IgorZh - stock.adobe.com
The Meteorological Service Singapore (MSS) is getting a new Cray supercomputer to improve weather forecasting and tropical climate research in the city-state and the broader Southeast Asia region.
The new supercomputer, to be supplied by Hewlett Packard Enterprise (HPE), will replace MSS’ current Cray system and is expected to deliver almost twice as much performance and advanced capabilities across compute, storage, software and networking.
With peak performance 401.4 teraflops, the supercomputer will enable MSS to handle increasingly complex climate modelling tasks due to changes in seasonal patterns. It will also increase its forecast skills by assimilating data from its SINGV weather prediction system that was developed together with the UK Met Office and other partners.
By running modern forecast postprocessing algorithms and machine learning techniques on its new supercomputer, MSS expects to improve the quality of its forecasts and develop high-resolution models to deliver better weather and climate products.
These products include an urban modelling system called uSINGV, which is being developed to represent the urban environment more appropriately in weather and climate applications, as well as cSINGV, a modelling system to better understand the interactions between the atmosphere, land and ocean that can have a significant impact on the weather and climate in Southeast Asia.
The new supercomputer, to be hosted at the datacentre of the MSS’ Centre for Climate Research Singapore (CCRS), is powered by 196 third-generation AMD EPYC processors to target simulations of weather and climate, the HPE Slingshot high-performance Ethernet fabric and the Cray ClusterStor E1000 parallel storage system.
MSS, which is part of Singapore’s National Environment Agency, will also use the HPE Cray Programming Environment to optimise modelling, simulations and artificial intelligence (AI) workloads and continue with its use of the Altair PBS Professional job scheduling and workload manager.
“At CCRS, our scientists and software engineers are committed to developing advanced modelling systems and examining complex data to provide timely weather forecasts for our nation, which, due to the island’s unique geological positioning, often experiences various weather processes on a daily basis,” said Dale Barker, director of CCRS.
“After collaborating with HPE to design the new supercomputer, our research centre will gain a faster system with next-generation technologies to advance modelling and simulation tools, while introducing new capabilities to test and apply future types of applications for deeper research methodologies,” he added.
Trish Damkroger, chief product officer and senior vice-president for high performance computing, AI and labs at HPE, said: “Singapore continues to drive its national initiatives with supercomputing projects that significantly contribute to science, accelerate innovation and improve a range of areas for the greater good of its citizens.”
In March 2022, public healthcare group SingHealth said it was building a new supercomputer to support medical research in areas such as personalised cancer therapies and triaging heart disease patients. Built together with the National Supercomputing Centre, the supercomputer will also support research in other fields such as climate science and datacentre operations.
The National University Health System is also using a new petabyte-scale supercomputer to reduce the time it takes to train AI models from days to hours, enabling it to faster predict patient health trajectories and train conversational chatbots that can converse with people in a more natural way, among other uses.
Read more about high performance computing in APAC
- Singapore’s National Supercomputing Centre is fast-tracking access to its high-performance computing resources for researchers working on Covid-19-related projects.
- The Gadi supercomputer at the Australian National University will run 10 times faster than its predecessor, giving researchers access to high performance computing resources to solve the toughest research problems.
- The University of Sydney has upgraded its supercomputing infrastructure to answer big questions on cosmology and keep pace with growing research needs.
- A Huawei executive makes the case for HPC infrastructure, despite the growth of public cloud services that have democratised access to HPC and AI capabilities.