Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Frontera: The Next Generation NSF HPC Resource, and Why HPC Still isn’t the Cloud

Dan Stanzione from TACC gave this talk at the MVAPICH User Group. “In this talk, I will describe the main components of the award: the Phase 1 system, “Frontera”, the plans for facility operations and scientific support for the next five years, and the plans to design a Phase 2 system in the mid-2020s to be the NSF Leadership system for the latter half of the decade, with capabilities 10x beyond Frontera. The talk will also discuss the key role MVAPICH and Infiniband play in the project, and why the workload for HPC still can’t fit effectively on the cloud without advanced networking support.”

NetApp EF600 Storage Array Speeds HPC and Analytics

Today NetApp announced the NetApp EF600 storage array. The EF600 is an end-to-end NVMe midrange array that accelerates access to data and empowers companies to rapidly develop new insights for performance-sensitive workloads. “The storage industry is currently transitioning from the SAS to the NVMe protocol, which significantly increases the speed of access to data,” said Tim Stammers, senior analyst, 451 Research. “But conventional storage systems do not fully exploit NVMe performance, because of latencies imposed by their main controllers. NetApp’s E-Series systems were designed to address this architectural issue and are already used widely in performance-sensitive applications. The EF600 sets a new level of performance for the E-Series by introducing end-to-end support for NVMe, and should be considered by IT organizations looking for high-speed storage to serve analytics and other data-intensive applications.”

ANSYS Cloud HPC Increases Simulation throughput for Hundreds of Organizations

Engineers are unlocking increased compute capacity to achieve advancements in 5G, autonomous systems, electric vehicles, and other global megatrends thanks to ANSYS Cloud HPC, powered by Microsoft Azure. Available from directly within ANSYS engineering simulation software, ANSYS Cloud is helping organizations rapidly run high-fidelity simulations, shortening development cycles and increasing time to market. “”Organizations benefit from Azure’s vast number of on-demand compute cores to run large parallel and tightly coupled simulations, enabled by infrastructure specifically designed for HPC featuring RDMA InfiniBand. With Azure, ANSYS customers get performance without sacrificing security as sensitive proprietary data remains highly secure and protected by technologies that prohibit unauthorized access.”

Intel Talks at Hot Chips gear up for “AI Everywhere”

Today at Hot Chips 2019, Intel revealed new details of upcoming high-performance AI accelerators: Intel Nervana neural network processors, with the NNP-T for training and the NNP-I for inference. Intel engineers also presented technical details on hybrid chip packaging technology, Intel Optane DC persistent memory and chiplet technology for optical I/O. InsideHPC has got all the details, here, all in one place.

Singularity Enterprise to Accelerate Adoption of Containers with Cryptographically Verifiable Trust

Today Sylabs announced that Singularity Enterprise is now generally available as a self-hosted offering, making it faster and easier for businesses to adopt containerization across their production environments. In private beta since April of this year, Singularity Enterprise has grabbed the attention of DevOps and IT infrastructure teams at leading businesses and government organizations for expediting containerized workloads from development into production.

OpenHPC: Community Building Blocks for HPC Systems

Karl Schultz from the Oden Institute gave this talk at HPCKP’19. “Formed initially in November 2015 and formalized as a Linux Foundation project in June 2016, OpenHPC has been adding new software components and now supports multiple OSes and architectures. This presentation will present an overview of the project, currently available software, and highlight more recent changes along with general project updates and future plans.”

Cerebras Systems Unveils the Industry’s First Trillion Transistor Chip for AI

Today AI startup Cerebras Systems unveiled the largest chip ever built. “The Cerebras Wafer-Scale Engine (WSE) is the largest chip ever built. 56x larger than any other chip, the WSE delivers more compute, more memory, and more communication bandwidth. This enables AI research at previously-impossible speeds and scale.”

UPMEM Puts CPUs Inside Memory to Allow Apps to Run 20 Times Faster

Today UPMEM announced a Processing-in-Memory (PIM) acceleration solution that allows big data and AI applications to run 20 times faster and with 10 times less energy. Instead of moving massive amounts of data to CPUs, the silicon-based technology from UPMEM puts CPUs right in the middle of data, saving time and improving efficiency. By allowing compute to take place directly in the memory chips where data already resides, data-intensive applications can be substantially accelerated.

Video: Unboxing the NVIDIA DGX-1 Supercomputer at Georgia Tech

In this video, Oded Green from NVIDIA unboxes a DGX-1 supercomputer at the College of Computing Data Center at Georgia Tech. “And while the DGX-1 arriving at Georgia Tech for student-use is exciting enough, there is cause for more celebration as a DGX Station also arrived this year as part of a new NVIDIA Artificial Intelligence Lab (NVAIL) grant awarded to CSE. The NVAIL grant focuses on developing multi-GPU graph analytics and the DGX station is constructed specifically for data science and artificial intelligence development.”

Simulating Shock Turbulence Interactions on Stampede II

In this special guest feature, Jorge Salazar from TACC writes that Researchers are using XSEDE supercomputers to better understand shock turbulence interactions. “We proposed that, instead of treating the shock as a discontinuity, one needs to account for its finite thickness as in real life which may be involved as a governing parameter in, for example, amplification factors,” Donzis said.