Fast and reconfigurable sort-in-memory system enabled by memristors

TL;DR

This paper introduces a fast, reconfigurable sort-in-memory system using memristors, achieving significant speed, energy, and area improvements over traditional systems, and demonstrating practical applications like shortest path search and neural network inference.

Contribution

The paper presents a novel memristor-based sort-in-memory system with digit read and tree node skipping techniques, enabling efficient, reconfigurable sorting within memory arrays.

Findings

Up to 7.70x speedup over state-of-the-art systems

Energy efficiency improved by up to 183.5x

Area reduced by up to 7.43x

Abstract

Sorting is fundamental and ubiquitous in modern computing systems. Hardware sorting systems are built based on comparison operations with Von Neumann architecture, but their performance are limited by the bandwidth between memory and comparison units and the performance of complementary metal-oxide-semiconductor (CMOS) based circuitry. Sort-in-memory (SIM) based on emerging memristors is desired but not yet available due to comparison operations that are challenging to be implemented within memristive memory. Here we report fast and reconfigurable SIM system enabled by digit read (DR) on 1-transistor-1-resistor (1T1R) memristor arrays. We develop DR tree node skipping (TNS) that support variable data quantity and data types, and extend TNS with multi-bank, bit-slice and multi-level strategies to enable cross-array TNS (CA-TNS) for practical adoptions. Experimented on benchmark sorting datasets, our memristor-enabled SIM system presents up to 3.32x~7.70x speedup, 6.23x~183.5x energy efficiency improvement and 2.23x~7.43x area reduction compared with state-of-the-art sorting systems. We apply such SIM system for shortest path search with Dijkstra's algorithm and neural network inference with in-situ pruning, demonstrating the capability in solving practical sorting tasks and the compatibility in integrating with other compute-in-memory (CIM) schemes. The comparison-free TNS/CA-TNS SIM enabled by memristors pushes sorting into a new paradigm of sort-in-memory for next-generation sorting systems.