OpenACC vs the Native Programming on Sunway TaihuLight: A Case Study with GTC-P

Cai, Linjin; Wang, Yichao; Tang, W. M.; Wang, Bei; Ethier, S.; Zhao, Lei; Lin, James

doi:10.1109/cluster.2018.00021

Cited by 9 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But the problem of threads' write conflict on sunway CPEs must be solved before involving this trick. When we assign computation tasks of one MPI processor to 64 CPE threads (In sunway native programming, one CPE can launch a light-weight working thread using Athread library [33]. ), spatial decomposition of simulation domain is achieved.…”

Section: Tasks Assignment On Cpesmentioning

confidence: 99%

MISA-MD: MD Simulation of Hundred-Billion-Metal-Atom Cascade Collision on Sunway Taihulight

2020

View full text Add to dashboard Cite

Radiation damage to the steel material of reactor pressure vessels is a major threat to the nuclear reactor safety. It is caused by the metal atom cascade collision, initialized when the atoms are struck by a high-energy neutron. The paper presents MISA-MD, a new implementation of molecular dynamics, to simulate such cascade collision with EAM potential. MISA-MD realizes (1) a hash-based data structure to efficiently store an atom and find its neighbors, and (2) several acceleration and optimization strategies based on SW26010 processor of Sunway Taihulight supercomputer, including an efficient potential table storage and interpolation method, a coloring method to avoid write conflicts, and double-buffer and data reuse strategies. The experimental results demonstrated that MISA-MD has good accuracy and scalability, and obtains a parallel efficiency of over 79% in an 655-billion-atom system. Compared with a state-of-the-art MD program LAMMPS, MISA-MD requires less memory usage and achieves better computational performance.

show abstract

Section: Tasks Assignment On Cpesmentioning

confidence: 99%

MISA-MD: MD Simulation of Hundred-Billion-Metal-Atom Cascade Collision on Sunway Taihulight

2020

View full text Add to dashboard Cite

show abstract

“…Currently, to port applications to these systems and achieve good performance requires quite a lot of efforts. One reason is that "automatic" parallelization through, for example, OpenACC results in rather poor performances in the case of TaihuLight (Cai et al, 2018), and currently only a subset of OpenCL is available on PEZY-SC2. In the case of PEZY-SC2, right now the host CPU on chip is disabled and thus the current system is an accelerator system with a Xeon-D CPU.…”

Section: Introductionmentioning

confidence: 99%

Implementation and performance of Barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures

Iwasawa

Namekata

Sakamoto³

et al. 2020

The International Journal of High Performance Computing Applica

Self Cite

View full text Add to dashboard Cite

In this paper, we report the implementation and measured performance of our extreme-scale whole planetary ring simulation code on Sunway TaihuLight and two PEZY-SC2 systems: Shoubu System B and Gyoukou. The numerical algorithm is the parallel Barnes-Hut tree algorithm, which has been used in many large-scale astrophysical particle-based simulations. Our implementation is based on our FDPS framework. However, the extremely large numbers of cores of the systems used (10 M on TaihuLight and 16 M on Gyoukou) and their relatively poor memory and network bandwidth pose new challenges. We describe the new algorithms introduced to achieve high efficiency on machines with low memory bandwidth. The measured performance is 47.9, 10.6 PF, and 1.01PF on TaihuLight, Gyoukou and Shoubu System B (efficiency 40%, 23.5% and 35.5%). The current code is developed for the simulation of planetary rings, but most of the new algorithms are useful for other simulations, and are now available in the FDPS framework.

show abstract

MD simulation of hundred-billion-metal-atom cascade collision on Sunway Taihulight

Chu

Zhao

et al. 2021

Computer Physics Communications

View full text Add to dashboard Cite

OpenACC vs the Native Programming on Sunway TaihuLight: A Case Study with GTC-P

Cited by 9 publications

References 12 publications

MISA-MD: MD Simulation of Hundred-Billion-Metal-Atom Cascade Collision on Sunway Taihulight

MISA-MD: MD Simulation of Hundred-Billion-Metal-Atom Cascade Collision on Sunway Taihulight

Implementation and performance of Barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures

MD simulation of hundred-billion-metal-atom cascade collision on Sunway Taihulight

Contact Info

Product

Resources

About