TY - GEN
T1 - Facilitating co-design for extreme-scale systems through lightweight simulation
AU - Engelmann, Christian
AU - Lauer, Frank
PY - 2010
Y1 - 2010
N2 - This work focuses on tools for investigating algorithm performance at extreme scale with millions of concurrent threads and for evaluating the impact of future architecture choices to facilitate the co-design of high-performance computing (HPC) architectures and applications. The approach focuses on lightweight simulation of extreme-scale HPC systems with the needed amount of accuracy. The prototype presented in this paper is able to provide this capability using a parallel discrete event simulation (PDES), such that a Message Passing Interface (MPI) application can be executed at extreme scale, and its performance properties can be evaluated. The results of an initial prototype are encouraging as a simple hello world MPI program could be scaled up to 1,048,576 virtual MPI processes on a four-node cluster, and the performance properties of two MPI programs could be evaluated at up to 16,384 virtual MPI processes on the same system.
AB - This work focuses on tools for investigating algorithm performance at extreme scale with millions of concurrent threads and for evaluating the impact of future architecture choices to facilitate the co-design of high-performance computing (HPC) architectures and applications. The approach focuses on lightweight simulation of extreme-scale HPC systems with the needed amount of accuracy. The prototype presented in this paper is able to provide this capability using a parallel discrete event simulation (PDES), such that a Message Passing Interface (MPI) application can be executed at extreme scale, and its performance properties can be evaluated. The results of an initial prototype are encouraging as a simple hello world MPI program could be scaled up to 1,048,576 virtual MPI processes on a four-node cluster, and the performance properties of two MPI programs could be evaluated at up to 16,384 virtual MPI processes on the same system.
KW - Hardware/software co-design
KW - High-performance computing
KW - Message Passing Interface
KW - Parallel discrete event simulation
KW - Performance evaluation
UR - http://www.scopus.com/inward/record.url?scp=78649838287&partnerID=8YFLogxK
U2 - 10.1109/CLUSTERWKSP.2010.5613113
DO - 10.1109/CLUSTERWKSP.2010.5613113
M3 - Conference contribution
AN - SCOPUS:78649838287
SN - 9781424483969
T3 - 2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010
BT - 2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010
T2 - 2010 IEEE International Conference on Cluster Computing Workshops and Posters, Cluster Workshops 2010
Y2 - 20 September 2010 through 24 September 2010
ER -