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


The Pending Age of Exascale

In this special guest feature from Scientific Computing World, Robert Roe looks at advances in exascale computing and the impact of AI on HPC development. “There is a lot of co-development, AI and HPC are not mutually exclusive. They both need high-speed interconnects and very fast storage. It just so happens that AI functions better on GPUs. HPC has GPUs in abundance, so they mix very well.”

Video: Exascale Deep Learning for Climate Analytics

Thorsten Kurth Josh Romero gave this talk at the GPU Technology Conference. “We’ll discuss how we scaled the training of a single deep learning model to 27,360 V100 GPUs (4,560 nodes) on the OLCF Summit HPC System using the high-productivity TensorFlow framework. This talk is targeted at deep learning practitioners who are interested in learning what optimizations are necessary for training their models efficiently at massive scale.”

HPE to Acquire Cray for $1.3 Billion

Today HPE announced that the company has entered into a definitive agreement to acquire Cray for approximately $1.3 billion. “This pending deal will bring together HPE, the global HPC market leader, and Cray, whose Shasta architecture is under contract to power America’s two fastest supercomputers in 2021,” said Steve Conway from Hyperion Research. “The Cray addition will boost HPE’s ability to pursue high-end procurements and will speed the combined company’s development of next-generation technologies that will benefit HPC and AI-machine learning customers at all price points.”

Achieving ExaOps with the CoMet Comparative Genomics Application

Wayne Joubert’s talk at the HPC User Forum described how researchers at the US Department of Energy’s Oak Ridge National Laboratory (ORNL) achieved a record throughput of 1.88 ExaOps on the CoMet algorithm. As the first science application to run at the exascale level, CoMet achieved this remarkable speed analyzing genomic data on the recently launched Summit supercomputer.

David Keyes named ISC 2020 Program Chair

Today the ISC High Performance conference announced that Prof. David Keyes from KAUST will be the ISC 2020 Program Chair. “It is my honor to serve as the ISC 2020 Program Chair,” continued Keyes. “I will do my best to keep the technical program in tune with the community, increase the prestige of being selected to present, expand the range of participants, and present a conference that encourages diverse constituents to take advantage of the latest enablements and fruits of HPC.”

Video: The Exascale Computing Project and the Future of HPC

Doug Kothe from ORNL presented this ACM Tech Talk in April, 2019. “The ECP is designing the software infrastructure to enable the next generation of supercomputers—systems capable of more than 1018 operations per second—to effectively and efficiently run applications that address currently intractable problems of strategic importance. The ECP is creating and deploying an expanded and vertically integrated software stack on DOE HPC exascale and pre-exascale systems, thereby defining the enduring US exascale ecosystem.”

ExaLearn: The ECP Co-Design Center for Machine Learning

In this video from the HPC User Forum, Frank Alexander from Brookhaven National Laboratory presents: ExaLearn – ECP Co-Design Center for Machine Learning. “It is increasingly clear that advances in learning technologies have profound societal implications and that continued U.S. economic leadership requires a focused effort, both to increase the performance of those technologies and to expand their applications. Linking exascale computing and learning technologies represents a timely opportunity to address those goals.”

AMD to Power Exascale Cray System at ORNL

Today AMD announced a new exascale-class supercomputer to be delivered to ORNL in 2021. Built by Cray, the “Frontier” system is expected to deliver more than 1.5 exaFLOPS of processing performance on AMD CPU and GPU processors to accelerate advanced research programs addressing the most complex compute problems. “The combination of a flexible compute infrastructure, scalable HPC and AI software, and the intelligent Slingshot system interconnect will enable Cray customers to undertake a new age of science, discovery and innovation at any scale.”

Jülich installs first Cluster Module for DEEP-EST Exascale Project

Researchers at the Jülich Supercomputing Centre have installed the first-ever Cluster Module from MEGWARE as part of the European DEEP-EST project for Exascale computing. The Cluster Module consist of a single rack with 50 Intel Xeon Scalable Processor-based dual-socket nodes with a Mellanox EDR-InfiniBand 100Gbps high-performance cluster fabric. “The DEEP-EST prototype will demonstrate that a Modular Supercomputer is much more flexible than a monolithic one, and matches very diverse application profiles in a cost-effective way.”

Podcast: Intel to Deliver Exascale for the Advancement of Science

In this Chip Chat podcast, Trish Damkroger from Intel outlines a few of the key technologies coming to the Aurora supercomputer in 2021. To enable Exascale levels of performance, Aurora will be built with a future generation Intel Xeon Scalable processor, the recently announced Intel Xe compute architecture, and Intel Optane DC persistent memory. Built by subcontractor Cray, Aurora will enable ground-breaking science such as precision medicine, climate modeling, weather forecasting, and materials science.