YJIT Benchmarks

Details for Benchmarks at 2022-05-21 07:12:55

Overall YJIT is 31.3% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 27.2% 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 5 194 75 194 20 194
hexapdf 5 15 20 15
liquid-render 5 137 75 137 20 137
mail 5 108 75 108 20 108
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 63 75 63 20 63
chunky_png 5 29 75 29 20 29
discourse 5 38 75 38 20 38
erubi 5 47 75 47 20 47
erubi_rails 5 798 75 798 20 798
fannkuchredux 5 15 75 15 20 15
lee 5 22 75 22 20 22
nbody 5 265 75 265 20 265
optcarrot 5 15 75 15 20 15
rubykon 5 15 26 15 20 15
30k_ifelse 5 56 75 56 20 56
30k_methods 5 22 29 22 20 22
cfunc_itself 5 445 75 445 20 445
fib 5 320 75 320 20 320
getivar 5 761 75 761 20 761
keyword_args 5 376 75 376 20 376
respond_to 5 104 75 104 20 104
setivar 5 1868 75 1868 20 1868
str_concat 5 203 75 203 20 203

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) 1013083 753421 131 1236 0 0% 0 0 0
hexapdf (click) 1120411 878458 683 7751 9 0% 0 0 0
liquid-render (click) 513883 393744 150 1640 2 0% 0 0 0
mail (click) 912091 658612 374 5568 15 0% 0 0 0
psych-load (click) 339355 254799 68 457 1 0% 0 0 0
railsbench (click) 2633243 1924374 1436 9811 16 0% 0 0 0
binarytrees (click) 173915 130095 13 58 0 0% 0 0 0
chunky_png (click) 381339 284590 88 1010 0 0% 0 0 0
discourse (click) 5941211 4406809 3196 25414 84 0% 2 0 0
erubi (click) 317147 240997 10 79 0 0% 0 0 0
erubi_rails (click) 1950363 1402902 300 2007 4 0% 0 0 0
fannkuchredux (click) 187931 140793 10 188 0 0% 0 0 0
lee (click) 375195 281094 58 622 0 0% 0 0 0
nbody (click) 182043 136435 12 158 0 0% 0 0 0
optcarrot (click) 514587 442545 207 3571 20 0% 0 0 0
rubykon (click) 321371 253056 144 1564 1 0% 0 0 0
30k_ifelse (click) 5562971 4350419 9265 57804 0 0% 0 0 0
30k_methods (click) 2178139 1658881 5784 19361 0 0% 0 0 0
cfunc_itself (click) 172443 128724 10 49 0 0% 0 0 0
fib (click) 170907 128332 10 38 0 0% 0 0 0
getivar (click) 172699 130843 10 65 0 0% 0 0 0
keyword_args (click) 173275 129365 11 51 0 0% 0 0 0
respond_to (click) 174555 130178 10 64 0 0% 0 0 0
setivar (click) 172635 129367 10 38 0 0% 0 0 0
str_concat (click) 172635 129687 12 62 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.