Simulation-based performance analysis and tuning for future supercomputers

Simulation;Performance Prediction;Mapping;System Noise;Collective Communication;BigSim;MPI_Alltoall;Productive, Easy-to-use, Reliable Computing System (PERCS)

Totoni, Ehsan ; Kale ; Laxmikant V.

关键词: Simulation;    Performance Prediction;    Mapping;    System Noise;    Collective Communication;    BigSim;    MPI_Alltoall;    Productive, Easy-to-use, Reliable Computing System (PERCS);   

Others  :  https://www.ideals.illinois.edu/bitstream/handle/2142/29847/Totoni_Ehsan.pdf?sequence=1&isAllowed=y

美国|英语

来源: The Illinois Digital Environment for Access to Learning and Scholarship

【 摘 要 】

Hardware and software co-design is becoming increasingly important due to complexities in supercomputing architectures. Simulating applications before there is access to the real hardware can assist machine architects in making better design decisions that can optimize application performance. At the same time, the application and run-time can be optimized and tuned beforehand. BigSim is a simulation-based performance prediction framework designed for these purposes. It can be used to perform packet-level network simulations of parallel applications using existing parallel machines. In this thesis, we demonstrate the utility of BigSim in analyzing and optimizing parallel application performance for future systems based on the PERCS network. We present simulation studies using benchmarks and real applications expected to run on future supercomputers. Future peta-scale systems will have more than 100,000 cores, and we present simulations at that scale.