In this bi-monthly feature, HPCwire highlights recently published research in the high-performance computing community and related domains. From parallel programming to exascale to quantum computing, the details are here.

Use AI to increase HPC energy efficiency

When supercomputers jump in computing capability, the energy needed to power them surges together. These researchers – a team from Nigeria and Korea – present a database for periodically consuming power component system components to function as input data for energy efficiency optimization. Furthermore, they discussed the application of AI to assess this database and automatically adjust components to maximize energy efficiency.

Author: Hilary Kelechi, Mohammed H. Alsharif, Okpe Jonah Bameyi, Paul Joan Ezra, Iorshase Kator Joseph, Aaron-Anthony Atayero, Zong Woo Geem and Junhee Hong.

Estimating volcanic emissions using supercomputers

When volcanoes erupt, they emit large amounts of sulfur dioxide into the atmosphere – sometimes enough to change the local or global climate for weeks or months. A research team from Guangzhou, Beijing and Jülich conducted a high-performance case study of this volcanic emission, using a particle dispersion model that runs on the Tianhe-2 supercomputer to estimate volcanic emissions.

Author: Mingzhao Liu, Yaopeng Huang, Lars Hoffman, Chunyan Huang, Pin Chen and Yi Heng.

Cloud HPC for docking complete proteins

As cloud computing continues its upward trajectory, its application in bioinformatics is increasing. In this paper, the Japanese research team discusses MEGADOCK port, a protein-protein interaction prediction model, for Microsoft Azure. The researchers found strong scaling values ​​for CPU and GPU and quoted high portability.

Author: Masahito Ohue, Kento Aoyama and Yutaka Akiyama.

Use the HPC environment for mobile cloud games

Even as cellular games become increasingly popular, the types of games that can be played on cellular systems remain limited to hardware. Cloud gaming – remote rendering of games and streaming in real-time to client devices – emerged as a solution to this bottleneck. This paper, written by a research team from Indonesia, discusses the use of the HPC cloud environment to manage and distribute the workload of this game.

Author: Dedy Prasetya Kristiadi, Ferry Sudarto, Evan Fabian Rahardja, Naufal Rayfi Hafizh, Christopher Samuel and Harco Leslie Hendric Spits Warnars.

Characterize and identify HPC applications in leadership computing facilities

Understanding applications that run on super computers is very important for planning design, development, and operation. In this paper, the team from Argonne National Laboratory, Oak Ridge National Laboratory and Northern Illinois University describe the use of correlational analysis of log subsystems to show patterns in applications that run on supercomputer leadership.

Author: Liu Zhengchun, Ryan Lewis, Rajkumar Kettimuthu, Kevin Harms, Philip Carns, Nageswara Rao, Ian Foster and Michael E. Papka.

Model climate with cloud computing

Climate modeling is usually done on supercomputers – but with a boom in cloud computing, new possibilities emerge. These authors (from Australia, Spain, and the United Kingdom) discuss the use of cloud computing for climate science by evaluating two different climate models that are adapted to run in the public cloud computing environment by Amazon, Google and Microsoft.

Author: Diego Montes, Juan A. Añel, David CH Wallom, Peter Uhe, Pablo V. Caderno and Tomás F. Pena.

Advanced HPC cluster with production CFD code

With the increasing complexity and heterogeneity of HPC clusters, effective programming for this platform is becoming a more difficult task. In this paper, four researchers from the Barcelona Supercomputing Center made a micro-comparison of three HPC clusters with diverse architectures that were on the Top500 list of the most powerful public ranking supercomputers in the world using the computational fluid dynamics (CFD) code of production.

Author: Fabio Banchelli, Marta Garcia-Gasulla, Guillaume Houzeaux and Filippo Mantovani.

Do you know about the research that should be included next month? If so, send us an email at [email protected]. We look forward to hearing from you.

image source

to request modification Contact us at Here or [email protected]