A limits study of benefits from nanostore-based future data-centric system architectures

Abstract

The adoption of non-volatile memories (NVMs) in system architecture and the growth in data-centric workloads offer exciting opportunities for new designs. In this paper, we examine the potential and limit of designs that move compute in close proximity to NVM-based data stores. To address the challenges in evaluating such system architectures for distributed systems, we develop and validate a new methodology for large-scale data-centric workloads. We then study "nanostores" as an example design that constructs distributed systems from building blocks with 3D-stacked compute and NVM layers on the same chip, replacing both traditional storage and memory with NVM. Our limits study demonstrates significant potential of this approach (3-162X improvement in energy delay product) over 2015 baselines, particularly for IO-intensive workloads. We also discuss and quantify the impact of network bandwidth, software scalability, and power density, and design tradeoffs for future NVM-based data-centric architectures.