NVIDIA cuFFTDx

The cuFFT Device Extensions (cuFFTDx) library enables you to perform Fast Fourier Transform (FFT) calculations inside your CUDA kernel. Fusing FFT with other operations can decrease the latency and improve the performance of your application.

The documentation consists of two main components:

• A quick start guide, First FFT using cuFFTDx.

• An cuFFTDx API Reference for a comprehensive overview of the provided functionality.

Highlights

• Fast Fourier Transform (FFT) embeddable into a CUDA kernel

• High performance, no unnecessary data movement from and to global memory

• Customizability, options to adjust selection of FFT routine for different needs (size, precision, batches etc.)

• Ability to fuse FFT kernels with other operations saving global memory trips

• Compatibility with future versions of the CUDA Toolkit

User guide:

• First FFT using cuFFTDx
  • What next?
  • Compilation
• Your next custom FFT kernels
  • What happens under the hood?
  • Why?
• Achieving high performance
  • General advice
  • Memory management
  • Kernel fusion
  • Advanced
  • Further reading
• Requirements and Functionality
  • Requirements
  • Supported Functionality
• cuFFTDx API Reference
  • Operators
  • Traits
  • Execution Methods
• Release Notes
  • 1.0.0
  • 0.3.1
• Software License Agreement