YJIT Benchmarks

Details for Benchmarks at 2022-03-21 07:13:05

Overall YJIT is 32.9% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 32.4% 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 MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 181 75 181 20 181
hexapdf 5 15 20 15
liquid-render 5 154 75 154 20 154
mail 5 123 75 123 20 123
psych-load 5 15 75 15 20 15
railsbench 5 15 75 15 20 15
binarytrees 5 68 75 68 20 68
chunky_png 5 30 75 30 20 30
discourse 5 37 75 37 20 37
erubi 5 48 75 48 20 48
erubi_rails 5 972 75 972 20 972
fannkuchredux 5 15 75 15 20 15
lee 5 21 75 21 20 21
nbody 5 284 75 284 20 284
optcarrot 5 15 75 15 20 15
rubykon 5 15 38 15 20 15
30k_ifelse 5 55 75 55 20 55
30k_methods 5 22 29 22 20 22
cfunc_itself 5 446 75 446 20 446
fib 5 320 75 320 20 320
getivar 5 806 75 806 20 806
keyword_args 5 379 75 379 20 379
respond_to 5 101 75 101 20 101
setivar 5 1904 75 1904 20 1904

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) 991633 760686 185 1201 0 0% 0 0 0
hexapdf (click) 1114705 913489 599 8166 615 7% 0 0 320
liquid-render (click) 491729 390037 143 1530 96 6% 0 0 1
mail (click) 879569 659804 324 5325 125 2% 0 0 39
psych-load (click) 330961 261772 59 434 1 0% 0 0 0
railsbench (click) 2538705 1934633 1297 9383 268 2% 0 0 26
binarytrees (click) 152849 117312 11 59 0 0% 0 0 0
chunky_png (click) 367249 286466 85 869 0 0% 0 0 0
discourse (click) 23601105 11760482 3134 299762 276205 92% 2 0 133
erubi (click) 322513 255431 10 79 0 0% 0 0 0
erubi_rails (click) 1908305 1436967 262 1902 18 0% 0 0 3
fannkuchredux (click) 166545 128010 8 189 0 0% 0 0 0
lee (click) 373649 294597 45 587 69 11% 0 0 12
nbody (click) 161553 124184 10 159 0 0% 0 0 0
optcarrot (click) 488785 429814 198 3576 20 0% 0 0 0
rubykon (click) 297553 240895 140 1584 1 0% 0 0 0
30k_ifelse (click) 5541457 4337460 9263 57805 0 0% 0 0 0
30k_methods (click) 2157009 1646098 5782 19362 0 0% 0 0 0
cfunc_itself (click) 150737 115612 8 50 0 0% 0 0 0
fib (click) 149841 115549 8 39 0 0% 0 0 0
getivar (click) 151249 117884 8 66 0 0% 0 0 0
keyword_args (click) 151825 116366 9 52 0 0% 0 0 0
respond_to (click) 153809 117563 8 65 0 0% 0 0 0
setivar (click) 151569 116536 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.