Reconfigurable Compute-In-Memory on Field-Programmable Ferroelectric Diodes.
Sign Up to like & getrecommendations! Published in 2022 at "Nano letters"
DOI: 10.1021/acs.nanolett.2c03169
Abstract: The deluge of sensors and data generating devices has driven a paradigm shift in modern computing from arithmetic-logic centric to data-centric processing. Data-centric processing require innovations at the device level to enable novel compute-in-memory (CIM)… read more here.
Keywords: ferroelectric diodes; compute memory; cim; reconfigurable compute ... See more keywords
Assessing Design Space for the Device-Circuit Codesign of Nonvolatile Memory-Based Compute-in-Memory Accelerators
Sign Up to like & getrecommendations! Published in 2025 at "Nano Letters"
DOI: 10.1021/acs.nanolett.4c05299
Abstract: Unprecedented penetration of artificial intelligence (AI) algorithms has brought about rapid innovations in electronic hardware, including new memory devices. Nonvolatile memory (NVM) devices offer one such attractive alternative with ∼2× density and data retention after… read more here.
Keywords: circuit; resistance; nonvolatile memory; memory ... See more keywords
Memristor-based adaptive analog-to-digital conversion for efficient and accurate compute-in-memory
Sign Up to like & getrecommendations! Published in 2025 at "Nature Communications"
DOI: 10.1038/s41467-025-65233-w
Abstract: Compute-in-memory technology offers promising solutions for neural network acceleration but its potential is severely limited by inflexible and resource-intensive analog-to-digital converters. Here, we present a memristor-based analog-to-digital converter featuring adaptive quantization for diverse output distributions.… read more here.
Keywords: memristor based; memory; analog digital; compute memory ... See more keywords
Experimental and modeled analysis of source-line loading effects in NOR flash compute-in-memory arrays
Sign Up to like & getrecommendations! Published in 2025 at "Applied Physics Letters"
DOI: 10.1063/5.0304098
Abstract: We investigate the fundamental electrical mechanisms driving non-ideal current behavior in NOR flash-based compute-in-memory (CIM) arrays. Measurements from an industrial 45 nm NOR flash process identify loading effects as the dominant degradation source. Unlike the conventional… read more here.
Keywords: loading effects; source; compute memory; line ... See more keywords
A Compute-in-Memory Hardware Accelerator Design With Back-End-of-Line (BEOL) Transistor Based Reconfigurable Interconnect
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Journal on Emerging and Selected Topics in Circuits and Systems"
DOI: 10.1109/jetcas.2022.3177577
Abstract: Compute-in-memory (CIM) paradigm using ferroelectric field effect transistor (FeFET) as the weight element is projected to exhibit excellent energy efficiency for accelerating deep neural network (DNN) inference. However, two challenges exist. On the technology level,… read more here.
Keywords: design; compute memory; back end; end line ... See more keywords
A Survey on Binary and Ternary Neural Networks and Their Realization in Compute-in-Memory for Edge Intelligence
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Internet of Things Journal"
DOI: 10.1109/jiot.2025.3633487
Abstract: Deep learning has achieved remarkable success across a wide range of applications, such as language modeling, computer vision, recommendation systems, and robotics. However, the growing size of models and their increasing computational demands pose significant… read more here.
Keywords: binary ternary; extreme quantization; ternary neural; compute memory ... See more keywords
HamQ: Hamming Weight-Based Energy-Aware Quantization for Analog Compute-in-Memory Accelerator in Intelligent Sensors
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Sensors Journal"
DOI: 10.1109/jsen.2024.3382479
Abstract: Compute-in-memory (CIM) has gained prominence as a promising hardware architecture for machine-learning accelerators (MLAs) within the landscape of intelligent sensors (ISs). The acceleration of deep neural networks (DNNs) by MLAs highlights the need for improved… read more here.
Keywords: energy; quantization; model; compute memory ... See more keywords
A 7-nm Compute-in-Memory SRAM Macro Supporting Multi-Bit Input, Weight and Output and Achieving 351 TOPS/W and 372.4 GOPS
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2020.3031290
Abstract: In this work, we present a compute-in-memory (CIM) macro built around a standard two-port compiler macro using foundry 8T bit-cell in 7-nm FinFET technology. The proposed design supports 1024 4 b $\times $ 4 b… read more here.
Keywords: 351 tops; 372 gops; compute memory; macro ... See more keywords
FLEX-CIM: A Flexible Kernel Size 1-GHz 181.6-TOPS/W 25.63-TOPS/mm2 Analog Compute-in-Memory Macro
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2024.3386192
Abstract: Compute-in-memory (CIM) is a promising approach for realizing energy-efficient convolutional neural network (CNN) accelerators. Previous CIM works demonstrated a high peak energy efficiency of over 100 TOPS/W, with larger fabrics of 1000+ channels. Yet, they… read more here.
Keywords: memory; size; energy efficiency; compute memory ... See more keywords
A Multiply-Less Approximate SRAM Compute-In-Memory Macro for Neural-Network Inference
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2024.3433417
Abstract: Compute-in-memory (CIM) is promising in reducing data movement energy and providing large bandwidth for matrix-vector multiplies (MVMs). However, existing work still faces various challenges, such as the digital logic overhead caused by the multiply-add operations… read more here.
Keywords: logic; multiply less; neural network; compute memory ... See more keywords
A 65 nm General-Purpose Compute-in-Memory Processor Supporting Both General Programming and Deep Learning Tasks
Sign Up to like & getrecommendations! Published in 2025 at "IEEE Journal of Solid-State Circuits"
DOI: 10.1109/jssc.2024.3453114
Abstract: This work presents a special unified compute-in-memory (CIM) processor supporting both general-purpose computing and deep neural network (DNN) operations, referred to as the general-purpose CIM (GPCIM) processor. By implementing a unique CIM macro with two… read more here.
Keywords: compute; supporting general; general purpose; compute memory ... See more keywords