YJIT Benchmarks

Details for Benchmarks at 2022-12-15 20:09:58

Overall YJIT is 41.1% faster than interpreted CRuby!
On Railsbench specifically, YJIT is 37.0% 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 YJIT warmups YJIT iters
activerecord 5 196 5 196
hexapdf 5 15 5 15
liquid-render 5 178 5 178
mail 5 138 5 138
psych-load 5 15 5 15
railsbench 5 15 5 15
ruby-lsp 5 287 5 287
binarytrees 5 86 5 86
chunky_png 5 32 5 32
erubi 5 69 5 69
erubi_rails 5 1148 5 1148
etanni 5 42 5 42
fannkuchredux 5 20 5 20
lee 5 22 5 22
nbody 5 269 5 269
optcarrot 5 15 5 15
rubykon 5 15 5 15
30k_ifelse 5 51 5 51
30k_methods 5 20 5 20
cfunc_itself 5 495 5 495
fib 5 318 5 318
getivar 5 437 5 437
keyword_args 5 385 5 385
respond_to 5 692 5 692
setivar 5 1360 5 1360
setivar_object 5 327 5 327
str_concat 5 450 5 450

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) 2272340 2270622 25 405 5 1% 0 0 0
hexapdf (click) 1714360 1713110 819 10426 218 2% 0 0 0
liquid-render (click) 522765 520378 156 1846 32 1% 0 0 0
mail (click) 1243514 1241042 373 4654 176 3% 0 0 0
psych-load (click) 760994 758400 70 651 19 2% 0 0 0
railsbench (click) 5525426 5522936 1779 14344 483 3% 0 0 0
ruby-lsp (click) 5371056 5370476 6428 41706 1539 3% 12404 0 0
binarytrees (click) 96267 94002 16 140 3 2% 0 0 0
chunky_png (click) 798540 797018 89 1177 31 2% 0 0 0
erubi (click) 737918 737416 13 149 4 2% 0 0 0
erubi_rails (click) 4647976 4646122 329 2824 111 3% 0 0 0
etanni (click) 105342 102972 13 108 3 2% 0 0 0
fannkuchredux (click) 108481 107742 14 273 3 1% 0 0 0
lee (click) 801838 799262 79 813 24 2% 0 0 0
nbody (click) 109148 108114 15 245 5 2% 0 0 0
optcarrot (click) 512607 510684 203 4439 92 2% 0 0 0
rubykon (click) 235430 233164 146 1641 30 1% 0 0 0
30k_ifelse (click) 5238111 5235722 9268 57200 3 0% 0 0 0
30k_methods (click) 1993486 1991930 5787 19427 3 0% 0 0 0
cfunc_itself (click) 94560 92970 13 135 3 2% 0 0 0
fib (click) 92325 91458 13 112 3 2% 0 0 0
getivar (click) 94099 92610 13 139 3 2% 0 0 0
keyword_args (click) 94538 93002 14 125 3 2% 0 0 0
respond_to (click) 94263 92758 13 139 4 2% 0 0 0
setivar (click) 93138 91890 13 119 3 2% 0 0 0
setivar_object (click) 93480 92038 13 119 3 2% 0 0 0
str_concat (click) 94011 92590 15 138 5 3% 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.