Design of high‐speed software defined radar with GPU accelerator

Abstract

Software defined radar (SDRadar) systems have become an important area for future radar development and are based on similar concepts to Software defined radio (SDR). Most of the processing like filtering, frequency conversion and signal generation are implemented in software. Currently, radar systems tend to have complex signal processing and operate at wider bandwidth, which means that limits on the available computational power must be considered when designing a SDRadar system. This paper presents a feasible solution to this potential limitation by accelerating the signal processing using a GPU to enable the development of a high speed SDRadar system. The developed system overcomes the limitation on the processing speed by CPU-only, and has been tested on three different SDR devices. Results show that, with GPU accelerator, the processing rate can achieve up to 80 MHz compared to 20 MHz with the CPU-only. The high speed processing makes it possible to run in real-time and process full bandwidth across the WiFi signal acquired by multiple channels. The gains made through porting the processing to the GPU moves the technology towards real-world application in various scenarios ranging from healthcare to IoT, and other applications that required significant computational processing. K E Y W O R D SGPU accelerator, signal processing, software defined radar | INTRODUCTIONThe applications of radar cover many broad and various areas, for example, the long-range airborne and weather surveillance, short-range target detection, target recognition and classification, etc. These applications have diverse demands, leading to the proliferation of highly specialised radar systems on the same platform, for example, ship, aircraft and others [1]. In addition, these platforms are also equipped with a number of other types of Radio Frequency (RF) sensors, such as communication and navigation systems. Many radar systems were implemented using hardware such as Field programmable gate arrays (FPGAs). However, a software implementation, which uses general-purpose processors is more desirable for its cost-effective, flexibility and fast development. Thus, the approach of sharing a platform with an SDRadar allows these requirements to be met [2]. However, increases in signal sampling rates (signal bandwidth) and the number of receiver channels in Multiple-Input and Multiple-Output (MIMO)/ distributed radar systems, mean there are more data need to be processed. For example, the universal software radio peripheral (USRP) family [3] has sampling rate from 20 MHz up to 160 MHz for 2 to 4 channels, the DigitizerNetbox (Dig-itizerNetbox) [4] can operate at 5 GHz with up to 16 channels, and also Ultra-Wide Band design [5]. Consequently, this increasing requirement in computational power becomes a key parameter to be considered for an SDRadar system.FPGA and GPU are commonly employed to accelerate computational processing. There are a number of differences between these two architectures, in terms of flexibility, powerThis is an open access...

Implementation of the sliding window moving target detection algorithm for blade server

“…Declare two two-dimensional shared memory variables [9], As and Bs, to access filter bank coefficients and radar data, respectively. To prevent data call errors caused by shared memory access conflicts, use the _ syncthreads() function [10] to synchronize threads and ensure the correctness of data processing during each iteration.…”

Implementation of a coherent real‐time noise radar system

“…The effective memory bandwidth of such memories when performing radar-specific operations, such as range-Doppler processing, remains to be seen. A high-speed radar processing design will likely consist of a mix of GPUs, CPUs, and FPGAssee references [46,47] for more details.…”