Back to Table of contents

Primeur weekly 2015-11-30

Focus

Turkey to prepare itself for European Open Science Cloud ...

Quantum computing

Quantum computer coding in silicon now possible ...

Middleware

Open Science Grid using SDSC's Comet supercomputer virtual clusters ...

IBM and OpenPOWER members deliver accelerated technologies to break Big Data speed barriers ...

Hardware

Hewlett Packard Enterprise sees significant momentum in high-performance computing ...

Mellanox announces ConnectX-4 Lx Programmable adapter with onboard Xilinx FPGA acceleration ...

Mellanox introduces the Switch-IB 2, world's first 100Gb/s smart switch ...

Supermicro debuts new 4U 90/60-bay storage server alongside 1U 4x GPU, NVMe, high-density server and storage solutions ...

Los Alamos National Labs selects Aeon Computing's next generation of supercomputing infrastructure ...

Dell innovation to democratize high performance computing and accelerate mainstream adoption ...

State grant enables energy-saving retrofit of Lawrence Livermore computing clusters ...

Applications

NSF-supported supercomputing resources enable research that would otherwise be impossible ...

New supercomputer simulations enhance understanding of protein motion and function ...

Scientists use supercomputer to model plasma turbulence, and solve a 50-year-old mystery ...

IBM Research and Rensselaer Polytechnic Institute pioneer next-generation cognitive environments for business decision making ...

How DNA and a supercomputer can help sustain honey bee populations ...

IRB Barcelona develops an advanced method and the first platform of DNA simulations ...

INCITE grants awarded to 56 computational research projects ...

OLCF supercomputer's GPUs advance earthquake simulations for high-frequency seismic hazard map ...

Researchers trains Watson AI to 'chat' and spark more creativity in humans ...

TOP500

HPC system Hazel Hen of High Performance Computing Center Stuttgart captures position 8 on new TOP500 list ...

HPCG-Benchmark: GCS Centre HLRS runs Europe's fastest supercomputer ...

The Cloud

ICGC brings more genomic health data to researchers on the Amazon Web Services Cloud ...

Penguin Computing increases customer compute capacity with availability of the Tundra platform on its Penguin Computing on Demand HPC Cloud service ...

Hewlett Packard Enterprise delivers Docker solutions from the data centre to the Cloud ...

State grant enables energy-saving retrofit of Lawrence Livermore computing clusters


Anna Maria Bailey, LLNL high performance computing facility manager, with the Cab supercomputer that will be retrofitted with liquid cooling in January. Photo by Julie Russell/LLNL.
12 Nov 2015 Livermore - Supercomputers at Lawrence Livermore National Laboratory (LLNL) will be retrofitted with liquid cooling systems under a California Energy Commission (CEC) grant to assess potential energy savings.

Asetek, a provider of energy, efficient liquid cooling systems for data centres, servers and HPC clusters, has received a $3.5 million grant from the CEC for retrofits at two California high performance computing (HPC) centres. A second yet-to-be-disclosed California data centre also will be retrofitted under the grant next year. Energy savings and the associated cost reductions are critical to data centers and supercomputing facilities around the world.

"We are excited about this important project", stated John Hamill, Asetek vice president for worldwide sales. "Not only will it benefit LLNL, but the results gathered from the project will be used to improve energy efficiency of data centres worldwide."

Lawrence Livermore's CAB supercomputer will undergo retrofitting in January during the first phase of the project. CAB, a Linux commodity cluster delivering 431 teraflops (trillions of floating point operations per second) for unclassified computing, is currently air cooled. Later next year, one of the recently announced Commodity Technology System (CTS-1) clusters slated for installation at Lawrence Livermore also will be fitted with an Asetek emerging future liquid cooling technology as the second phase of this grant.

"This is an exciting project with Asetek that will help advance the state-of-the-art in energy savings for data centres", stated Anna Maria Bailey, LLNL's HPC facilities manager and a co-organizer of the annual Energy Efficient Working Group workshop conducted at the upcoming Supercomputing Conference. "As part of this project, we will measure savings and assess such potential benefits as improved computational performance."

LLNL has entered into a "work for others" contract with Asetek to undertake the retrofits. The selected systems for the first phase of the project, all currently air cooled, will be retrofitted with Asetek's all-in-one liquid cooling technology. The liquid cooling technology is used to reduce power, greenhouse gas emissions and lower noise in data centers, servers, as well as HPC systems.

The project and many other similar energy-efficient HPC efforts were discussed during the Energy Efficient High Performance Computing Working Group's all-day workshop at SC15. Anna Maria Bailey was the co-chair of the group.

“Reducing power consumption and the associated costs at data centres and high performance computing facilities is a leading concern of the HPC community", Anna Maria Bailey stated, noting that "addressing this issue is critical as we develop ever more powerful next-generation supercomputers."
Source: Lawrence Livermore National Laboratory

Back to Table of contents

Primeur weekly 2015-11-30

Focus

Turkey to prepare itself for European Open Science Cloud ...

Quantum computing

Quantum computer coding in silicon now possible ...

Middleware

Open Science Grid using SDSC's Comet supercomputer virtual clusters ...

IBM and OpenPOWER members deliver accelerated technologies to break Big Data speed barriers ...

Hardware

Hewlett Packard Enterprise sees significant momentum in high-performance computing ...

Mellanox announces ConnectX-4 Lx Programmable adapter with onboard Xilinx FPGA acceleration ...

Mellanox introduces the Switch-IB 2, world's first 100Gb/s smart switch ...

Supermicro debuts new 4U 90/60-bay storage server alongside 1U 4x GPU, NVMe, high-density server and storage solutions ...

Los Alamos National Labs selects Aeon Computing's next generation of supercomputing infrastructure ...

Dell innovation to democratize high performance computing and accelerate mainstream adoption ...

State grant enables energy-saving retrofit of Lawrence Livermore computing clusters ...

Applications

NSF-supported supercomputing resources enable research that would otherwise be impossible ...

New supercomputer simulations enhance understanding of protein motion and function ...

Scientists use supercomputer to model plasma turbulence, and solve a 50-year-old mystery ...

IBM Research and Rensselaer Polytechnic Institute pioneer next-generation cognitive environments for business decision making ...

How DNA and a supercomputer can help sustain honey bee populations ...

IRB Barcelona develops an advanced method and the first platform of DNA simulations ...

INCITE grants awarded to 56 computational research projects ...

OLCF supercomputer's GPUs advance earthquake simulations for high-frequency seismic hazard map ...

Researchers trains Watson AI to 'chat' and spark more creativity in humans ...

TOP500

HPC system Hazel Hen of High Performance Computing Center Stuttgart captures position 8 on new TOP500 list ...

HPCG-Benchmark: GCS Centre HLRS runs Europe's fastest supercomputer ...

The Cloud

ICGC brings more genomic health data to researchers on the Amazon Web Services Cloud ...

Penguin Computing increases customer compute capacity with availability of the Tundra platform on its Penguin Computing on Demand HPC Cloud service ...

Hewlett Packard Enterprise delivers Docker solutions from the data centre to the Cloud ...