0 0 15.309447
tinygql (click) 306073 257268 63 788 5 0% 0 0 22.922185
30k_ifelse (click) 5222597 4374236 9264 50813 0 0% 0 0 1459.951388
30k_methods (click) 2019614 1594052 5782 19369 0 0% 0 0 520.592423
cfunc_itself (click) 7589 5810 9 70 0 0% 0 0 2.312858
fib (click) 5017 4633 8 49 0 0% 0 0 1.76473
getivar (click) 6102 6023 8 74 0 0% 0 0 2.245528
keyword_args (click) 8472 6502 10 72 0 0% 0 0 2.514273
respond_to (click) 8341 7760 9 85 0 0% 0 0 2.659015
ruby-xor (click) 8142 7087 9 87 0 0% 0 0 2.656825
setivar (click) 5193 4604 8 54 0 0% 0 0 1.817878
setivar_object (click) 5561 4624 8 54 0 0% 0 0 1.847762
setivar_young (click) 6284 5274 9 62 0 0% 0 0 2.030491
str_concat (click) 7932 7204 11 85 0 0% 0 0 2.788641
throw (click) 7946 6065 10 69 0 0% 0 0 2.366597

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.