Asilomar Conference on Signals, Signals, and Computers
Real-Time High-Throughput Sonar Beamforming Kernels Using
Native Signal Processing and Memory Latency Hiding Techniques
Gregory E. Allen (1),
Brian L. Evans (2),
and
Lizy K. John (2)
(1) Applied Research Laboratories,
The University of Texas at Austin,
P.O. Box 8029,
Austin, TX 78713-8029 USA
gallen@arlut.utexas.edu
(2) Department of Electrical and Computer Engineering,
Engineering Science Building,
The University of Texas at Austin,
Austin, TX 78712-1084 USA
bevans@ece.utexas.edu
Presentation
Software Release
Process Networks Research at UT Austin
Abstract
We evaluate the use of native signal processing with loop unrolling and
software prefetching to achieve high-performance digital signal
processing on general-purpose processors. We apply these techniques to
minimize the number of processors necessary for real-time implementation
of a 3-D sonar beamformer. Because our beamforming kernels operate on
high-throughput (~100 MB/s) input/output streams, memory latency hiding
techniques are key for maximum performance. On the Sun UltraSPARC-II
processor, we find speedups of 2.4 for hand loop unrolling, 1.46 for the
Visual Instruction Set over floating-point arithmetic in C, and 1.33 for
software prefetching.
The full paper is available in
PDF
format.
Slides for the lecture presentation
Greg Allen's
Beamforming Web Page.
Last Updated 05/21/14.