Exploiting Parallelism in a QPALM-based Solver for Optimal Control

TL;DR

This paper enhances a quadratic programming solver for optimal control by exploiting parallelism and vectorization, leading to improved computational efficiency through an optimized C++ implementation and benchmark testing.

Contribution

It introduces a parallelized and vectorized version of the QPALM-OCP algorithm, specifically tailored for optimal control problems, with significant performance improvements.

Findings

Parallelization accelerates the solver for optimal control problems.

Vectorization further improves computational efficiency.

Benchmark results show superior performance over the original QPALM method.

Abstract

We discuss the opportunities for parallelization in the recently proposed QPALM-OCP algorithm, a solver tailored to quadratic programs arising in optimal control. A significant part of the computational work can be carried out independently for the different stages in the optimal control problem. We exploit this specific structure to apply parallelization and vectorization techniques in an optimized C++ implementation of the method. Results for optimal control benchmark problems and comparisons to the original QPALM method are provided.