Radar Signal Processing with Graphics Processors (GPUs)

Radar Signal Processing algorithms place strong real-time performance demands on computer architectures. These algorithms do however have an inherent data-parallelism that allows for great performance on massively parallel architectures, such as the Graphics Processing Unit (GPUs). Recently, using GPUs for other than graphics processing has become a possibility through the CUDA and OpenCL (Open Computing Language) architectures. This master thesis aims at evaluating the Nvidia GT200 series GPU-architecture for radar signal processing applications. The investigation is conducted through comparing a GPU (GTX260) against a modern desktop CPU for several HPEC (High Performance Embedded Computing) and other radar signal processing algorithms; 12 in total. Several other aspects are also investigated, such as programming environment and efficiency, future GPU-architectures, and applicability in radar systems. Our CUDA GPU-implementations perform substantially better than the CPU and associated CPU-code used for all but one of the 12 algorithms tested, sometimes by a factor of 100 or more. The OpenCL implementations also perform substantially better than the CPU. The substantial performance achieved when using CUDA for almost all benchmarks can be attributed to both the high theoretical performance of the GPU, but also to the inherent data-parallelism, and hence GPU-suitability, of almost all of the investigated algorithms. Programming CUDA is reasonably straight forward, largely due to the mature development environment and abundance of documentation and white-papers. OpenCL is a lot more tedious to program. Furthermore, the coming CUDA GPU-architecture called Fermi is expected to further increase performance and programmability. When considering system integration of GPU-architectures into harsh radar application environments, one should be aware of potential heat and also possible obsolescence issues. COMPANY UNCLASSIFIED MASTER THESIS 2 (127) Prepared (also subject responsible if other) No. SMW/DD/GX Jimmy Pettersson, Ian Wainwright 5/0363-FCP1041180 en Approved Checked Date Rev Reference SMW/DD/GCX Lars Henricson DD/LX K.Lind 2010-01-27 A