YJIT Benchmarks

Details for Benchmarks at 2021-12-24 07:11:14

Overall YJIT is 25.6% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 27.0% 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 MJIT3.0 warmups MJIT3.0 iters MJIT warmups MJIT iters YJIT warmups YJIT iters
activerecord 5 193 20 193 75 193 20 193
hexapdf 5 15 20 15 20 15
liquid-render 5 173 20 173 75 173 20 173
mail 5 138 20 138 75 138 20 138
psych-load 5 15 20 15 75 15 20 15
railsbench 5 15 20 15 75 15 20 15
binarytrees 5 87 20 87 75 87 20 87
erubi 5 49 20 49 75 49 20 49
erubi_rails 5 554 20 554 75 554 20 554
fannkuchredux 5 15 20 15 54 15 20 15
jekyll 5 15 20 15 36 15 20 15
lee 5 26 20 26 75 26 20 26
nbody 5 342 20 342 75 342 20 342
optcarrot 5 15 20 15 75 15 20 15
rubykon 5 15 20 15 44 15 20 15
30k_ifelse 5 63 20 63 66 63 20 63
30k_methods 5 26 20 26 42 26 20 26
cfunc_itself 5 503 20 503 75 503 20 503
fib 5 383 20 383 75 383 20 383
getivar 5 563 20 563 75 563 20 563
keyword_args 5 451 20 451 75 451 20 451
respond_to 5 133 20 133 75 133 20 133
setivar 5 478 20 478 75 478 20 478

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) 979370 747611 185 1194 0 0% 0 0 0
hexapdf (click) 1123690 918341 598 8105 618 7% 0 0 321
liquid-render (click) 475319 376055 143 1465 95 6% 0 0 1
mail (click) 872490 648161 325 5442 124 2% 0 0 39
psych-load (click) 300385 237169 57 423 1 0% 0 0 0
railsbench (click) 2511010 1899779 1295 9208 266 2% 0 0 26
binarytrees (click) 116005 89076 9 48 0 0% 0 0 0
erubi (click) 280161 220810 8 35 0 0% 0 0 0
erubi_rails (click) 2459490 1773441 260 1968 17 0% 0 0 3
fannkuchredux (click) 131877 101248 6 202 0 0% 0 0 0
jekyll (click) 1848426 1486110 338 3756 185 4% 0 0 0
lee (click) 338209 266764 43 557 70 12% 0 0 12
nbody (click) 125285 96439 8 148 0 0% 0 0 0
optcarrot (click) 454949 402467 196 3566 20 0% 0 0 0
rubykon (click) 256677 208821 139 1517 1 0% 0 0 0
30k_ifelse (click) 5505445 4309778 9261 57794 0 0% 0 0 0
30k_methods (click) 2120613 1618240 5780 19351 0 0% 0 0 0
cfunc_itself (click) 114341 87754 6 39 0 0% 0 0 0
fib (click) 113381 87691 6 28 0 0% 0 0 0
getivar (click) 114661 89986 6 55 0 0% 0 0 0
keyword_args (click) 115749 88724 7 41 0 0% 0 0 0
respond_to (click) 116453 89208 6 54 0 0% 0 0 0
setivar (click) 114661 88510 6 28 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.