A Reconfigurable Computing In-Memory Macro with Charge-sharing-based Weighted Accumulator

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Junyi, Dong, Shuai, Fu, Zhengnan, Shang, Hongyang, Basu, Arindam
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914615751868416
author Yang, Junyi
Dong, Shuai
Fu, Zhengnan
Shang, Hongyang
Basu, Arindam
author_facet Yang, Junyi
Dong, Shuai
Fu, Zhengnan
Shang, Hongyang
Basu, Arindam
contents SRAM-based analog computing-in-memory demonstrates outstanding efficiency. However, it faces three critical challenges: significant ADC overhead, high latency for multi-bit inputs, and limited read bitline voltage. To address these issues, this work proposes a multi-bit highly reconfigurable 256x128 in-memory computing array supporting 1-7b input, 2-4b weight, and 1-7b output. Three key innovations are introduced: 1) The IMADC occupies only 3% area overhead, achieving a 9x improvement compared to previous IMADC; 2) The BSCHA reduces latency by 1.9x and 6.6x compared to traditional pulse-width modulation (PWM) and bit-slicing modes, respectively; 3) A dual-8T bitcell enabling ternary weight storage through a decoupled read path, integrated with a read wordline under-driven cascode technique, improves linearity of unit discharge current by 7x and increases the usable read bitline voltage by 3.5x.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30814
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Reconfigurable Computing In-Memory Macro with Charge-sharing-based Weighted Accumulator
Yang, Junyi
Dong, Shuai
Fu, Zhengnan
Shang, Hongyang
Basu, Arindam
Hardware Architecture
SRAM-based analog computing-in-memory demonstrates outstanding efficiency. However, it faces three critical challenges: significant ADC overhead, high latency for multi-bit inputs, and limited read bitline voltage. To address these issues, this work proposes a multi-bit highly reconfigurable 256x128 in-memory computing array supporting 1-7b input, 2-4b weight, and 1-7b output. Three key innovations are introduced: 1) The IMADC occupies only 3% area overhead, achieving a 9x improvement compared to previous IMADC; 2) The BSCHA reduces latency by 1.9x and 6.6x compared to traditional pulse-width modulation (PWM) and bit-slicing modes, respectively; 3) A dual-8T bitcell enabling ternary weight storage through a decoupled read path, integrated with a read wordline under-driven cascode technique, improves linearity of unit discharge current by 7x and increases the usable read bitline voltage by 3.5x.
title A Reconfigurable Computing In-Memory Macro with Charge-sharing-based Weighted Accumulator
topic Hardware Architecture
url https://arxiv.org/abs/2605.30814