Performance & benchmarks

PedalKernel circuits are designed for real-time performance. This page shows actual CPU usage and scaling behavior.

Pedal benchmarks

All pedals run comfortably in real-time. Measurements on an Apple M-series chip at 48 kHz:

Pedal	CPU Budget	Samples/sec	Realtime ×
Tube Screamer	1.2%	3.8M	80×
Big Muff	1.7%	2.8M	59×
Fuzz Face	0.04%	122M	2500×
Blues Driver	5.9%	818K	17×
Dyna Comp	0.4%	12M	252×
Klon Centaur	1.4%	3.5M	72×
ProCo RAT	0.3%	16M	330×
Boss CE-2 (BBD)	0.5%	9.9M	207×

CPU Budget = fraction of real-time budget consumed. Under 100% means glitch-free audio.

WDF processing cost per sample depends on circuit complexity:

A Tube Screamer (1 clipping stage) needs ~12 MFLOPS at 48 kHz. A Big Muff (4 cascaded stages) needs ~48 MFLOPS.

The BBD model (Boss CE-2) includes full analog bucket-brigade emulation:

Companding — NE571-style 2:1 compression/expansion with mismatched attack/release (causes "breathing")
Charge leakage — per-stage loss accumulates across 1024+ stages, darkening long delays (the Memory Man warmth)
Clock feedthrough — parasitic capacitance couples switching clock into signal (the characteristic BBD whine)
Bandwidth limiting — Nyquist limit at half clock frequency with anti-alias LPF
Soft clipping — BBD voltage swing saturation with cubic waveshaping

Despite this, BBD overhead is modest (~0.5% CPU) because most operations are simple one-pole filters.

Cascaded WDF stages scale linearly:

The Tube Screamer at various sample rates:

Run the full benchmark suite yourself:

cargo bench --bench wdf_bench

This gives you precise CPU timing on your machine, sample rates, and pedals of your choice.