Efficient Error-Correcting-Code Mechanism for High-Throughput Memristive Processing-in-Memory

TL;DR

This paper introduces an efficient ECC method for memristive PIM that enhances reliability significantly with minimal latency increase, enabling more dependable in-memory computation.

Contribution

The paper proposes a novel diagonal-based ECC technique that improves error correction in memristor arrays without data movement, enhancing PIM reliability.

Findings

Over eight orders of magnitude increase in reliability

Approximately 26% increase in computation latency

Effective ECC implementation inside memory arrays

Abstract

Inefficient data transfer between computation and memory inspired emerging processing-in-memory (PIM) technologies. Many PIM solutions enable storage and processing using memristors in a crossbar-array structure, with techniques such as memristor-aided logic (MAGIC) used for computation. This approach provides highly-paralleled logic computation with minimal data movement. However, memristors are vulnerable to soft errors and standard error-correcting-code (ECC) techniques are difficult to implement without moving data outside the memory. We propose a novel technique for efficient ECC implementation along diagonals to support reliable computation inside the memory without explicitly reading the data. Our evaluation demonstrates an improvement of over eight orders of magnitude in reliability (mean time to failure) for an increase of about 26% in computation latency.