High-level Abstractions for Performance, Portability and Continuity of Scientific Software on Future Computing Systems

In this report we present research on applying a domain specific high-level abstractions development strategy with the aim to “future-proof“ a key class of high performance computing (HPC) applications that simulate hydro-dynamics computations at AWE plc. We build on an existing high-level abstraction framework, OPS, that is being developed for the solution of multi-block structured meshbased applications at the University of Oxford. The target application, is an unclassified benchmark application, CloverLeaf, that consists of algorithms of interest from the hydro-dynamics workload at AWE plc. OPS uses an “active library” approach where a single application code written using the OPS API can be transformed into different parallel implementations which can then be linked against the appropriate parallel library enabling execution on different back-end hardware platforms. At the same time the generated code and the platform specific back-end libraries are highly optimized utilizing the best low-level features of a target architecture to make an OPS application achieve near-optimal performance including high computational efficiency and minimized memory traffic. We present (1) the conversion of CloverLeaf to utilize OPS, (2) the utilization of OPS’s code generation tools for obtaining several parallel implementations of the application and finally (3) its performance compared to the original application on a range of parallel systems including multi-core CPUs, NVIDIA GPUs and a Cray XC30 distributed memory system. Our results show that the development of parallel HPC applications through the careful factorization of a parallel program’s functionality and implementation, through a high-level framework such as OPS is no more time consuming nor difficult than writing a one-off parallel program targeting only a single parallel implementation. However the OPS strategy pays off with a highly maintainable single application source without compromising performance portability on the parallel systems on which it will be executed. It also lays the groundwork for providing support for execution on future parallel systems. We believe such an approach will be an essential paradigm shift for utilizing the ever-increasing complexity of novel hardware/software technologies.