YJIT Benchmarks

Details for Benchmarks at 2024-07-05 19:08:14 UTC

YJIT metrics from the yjit-bench suite using Ruby 3fede665ff

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 78.2% faster than CRuby 3.4.0dev
  • 1.0% faster than YJIT 3.3.3
On railsbench it is
  • 78.7% faster than CRuby 3.4.0dev
  • the same speed as 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 10 116 10 122
chunky-png 10 18 10 13 10 36 10 43
erubi-rails 10 10 10 10 10 20 10 19
hexapdf 10 10 10 10 10 10 10 10
liquid-c 10 352 10 330 10 502 10 481
liquid-compile 10 341 10 329 10 491 10 485
liquid-render 10 138 10 131 10 353 10 347
lobsters 10 14 10 12 10 23 10 23
mail 10 162 10 146 10 237 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 10 228 10 238
ruby-lsp 10 127 10 120 10 209 10 206
sequel 10 324 10 298 10 438 10 409
binarytrees 10 51 10 47 10 117 10 112
blurhash 10 62 10 56 10 118 10 142
erubi 10 83 10 77 10 103 10 102
etanni 10 59 10 55 10 68 10 67
fannkuchredux 10 10 10 10 10 18 10 15
fluentd 10 10 10 10 10 10 10 10
graphql 10 10 10 10 10 10 10 10
graphql-native 10 34 10 32 10 40 10 38
lee 10 11 10 10 10 19 10 20
matmul 10 10 10 10 10 15 10 15
nbody 10 210 10 202 10 385 10 468
nqueens 10 115 10 98 10 115 10 410
optcarrot 10 10 10 10 10 10 10 10
protoboeuf 10 190 10 167 10 681 10 639
rack 10 464 10 451 10 802 10 847
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 27
tinygql 10 25 10 22 10 52 10 51
30k_ifelse 10 10 10 10 10 70 10 69
30k_methods 10 10 10 10 10 26 10 26
cfunc_itself 10 257 10 218 10 1105 10 1212
fib 10 104 10 99 10 616 10 618
getivar 10 255 10 204 10 1283 10 1334
keyword_args 10 90 10 83 10 726 10 946
respond_to 10 89 10 87 10 1780 10 2150
ruby-xor 10 31 10 24 10 100 10 128
setivar 10 415 10 397 10 2357 10 3566
setivar_object 10 261 10 267 10 653 10 661
setivar_young 10 261 10 266 10 650 10 662
str_concat 10 327 10 289 10 593 10 508
throw 10 976 10 792 10 1277 10 991

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
activerecord (click) 1418909 1187144 214 2222 0 0% 0 0
chunky-png (click) 339456 277670 83 1092 1 0% 0 0
erubi-rails (click) 1715150 1489592 288 3100 17 0% 0 0
hexapdf (click) 1296602 1082055 505 11719 41 0% 0 0
liquid-c (click) 522539 422328 120 1762 5 0% 0 0
liquid-compile (click) 445208 360246 151 2065 2 0% 0 0
liquid-render (click) 618242 506824 137 2311 8 0% 0 0
lobsters (click) 7584788 6513229 3077 49774 86 0% 0 0
mail (click) 738013 644990 346 4971 14 0% 0 0
psych-load (click) 296214 239100 61 594 3 0% 0 0
railsbench (click) 2976076 2544766 1650 16214 71 0% 0 0
rubocop (click) 5471883 4774337 2891 50557 110 0% 4 0
ruby-lsp (click) 836459 694818 310 4514 24 0% 0 0
sequel (click) 494521 433030 16 115 0 0% 0 0
binarytrees (click) 8756 7777 10 70 0 0% 0 0
blurhash (click) 50429 43324 31 457 0 0% 0 0
erubi (click) 277381 214301 10 120 0 0% 0 0
etanni (click) 35885 34724 12 104 0 0% 0 0
fannkuchredux (click) 21198 26809 5 228 0 0% 0 0
fluentd (click) 379390 316762 4 28 0 0% 0 0
graphql (click) 445635 361697 66 648 0 0% 0 0
graphql-native (click) 417119 338123 41 273 0 0% 0 0
lee (click) 300965 247035 34 557 0 0% 0 0
matmul (click) 8315 983 8 86 0 0% 0 0
nbody (click) 14798 17933 11 185 0 0% 0 0
nqueens (click) 22145 28339 10 257 0 0% 0 0
optcarrot (click) 304463 277860 188 4310 34 0% 0 0
protoboeuf (click) 140419 133760 17 1349 0 0% 0 0
rack (click) 282867 212013 37 445 0 0% 0 0
ruby-json (click) 31806 21355 8 167 0 0% 0 0
rubykon (click) 129876 98074 138 1500 3 0% 0 0
sudoku (click) 41994 57542 8 473 0 0% 0 0
tinygql (click) 312037 255630 58 734 5 0% 0 0
30k_ifelse (click) 5134674 4729436 9259 50778 0 0% 0 0
30k_methods (click) 2016920 1591842 5778 19339 0 0% 0 0
cfunc_itself (click) 7534 6180 9 70 0 0% 0 0
fib (click) 4970 5003 8 49 0 0% 0 0
getivar (click) 5963 6375 8 74 0 0% 0 0
keyword_args (click) 8409 6912 10 72 0 0% 0 0
respond_to (click) 8277 8274 9 85 0 0% 0 0
ruby-xor (click) 5565 5673 5 62 0 0% 0 0
setivar (click) 5102 5375 8 54 0 0% 0 0
setivar_object (click) 5470 5395 8 54 0 0% 0 0
setivar_young (click) 6182 6093 9 62 0 0% 0 0
str_concat (click) 7774 7946 11 85 0 0% 0 0
throw (click) 7895 6377 10 69 0 0% 0 0

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.