YJIT Benchmarks

Details for Benchmarks at 2024-04-02 19:08:13 UTC

YJIT metrics from the yjit-bench suite using Ruby 24a7407960

Using the geomean of the headline benchmarks for x86 YJIT 3.4.0dev is
  • 73.4% faster than CRuby 3.4.0dev
On railsbench it is
  • 79.5% 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 30 531 30 531
chunky-png 30 31 30 31
erubi-rails 30 20 30 20
hexapdf 30 15 30 15
liquid-c 30 348 30 348
liquid-compile 30 356 30 356
liquid-render 30 252 30 252
lobsters 30 23 30 23
mail 30 163 30 163
psych-load 30 15 30 15
railsbench 30 15 30 15
rubocop 30 184 30 184
ruby-lsp 30 206 30 206
sequel 30 291 30 291
binarytrees 30 87 30 87
blurhash 30 101 30 101
erubi 30 75 30 75
etanni 30 25 30 25
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 30 333 30 333
nqueens 30 290 30 290
optcarrot 30 15 30 15
protoboeuf 30 421 30 421
rack 30 179 30 179
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 24 30 24
cfunc_itself 30 827 30 827
fib 30 416 30 416
getivar 30 947 30 947
keyword_args 30 591 30 591
respond_to 30 1480 30 1480
ruby-xor 30 100 30 100
setivar 30 2393 30 2393
setivar_object 30 488 30 488
setivar_young 30 503 30 503
str_concat 30 427 30 427
throw 30 758 30 758

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) 883760 773708 49 524 0 0% 0 0 15.457928
chunky-png (click) 337635 282733 87 1087 1 0% 0 0 32.056905
erubi-rails (click) 1708179 1443137 276 2906 6 0% 0 0 81.636679
hexapdf (click) 1418336 1191842 595 12568 38 0% 0 0 366.455702
liquid-c (click) 524422 446803 119 1754 5 0% 0 0 47.445694
liquid-compile (click) 449180 398681 151 2077 2 0% 0 0 63.115309
liquid-render (click) 623922 564499 136 2285 8 0% 0 0 61.710041
lobsters (click) 7893287 6597405 3211 50171 73 0% 0 0 1694.154973
mail (click) 731013 625419 346 4833 14 0% 0 0 141.114304
psych-load (click) 301393 252981 65 653 3 0% 0 0 20.205664
railsbench (click) 2991629 2599896 1634 15756 54 0% 0 0 450.880863
rubocop (click) 5369193 4607514 2901 47763 106 0% 4 0 1407.770247
ruby-lsp (click) 633865 556837 159 2735 14 0% 0 0 75.049257
sequel (click) 493042 432455 16 118 0 0% 0 0 4.36906
binarytrees (click) 9384 7556 11 75 0 0% 0 0 3.033229
blurhash (click) 51809 46977 32 459 0 0% 0 0 15.291143
erubi (click) 271655 230266 10 111 0 0% 0 0 3.876517
etanni (click) 31131 27054 11 91 0 0% 0 0 2.997197
fannkuchredux (click) 24443 9175 9 257 0 0% 0 0 7.652042
fluentd (click) 388157 327642 11 111 0 0% 0 0 3.575705
graphql (click) 443950 381434 70 673 0 0% 0 0 19.986522
graphql-native (click) 411003 344816 42 276 0 0% 0 0 9.125138
lee (click) 316487 277439 49 732 0 0% 0 0 22.708621
matmul (click) 12555 12107 12 126 0 0% 0 0 4.192982
nbody (click) 15072 7506 11 185 0 0% 0 0 4.981545
nqueens (click) 23418 17741 10 260 0 0% 0 0 7.759877
optcarrot (click) 314912 252069 192 4322 34 0% 0 0 102.985464
protoboeuf (click) 153790 132358 17 1378 0 0% 0 0 41.40254
rack (click) 272410 234193 31 319 0 0% 0 0 9.120021
ruby-json (click) 34095 28619 12 196 0 0% 0 0 5.708638
rubykon (click) 135831 116352 143 1518 3 0% 0 0 42.456209
sudoku (click) 46892 53197 11 507 0 0% 0 0 15.366203
tinygql (click) 313430 265839 63 786 5 0% 0 0 22.68114
30k_ifelse (click) 5222589 4374204 9264 50813 0 0% 0 0 1448.359291
30k_methods (click) 2019606 1594020 5782 19369 0 0% 0 0 518.237289
cfunc_itself (click) 7581 5778 9 70 0 0% 0 0 2.204148
fib (click) 5009 4601 8 49 0 0% 0 0 1.793733
getivar (click) 6094 5991 8 74 0 0% 0 0 2.119298
keyword_args (click) 8464 6470 10 72 0 0% 0 0 2.542754
respond_to (click) 8333 7728 9 85 0 0% 0 0 2.644118
ruby-xor (click) 8062 6902 9 87 0 0% 0 0 3.115483
setivar (click) 5185 4572 8 54 0 0% 0 0 1.748887
setivar_object (click) 5553 4592 8 54 0 0% 0 0 1.837044
setivar_young (click) 6276 5242 9 62 0 0% 0 0 2.032784
str_concat (click) 7876 7217 11 85 0 0% 0 0 2.843138
throw (click) 7938 6033 10 69 0 0% 0 0 2.453492

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.