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


For HPC and Deep Learning, GPUs are here to stay

In this special guest feature from Scientific Computing World, David Yip, HPC and Storage Business Development at OCF, provides his take on the place of GPU technology in HPC. “Using GPUs in the HPC datacenter in place of CPUs can dramatically increase the power requirements needed, but if your computational performance goes through the roof, then I’d argue it’s a trade-off worth making.”

GRC Builds GPU-Based Immersion Cluster for TACC

Green Revolution Cooling has announced plans to deliver a custom GPU-based cluster to the Texas Advanced Computing Center (TACC). Our goal is to make HPC more affordable. Offering lower cost, energy dense servers that take full advantage of our highly efficient CarnotJet cooling system is a huge benefit to our customers,” said Larry Stone, VP of Engineering at GRC “we are seeing a growing number of people opt for servers designed for immersion, over traditional big brand OEM hardware.”

SkyScale HPC Cloud steps up with Volta GPUs

Last week at SC17, SkyScale announced its partnership with Rescale, the foremost cloud simulation and HPC solution provider, and availability of NVIDIA Tesla V100 GPU accelerators on its GPU as a Service cloud platform. Enhancing SkyScale’s dedicated, cloud-based ultra-fast multi-GPU platforms for deep learning and HPC applications, the Tesla V100 offers the performance of 100 CPUs in a single GPU—enabling data scientists, researchers, and engineers to tackle the most difficult deep learning and HPC challenges.

Video: Nyriad Unveils GPU-accelerated Storage Device for the Square Kilometer Array

At SC17 last week, Nyriad Limited demonstrated their company’s first commercial product, Nsulate, a GPU-accelerated storage solution that enables increased storage resilience while reducing the storage power requirements by over 50 percent. “Using a GPU as a storage controller inserts an enormous amount of general purpose processing power directly into the storage pipeline, enabling modern HPC storage appliances to deliver unprecedented speed, scale, security, storage efficiency and intelligence in real-time.”

Video: Project Cyclops comes to SC17 in a Quest to Build the World’s Fastest Node

In this video from SC17, Rich Brueckner from insideHPC describes Project Cyclops, a benchmarking quest to build the world’s fastest single node. The single-node Cyclops supercomputer demonstrates the computational power that individual scientists, engineers, artificial intelligence practitioners, and data scientists can deploy in their offices. Cyclops looks to rank well on the HPCG benchmark.

AMD Delivers ‘Supercomputing for All’ at SC17

At SC17 in Denver, AMD and its ecosystem partners announced at SC17 immediate availability of a suite of new, high performance systems powered by AMD EPYC CPUs and AMD Radeon Instinct GPUs to accelerate innovation in supercomputing. “Target workloads for AMD solutions include machine learning, weather modeling, computational fluid dynamics, simulation and crash analysis in aviation and automotive manufacturing, oil and gas exploration, and more.”

One Stop Systems Rolls Out Composable Infrastructure Solutions at SC17

This week at SC17, One Stop Systems is showcasing all-new “HPC composable infrastructure solutions” designed for data scientists requiring flexible high performance infrastructure across multiple nodes. “By adding NVIDIA GPU and NVMe expansion, customers can add unlimited flexibility to their HPC architecture by decoupling the latest innovations in CPU capabilities, NVIDIA GPU performance, and NVMe storage into a system called “composable HPC infrastructure.”

SC17 Video Replay: Jensen Huang from NVIDIA on the AI Revolution in HPC

We are excited to bring our readers this special livestream from NVIDIA at SC17 in Denver. Tune in right here for a live presentation from NVIDIA CEO Jensen Huang entitled, “Accelerated Computing: The Path Forward.” It all starts at Monday at 3:00pm Mountain time.

Live! Radio Free HPC does the Latest TOP500 List

In this podcast, the Radio Free HPC team reviews the latest TOP500 list in front of a live audience in Denver at SC17. “The fiftieth TOP500 list of the fastest supercomputers in the world has China overtaking the US in the total number of ranked systems by a margin of 202 to 144. It is the largest number of supercomputers China has ever claimed on the TOP500 ranking, with the US presence shrinking to its lowest level since the list’s inception 25 years ago.”

Video: The Legion Programming Model

“Developed by Stanford University, Legion is a data-centric programming model for writing high-performance applications for distributed heterogeneous architectures. Legion provides a common framework for implementing applications which can achieve portable performance across a range of architectures. The target class of users dictates that productivity in Legion will always be a second-class design constraint behind performance. Instead Legion is designed to be extensible and to support higher-level productivity languages and libraries.”