Re-imagining Computer System Memories

In modern computer systems, memories located close to the processing unit must be fast with nearly infinite endurance to support operation rates exceeding a billion instructions per second. These memories, however, are volatile at present. Existing high-capacity non-volatile memories, such as solid-state hard drives, must be situated away from the processing unit because they are slow. As a result, it takes even more time for a processing unit to fetch data, process it, and send it back. Furthermore, most non-volatile memories can only be erased and written a finite number of times. An ultimate memory would be suitable to all systems, with the desired features of non-volatility, low-power operation, infinite endurance, nanosecond writing time, sub-nanosecond reading time, good scalability, and more.

H. Grace Xing, Electrical and Computer Engineering/Materials Science Engineering, is leading an interdisciplinary team spanning materials, devices, circuits, and architectures to realize such a memory and a paradigm shift in memory-processing architecture. The outcome will be durable, energy-efficient, pausable processing in polymorphic memories (DEEP3M), where computational capabilities are pushed directly into the high-capacity memories. This will enable massively parallel computation with fast and energy-efficient memory access. Xing and her team’s approach builds on recent breakthroughs in the physics of magnetic switching and advanced materials and enables a transformative, holistic exploration of processing and memory by re-imagining the memory device as a computing element itself. This view will provide new insights and an entirely new paradigm for the semiconductor industry in the emerging era of big data.

The project is jointly funded by the National Science Foundation and the Semiconductor Research Corporation, Inc.

Cornell Researchers

Funding Received

$2.8 Million spanning 3 years

Sponsored by

Other Research Sponsored by National Science Foundation