Solving Quadratic Programming Problems on Graphics Processing Unit

Quadratic Programming (QP) problems frequently appear as core component when solving constrained optimal control or estimation problems. The focus of this paper is on accelerating an existing Interior Point Method (IPM) for solving QP problems by exploiting the parallel computing characteristics of GPU. We compare the so-called data-parallel and the problem-parallel approaches to achieve speed up for solving QP problems. The data-parallel approach achieves speed up by parallelizing the vector and matrix computations such as the dot-product, while the problem-parallel approach solves multiple QP problems in parallel using one GPU. Our results show that solving several QP problems in parallel could lead to better utilization of the GPU resources. This problem-parallel approach is well-suited for implementing a new type of Model Predictive Control algorithm characterized by solving multiple copies of MPC in parallel to improve closed-loop performance.

[1]  Stephen J. Wright,et al.  Applying new optimization algorithms to more predictive control , 1996 .

[2]  K.V. Ling,et al.  A FPGA implementation of model predictive control , 2006, 2006 American Control Conference.

[3]  Michael Minkoff,et al.  Randomly Generated Test Problems for Positive Definite Quadratic Programming , 1984, TOMS.

[4]  W. Marsden.  I and J , 2012 .

[5]  Jan M. Maciejowski,et al.  Embedded Model Predictive Control (MPC) using a FPGA , 2008 .

[6]  Stephen J. Wright,et al.  Application of Interior-Point Methods to Model Predictive Control , 1998 .

[7]  Manfred Morari,et al.  Model predictive control: Theory and practice , 1988 .

[8]  Jonathan P. How,et al.  Model predictive control of vehicle maneuvers with guaranteed completion time and robust feasibility , 2003, Proceedings of the 2003 American Control Conference, 2003..

[9]  Johan U. Backstrom,et al.  Quadratic programming algorithms for large-scale model predictive control , 2002 .

[10]  Jan M. Maciejowski,et al.  Multiplexed Model Predictive Control , 2011, Autom..

[11]  Maciej Ławryńczuk,et al.  Computationally efficient nonlinear predictive control based on state-space neural models , 2009 .

[12]  Eric C. Kerrigan,et al.  Parallel MPC for Real-Time FPGA-based Implementation , 2011 .

[14]  Jan M. Maciejowski,et al.  Predictive control : with constraints , 2002 .

[15]  R. Stephenson.  A and V , 1962, The British journal of ophthalmology.

[16]  Graham C. Goodwin,et al.  Model Predictive Rudder Roll Stabilization Control for Ships , 2000 .

[17]  Henri Calandra,et al.  Fast seismic modeling and Reverse Time Migration on a GPU cluster , 2009, 2009 International Conference on High Performance Computing & Simulation.

[18]  Jia Guo,et al.  Channel-Hopping Model Predictive Control , 2011 .

[19]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[20]  Weng Khuen Ho,et al.  Multiplexed MPC for Multizone Thermal Processing in Semiconductor Manufacturing , 2010, IEEE Transactions on Control Systems Technology.

[21]  H. Michalska,et al.  Receding horizon control of nonlinear systems , 1988, Proceedings of the 28th IEEE Conference on Decision and Control,.