MRI/Dev.: Development of Instrumentation for Project Green Light Project Proposed: This project, developing an instrument called GreenLight, measures, monitors, and optimizes the energy consumption of large-scale scientific applications from many different areas. The work enables inter-disciplinary researchers to understand how to make ?green? (i.e., energy efficient) decision for IT computation and storage. Consequently, an experienced team might be able to make deep and quantitative explorations in advanced architecture, including alternative circuit fabrics such as Field Programmable Gate Arrays (FPGAs), direct-graph execution machines, graphics processors, solid-state disks, and photonic networking. The enabled computing and systems research will yield new quantitative data to support engineering judgments on comparative ?computational work per watt? across full-scale applications running at-scale computing platforms, thus helping to re-define fundamentals of systems engineering for a transformative concept, that of green CyberInfrastructure (CI). Keeping in mind that the IT industry consumes as much energy (same carbon footprint) as the airline industry, this project enables five communities of application scientists, drawn from metagenomics, ocean observing, microscopy, bioinformatics, and the digital media, to understand how to measure and then minimize energy consumption, to make use of novel energy/cooling sources, and employ middleware that automates optimal choice of compute/power strategies. The research issues addressed include studying the dynamic migration of applications to virtual machines for power consumption reduction, studying the migrations of virtual machines to physical machines to achieve network locality, developing new power/thermal management policies (closed loop, using feedback from sensors), classifying scientific algorithms in the context of co-processing hardware such as GPUs and FPGAs, and developing algorithms for resource sharing/scheduling in heterogeneous platforms. The full-scale virtualized device, the GreenLight Instrument, will be developed to measure, monitor, and make publicly available (via service oriented architecture methodology), real-time sensor outputs, empowering researchers anywhere to study the energy cost of at-scale scientific computing. Hence, this work empowers domain application researchers to continue to exploit exponential improvements in silicon technology, and to compete globally. Although the IT industry has begun to develop strategies for ?greening? traditional data centers, the physical reality of modern campus CI currently involves a complex network of ad hoc and suboptimal energy environments in departmental facilities. The number of these facilities increases extremely fast creating campus-wide crisis of space, power, and cooling due to the value of computational and data intensive approaches to research. This project addresses these important issues offering the possibility to improve.
Broader Impacts: The project enables researchers to carry-out quantitative explorations into energy efficient CyberInfrastructure (CI) and to train the next generation of energy-aware scientists. It enlists graduate students from five disciplinary projects, involves minority serving institutions, and is likely to have direct impact on commercial components of the nation?s CI.
– Project Outcome Report Outcome: Project GreenLight built a fully instrumented modular data center enclosed in a SunMD (an 8’x20’ modular sea storage container outfitted with 8 racks for computers and communications equipment). The racks were filled with a variety of computing and environmental sensing systems and turned over to GreenLight investigators to support energy efficiency research. Environmental data for the container and the computers within, including thermal characterization and power consumption, was collected 7/24 and made available to the researchers via a custom service oriented architecture application, GLIMPSE, with an easy to use graphical web interface, running on laptops, desktop computers and iPad’s. Also developed was a collection of visualization technologies, include 3D immersive CAVE and "Virtual Room" (VROOM) display walls used to display and share GreenLight energy data and allow for improved collaborations among groups of researchers. Impact/benefits: Project GreenLight energy efficiency research activities have resulted in proof-of-concept experiments deploying many different techniques for reducing the energy costs in data centers, servers and networking equipment. These approaches to improving energy efficiency in Information and Communications Technology (ICT) are being put into practice in next generation data centers. Areas of demonstrated improvement include: Conservation of networking resources using virtualization supported by low latency power aware networking equipment and novel network management techniques Use of virtual and augmented reality to improve understanding of data and the feasibility of remote collaboration (and thus reduced need for travel) Use of process migration, improved fan speed algorithms and processor control, and liquid cooling to more efficiently manage computation, thermal generation and dissipation Use of coprocessors and alternative processing architectures, including FPGAs and GP GPUs, to reduce computational driven energy consumption Use of renewable energy (through direct DC power) and automated virtual machine migration (to remote computers using renewable energy, including photovoltaic, fuel cell, hydro and wind power) to reduce the carbon footprint of ICT (in servers, network switches and data centers) Application of service oriented architectures to energy and environmental related data collection, aggregation, management and display Application of advanced visualization techniques to allow for access to and interaction with the modular data center and its resources, to include environmental and energy data Virtual room (VROOM) technologies will enable next generation scalable distributed, high-resolution visualization resources for collaborative work in the sciences, engineering and the arts. Examples of distributed applications include: collaboration with multiple high-resolution data types; prototyping command and control environments; digital cinema post-production review and editing; tele-immersive 3D interactions; brainstorming/storyboarding, and other pedagogical activities. The constructed VROOM facility also supports GreenLight research and education outreach through ongoing demonstrations and workshops. A series of workshops were presented to minority-serving institutions in efforts to spread knowledge of Project GreenLight energy efficiency research activities and visualization technologies while they were under development. The workshops, in collaboration with the Minority Serving Institutions (MSI)—CyberInfrastructure (CI) Empowerment Coalition (MSI-CIEC), were held yearly at UCSD and promoted the use of advanced cyber-infrastructure to support data analysis and distance collaboration, using high resolution display wall environments connected by high speed networks: June 2010, MSI-CIEC Project GreenLight Workshop September 2011 MSI-CIEC Workshop on Visualization Tools to Bridge Gaps for Distributed Knowledge and Distance Collaboration August 2012 MSI-CIEC Workshop on Advancing the Building of Virtualization Environments for Faculty Research Explanation: Energy efficiencies attainable in modern data centers come from many areas. Project GreenLight supported research and experiments to identify those areas and quantify potential efficiency improvements, many of which are being incorporated into new data centers. Dramatic display walls are much more than showcases of spectacular graphics. They enhance faculty and students’ capacity to analyze local and remote data and to participate in remote/distributed collaborations. The above workshops helped faculty and staff understand the benefits and potential uses for display wall collaboration technologies, coupled with inspiring and practical ideas for using these technologies at their own institutions. Following the workshop’s practical implementation training, MSI-CIEC worked with participants to discuss these technologies with colleagues and explore potential collaborative grant proposals to enable campus installations. GreenLight technologies were also disseminated through numerous demonstrations as well as their adoption by GreenLight researchers into UCSD curricula, to seed energy conservation, data visualization and advanced collaboration techniques in the upcoming generation of computer scientists and engineers.
