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


Update from the Frontier of Exascale Software Development

In advance of the scheduled shipment this year of the U.S.’s first exascale supercomputer, Frontier, at Oak Ridge National Laboratory, an international team of software developers led by a University of Delaware professor is working on a plasma physics application. An article published yesterday in the university’s UDaily by Tracey Bryant details the work underway […]

Northern Data: Existing Bitcoin Mining Customer Expands Contract Volume by More Than 200MW

Frankfurt am Main – Northern Data AG (XETRA: NB2, ISIN: DE000A0SMU87), a provider of high-performance computing (HPC) solutions, has announced the extension of a customer contract of a volume of ASIC chips worth USD $100 million. The existing customer, from the bitcoin mining sector, is making use of an extension option, which it drew at […]

Graphcore Announces $222M Series E Funding Round

Bristol, UK — Graphcore announced it has raised $222m of investment to help support the company’s global expansion and accelerate future IPU silicon, systems and software development. The Series E funding round is led by Ontario Teachers’ Pensions Plan Board and adds funds managed by Fidelity International and Schroders as new investors. Also participating in this round are existing Graphcore investors, […]

AMAX Extends Line of Workstations to Support Nvidia RTX A6000 GPUs

Fremont, CA, December 15, 2020 – AMAX’s HPC and AI Solution Group announced that it is now offering a wide selection of AceleMax workstations for AI, rendering and visualization featuring the new NVIDIA RTX A6000 GPU. These powerful professional GPU workstations deliver unprecedented performance and features that will allow researchers, scientists and designers to accelerate […]

At SC20: AMD Says New GPU Surpasses 10TFLOPS for HPC Acceleration

AMD today announced the new Instinct MI100 accelerator, which the company said is the first x86 server GPU to surpass 10 teraflops (FP64) performance. Built on the new AMD CDNA architecture, the Instinct MI100 “enables a new class of accelerated systems for HPC and AI when paired with 2nd Gen AMD Epyc processors,” the company said. The […]

At SC20: Nvidia Announces A100 80GB GPU

Nvidia today unveiled the A100 80GB GPU for the Nvidia HGXTM AI supercomputing platform with twice the memory of its predecessor. The new chip with HBM2e doubles the A100 40GB GPU’s high-bandwidth memory to 80GB and delivers more than 2TB/sec of memory bandwidth, according to Nvidia. The A100 80GB GPU is available in Nvidia DGX […]

Nvidia Says It’s Building UK’s Most Powerful Supercomputer, Targeting AI Research in Healthcare

Today at Nvidia’s virtual GTC event, the company announced what it said will be the United Kingdom’s most powerful supercomputer, to be made available by the end of this year to UK healthcare researchers using AI to solve medical challenges, including COVID-19. Powered by 80 Nvidia DGX A100 GPU-based Systems connected by Nvidia Mellanox InfiniBand, […]

HPC End User Survey: Intel Xeon Still Dominates but AMD EPYC Gaining

Industry analyst firm Intersect360 has released partial results from an HPC end-user survey identifying the top user-rated processors, servers and cloud vendors. The key finding, according firm CEO Addison Snell: the disconnect between the HPC users, who want integration of Nvidia GPUs with CPUs from Intel or AMD, over against HPC vendors developing their own integrated solutions.

Exascale Exasperation: Why DOE Gave Intel a 2nd Chance; Can Nvidia GPUs Ride to Aurora’s Rescue?

The most talked-about topic in HPC these days – another Intel chip delay and therefore delay of the U.S.’s flagship Aurora exascale system – is something no one directly involved wants to talk about. Not Argonne National Laboratory, where Intel was to install Aurora in 2021; not the Department of Energy’s Exascale Computing Project, guiding […]

Google Unveils 1st Public Cloud VMs using Nvidia Ampere A100 Tensor GPUs

Google today introduced the Accelerator-Optimized VM (A2) instance family on Google Compute Engine based on the NVIDIA Ampere A100 Tensor Core GPU, launched in mid-May. Available in alpha and with up to 16 GPUs, A2 VMs are the first A100-based offering in a public cloud, according to Google. At its launch, Nvidia said the A100, built on the company’s new Ampere architecture, delivers “the greatest generational leap ever,” according to Nvidia, enhancing training and inference computing performance by 20x over its predecessors.