Heterogeneous transmission and parallel computing platform (HTPCP) for remote sensing applications
Yi Peng Guo, Antonio Rius, Serni Ribó, Carles Ferrer · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2011
The increasing campaigns of GNSS-R scenario have put great pressure on high performance post-processing design into the space level instrumentation. Due to large scale of information acquisition and the intensive computation of cross-correlation waveform (CC-WAV), the overhead between the processing time and the storage of amount of data prior to downlink issues has lead us to get the solution of real-time parallel processing design on board. In this paper, we focus on the interaction of the chip level multiprocessing architecture and applications, which show that the unbalanced workload of the transmission and processing can be compensated on the novel architecture, Heterogeneous Transmission and Parallel Computing Platform (HTPCP). The intention of HTPCP is to get a solution for the bus congestion and memory allocation issues. The pros and cons of SMP and HTPCP are discussed, and the simulation results prove that HTPCP can highly improve the throughput of the GOLD-RTR system.