14 DAY TRIAL // Microsoft, via its research division, is embarking on new initiatives designed to explore next-generation computing by offering support for enhancements resulting in increased energy efficiency. According to the company, there are several areas where the focus is at an apex, including advanced power management, the efficient consumption of datacenter power, as well as building parallel computing architectures capable of delivering reduced power demands. As a part of the Sustainable Computing Program, Microsoft is committed to supporting with financial resources no less than four energy-efficiency computing research projects.
"We want to open new avenues of research and raise the awareness of power as a critical resource that needs to be managed. Through this program, we are encouraging novel thinking about how to reduce that power consumption and how to make technology more environmentally friendly into the future," explained Sailesh Chutani, senior director of Microsoft External Research.
Academic research projects from the University of Tennessee, Stanford University, Harvard University and the University of Oklahoma will receive no less than $500,000. In this manner Microsoft Research is financing four initiatives that fit onto its environmental efforts. The new "power aware" program will deal with "Control-Theoretic Power and Performance Management for Green Data Centers" (University of Tennessee); "Building a Building-scale Power Analysis Infrastructure"; (Stanford); "A Synergistic Approach to Adaptive Power Management" (Harvard) and "Simulating Low Power x86 Architectures with Sooner, a Phoenix-based Simulation Framework" (University of Oklahoma).
Microsoft is working on two different approaches for building energy efficient computing. "Pay for play" is a concept focused on delivering a correlation between power consumption and the amount of the workload a device has to deal with. But at the same time, the company aims to improve the efficiency of energy consumption even at high loads. This can only be achieved by innovation in terms of hardware, software and networking design, as well as advanced benchmarking, even analysis and virtualization.