TY - GEN
T1 - Decoupled I/O for Data-Intensive High Performance Computing
AU - Chen, Chao
AU - Chen, Yong
AU - Feng, Kun
AU - Yin, Yanlong
AU - Eslami, Hassan
AU - Thakur, Rajeev
AU - Sun, Xian He
AU - Gropp, William D.
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2015/5/7
Y1 - 2015/5/7
N2 - The I/O bottleneck issue has been acknowledged as one of main performance issues of high performance computing (HPC) systems for data-intensive scientific applications, and has attracted intensive studies in recent years. With the enlarging gap between the computing bandwidth and I/O bandwidth in projected next-generation HPC systems, this issue will become even worse. In this paper, we present a novel decoupledI/O to address the fundamental I/O bottleneck issue. The decoupled I/O is a software stack including MPI extensions, compiler improvements, and runtime library support, based one decoupled HPC system architecture. It allows users to treat the computing of data-intensive operations and the traditionalI/O operation as an ensemble and offload them into dedicateddata nodes, which are near to the data source, to reduce the overhead of data movement and improve the I/O bandwidth usage. The decoupled I/O is user-friendly and requires littlechanges in application codes. Experiments were conducted to evaluate the performance of the decoupled I/O, and the results show that it outperforms existing solutions (such as active storage I/O) and provides an attractive I/O solution for data-intensive high performance computing.
AB - The I/O bottleneck issue has been acknowledged as one of main performance issues of high performance computing (HPC) systems for data-intensive scientific applications, and has attracted intensive studies in recent years. With the enlarging gap between the computing bandwidth and I/O bandwidth in projected next-generation HPC systems, this issue will become even worse. In this paper, we present a novel decoupledI/O to address the fundamental I/O bottleneck issue. The decoupled I/O is a software stack including MPI extensions, compiler improvements, and runtime library support, based one decoupled HPC system architecture. It allows users to treat the computing of data-intensive operations and the traditionalI/O operation as an ensemble and offload them into dedicateddata nodes, which are near to the data source, to reduce the overhead of data movement and improve the I/O bandwidth usage. The decoupled I/O is user-friendly and requires littlechanges in application codes. Experiments were conducted to evaluate the performance of the decoupled I/O, and the results show that it outperforms existing solutions (such as active storage I/O) and provides an attractive I/O solution for data-intensive high performance computing.
KW - Decoupled I/O
KW - data-intensive computing
KW - high performance computing
KW - parallel I/O
KW - storage
UR - http://www.scopus.com/inward/record.url?scp=84946576832&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84946576832&partnerID=8YFLogxK
U2 - 10.1109/ICPPW.2014.48
DO - 10.1109/ICPPW.2014.48
M3 - Conference contribution
AN - SCOPUS:84946576832
T3 - Proceedings of the International Conference on Parallel Processing Workshops
SP - 312
EP - 320
BT - Proceedings - 43rd International Conference on Parallel Processing Workshops, ICPPW 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 43rd International Conference on Parallel Processing Workshops, ICPPW 2014
Y2 - 9 September 2014 through 12 September 2014
ER -