lib_xcore_math: VPU-optimized math for the xcore architecture

FAVOURITE VERSION RELEASED COMMENTS DOCUMENTATION SOFTWARE
3.0.0 2026-05-27 v3 adds preliminary support for XCORE architecture VX4B product and removes obsolete build system support VIEW HTML VIEW PDF ZIP
View older versions
2.4.1 2026-02-16 2.4.1 brings minor bug fixes (XMATH_BFP_DEBUG_CHECK_LENGTHS now enabled at build, FFT Lookup script path in CMakeLists.txt), and change linking libm & enabling position-independent code for native x86 builds ZIP ZIP
2.4.0 2024-11-06 ZIP ZIP
v2.2.0 2024-06-04 ZIP ZIP
INFO

Summary

lib_xcore_math is an arithmetic and DSP library which leverages the Vector Processing Unit (VPU) of XS3/xcore.ai based devices in order to accelerate costly operations on vectors of 16- or 32-bit data. Included are functions for block floating-point arithmetic, fast Fourier transforms, discrete cosine transforms, linear filtering and more.

Features

  • Block Floating-Point Vector API

  • Vector/Array API

  • Scalar API

  • Linear Filtering API

  • Fast Fourier Transform API

  • Discrete Cosine Transform API

Known issues

  • Native build only supports xs3a VPU emulation

Development repo

Required tools

  • XMOS XTC Tools: 15.3.1

Required libraries (dependencies)

  • None

Support

This package is supported by XMOS Ltd. Issues can be raised against the software at www.xmos.com/support or using GitHub issues.

Scroll to Top