Related papers: Block-Wise Mixed-Precision Quantization: Enabling …

Using Resistive Random Access Memory (RRAM) crossbars in Computing-in-Memory (CIM) architectures offers a promising solution to overcome the von Neumann bottleneck. Due to non-idealities like cell variability, RRAM crossbars are often…

The increasing computational demand of Convolutional Neural Networks (CNNs) necessitates energy-efficient acceleration strategies. Compute-in-Memory (CIM) architectures based on Resistive Random Access Memory (RRAM) offer a promising…

Conventional multiply-accumulate (MAC) operations have long dominated computation time for deep neural networks (DNNs), espcially convolutional neural networks (CNNs). Recently, product quantization (PQ) has been applied to these workloads,…

Quantization is a technique for creating efficient Deep Neural Networks (DNNs), which involves performing computations and storing tensors at lower bit-widths than f32 floating point precision. Quantization reduces model size and inference…

Large-scale deep neural networks (DNNs) have achieved remarkable success in many application scenarios. However, high computational complexity and energy costs of modern DNNs make their deployment on edge devices challenging. Model…

Non-volatile memory, such as resistive RAM (RRAM), is an emerging energy-efficient storage, especially for low-power machine learning models on the edge. It is reported, however, that the bit error rate of RRAMs can be up to 3.3% in the…

With an ever-growing number of parameters defining increasingly complex networks, Deep Learning has led to several breakthroughs surpassing human performance. As a result, data movement for these millions of model parameters causes a…

Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs')…

In this paper, we present GradPIM, a processing-in-memory architecture which accelerates parameter updates of deep neural networks training. As one of processing-in-memory techniques that could be realized in the near future, we propose an…

Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e.g. video, audio) at…

Processing-in-memory (PIM) architecture is an inherent match for data analytics application, but we observe major challenges to address when accelerating it using PIM. In this paper, we propose Darwin, a practical LRDIMM-based multi-level…

Quantization is an effective approach to reduce the memory footprint and inference cost of large language models (LLMs), yet maintaining performance in the ultra-low-bit regime remains challenging. Existing post-training methods often…

Bit-serial Processing-In-Memory (PIM) is an attractive paradigm for accelerator architectures, for parallel workloads such as Deep Learning (DL), because of its capability to achieve massive data parallelism at a low area overhead and…

Architectures that incorporate Computing-in-Memory (CiM) using emerging non-volatile memory (NVM) devices have become strong contenders for deep neural network (DNN) acceleration due to their impressive energy efficiency. Yet, a significant…

The increasing complexity and energy demands of deep learning models have highlighted the limitations of traditional computing architectures, especially for edge devices with constrained resources. Spiking Neural Networks (SNNs) offer a…

SRAM-based Analog Compute-in-Memory (ACiM) demonstrates promising energy efficiency for deep neural network (DNN) processing. Nevertheless, efforts to optimize efficiency frequently compromise accuracy, and this trade-off remains…

Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…

To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into low-bitwidth numbers without significant accuracy…

The accuracy of neural networks has greatly improved across various domains over the past years. Their ever-increasing complexity, however, leads to prohibitively high energy demands and latency in von Neumann systems. Several…

The performance and efficiency of running large-scale datasets on traditional computing systems exhibit critical bottlenecks due to the existing "power wall" and "memory wall" problems. To resolve those problems, processing-in-memory (PIM)…