YJIT Benchmarks

Details for Benchmarks at 2022-10-27 20:10:37

Overall YJIT is 34.5% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 34.3% 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 5 208 5 208
hexapdf 5 15 5 15
liquid-render 5 176 5 176
mail 5 128 5 128
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 244 5 244
binarytrees 5 88 5 88
chunky_png 5 32 5 32
erubi 5 68 5 68
erubi_rails 5 1075 5 1075
etanni 5 42 5 42
fannkuchredux 5 15 5 15
lee 5 20 5 20
nbody 5 245 5 245
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 49 5 49
30k_methods 5 20 5 20
cfunc_itself 5 494 5 494
fib 5 324 5 324
getivar 5 427 5 427
keyword_args 5 385 5 385
respond_to 5 712 5 712
setivar 5 404 5 404
str_concat 5 471 5 471

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) 2313955 2312123 23 341 6 1% 0 0 0
hexapdf (click) 1771717 1770507 817 10055 189 1% 0 0 0
liquid-render (click) 591190 590610 154 1769 34 1% 0 0 0
mail (click) 1346276 1344978 371 5130 176 3% 0 0 0
psych-load (click) 795530 794999 68 574 19 3% 0 0 0
railsbench (click) 5533454 5530808 1777 13668 483 3% 0 0 0
ruby-lsp (click) 5602667 5601557 6423 41535 1520 3% 12704 0 0
binarytrees (click) 121378 119042 14 79 4 5% 0 0 0
chunky_png (click) 822232 821079 87 1061 31 2% 0 0 0
erubi (click) 745527 745255 11 87 4 4% 0 0 0
erubi_rails (click) 4636058 4635174 327 2621 111 4% 0 0 0
etanni (click) 129371 126501 11 47 4 8% 0 0 0
fannkuchredux (click) 141142 140453 11 209 4 1% 0 0 0
lee (click) 829056 828371 77 758 25 3% 0 0 0
nbody (click) 135759 134318 13 188 6 3% 0 0 0
optcarrot (click) 563994 561996 201 4014 93 2% 0 0 0
rubykon (click) 279276 278769 143 1588 32 2% 0 0 0
30k_ifelse (click) 5420144 5419577 9266 57136 4 0% 0 0 0
30k_methods (click) 2081304 2080603 5785 19365 4 0% 0 0 0
cfunc_itself (click) 126405 125081 11 62 4 6% 0 0 0
fib (click) 117862 116641 11 51 4 7% 0 0 0
getivar (click) 119933 118524 11 78 4 5% 0 0 0
keyword_args (click) 120097 117946 12 64 4 6% 0 0 0
respond_to (click) 119828 118038 11 78 5 6% 0 0 0
setivar (click) 120091 117975 11 51 4 7% 0 0 0
str_concat (click) 119535 118078 13 77 6 7% 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.