Guided Start

This page is the shortest serious route through the project. Read it when you want to evaluate fit, boundaries, and next steps without wandering the whole docs tree.

Fast read: if you only have ten minutes, read this page, skim the architecture overview, then open the benchmarks page. That sequence is usually enough to understand what the project is and where its limits are.

What you are evaluating

• A browser-native FFT core built around WebGPU compute shaders
• CPU fallback paths for environments without WebGPU
• Real-input APIs that expose half-spectrum contracts explicitly
• CPU-only utilities for spectrum analysis and image filtering

A ten-minute route

1. Read the homepage to understand the public story and current product slice.
2. Jump to Quick Start to see the supported API shapes.
3. Open Architecture Overview to inspect the execution boundary.
4. Read Benchmarks to see what is measured versus what is intentionally not claimed.
5. Use Reference Hub if you want external context before making a call.

Capability boundary

Capability matrix

Separate the GPU core from the CPU-only utilities

Surface	GPU	CPU	Notes
1D FFT / IFFT	Native	Fallback	Complex interleaved input contract
1D RFFT / IRFFT	Wrapped	Native	Half-spectrum contract
2D FFT / IFFT	Native	Fallback	Row-column decomposition
Spectrum analyzer	—	CPU only	Built on window functions and CPU FFT
Image filter	—	CPU only	Frequency-domain utility, not a GPU shader pipeline

Good fit, not a fit

Good fit

• You need browser-side FFT with a real WebGPU path.
• You want clear API contracts and low package overhead.
• You care about documented GPU versus CPU boundaries.

Not a fit

• You need GPU-native spectrum analysis or GPU-native image filtering.
• You need arbitrary-size FFT without preprocessing.
• You want a broad DSP framework far outside FFT-centered workloads.

Where to go next

If you care most about	Read next
API shape and installation	Quick Start
Browser readiness	Browser Support
Architectural credibility	Architecture Overview
Performance honesty	Benchmarks
Research context	Academic Papers