Energy-efficient computing needs new devices and architectures
The result of a workshop funded by the SRC and NSF, the report focuses on issues related to energy consumption, and the inefficiencies of today’s computing technologies, from transistor level to system level. According to its findings, the circuits in today’s computer chips "still operate far from any fundamental limits to energy efficiency" and much of the energy used by today’s computers is from moving data between memory and the CPU.
Even as increases in computing performance slow, the amount of data being generated is growing exponentially. It is estimated that by 2020, 44 zettabytes of data – where one zettabyte equals one trillion gigabytes – will be created on an annual basis.
As a result, the report concludes, "a new paradigm for computing is necessary." Its recommendations align with the recently announced Grand Challenge for Future Computing, which proposes using nanotechnology-based approaches to create "a new type of computer that can proactively interpret and learn from data, solve unfamiliar problems using what it has learned, and operate with the energy efficiency of the human brain."
It is expected that such breakthroughs could take a decade or more to achieve, and would require multi-disciplinary fundamental research into "new kinds of nanoscale devices and materials integrated into three-dimensional systems" in conjunction with new computer architectures. The NSF and SRC are seen as having a long history of supporting long-term research in these areas.
“New devices, and new architectures based on those devices, could take computing far beyond the limits of today’s technology. The benefits to society would be enormous,” says Tom Theis, Nanoelectronics Research Initiative Executive Director at SRC.
For more, see the full report: Report to the National Science Foundation on The Workshop for Energy Efficient Computing (PDF).
Semiconductor Research Corporation
National Science Foundation