Abstract: Despite significant pressure on both Moore’s Law and Dennard scaling, the appetite for ever larger systems continues to grow. Computing trends, in terms of highly optimized hardware platforms that may leverage accelerators or other non-traditional components, scalable and highly performing applications, and the requirements to manage exponentially larger data sets are driving facility demands not envisioned just a few years ago. The facility demands for supercomputing centers (SCs) are characterized by electrical power demands for computing systems that scale to tens of megawatts (MW) and millisecond voltage fluctuations approaching 10MW for the largest systems. The demand for primary electrical distribution capabilities to current large-scale facilities can exceed 60MW. The operational costs of these facilities must be balanced versus the demand from the systems owners and users for high availability, high utilization, and low-impact facility maintenance and service demands. To achieve this balance, many SCs continue to innovate their operational design practices and technologies.
The workshop for the Energy Efficient HPC Working Group brings together those concerned with HPC energy efficiency and energy conservation of both HPC systems and facilities. The annual workshop has a broad scope of energy efficiency in HPC ranging from silicon and components, through platform integration, software, and firmware and up to the data center, facility, and connection to the utility provider. Because of this broad scope, we engage a wide spectrum of participants- both facilities and operationally focused people as well as computer engineers and architects- which enhances the discussions and sharing that occurs.