YJIT Benchmarks

Details for Benchmarks at 2022-04-01 07:14:41

Overall YJIT is 30.8% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 31.0% 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 MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 181 75 181 20 181
hexapdf 5 15 20 15
liquid-render 5 148 75 148 20 148
mail 5 122 75 122 20 122
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 66 75 66 20 66
chunky_png 5 30 75 30 20 30
discourse 5 36 75 36 20 36
erubi 5 47 75 47 20 47
erubi_rails 5 934 75 934 20 934
fannkuchredux 5 15 74 15 20 15
lee 5 21 75 21 20 21
nbody 5 283 75 283 20 283
optcarrot 5 15 75 15 20 15
rubykon 5 15 22 15 20 15
30k_ifelse 5 55 75 55 20 55
30k_methods 5 22 29 22 20 22
cfunc_itself 5 451 75 451 20 451
fib 5 318 75 318 20 318
getivar 5 777 75 777 20 777
keyword_args 5 376 75 376 20 376
respond_to 5 103 75 103 20 103
setivar 5 1899 75 1899 20 1899

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) 988177 758526 185 1199 0 0% 0 0 0
hexapdf (click) 1114193 913061 599 8162 614 7% 0 0 320
liquid-render (click) 493841 392526 143 1564 95 6% 0 0 1
mail (click) 842385 634297 324 4983 125 2% 0 0 39
psych-load (click) 330577 261076 59 434 1 0% 0 0 0
railsbench (click) 2536337 1931816 1297 9380 268 2% 0 0 26
binarytrees (click) 153041 117621 11 59 0 0% 0 0 0
chunky_png (click) 365201 284873 85 858 0 0% 0 0 0
discourse (click) 23325009 11656505 3146 295197 271442 91% 2 0 133
erubi (click) 322065 255098 10 79 0 0% 0 0 0
erubi_rails (click) 1908945 1437860 262 1892 18 0% 0 0 3
fannkuchredux (click) 166481 127941 8 189 0 0% 0 0 0
lee (click) 373265 294326 45 587 69 11% 0 0 12
nbody (click) 161681 123870 10 159 0 0% 0 0 0
optcarrot (click) 489233 430074 198 3576 20 0% 0 0 0
rubykon (click) 293393 237240 140 1527 2 0% 0 0 0
30k_ifelse (click) 5541457 4336993 9263 57805 0 0% 0 0 0
30k_methods (click) 2157009 1646029 5782 19362 0 0% 0 0 0
cfunc_itself (click) 151697 116005 8 50 0 0% 0 0 0
fib (click) 149457 114906 8 39 0 0% 0 0 0
getivar (click) 152017 118124 8 66 0 0% 0 0 0
keyword_args (click) 152081 116513 9 52 0 0% 0 0 0
respond_to (click) 153553 117439 8 65 0 0% 0 0 0
setivar (click) 151633 116628 8 39 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.