Xilinx is now part ofAMDUpdated Privacy Policy

The Vitis™ Solver library offers a collection of performance-optimized standard matrix decomposition, linear solvers, and eigenvalue solvers that can be used for designing accelerated algorithms across several applications like Computational Finance, RADAR, LiDAR, Computer Vision, DSP, and Controls among others.

Vitis Solver Library Kernels can be used as standalone accelerators that you can call in your Embedded/Host CPU code or combine with other Vitis Library Kernel and Primitives to accelerate your end-to-end processing pipeline.

While the Vitis Solver library will continue to improve and expand in functionality, some of the key accelerated functions currently available include Singular Value Decomposition (SVD), QR & LU Decomposition, Matrix Inverse, Triangular Solvers, Eigen Value Decomposition, and others.

Getting Started