YJIT Benchmarks

Details for Benchmarks at 2024-04-05 06:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 9d1d2de2fe

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.1% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.6% 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 30 523 30 523
chunky-png 30 32 30 32
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 347 30 347
liquid-compile 30 358 30 358
liquid-render 30 252 30 252
lobsters 30 23 30 23
mail 30 162 30 162
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 183 30 183
ruby-lsp 30 206 30 206
sequel 30 287 30 287
binarytrees 30 84 30 84
blurhash 30 102 30 102
erubi 30 76 30 76
etanni 30 24 30 24
fannkuchredux 30 23 30 23
fluentd 30 15 30 15
graphql 30 15 30 15
graphql-native 30 33 30 33
lee 30 20 30 20
matmul 30 18 30 18
nbody 30 330 30 330
nqueens 30 301 30 301
optcarrot 30 15 30 15
protoboeuf 30 414 30 414
rack 30 175 30 175
ruby-json 30 15 30 15
rubykon 30 15 30 15
sudoku 30 25 30 25
tinygql 30 39 30 39
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 946 30 946
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 108 30 108
setivar 30 2393 30 2393
setivar_object 30 468 30 468
setivar_young 30 507 30 507
str_concat 30 423 30 423
throw 30 764 30 764

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) 883029 748409 49 525 0 0% 0 0 15.564171
chunky-png (click) 337635 282733 87 1087 1 0% 0 0 32.519862
erubi-rails (click) 1712842 1431125 276 2964 6 0% 0 0 85.047777
hexapdf (click) 1417477 1182591 595 12558 38 0% 0 0 369.497869
liquid-c (click) 523304 437760 119 1754 5 0% 0 0 48.473205
liquid-compile (click) 445136 387125 151 2053 2 0% 0 0 62.597746
liquid-render (click) 622804 547304 136 2285 8 0% 0 0 62.930778
lobsters (click) 7885277 6556860 3211 50107 73 0% 0 0 1712.724327
mail (click) 731013 625189 346 4833 14 0% 0 0 143.237554
psych-load (click) 301724 253180 65 655 3 0% 0 0 20.458429
railsbench (click) 2990605 2573833 1634 15744 54 0% 0 0 452.132543
rubocop (click) 5365482 4636770 2901 47723 106 0% 4 0 1428.790878
ruby-lsp (click) 632747 539666 159 2735 14 0% 0 0 76.46537
sequel (click) 496614 427713 16 117 0 0% 0 0 4.10334
binarytrees (click) 9384 7556 11 75 0 0% 0 0 3.033029
blurhash (click) 51809 46977 32 459 0 0% 0 0 15.483481
erubi (click) 270537 237607 10 111 0 0% 0 0 3.896938
etanni (click) 30003 26174 11 90 0 0% 0 0 2.968094
fannkuchredux (click) 24443 9175 9 257 0 0% 0 0 7.785124
fluentd (click) 387039 326933 11 111 0 0% 0 0 3.599433
graphql (click) 442942 364390 70 673 0 0% 0 0 20.280207
graphql-native (click) 409997 344213 42 276 0 0% 0 0 9.194389
lee (click) 316487 277439 49 732 0 0% 0 0 22.793471
matmul (click) 12555 12107 12 126 0 0% 0 0 4.190272
nbody (click) 15072 7506 11 185 0 0% 0 0 5.041962
nqueens (click) 23418 17741 10 260 0 0% 0 0 7.834425
optcarrot (click) 314912 252069 192 4322 34 0% 0 0 103.87172
protoboeuf (click) 153790 132358 17 1378 0 0% 0 0 41.948365
rack (click) 272408 234277 31 319 0 0% 0 0 9.142142
ruby-json (click) 33300 28167 12 196 0 0% 0 0 5.82769
rubykon (click) 133569 130861 143 1498 3 0% 0 0 41.87952
sudoku (click) 46892 53197 11 507 0 0% 0 0 15.552444
tinygql (click) 313430 265839 63 786 5 0% 0 0 23.241064
30k_ifelse (click) 5222589 4374204 9264 50813 0 0% 0 0 1469.030702
30k_methods (click) 2019606 1594020 5782 19369 0 0% 0 0 521.641303
cfunc_itself (click) 7581 5778 9 70 0 0% 0 0 2.241149
fib (click) 5009 4601 8 49 0 0% 0 0 1.796562
getivar (click) 6094 5991 8 74 0 0% 0 0 2.141947
keyword_args (click) 8464 6470 10 72 0 0% 0 0 2.606923
respond_to (click) 8333 7728 9 85 0 0% 0 0 2.661609
ruby-xor (click) 8062 6902 9 87 0 0% 0 0 3.099132
setivar (click) 5185 4572 8 54 0 0% 0 0 1.75217
setivar_object (click) 5553 4592 8 54 0 0% 0 0 1.842406
setivar_young (click) 6276 5242 9 62 0 0% 0 0 2.054916
str_concat (click) 7876 7217 11 85 0 0% 0 0 2.855211
throw (click) 7938 6033 10 69 0 0% 0 0 2.501648

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.