Hybrid Supercomputer Desmos with Torus Angara Interconnect: Efficiency Analysis and Optimization

Kondratyuk, Nikolay; Smirnov, Grigory S.; Dlinnova, Ekaterina; Biryukov, S. V.; Stegaĭlov, V. V.

doi:10.1007/978-3-319-99673-8_6

Cited by 4 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…All server PEs considered work with the turbo boost option enabled. The study of the influence of the dynamic voltage and frequency scaling (DVFS) is beyond the scope of this paper (in our previous studies we did not find any positive effect of DVFS or reduced CPU frequencies, however other studies claim certain benefits of DVFS …”

Section: Hardware and Softwarementioning

confidence: 86%

VASP hits the memory wall: Processors efficiency comparison

Stegaĭlov

Smirnov

Vecher

2019

Concurrency and Computation

Self Cite

View full text Add to dashboard Cite

Summary First‐principles calculations of electronic structure have been one of the most important classes of supercomputer applications for a long time. In this paper, we consider VASP as a de facto standard tool for density functional theory calculations widely used in materials science, condensed matter research, and other related fields. The choice of hardware for the efficient VASP calculations is not easy because of the large number of processor types available. We use the benchmark metric that is based on the balance of the peak floating point performance and the memory bandwidth. This metric gives us the possibility to compare different types of processors. We consider time‐to‐solution and energy‐to‐solution criteria and compare different Intel, AMD, and ARM 64‐bit CPUs and hybrid CPU‐GPU systems based on Nvidia Tesla P100.

show abstract

Section: Hardware and Softwarementioning

confidence: 86%