Mandelbrot (FP)

Escape-time render of the Mandelbrot set at 200×200 with 80 iters/pixel. Pure float64 tight loop.

Runtime Compile time

Compile time · median (cold)

median of 10 runs

Native Gocompiled

181 ms246×

Piko interpbytecode VM

735 µsbaseline

CPython 3.13bytecode VM

262 µs0.36×

PyPy 7.3tracing JIT

237 µs0.32×

Ttengobytecode VM

208 µs0.28×

Sscriggobytecode VM

236 µs0.32×

Mmvmbytecode VM

274 µs0.37×

YyaegiAST walker

304 µs0.41×

Full statistics

Runner	N	Compile	Runtime	P95	Stddev	RSS	vs piko	Status
Native Gocompiled	10	181 ms	3.38 ms	3.39 ms	4.30 µs	69 MiB	246×	OK
Piko interpbytecode VM	10	735 µs	28.8 ms	29.4 ms	226 µs	82 MiB	1.00×	OK
CPython 3.13bytecode VM	10	262 µs	140 ms	147 ms	3.26 ms	n/a	0.36×	OK
PyPy 7.3tracing JIT	10	237 µs	11.0 ms	11.3 ms	175 µs	n/a	0.32×	OK
tengobytecode VM	10	208 µs	269 ms	278 ms	3.54 ms	1.45 GiB	0.28×	OK
scriggobytecode VM	10	236 µs	199 ms	230 ms	9.41 ms	72 MiB	0.32×	OK
mvmbytecode VM	10	274 µs	291 ms	322 ms	22.1 ms	62 MiB	0.37×	OK
yaegiAST walker	10	304 µs	237 ms	266 ms	15.0 ms	66 MiB	0.41×	OK

Workload & symmetry rules

Workload

For each of 200×200 pixels: iterate the Mandelbrot recurrence z = z² + c up to 80 times, count the iteration at which |z| > 2. Output the sum of iteration counts so canonical hashing doesn't depend on FP equality.

Symmetry rules

Pure float64 scalar arithmetic (no complex type, no numpy, no math.cmath).
Inner loop manually unrolled per the README's reference shape; no language-specific shortcuts.

Why this benchmark exists

The one shape of work missing from the rest of the suite: a tight float64 inner loop. This is where piko's typed float register bank pays its biggest dividend.

Source code

piko / Go
piko_source.go
native Go
native_main.go
CPython / PyPy
cpython.py
tengo
script.tengo