Intel Builds the World’s Largest Neuromorphic System
Intel has built the world's largest neuromorphic system code-named Hala Point.
Hewlett Packard Enterprise was awarded a $35+ million contract to build a new supercomputer using its end-to-end high performance computing technologies for the National Center for Atmospheric Research (NCAR). It is a U.S. federally funded R&D center focused on advancing knowledge of geosciences, including meteorology, climate change, and solar activity.
The new system will be installed later this year at the National Center of Atmospheric Research - Wyoming Supercomputing Center (NWSC) in Cheyenne, Wyoming and put into use in 2022. It is a significant upgrade to NCAR’s existing system, Cheyenne, running on HPE’s HPC solutions, which include compute, storage, networking and software and delivering nearly 3.5X faster speed. Latest system design will help NCAR process compute and image-intensive data to create digital models of various occurrences, from wildfires and solar storms to hurricanes and droughts, with greater accuracy.
"This new system is a major step forward in supercomputing power, providing the scientific community with the most cutting-edge technology to better understand the Earth system,“ said Anke Kamrath, director of Computational and Information Systems Laboratory at the National Center of Atmospheric Research. “The resulting research will lead to new insights into potential threats ranging from severe weather and solar storms to climate change, helping to advance the knowledge needed for improved predictions that will strengthen society’s resilience to potential disasters.“
The system will be powered by HPE Cray EX supercomputer, which is a purposefully engineered HPC architecture to enable large, next-generation supercomputing, including exascale systems, and features the latest compute and dedicated AI performance. NCAR will use the system to tackle research in a wide range of earth’s phenomenal events, including determining how to make some predictions up to a decade in advance. It will have a theoretical peak performance of 19.87 petaflops.
Više vijesti iz kategorije
Meta Announced Its New AI Chip
Meta Platforms unveiled the second generation of its Meta Training and Inference Accelerator (MTIA) AI chip.
Intel Unveils New AI Chip
Intel announced its latest chip to challenge Nvidia’s dominant market position for semiconductors that train and deploy large AI models.
