TY - JOUR
T1 - Design and evaluation of I/O strategies for parallel pipelined STAP applications
AU - Liao, Wei-Keng
AU - Choudhary, Alok Nidhi
AU - Weiner, Donald
AU - Varshney, Pramod
PY - 2000/1/1
Y1 - 2000/1/1
N2 - This paper presents experimental results for a parallel pipeline STAP system with I/O task implementation using the parallel file systems on the Intel Paragon and the IBM SP. In our previous work, a parallel pipeline model was designed for radar signal processing applications on parallel computers. Based on this model, we implemented a real STAP application which demonstrated the performance scalability of this model in terms of throughput and latency. In this paper, we study the effect on system performance when the I/O task is incorporated in the parallel pipeline model. There are two alternatives for I/O implementation: embedding I/O in the pipeline or having a separate I/O task. From these two I/O implementations, we discovered that the latency may be improved when the structure of the pipeline is reorganized by merging multiple tasks into a single task. All the performance results shown in this paper demonstrated the scalability of parallel I/O implementation on the parallel pipeline STAP system.
AB - This paper presents experimental results for a parallel pipeline STAP system with I/O task implementation using the parallel file systems on the Intel Paragon and the IBM SP. In our previous work, a parallel pipeline model was designed for radar signal processing applications on parallel computers. Based on this model, we implemented a real STAP application which demonstrated the performance scalability of this model in terms of throughput and latency. In this paper, we study the effect on system performance when the I/O task is incorporated in the parallel pipeline model. There are two alternatives for I/O implementation: embedding I/O in the pipeline or having a separate I/O task. From these two I/O implementations, we discovered that the latency may be improved when the structure of the pipeline is reorganized by merging multiple tasks into a single task. All the performance results shown in this paper demonstrated the scalability of parallel I/O implementation on the parallel pipeline STAP system.
UR - http://www.scopus.com/inward/record.url?scp=0033876714&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0033876714&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:0033876714
SN - 1063-7133
SP - 655
EP - 662
JO - Proceedings of the International Parallel Processing Symposium, IPPS
JF - Proceedings of the International Parallel Processing Symposium, IPPS
ER -