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


Nutanix Partners with Microsoft Azure for a Seamless Hybrid Experience

SAN JOSE –– Nutanix (NASDAQ: NTNX), a leader in enterprise cloud computing, today announced a new partnership with Microsoft that will enable both companies to deliver a hybrid solution with seamless application, data, and license mobility as well as unified management across on-premises and Azure environments, using Nutanix Clusters on Azure. “With this partnership, Microsoft and Nutanix show […]

Azure HPC Cache: File caching for high performance computing

In this video, Scott Jeschonek from Microsoft describes the performance advantages of Azure HPC Cache. “Whether you are rendering a movie scene, searching for variants in a genome, or running machine learning against a data set, HPC Cache can provide very low latency high throughput access to the required file data. Even more, your data can remain on its Network Attached Storage (NAS) environment in your data center while you drive your jobs into Azure Compute.”

Video: Fighting COVID-19 with HPE’s Sentinel supercomputer through the cloud

At HPE, we believe in being a force for good, so when the COVID-19 pandemic struck, HPE quickly made available supercomputing resources, along with a dedicated technical staff, free of charge to help scientists tackle complex research. That’s when we met Dr. Baudry and set him and his team up on HPE’s Sentinel supercomputer, which can perform 147 trillion floating point operations per second and store 830 terabytes of data. Sentinel – which is as fast as the earth’s entire population performing 20,000 calculations per second – is significantly accelerating discovery and saving months of research time and hundreds of thousands of dollars.

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.”

Azure Looks to Real-Time Derivatives Pricing using Riskfuel AI Technology on GPUs

In this special guest feature, Ian Finder from Microsoft Azure writes that GPU VMs with Riskfuel’s derivatives models based on artificial intelligence are much faster than previous methods. “Using conventional algorithms, real-time pricing, and risk management is out of reach. But as the influence of machine learning extends into production workloads, a compelling pattern is emerging across scenarios and industries reliant on traditional simulation. Once computed, the output of traditional simulation can be used to train DNN models that can then be evaluated in near real-time with the introduction of GPU acceleration.”

Rescale Partners with Google Cloud and Azure to Offer Cloud HPC for COVID-19 Researchers

Today Rescale, in cooperation with Google Cloud and Microsoft Azure, announced a new program that immediately offers high performance computing resources at no cost to teams working to develop test kits and vaccines for COVID-19. “Those working on coronavirus vaccines and testing who would benefit from HPC in the cloud at no cost should apply at techagainstcovid.com. Researchers can rapidly run simulations in the cloud without setup time or IT teams using Rescale’s turnkey platform combined with cloud computing resources from Google Cloud Platform and Microsoft Azure.”

AMD Powers Azure HBv2 Virtual Machines for HPC Workloads

The AMD and Microsoft partnership continues to expand this week with the launch of Microsoft Azure NVv4 Virtual Machines. Powered by 2nd Gen AMD EPYC  Processors and AMD Radeon Instinct GPUs, the powerful new VMs are now generally available to customers in South Central US, East US, and West Europe regions, with additional regions planned for the coming months. “These VMs, the first in the industry to be powered by both AMD EPYC CPUs and Radeon Instinct GPUs, enable customers to scale virtual desktops in the cloud that support a variety of workloads.”

Azure HBv2 Virtual Machines eclipse 80,000 cores for MPI HPC

Today Microsoft announced general availability of Azure HBv2-series Virtual Machines designed to deliver leadership-class performance, message passing interface (MPI) scalability, and cost efficiency for a variety of real-world HPC workloads. “HBv2 VMs deliver supercomputer-class performance, message passing interface (MPI) scalability, and cost efficiency for a variety of real-world high performance computing (HPC) workloads, such as CFD, explicit finite element analysis, seismic processing, reservoir modeling, rendering, and weather simulation. Azure HBv2 VMs are the first in the public cloud to feature 200 gigabit per second HDR InfiniBand from Mellanox. 

Predictions for HPC in 2020

In this special guest feature from Scientific Computing World, Laurence Horrocks-Barlow from OCF predicts that containerization, cloud, and GPU-based workloads are all going to dominate the HPC environment in 2020. “Over the last year, we’ve seen a strong shift towards the use of cloud in HPC, particularly in the case of storage. Many research institutions are working towards a ‘cloud first’ policy, looking for cost savings in using the cloud rather than expanding their data centres with overheads, such as cooling, data and cluster management and certification requirements.”

Second GPU Cloudburst Experiment Paves the Way for Large-scale Cloud Computing

Researchers at SDSC and the Wisconsin IceCube Particle Astrophysics Center have successfully completed a second computational experiment using thousands of GPUs across Amazon Web Services, Microsoft Azure, and the Google Cloud Platform. “We drew several key conclusions from this second demonstration,” said SDSC’s Sfiligoi. “We showed that the cloudburst run can actually be sustained during an entire workday instead of just one or two hours, and have moreover measured the cost of using only the two most cost-effective cloud instances for each cloud provider.”