Energy-Efficient 3D Near-Threshold Computing Systems for Future Embedded Applications Energy-Efficient 3D Near-Threshold Computing for Embedded Applications Arizona State University will work on increasing memory resiliency of the proposed 3D computing system. First, we will develop techniques spanning circuit, architecture and system-levels to address the increasing number of soft and hard errors in DRAM memory structures. We will provide tradeoffs between failure rate, energy consumption and memory performance. Next we will address the reliability issues of non volatile memories (NVM) such as PRAM and STT-MRAM and heterogeneous memory structures built with DRAM and NVM. We will develop accurate error models starting from first principles and develop techniques spanning multiple levels that increase the reliability significantly with reduced energy cost.
|Effective start/end date||10/19/12 → 12/30/15|
- US Department of Defense (DOD): $265,372.00
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.