English
Related papers

Related papers: CHARM: Composing Heterogeneous Accelerators for Ma…

200 papers

To overcome the well-known memory bottleneck of AI chips, 3D stacked architectures that employ advanced packaging technology with high-density through-silicon vias (TSVs) pins have proven to be a promising solution. The 3D-stacked AI chip…

Hardware Architecture · Computer Science 2026-04-30 Yiqi Liu , Noelle Crawford , Michael Wang , Jilong Xue , Jian Huang

This paper presents a novel architecture utilizing a 10T SRAM cell for XNOR-based in-memory computing, aimed at mitigating the extensive routing challenges typically encountered in conventional in-memory computing systems. By integrating a…

Hardware Architecture · Computer Science 2026-05-18 Narendra Singh Dhakad , Santosh Kumar Vishvakarma

General Matrix Multiplication (GEMM) is a critical kernel in high-performance computing and deep learning. While modern architectures like ARM's Scalable Matrix Extension (SME) introduce dedicated hardware for matrix operations, existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-29 Chencheng Deng , Weiling Yang , Jianbin Fang , Dezun Dong

The emergence of Phase-Change Memory (PCM) provides opportunities for directly connecting persistent memory to main memory bus. While PCM achieves high read throughput and low standby power, the critical concerns are its poor write…

Hardware Architecture · Computer Science 2020-07-28 Yinjin Fu

In-memory database query processing frequently involves substantial data transfers between the CPU and memory, leading to inefficiencies due to Von Neumann bottleneck. Processing-in-Memory (PIM) architectures offer a viable solution to…

The rapid adoption of large language models (LLMs) is pushing AI accelerators toward increasingly powerful and specialized designs. Instead of further complicating software development with deeply hierarchical scratchpad memories (SPMs) and…

Hardware Architecture · Computer Science 2025-12-09 Zhongchun Zhou , Chengtao Lai , Yuhang Gu , Wei Zhang

The rapid advancement of machine learning (ML) technologies has driven the development of specialized hardware accelerators designed to facilitate more efficient model training. This paper introduces the CARAML benchmark suite, which is…

Hardware Architecture · Computer Science 2025-03-14 Chelsea Maria John , Stepan Nassyr , Carolin Penke , Andreas Herten

As the landscape of deep neural networks evolves, heterogeneous dataflow accelerators, in the form of multi-core architectures or chiplet-based designs, promise more flexibility and higher inference performance through scalability. So far,…

Hardware Architecture · Computer Science 2025-10-08 Arne Symons , Linyan Mei , Steven Colleman , Pouya Houshmand , Sebastian Karl , Marian Verhelst

Efficient AI inference on AMD's Versal AI Engine (AIE) is challenging due to tightly coupled VLIW execution, explicit datapaths, and local memory management. Prior work focused on first-generation AIE kernel optimizations, without tackling…

We develop and implement in this paper a fast sparse assembly algorithm, the fundamental operation which creates a compressed matrix from raw index data. Since it is often a quite demanding and sometimes critical operation, it is of…

Distributed, Parallel, and Cluster Computing · Computer Science 2016-04-28 Stefan Engblom , Dimitar Lukarski

The GEneral Matrix Multiplication (GEMM) is one of the essential algorithms in scientific computing. Single-thread GEMM implementations are well-optimised with techniques like blocking and autotuning. However, due to the complexity of…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-01-15 Yufan Xia , Marco De La Pierre , Amanda S. Barnard , Giuseppe Maria Junior Barca

Neural network (NN) accelerators with multi-chip-module (MCM) architectures enable integration of massive computation capability; however, they face challenges of computing resource underutilization and off-chip communication overheads.…

Hardware Architecture · Computer Science 2026-02-17 Zongle Huang , Hongyang Jia , Kaiwei Zou , Yongpan Liu

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy,…

The sparse Mixture-of-Experts (MoE) architecture is increasingly favored for scaling Large Language Models (LLMs) efficiently, but it depends on heterogeneous compute and memory resources. These factors jointly affect system Cost, Accuracy,…

The demand for computation resources and energy efficiency of Convolutional Neural Networks (CNN) applications requires a new paradigm to overcome the "Memory Wall". Analog In-Memory Computing (AIMC) is a promising paradigm since it…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-11-24 Nazareno Bruschi , Giuseppe Tagliavini , Angelo Garofalo , Francesco Conti , Irem Boybat , Luca Benini , Davide Rossi

High-performance sparse matrix-matrix (SpMM) multiplication is paramount for science and industry, as the ever-increasing sizes of data prohibit using dense data structures. Yet, existing hardware, such as Tensor Cores (TC), is ill-suited…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-08-22 Patrik Okanovic , Grzegorz Kwasniewski , Paolo Sylos Labini , Maciej Besta , Flavio Vella , Torsten Hoefler

The use of Air traffic management (ATM) simulators for planing and operations can be challenging due to their modelling complexity. This paper presents XALM (eXplainable Active Learning Metamodel), a three-step framework integrating active…

The rapid advancements in artificial intelligence (AI), particularly the Large Language Models (LLMs), have profoundly affected our daily work and communication forms. However, it is still a challenge to deploy LLMs on resource-constrained…

Hardware Architecture · Computer Science 2025-03-03 Mingqiang Huang , Ao Shen , Kai Li , Haoxiang Peng , Boyu Li , Yupeng Su , Hao Yu

Modern central processing units (CPUs) feature single-instruction, multiple-data pipelines to accelerate compute-intensive floating-point and fixed-point workloads. Traditionally, these pipelines and corresponding instruction set…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-30 Stefan Remke , Alexander Breuer

To address the challenge of performance portability, and facilitate the implementation of electronic structure solvers, we developed the Basic Matrix Library (BML) and Parallel, Rapid O(N) and Graph-based Recursive Electronic Structure…