HPE Weather HPC System Stood up at Meteorological Service Singapore – High-Performance Computing News Analysis

HPE continued its strong showing in the weather segment of the supercomputing industry by announcing that it has built the HPC Singapore Meteorological Service (MSS) to advance tropical climate forecasting and research for Singapore and the broader Southeast Asia region.

The HPC system replaces the existing MSS system and provides nearly twice the performance and advanced capabilities across compute, storage, software and networking, according to HPE. MSS has a peak performance of 401.4 teraflops, using the following set of new technologies that include computing, networking, storage, and software:

• 196 3rd generation AMD EPYC processors to target weather and climate data modeling and simulation
• HPE Slingshot, the world’s only high-performance Ethernet fabric designed to power data and AI solutions, delivers an additional boost in speed while enabling congestion control for data-intensive workloads and greater AI
• HPE Cray ClusterStor E1000 parallel storage system and HPE Data Management Framework to meet the storage demands of data growth and complexity from increasing modeling, simulation and AI workloads
• HPE Cray operating system and HPE Cray programming environment to allow users to access an integrated software suite to improve modeling, simulation, and AI workloads

Also Read :  Microsoft is losing the computing war to Apple — and the Surface Pro 9 is proof

In addition, as with the previous MSS Cray-based supercomputer, the new system will continue to use Altair PBS Professional, one of the industry’s leading job scheduling and workload management solutions to scale modeling, simulation, and various AI workloads. The supercomputer is hosted in a CCRS data center.

The company said the enhanced supercomputing power will help increase forecasting skills through improved numerical model configurations and assimilation of advanced data for terrestrial and space-based weather observations into the MSS Numerical Weather Forecasting System called “SINGV”. Developed by MSS’ Center for
The Center for Climate Research Singapore (CCRS) through collaboration with the UK Met Office and partners, is configured specifically for weather forecasts and climate applications in Singapore and the nearby region.

In addition, the supercomputer will enable the use of modern prediction post-processing algorithms, using machine learning techniques, to improve the quality of predictions. The computational power will also allow for further development of the following high-resolution models to provide better weather and climate products:

Also Read :  Microsoft warns of cloud computing slowdown

• Sub-kilometre scale urban modeling (uSINGV), which is being developed to more adequately represent the urban environment in weather and climate applications
• Coupled Ocean-Atmosphere-Earth Wave Modeling System (cSINGV) to capture and improve understanding of the powerful feedbacks between the atmosphere, land and oceans, which influence weather and climate in the Southeast Asian region

“Singapore continues to advance its national initiatives with supercomputing projects that make a significant contribution to science, accelerating innovation and improving a range of areas for the benefit of its citizens,” said Trish Damkruger, Chief Product Officer and Vice President, HPC, Artificial Intelligence & Labs at HPE.

“We are honored to play a role in the country’s digital agenda and to be selected by the Singapore Meteorological Service to build a robust system with cutting-edge and comprehensive supercomputing technologies that will feed into Singapore’s weather intelligence and accelerate forecasts of severe weather events.”

MSS, part of Singapore’s National Environment Agency (NEA), is dedicated to providing the nation with timely weather forecasts, insight into Singapore’s tropical climate, and a better understanding of event patterns in monsoons, heat waves and air pollution. To advance MSS’s mission, the new system, which will be built using the HPE Cray supercomputer to deliver robust and comprehensive performance and capabilities, will improve the modeling and simulation of complex weather data to provide more accurate, real-time weather forecasts and warnings to citizens.

Also Read :  Ukraine minister tells Iranian counterpart: Stop sending weapons | Russia-Ukraine war News

“At CCRS, our scientists and software engineers are committed to developing advanced modeling systems and examining complex data to deliver timely weather forecasts for our nation, which often encounters many weather processes daily due to the island’s unique geological location,” said Professor Dale Parker, Director (CCRS). “After collaborating with Hewlett Packard Enterprise to design the new supercomputer, our research center will gain a faster system with the next generation.
Techniques for developing modeling and simulation tools, while offering new possibilities for testing and applying future types of applications to deeper research methodologies. “



Source

Leave a Reply

Your email address will not be published. Required fields are marked *

Related Articles

Back to top button