Birds of a Feather
Power, Cooling and Energy Consumption for Petascale and Beyond

Wednesday, November 14, 2007

For decades, the notion of "performance of computer" has been synonymous with "raw speed" in FLOP/S. This has increased power consumption dramatically creating problems economically providing enough power, making the most efficient use of the power, and managing the byproduct of waste heat. Total cost of ownership of supercomputers has increased extraordinarily.

Leading research and industry groups will present an overview of power consumption trends and discuss solutions for petascale computing power and cooling. Topics include

• Performance, power-related and efficiency metrics for system ranking.
• Minimization of power consumption.
• Air or liquid cooling for rooms, systems, racks, nodes, or chips.
• Dense server packaging and cooling alternatives
• AC or DC power feeds with or without UPS.
• Chiller free cooling and cooling with outside air.
ASHRAE allowable conditions
• Efficiency rebate programs.

Datacenter case studies will cover acquisition and risk management as well as competitive analysis.

Organizers: John Shalf
Lawrence Berkeley National Laboratory
Erich Strohmaier
Lawrence Berkeley National Laboratory
Stephen Elbert
Pacific Northwest National Laboratory
Rob Pennington
National Center for Supercomputing Applications

Introduction: Looming Power Crisis in HPC and Computer Architecture Trends

John Shalf, Lawrence Berkeley National Laboratory, Rob Pennington National Center for Supercomputing Applications

Presentation: (PDF) (PPT)

Data Center Energy Efficiency

Bill Tschudi, Lawrence Berkeley National Laboratory

Presentation: (PDF) (PPT)

Systesm: A Holistic View

Andres Marquez, Pacific Northwest National Laboratory

Presentation: (PDF) (PPT)

ASHRAE TC9.9 Overview

Tim McCann Silicon Graphics Inc.

Presentation: (PDF)(PPT)

Overview of the Green Grid

Tahir Cader ISR Spray Cooling

Presentation: (PDF) (PPT)

What Next

Presentation: (PDF) (PPT)

Related Information:

• PNNL Energy Smart Data Centers
• The Landscape of Parallel Computing Research: A View from Berkeley