Sign up for our newsletter and get the latest HPC news and analysis.

Bright Cluster Manager Wrangles New NVIDIA Tesla K80 GPU

bright-cluster-manager-standard

This week at SC14, Bright Computing announced support for the new NVIDIA Tesla K80 dual-GPU accelerator.

Dell Bumps Up GPU Computing with PowerEdge C4130

OriginalJPG

This week Dell unveiled the PowerEdge C4130. As an incredibly GPU dense and flexible HPC-focused rack server, the PowerEdge C4130 is the only Intel Xeon E5-2600v3 1U server to offer up to four GPUs/accelerators.

Radio Free HPC Takes a Hard Look at the Two 2017 Coral Supercomputers

bubble

In this video, the Radio Free HPC team meets at SC14 in New Orleans to discuss the recent news that Nvidia & IBM will build two Coral 150+ Petaflop Supercomputers in 2017 for Lawrence Livermore and Oak Ridge National Laboratories. The two machines will feature IBM POWER9 processors coupled with Nvidia’s future Volta GPU technology. NVLink will be a critical piece of the architecture as well, along with a system interconnect powered by Mellanox.

AMD Awarded $32 Million FastForward2 Contract

amd logo

Today ​AMD announced that for the third straight year it was awarded research grants for development of critical technologies needed for extreme-scale computing in conjunction with projects associated with the U.S. Department of Energy (DOE) Extreme-Scale Computing Research and Development Program, known as “FastForward 2.”

Slidecast: Nvidia/IBM to Build Two Coral 100+ Petaflop Supercomputers in 2017

coral

In this slidecast, Sumit Gupta from Nvidia describes the company’s big win with IBM for two DOE supercomputers for deployment in 2017. The two machines will feature IBM POWER9 processors coupled with Nvidia’s future Volta GPU technology. NVLink will be a critical piece of the architecture as well, along with a system interconnect powered by Mellanox.

AMD Firepro GPUs Power GSI Physics Research

amd logo

Today AMD announced that the company’s FirePro GPU accelerators are delivering more than 3 petaFLOPS to the GSI GmbH for physics research.

NICE DCV Enhances Visualization in the Cloud

Today NICE announced plans to demonstrate their upcoming Desktop Cloud Visualization (DCV) 2014 technology at the AWS re:Invent conference as well as SC14.

Optimizing the HPCG Benchmark on GPUs

HPCG_Figure5_overhead-624x483

“Over at the Parallel for All Blog, Everett Phillips and Massimiliano Fatica write that GPUs offer good acceleration on the new HPCG benchmark that has been designed to augment Linpack as a measure of performance for the TOP500. Their GPU porting strategy focused on parallelizing the Symmetric Gauss-Seidel smoother (SYMGS), which accounts for approximately two thirds of the benchmark flops.”

Bill Gropp to Teach Designing and Building Applications for Extreme-Scale Systems

Bill Gropp

NCSA’s Blue Waters project will offer of an online graduate course on Designing and Building Applications for Extreme-Scale Systems in spring 2015.

GPUdb: A Distributed Database for Many-Core Devices

imgres

GPUdb is a scalable, distributed database with SQL-style query capability, capable of storing Big Data. Developers using the GPUdb API add data, and query the data with operations like select, group by, and join. GPUdb includes many operations not available in other “cloud database” offerings. GPUdb applies a new (patented) concept in database design that puts emphasis on leveraging the growing trend of many-core devices. By building GPUdb from the ground up around this new concept we are able to provide a system that merges the query needs of the traditional relational database developer with the scalability demands of the modern cloud-centric enterprise.