Accelerate provides high-performance, energy-efficient computation on the CPU by leveraging its vector-processing capability. The following Accelerate libraries abstract that capability so that code written for them executes appropriate instructions for the processor available at runtime:
- BNNS. Subroutines for constructing and running neural networks for both training and inference.
- vImage. A wide range of image-processing functions, including Core Graphics and Core Video interoperation, format conversion, and image manipulation.
- vDSP. Digital signal processing functions, including 1D and 2D fast Fourier transforms, biquadratic filtering, vector and matrix arithmetic, convolution, and type conversion.
- vForce. Functions for performing arithmetic and transcendental functions on vectors.
- Sparse Solvers, BLAS, and LAPACK. Libraries for performing linear algebra on sparse and dense matrices.
Although not part of the Accelerate framework, the following libraries are closely related:
- Apple Archive. A framework for performing multithreaded lossless compression of directories, files, and data.
- Compression. Algorithms for lossless data compression that support LZFSE, LZ4, LZMA, and ZLIB algorithms.
- simd. A module for performing computations on small vectors and matrices.