Novel Liquid Cooling Technologies for HPC

In this special guest feature, Robert Roe from Scientific Computing World writes that increasingly power-hungry and high-density processors are driving the growth of liquid and immersion cooling technology. “We know that CPUs and GPUs are going to get denser and we have developed technologies that are available today which support a 500-watt chip the size of a V100 and we are working on the development of boiling enhancements that would allow us to go beyond that.”

Podcast: ColdQuanta Serves Up Some Bose-Einstein Condensate

“ColdQuanta is headed by an old pal of ours Bo Ewald and has just come out of stealth mode into the glaring spotlight of RadioFreeHPC. When you freeze a gas of Bosons at low density to near zero you start to get macroscopic access to microscopic quantum mechanical effects, which is a pretty big deal. With the quantum mechanics start, you can control it, change it, and get computations out of it. The secret sauce for ColdQuanta is served cold, all the way down into the micro-kelvins and kept very locally, which makes it easier to get your condensate.”

AMD to Power Cray Shasta Supercomputer at Navy DSRC

The Department of Defense High Performance Computing Modernization Program (HPCMP) is upgrading its supercomputing capabilities with a new Cray Shasta system powered by AMD EPYC processors. The system, the HPCMP’s first with more than 10 PetaFLOPS of peak computational performance, will be installed at the Navy’s DSRC’s facility at Stennis Space Center, Mississippi and will serve users from all of the services and agencies of the Department.

UK to establish Northern Intensive Computing Environment (NICE)

The N8 Centre of Excellence in Computationally Intensive Research, N8 CIR, has been awarded £3.1m from the Engineering and Physical Sciences Resources Council to establish a new Tier 2 computing facility in the north of England. This investment will be matched by £5.3m from the eight universities in the N8 Research Partnership which will fund operational costs and dedicated research software engineering support. “The new facility, known as the Northern Intensive Computing Environment or NICE, will be housed at Durham University and co-located with the existing STFC DiRAC Memory Intensive National Supercomputing Facility. NICE will be based on the same technology that is used in current world-leading supercomputers and will extend the capability of accelerated computing. The technology has been chosen to combine experimental, modelling and machine learning approaches and to bring these specialist communities together to address new research challenges.”

OSS PCI Express 4.0 Expansion System does AI on the Fly with Eight GPUs

Today One Stop Systems (OSS) announced the availability of a new OSS PCIe 4.0 value expansion system incorporating up to eight of the latest NVIDIA V100S Tensor Core GPU. As the newest member of the company’s AI on the Fly product portfolio, the system delivers data center capabilities to HPC and AI edge deployments in the field or for mobile applications. “The 4U value expansion system adds massive compute capability to any Gen 3 or Gen 4 server via two OSS PCIe x16 Gen 4 links. The links can support an unprecedented 512 Gpbs of aggregated bandwidth to the GPU complex.”

Dell Technologies Introduces New Solutions to Advance HPC and AI Innovation

At SC19 this week, Dell Technologies is introducing several new solutions, reference architectures and portfolio advancements all designed to simplify and accelerate customers’ HPC and AI efforts. “There’s a lot of value in the data that organizations collect, and HPC and AI are helping organizations get the most out of this data,” said Thierry Pellegrino, vice president of HPC at Dell Technologies. “We’re committed to building solutions that simplify the use and deployment of these technologies for organizations of all sizes and at all stages of deployment.”

GMS Launches Ruggedized TITAN AI-Equipped Rackmount Servers

Today General Micro Systems (GMS) launched TITAN, the industry’s first sealed, fanless, conduction-cooled rackmount servers with artificial intelligence (AI) and mil-circular (38999) connectors for superior ruggedness in the most demanding defense and aerospace applications. The American-designed, sourced, and manufactured TITAN, a fully configurable server, also uses up to four of Intel’s latest 2nd gen Scalable […]

Dell Powers Alzheimer’s Disease Breakthrough at The University of Queensland

Today Dell Technologies announced one of the first computational projects for The University of Queensland’s Dell HPC system may enable a non-invasive disease-modifying strategy for Alzheimer’s Disease. “With this supercomputer, the University of Queensland can harness machine learning to drive innovation, across a broad range of use cases, that previously wasn’t possible. We’re honored to play our part in the resulting discoveries that can change lives for the better.”

The ABCI Supercomputer: World’s First Open AI Computing Infrastructure

Shinichiro Takizawa from AIST gave this talk at the MVAPICH User Group. “ABCI is the world’s first large-scale Open AI Computing Infrastructure, constructed and operated by AIST, Japan. It delivers 19.9 petaflops of HPL performance and world’ fastest training time of 1.17 minutes in ResNet-50 training on ImageNet datasets as of July 2019. In this talk, we focus on ABCI’s network architecture and communication libraries available on ABCI and shows their performance and recent research achievements.”

Summit Supercomputer Triples Performance Record on new HPL-AI Benchmark

“Using HPL-AI, a new approach to benchmarking AI supercomputers, ORNL’s Summit system has achieved unprecedented performance levels of 445 petaflops or nearly half an exaflops. That compares with the system’s official performance of 148 petaflops announced in the new TOP500 list of the world’s fastest supercomputers.”