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

Video: AI for Science

Rick Stevens from Argonne gave this talk at the HPC User Forum. “Argonne has launched an “AI for Science” initiative aimed at accelerating the development and adoption of AI approaches in scientific and engineering domains with the goal to accelerate research and development breakthroughs in energy, basic science, medicine, and national security, especially where we have significant volumes of data and relatively less developed theory. AI methods allow us to discover patterns in data that can lead to experimental hypotheses and thus link data driven methods to new experiments and new understanding.”

Massively Parallel Computer Aided Design of Nano-Transistors: When Physics Lets You Down

“In this talk, the capabilities of a state-of-the-art quantum mechanical device simulator will be briefly reviewed, insisting on the developed multi-level parallelization scheme and highlighting the fact that physics can lead to wrong assumptions regarding the best-suited distribution of the workload. This problem will be addressed through a data-centric transformation of the code.”

A Simulation Booster for Nanoelectronics

Researchers from ETH Zurich have developed a method that can simulate nanoelectronics devices and their properties realistically, quickly and efficiently. This offers a ray of hope for the industry and data centre operators alike, both of which are struggling with the (over)heating that comes with increasingly small and powerful transistors – and with the high resulting electricity costs for cooling.

IBM Brings World’s Largest Fleet of Quantum Computing Systems Online

Today, IBM announced the opening of the IBM Quantum Computation Center in New York State. “To meet growing demand for access to real quantum hardware, ten quantum computing systems are now online through IBM’s Quantum Computation Center. The fleet is now composed of five 20-qubit systems, one 14-qubit system, and four 5-qubit systems. Five of the systems now have a Quantum Volume of 16 – a measure of the power of a quantum computer – demonstrating a new sustained performance milestone.”

New Liquid Cooled AMD EPYC 7H12 Processor Breaks Performance Records

Today AMD announced a new addition to the 2nd Generation AMD EPYC family, the AMD EPYC 7H12 processor. The 64 core/128 thread, 2.6Ghz base frequency, 3.3Ghz max boost frequency, 280W TDP processor is specifically built for HPC customers and workloads, using liquid cooling to deliver leadership supercomputing performance. “In an ATOS testing on their BullSequana XH2000, the new AMD EPYC 7H12 processor has set four new world-records in server performance. With a LINPACK score of ~ 4.2 TeraFLOPS, the new chip performs ~11% better than the AMD EPYC 7742 processor.”

Gadi – Australia’s Newest Supercomputer

Allan Williams from NCI gave this talk at the Perth HPC Conference. “With 3,200 nodes, Gadi will power some of Australia’s most crucial research, seeking to solve some of the most complex and pressing challenges facing the world currently. Researchers from organizations including the CSIRO, Geosciences Australia, and the Bureau of Meteorology will benefit from faster speeds and higher capacity compared to the existing supercomputer.”

ExaNeSt Project Successfully Builds Prototype for Exascale

In this video, researchers describe the results from the ExaNeSt project. “The prototype is now successfully built, demonstrating energy efficiency in a High-Performance Computing (HPC) testbed: the energy consumed for solving a given problem on this new platform is 3 to 10 times lower than what traditional HPC processors of the same time generation consume for solving the same problem. The substantial prototype has been validated through the execution of full HPC applications from materials science, climate forecasting, computational fluid dynamics, astrophysics, neuroscience, and a database.”

Video: The SX Aurora TSUBASA (Vector Engine)

Deepak Pathania from NEC gave this talk at the HPC User Forum. “The NEC Vector Engine Processor was developed using 16 nm FinFET process technology for extreme high performance and low power consumption. The Vecor Engine Processor has the world’s first implementation of one processor with six HBM2 memory modules using Chip-on-Wafer-on-Substrate technology, leading to the world-record memory bandwidth of 1.2 TB/s.”

Computational Evaluation of Cloud HPC with a Global Atmospheric Model

Daniel Arevalo from DeVine Consulting gave this talk at the HPC User Forum. “Prompted by DoD priorities for modernization, cost savings, and redundancy, this project compared the performance of the NAVGEM on an in-house Cray system against the follow cloud offerings: AWS c4.8xlarge, Penguin B30 queue, Azure H16r, and AWS c5n.18xlarge.”

NVIDIA Powers Rosie Supercomputer at MSOE

An NVIDIA GPU-powered supercomputer named “Rosie” is at the heart of a new computational science facility at the Milwaukee School of Engineering. “Housed in a glass-walled area within the newly constructed four-story Diercks Hall, the new NVIDIA-powered AI supercomputer includes three NVIDIA DGX-1 pods, each with eight NVIDIA V100 Tensor Core GPUs, and 20 servers each with four NVIDIA T4 GPUs. The nodes are joined together by Mellanox networking fabric and share 200TB of network-attached storage. Rare among supercomputers in higher education, the system —which provides 8.2 petaflops of deep learning performance — will be used for teaching undergrad classes.”