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

Search Results for: pue

Video: Panel Discussion – Has the PUE Issue Already Been Solved for the Datacenter?

Has the issue of optimized PUE largely been solved already for large datacenters? In this presentation, you’ll hear from the following individuals in a panel discussion moderated by James Hamilton of Amazon. Chris Malone, Google Rob Coupland, Telecity Group Ian Bitterlin, Ark Continuity Ltd Brian Waddell, Norman Disney & Young Recorded at the 2011 Data […]

The Green Grid juices PUE datacenter measure

The Green Grid has recently updated its PUE metric (Power Usage Effectiveness) that attempts to wrangle some of the uncertainty in the prior definition of the measure. Ted Samson has a nice analysis One of the greatest strengths of the PUE metric, the industry standard for measuring data center energy efficiency, is its simplicity: Calculate […]

Google tips for getting to a PUE of 1.5

Ted Samson writes about comments that Google Green Energy Czar Bill Weihl made at last weeks’ GreenNet 2010 conference in San Francisco. The most interesting tip Weihl shared pertained to power infrastructure. Whereas most companies use large PDUs (power distribution units) to provide backup power for their data center hardware, Google instead equips each server […]

New international agreement on PUE may get momentum going

Enterprise IT Planet’s Green blog has a post up this morning about an international agreement reached over the weekend that may help build momentum for a common vocabulary when it comes to measuring datacenter efficiency Over the weekend, news emerged of an international agreement to establish data center energy efficiency. The agreement is between The […]

Eurotech Introduces Hi√e, The Ultimate Accelerated Computing Solution

Eurotech launched the Hi√e (High Velocity) system, the new addition to the Aurora line of supercomputers. It is a new family of HPC systems, built on the innovative “Brick” supercomputing architecture that promises to raise the bar for acceleration, optimization and flexibility. The Hi√e HPC systems are optimized for accelerated workloads, offering performance and energy efficiency […]

Tackling Power Grid Challenges with the Peregrine Supercomputer

Energy Secretary Ernest Moniz, right, joins NREL Director Dan Arvizu, center, and NREL Computational Science Center Director Steve Hammond, left, at the unveiling of Peregrine.

Peregrine provides much-needed computational capability to model complex systems such as the grid, to allow us to ask ‘what if’ questions, and to optimize how these systems are designed and deployed with much higher confidence in their efficiency and robustness.”

How the NREL Peregrine Supercomputer Sets the Bar for Energy Efficiency

nrel

In this video from ISC’14, Steve Hammond from NREL and Nic Dube from HP describe the energy efficient Peregrine supercomputer at the National Renewable Energy Lab. As a prototype for the HP Apollo 8000 system, Peregrine has achieved a remarkable 1.05 PUE rating for energy efficiency.

Sugon Unveils Liquid-cooled Prototype at ISC’14

sugon

In this video from ISC’14, Shen Weidong from Sugon describes the company’s liquid-cooled “personal supercomputer” prototype designed to run in office environments. “The PHPC300 has 12 blades. Each blade is a sealed box with (3M Novec) liquid in it with a boiling point of about 50 degrees Celsius. So the liquid near the CPU will evaporate and then be circulated to a condenser where it is turned back into a liquid. We can use this technology in China to achieve a PUE of 1.05.”

x86 Says Goodbye to IBM. Hello Inspur?

Tom Wilkie, Scientific Computing World

In this special report from Scientific Computing World, Tom Wilkie reports on Chinese technology ambitions on display at ISC’14. “Inspur used the event to launch an ambitious expansion program that it is calling ‘I2I’. The acronym stands for ‘IBM to Inspur’, and it encapsulates the company’s aim to replace IBM as the reliable provider of servers and supercomputers based on the standard x86 processor chip architecture.”

Benefits of Liquid Cooling for HPC

CoolIT Rack DCLC

In this Sponsored Post from CoolIT we explore the many benefits liquid cooling offers to HPC and data center operators. For starters liquid cooling is about 3,500 times better at storing and transferring heat than air. Direct contact liquid cooling (DCLC) uses the exceptional thermal conductivity of liquid to provide dense, concentrated cooling to targeted areas. The many benefits of liquid cooling may surprise you.