Journal
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
Volume 33, Issue 8, Pages 1888-1901Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TPDS.2021.3127138
Keywords
Optimization; Bandwidth; Supercomputers; Electric potential; Boundary conditions; Electrostatics; Silicon; Poisson solver; architecture-specific optimizations; many-core processor
Funding
- National Natural Science Foundation of China [62090024, 61872043, 61802368, 22003073]
- State Key Laboratory of Computer Architecture Foundation [CARCH 4205, CARCH 4411]
Ask authors/readers for more resources
This article proposes a highly-optimized and scalable Poisson solver, MMEwald, for the calculation of electrostatic potential, and tests its efficiency on a new generation supercomputer.
The Poisson solver for the calculation of the electrostatic potential is an essential primitive in quantum mechanics calculations. In this article, we adopt the Ewald method and propose a highly-optimized and scalable framework for Poisson solver, MMEwald, on the new generation Sunway supercomputer, capable of utilizing the collection of 390-core accelerators it uses. The MMEwald is based on a grid adapted cut-plane approach to partition the points into batches and distribute the batch to the processors. Furthermore, we propose a set of architecture-specific optimizations to efficiently utilize the memory bandwidth and computation capacity of the supercomputer. Experimental results demonstrate the efficiency of the MMEwald in providing strong and weak scaling performance.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available
Share Paper
