Summit is the next leap in leadership-class computing systems for open science. The 200 petaflop IBM AC922 system links more than 27,000 NVIDIA Volta GPUs with more than 9,000 IBM Power9 CPUs to provide unprecedented opportunities for the integration of artificial intelligence (AI) and scientific discovery. With Summit, we can address, with greater complexity and fidelity, questions concerning who we are, our place on earth, and in our universe.
In May 2022, the Oak Ridge Leadership Computing Facility debuted the world’s first exascale computer, Frontier, based on HPE Cray’s EX architecture and Slingshot interconnect. The new system is capable of over a quintillion calculations per second – five times faster than today’s fastest supercomputers – allowing users to model the entire lifespan of a nuclear reactor, uncover disease genetics, and continue to push the boundaries of data analytics, simulation, and scientific innovation.
Andes is a (704)-node commodity-type Linux cluster that serves as a conduit for large-scale scientific discovery via pre-and post-processing of simulation data generated on Summit. The system is connected to the OLCF’s high-performance GPFS filesystem, Alpine.
Wombat is a single rack cluster from HPE available to support computer science research projects that explore the ARM architecture. Research topics include functionality testing of research software and prototypes, power-efficiency evaluations, and efforts to improve system software, runtime support, and programming environment.
Quantum Computing User Program
The Quantum Computing User Program (QCUP) provides access to state-of-the-art quantum computing resources for purposes of discovery and innovation in scientific computing applications. Access is managed through the Oak Ridge Leadership Computing Facility.
Storage & Visualization Resources
Alpine is an IBM Spectrum Scale parallel file system for the OLCF’s HPC computational resources, include Summit, Andes, and the data transfer nodes. Despite having tens of thousands of clients, Alpine can move data at a rate of 2.5 TB per second.
EVEREST, the Exploratory Visualization Environment for Research in Science and Technology, provides analysis and visualization of simulation data generated on the OLCF supercomputers. Consisting of three computing systems and two display walls, EVEREST is an essential tool for computational simulation.
The High-Performance Storage System (HPSS) is the archival mass-storage resource at ORNL used to archive petabytes of data each month. The data storage capabilities of HPSS support multiple program partnerships in NCCS and ORNL.
ORION and I/O Subsystem
An I/O subsystem from HPE is being brought online in 2022 to support Frontier and the OLCF. The I/O subsystem features an in-system storage layer and ORION, a Lustre-based enhanced center-wide file system. The in-system storage layer will employ compute-node local storage devices connected via PCIe Gen4 links to provide peak read speeds of more than 75 terabytes per second (TBps), peak write speeds of more than 35 TBps, and more than 15 billion random-read input/output operations per second (IOPS). The Orion center-wide file system will provide around 700 PB of storage capacity and 5 TB/s peak write speeds.