SPIKA: an energy-efficient time-domain hybrid CMOS-RRAM compute-in-memory macro

The increasing significance of machine learning (ML) has led to the development of circuit architectures suited to handling its multiply-accumulate-heavy computational load such as Compute-In-Memory (CIM). A big class of such architectures uses resistive RAM (RRAM) devices, typically in the role of...

Full description

Saved in:
Bibliographic Details
Main Authors: Khaled Humood, Yihan Pan, Grahame Reynolds, Mohammed Mughal, Shiwei Wang, Alexander Serb, Themis Prodromakis
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Electronics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/felec.2025.1567562/full
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The increasing significance of machine learning (ML) has led to the development of circuit architectures suited to handling its multiply-accumulate-heavy computational load such as Compute-In-Memory (CIM). A big class of such architectures uses resistive RAM (RRAM) devices, typically in the role of neural weights, to save power and area. In this work, we introduce SPIKA, a novel RRAM-based ML accelerator implemented in 180nm CMOS technology. The design features a 64×128 crossbar array, supports 4-bit inputs, ternary weights, and 5-bit outputs. Post-layout analysis indicates a remarkable performance of the proposed system compared to state-of-the-art with a peak throughput of 1092 GOPS and energy efficiency of 195 TOPS/W. The key innovation of SPIKA lies in its natural signal domain crossing, which eliminates the need for power-hungry data converters. Specifically, digital input signals are converted to pulse-width modulated (time-domain), then applied on the RRAM weights that convert them to analog currents, and then aggregated into digital values using a simple switch capacitor read-out system.
ISSN:2673-5857