Title :
Obtaining a 35x Speedup in 2D Phase Unwrapping Using Commodity Graphics Processors
Author :
Karasev, P.A. ; Campbell, Daniel P. ; Richards, Mark A.
Author_Institution :
Georgia Inst. of Technol., Atlanta
Abstract :
Graphics processing units (GPUs) are a powerful tool for numerical computation. The GPU architecture and computational model are uniquely designed for high-resolution high-speed grid-based calculations. This capability can be utilized to accelerate certain classes of compute-intensive radar signal processing algorithms. Characteristics of a problem well-suited for computation on a GPU include high levels of data parallelism, low control logic, uniform boundary conditions, and well-defined input and output. We describe the implementation of two-dimensional multigrid least-squares weighted phase unwrapping on a GPU and demonstrate a large speedup over C and MATLAB implementations. Details of the GPU computation are provided. Background information on the GPU architecture and its applicability to general-purpose computation is discussed.
Keywords :
computer graphic equipment; differential equations; least squares approximations; microprocessor chips; radar computing; radar signal processing; 2D multigrid least-squares weighted phase unwrapping; 2D phase unwrapping; GPU architecture; commodity graphics processors; computational model; data parallelism; graphics processing units; high-resolution high-speed grid-based calculation; low control logic; numerical computation; radar signal processing; uniform boundary condition; Acceleration; Computational modeling; Computer architecture; Concurrent computing; Graphics; Grid computing; Mathematical model; Parallel processing; Radar signal processing; Signal processing algorithms;
Conference_Titel :
Radar Conference, 2007 IEEE
Conference_Location :
Boston, MA
Print_ISBN :
1-4244-0284-0
Electronic_ISBN :
1097-5659
DOI :
10.1109/RADAR.2007.374282
