SDC 2017 - Memories of Tomorrow - Tom Coughlin, Jim Handy

Download Presentation:

Abstract:
Computer architecture is embarked on several new paths including quantum computing, adiabatic computing, approximate computing and several approaches to bringing processing closer to the memory. These new architectures will allow important developments in Deep Learning, Artificial Intelligence, and machine learning which will facilitate the development of advanced robotics, industrial IoT, autonomous vehicles, and other applications. A common link between all of these is their need for storage and memory.

These new computer architectures will require high speed persistent memory and reduced latency between processing and memory. Meanwhile, Storage Class Memory is blurring the once-clear line between two dramatically different layers of the storage/memory hierarchy. These emerging solid state storage technologies require advances in the operating system and a re-evaluation of fundamental data handling firmware as well as shorter data paths to bring compute memory access speeds closer to the inherent speeds of the memory device.

This presentation will explore factors that are driving these developments including current emerging solid state memory technologies. We will explore challenges in semiconductor scaling that will unify memory and storage. This presentation will also show how new memory/storage hybrids will drive architectural changes in processors, storage systems, and storage/memory devices.