Related papers: Computing-In-Memory Dataflow for Minimal Buffer Tr…

This paper investigates hardware-based memory compression designs to increase the memory bandwidth. When lines are compressible, the hardware can store multiple lines in a single memory location, and retrieve all these lines in a single…

Merging mobile edge computing (MEC) functionality with the dense deployment of base stations (BSs) provides enormous benefits such as a real proximity, low latency access to computing resources. However, the envisioned integration creates…

In this paper, we introduce a memory-efficient CNN (convolutional neural network), which enables resource-constrained low-end embedded and IoT devices to perform on-device vision tasks, such as image classification and object detection,…

Ensuring safety in high-speed autonomous vehicles requires rapid control loops and tightly bounded delays from perception to actuation. Many open-source autonomy systems rely on ROS 2 middleware; when multiple sensor and control nodes share…

Recently, analog compute-in-memory (CIM) architectures based on emerging analog non-volatile memory (NVM) technologies have been explored for deep neural networks (DNN) to improve energy efficiency. Such architectures, however, leverage…

Computing-in-Memory (CIM) accelerators are a promising solution for accelerating Machine Learning (ML) workloads, as they perform Matrix-Vector Multiplications (MVMs) on crossbar arrays directly in memory. Although the bit widths of the…

Leveraging the high density and energy efficiency of Compute-In-Memory (CIM) crossbar-based Deep Neural Network (DNN) accelerators requires optimal Design Space Exploration (DSE), which becomes increasingly challenging as complex models for…

Computing-in-memory (CIM) promises to alleviate the Von Neumann bottleneck and accelerate data-intensive applications. Depending on the underlying technology and configuration, CIM enables implementing compute primitives in place, such as…

The expansion of long-context Large Language Models (LLMs) creates significant memory system challenges. While Processing-in-Memory (PIM) is a promising accelerator, we identify that it suffers from critical inefficiencies when scaled to…

Training machine learning algorithms is a computationally intensive process, which is frequently memory-bound due to repeatedly accessing large training datasets. As a result, processor-centric systems (e.g., CPU, GPU) suffer from costly…

Content Addressable Memories (CAMs) are considered a key-enabler for in-memory computing (IMC). IMC shows order of magnitude improvement in energy efficiency and throughput compared to traditional computing techniques. Recently, analog CAMs…

Multimodal Transformers are emerging artificial intelligence (AI) models designed to process a mixture of signals from diverse modalities. Digital computing-in-memory (CIM) architectures are considered promising for achieving high…

Processing-in-Memory (PIM) has emerged as a promising computing paradigm to address the memory wall and the fundamental bottleneck of the von Neumann architecture by reducing costly data movement between memory and processing units. As with…

Modern Artificial Intelligence (AI) applications are increasingly utilizing multi-tenant deep neural networks (DNNs), which lead to a significant rise in computing complexity and the need for computing parallelism. ReRAM-based…

Deploying pretrained visual models in real-world environments often suffers from significant performance degradation due to the diversity of testing scenarios. Continuous adaptation of learning models on edge devices via unlabeled data…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge retrieval but faces challenges on edge devices due to high storage, energy, and latency demands. Computing-in-Memory (CIM) offers a…

Convolution is the most time-consuming operation in deep neural network operations, so its performance is critical to the overall performance of the neural network. The commonly used methods for convolution on GPU include the general matrix…

Large Language Models (LLMs) such as LLaMA and DeepSeek, are built on transformer architectures, which have become a standard model for achieving state-of-the-art performance in natural language processing tasks. Recently, there has been…

Compute-Near-Memory (CNM) systems offer a promising approach to mitigate the von Neumann bottleneck by bringing computational units closer to data. However, optimizing for these architectures remains challenging due to their unique hardware…

Machine learning inference engine is of great interest to smart edge computing. Compute-in-memory (CIM) architecture has shown significant improvements in throughput and energy efficiency for hardware acceleration. Emerging non-volatile…