Recent scientific computing increasingly relies on multi-physics simulations to enhance predictive capabilities. Inevitably, multi-physics simulation demands high performance computing (HPC) through advanced hardware and software accelerating due to its intensive computing workload and runtime communication needs. Thus, its research has become a hotspot across different disciplines. However, it is observed that most benchmarks used in the evaluation of corresponding work are through commercial or in-house codes. Then, the lack of accessible open-source multi-physics benchmark suites has presented a challenge in uniformly evaluating simulation performance across related disciplines.
Some benchmarks have been selected to create such benchmarks suite at Clarkson University, which are from key applications of multi-physics simulation and highly cited publications. However, they are not coupled by the multi-physics simulation framework yet. In addition, none of GPU acceleration-aware benchmarks has been selected and evaluated, but GPU is becoming increasingly important in multi-physics simulation. This summer work will enhance the benchmark suite by coupling these selected benchmarks and add GPU acceleration-aware ones. Upon finishing this work, a comprehensive benchmarks suite for Multiphysics simulation will be shared to the research community. Moreover, it is expected that these benchmarks can run on. cycle-accurate simulators (e.g., gem5, GPGPUSim).
1. C/C++ Programming Skills in Linux;
2. Basic knowledge of compilers and simulators;
3. Prefer Computer Science, Software Engineering or Computer Engineering students.