YJIT Benchmarks

Details for Benchmarks at 2023-07-13 19:08:14

Overall YJIT is 52.0% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 52.4% faster than CRuby!
The basic "faster" measurement is the geomean of all "headlining" x86 benchmarks on this page.

Headlining Benchmarks

These are "headlining" because the "overall" speedup above is based on these benchmarks specifically.

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Other Benchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

MicroBenchmarks

Speed of each Ruby implementation (iterations/second) relative to the CRuby interpreter. Higher is better.

Want Raw Graphs and CSV?

Benchmarks Speed Details

Benchmark Memory Usage Details

Number of Iterations and Warmups Tested

bench No JIT warmups No JIT iters YJIT warmups YJIT iters
activerecord 30 471 30 471
chunky-png 30 30 30 30
erubi-rails 30 1275 30 1275
hexapdf 30 15 30 15
liquid-c 30 333 30 333
liquid-compile 30 368 30 368
liquid-render 30 191 30 191
mail 30 149 30 149
psych-load 30 15 30 15
railsbench 30 15 30 15
ruby-lsp 30 363 30 363
sequel 30 285 30 285
binarytrees 30 86 30 86
erubi 30 77 30 77
etanni 30 49 30 49
fannkuchredux 30 26 30 26
lee 30 21 30 21
nbody 30 288 30 288
optcarrot 30 15 30 15
rack 30 184 30 184
ruby-json 30 15 30 15
rubykon 30 15 30 15
30k_ifelse 30 55 30 55
30k_methods 30 23 30 23
cfunc_itself 30 504 30 504
fib 30 448 30 448
getivar 30 945 30 945
keyword_args 30 411 30 411
respond_to 30 754 30 754
setivar 30 1667 30 1667
setivar_object 30 475 30 475
setivar_young 30 473 30 473
str_concat 30 417 30 417
throw 30 830 30 830

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) 679853 625369 51 432 1 0% 0 0 0
chunky-png (click) 258682 249755 86 1063 1 0% 0 0 0
erubi-rails (click) 1607100 1369130 288 2502 1 0% 0 0 0
hexapdf (click) 1177654 1151000 600 10725 22 0% 0 0 0
liquid-c (click) 412650 416652 125 1581 3 0% 0 0 0
liquid-compile (click) 307576 308884 149 1994 2 0% 0 0 0
liquid-render (click) 445103 448063 146 1883 8 0% 0 0 0
mail (click) 613809 573553 346 4393 9 0% 0 0 0
psych-load (click) 212764 203554 64 570 1 0% 0 0 0
railsbench (click) 2280649 2015322 1355 10890 7 0% 0 0 0
ruby-lsp (click) 5098227 4703655 3402 44587 319 0% 4 0 0
sequel (click) 397829 376008 15 97 0 0% 0 0 0
binarytrees (click) 9076 7468 11 75 0 0% 0 0 0
erubi (click) 178711 182146 9 83 0 0% 0 0 0
etanni (click) 12317 10568 11 55 0 0% 0 0 0
fannkuchredux (click) 19589 20370 8 219 0 0% 0 0 0
lee (click) 238159 220701 49 657 0 0% 0 0 0
nbody (click) 16822 16627 10 178 0 0% 0 0 0
optcarrot (click) 321041 382506 197 4341 22 0% 0 0 0
rack (click) 184416 182091 29 268 0 0% 0 0 0
ruby-json (click) 25650 22151 11 191 0 0% 0 0 0
rubykon (click) 132747 139110 145 1528 2 0% 0 0 0
30k_ifelse (click) 5362743 4368508 9263 50806 0 0% 0 0 0
30k_methods (click) 1992158 1528536 5781 19360 0 0% 0 0 0
cfunc_itself (click) 6422 4947 8 61 0 0% 0 0 0
fib (click) 4917 4454 8 49 0 0% 0 0 0
getivar (click) 6058 5980 8 74 0 0% 0 0 0
keyword_args (click) 7197 5541 9 63 0 0% 0 0 0
respond_to (click) 6928 6857 8 76 0 0% 0 0 0
setivar (click) 5209 4541 8 54 0 0% 0 0 0
setivar_object (click) 5544 4561 8 54 0 0% 0 0 0
setivar_young (click) 6335 5537 9 62 0 0% 0 0 0
str_concat (click) 6802 6350 10 76 0 0% 0 0 0
throw (click) 3993 3228 10 37 0 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.