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.

cuFFTDx is a part of the MathDx package which also includes the cuBLASDx library providing selected linear algebra functions like General Matrix Multiplication (GEMM) Both libraries are designed to work together. Examples of kernels with both libraries are included in the package as cuBLASDx samples. When using multiple device extensions libraries in a single project they should all come from the same MathDx release.

The documentation consists of three main components:

• Requirements and supported features.

• A quick start guide, First FFT Using cuFFTDx.

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

Highlights

The cuFFTDx library provides:

• Fast Fourier Transform (FFT) CUDA functions 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, number of batches, etc.).

• Ability to fuse FFT kernels with other operations in order to save global memory trips.

• Compatibility with future versions of the CUDA Toolkit.

User guide:

• Requirements and Functionality
  • Requirements
  • Supported Functionality
• Quick Installation Guide
  • cuFFTDx In Your Project
  • cuFFTDx In Your CMake Project
• First FFT Using cuFFTDx
  • Defining Basic FFT
  • Executing FFT
  • Launching FFT Kernel
  • Compilation
• Your Next Custom FFT Kernels
  • Using Optimal parameters
  • Extra Shared Memory
  • What happens under the hood
• Achieving High Performance
  • General Advice
  • Memory Management
  • Kernel Fusion
  • Advanced
  • Further Reading
• cuFFTDx API Reference
  • Operators
  • Traits
  • Execution Methods
• Examples
  • Introduction Examples
  • Simple FFT Examples
  • NVRTC Examples
  • FFT Performance
  • Convolution Examples
  • 2D/3D FFT Advanced Examples
  • Input/Output Helper Functions
• Release Notes
  • 1.1.1
  • 1.1.0
  • 1.0.0
  • 0.3.1
• Software License Agreement