X-SRAM: Enabling In-Memory Boolean Computations in CMOS Static Random Access Memories

TL;DR

This paper introduces X-SRAM, an augmented SRAM design that enables in-memory Boolean computations, aiming to reduce the von-Neumann bottleneck and improve energy efficiency for data-intensive applications.

Contribution

The paper presents novel in-memory computation schemes integrated into SRAM cells, including NAND, NOR, IMP, XOR, and a read-compute-store method, verified through predictive modeling.

Findings

Multiple in-memory Boolean logic schemes demonstrated

Feasibility confirmed via transistor models and variation analysis

Potential for reduced energy and throughput bottlenecks

Abstract

Silicon-based Static Random Access Memories (SRAM) and digital Boolean logic have been the workhorse of the state-of-art computing platforms. Despite tremendous strides in scaling the ubiquitous metal-oxide-semiconductor transistor, the underlying \textit{von-Neumann} computing architecture has remained unchanged. The limited throughput and energy-efficiency of the state-of-art computing systems, to a large extent, results from the well-known \textit{von-Neumann bottleneck}. The energy and throughput inefficiency of the von-Neumann machines have been accentuated in recent times due to the present emphasis on data-intensive applications like artificial intelligence, machine learning \textit{etc}. A possible approach towards mitigating the overhead associated with the von-Neumann bottleneck is to enable \textit{in-memory} Boolean computations. In this manuscript, we present an augmented version of the conventional SRAM bit-cells, called \textit{the X-SRAM}, with the ability to perform in-memory, vector Boolean computations, in addition to the usual memory storage operations. We propose at least six different schemes for enabling in-memory vector computations including NAND, NOR, IMP (implication), XOR logic gates with respect to different bit-cell topologies $-$ the 8T cell and the 8$^+$T Differential cell. In addition, we also present a novel \textit{`read-compute-store'} scheme, wherein the computed Boolean function can be directly stored in the memory without the need of latching the data and carrying out a subsequent write operation. The feasibility of the proposed schemes has been verified using predictive transistor models and Monte-Carlo variation analysis.