YJIT Benchmarks

Details for Benchmarks at 2024-01-06 06:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 4112585be5

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 63.7% faster than CRuby 3.4.0dev
On railsbench it is
  • 67.4% 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 30 481 30 481
chunky-png 30 30 30 30
erubi-rails 30 15 30 15
hexapdf 30 15 30 15
liquid-c 30 348 30 348
liquid-compile 30 335 30 335
liquid-render 30 245 30 245
lobsters 30 23 30 23
mail 30 164 30 164
psych-load 30 15 30 15
railsbench 30 15 30 15
ruby-lsp 30 390 30 390
sequel 30 295 30 295
binarytrees 30 81 30 81
erubi 30 74 30 74
etanni 30 50 30 50
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
nbody 30 275 30 275
optcarrot 30 15 30 15
rack 30 178 30 178
ruby-json 30 15 30 15
rubykon 30 15 30 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 30 934 30 934
keyword_args 30 492 30 492
respond_to 30 1173 30 1173
setivar 30 1668 30 1668
setivar_object 30 472 30 472
setivar_young 30 469 30 469
str_concat 30 447 30 447
throw 30 820 30 820

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) 734650 674578 50 504 3 0% 0 0 0 14.794323
chunky-png (click) 308131 269483 87 1099 1 0% 0 0 0 32.947962
erubi-rails (click) 1613647 1409753 287 2917 1 0% 0 0 0 82.901145
hexapdf (click) 1334507 1226563 598 12108 36 0% 0 0 0 356.382258
liquid-c (click) 485504 442539 120 1701 5 0% 0 0 0 47.125051
liquid-compile (click) 346152 297484 150 2020 2 0% 0 0 0 62.14013
liquid-render (click) 515547 456660 143 2149 5 0% 0 0 0 59.423145
lobsters (click) 7387019 6329546 3182 48001 64 0% 0 0 0 1604.632019
mail (click) 684515 604278 345 4760 12 0% 0 0 0 141.227049
psych-load (click) 262571 220831 65 600 3 0% 0 0 0 18.852127
railsbench (click) 2461667 2137633 1357 12410 16 0% 0 0 0 362.892016
ruby-lsp (click) 5309559 4598257 3395 49727 397 0% 4 0 0 1528.406578
sequel (click) 455547 431103 16 120 0 0% 0 0 0 4.416122
binarytrees (click) 9306 8120 11 75 0 0% 0 0 0 2.952671
erubi (click) 234394 221682 10 95 0 0% 0 0 0 3.209907
etanni (click) 32063 22322 12 90 0 0% 0 0 0 3.033178
fannkuchredux (click) 22558 23293 9 233 0 0% 0 0 0 7.171966
fluentd (click) 334926 292827 12 104 0 0% 0 0 0 3.419227
graphql (click) 398661 343468 70 658 0 0% 0 0 0 20.14381
graphql-native (click) 364464 312125 42 264 0 0% 0 0 0 8.828135
lee (click) 282858 259179 49 691 0 0% 0 0 0 21.996913
nbody (click) 18283 17348 11 189 0 0% 0 0 0 5.723435
optcarrot (click) 314630 268142 194 4242 32 0% 0 0 0 100.468089
rack (click) 240390 206750 31 301 0 0% 0 0 0 8.699302
ruby-json (click) 27788 25201 12 203 0 0% 0 0 0 6.257971
rubykon (click) 128662 101831 144 1471 3 0% 0 0 0 41.421907
tinygql (click) 278942 237473 63 773 5 0% 0 0 0 22.39184
30k_ifelse (click) 4909644 4374870 9264 50817 0 0% 0 0 0 1384.904011
30k_methods (click) 1850351 1594387 5782 19371 0 0% 0 0 0 491.552225
cfunc_itself (click) 7868 6931 9 73 0 0% 0 0 0 2.408453
fib (click) 5044 5012 8 49 0 0% 0 0 0 1.804478
getivar (click) 6179 6402 8 74 0 0% 0 0 0 2.157697
keyword_args (click) 8481 7140 10 75 0 0% 0 0 0 2.590551
respond_to (click) 8611 8551 9 88 0 0% 0 0 0 2.817311
setivar (click) 5330 4983 8 54 0 0% 0 0 0 1.800719
setivar_object (click) 5668 5003 8 54 0 0% 0 0 0 1.854547
setivar_young (click) 6435 5792 9 62 0 0% 0 0 0 2.124569
str_concat (click) 8079 7814 11 87 0 0% 0 0 0 2.77889
throw (click) 7723 6444 10 69 0 0% 0 0 0 2.334259

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.