English
Related papers

Related papers: Implementing and Optimizing the Scaled Dot-Product…

200 papers

FPGAs are well-suited for dataflow architectures that process data in a streaming or pipelined manner, thus satisfying the high computational and communication demands of emerging applications. However, manually implementing an efficient…

Hardware Architecture · Computer Science 2026-04-15 Weichuang Zhang , Yiquan Wang , Xinzhou Zhang , Chi Zhang , Yu Feng , Xiaofeng Hou , Chao Li , Jieru Zhao , Minyi Guo

The growth in the number of parameters of Large Language Models (LLMs) has led to a significant surge in computational requirements, making them challenging and costly to deploy. Speculative decoding (SD) leverages smaller models to…

Computation and Language · Computer Science 2025-04-04 Matthieu Zimmer , Milan Gritta , Gerasimos Lampouras , Haitham Bou Ammar , Jun Wang

The attention mechanism of a transformer has a quadratic complexity, leading to high inference costs and latency for long sequences. However, attention matrices are mostly sparse, which implies that many entries may be omitted from…

Machine Learning · Computer Science 2025-11-25 Jeffrey Willette , Heejun Lee , Sung Ju Hwang

Transformers have significantly advanced AI and machine learning through their powerful attention mechanism. However, computing attention on long sequences can become a computational bottleneck. FlashAttention mitigates this by fusing the…

Hardware Architecture · Computer Science 2026-02-10 Kosmas Alexandridis , Giorgos Dimitrakopoulos

The increased usage of Internet of Things devices at the network edge and the proliferation of microservice-based applications create new orchestration challenges in Edge computing. These include detecting overutilized resources and scaling…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-08 Narges Mehran , Nikolay Nikolov , Radu Prodan , Dumitru Roman , Dragi Kimovski , Frank Pallas , Peter Dorfinger

Following the success of dot-product attention in Transformers, numerous approximations have been recently proposed to address its quadratic complexity with respect to the input length. While these variants are memory and compute efficient,…

Computation and Language · Computer Science 2021-06-15 Ankit Gupta , Guy Dar , Shaya Goodman , David Ciprut , Jonathan Berant

Commercial FPGAs, such as AMD Versal devices, increasingly incorporate AI engines that exploit low-precision packed-SIMD fused multiply-accumulate (FMA) to achieve proportional throughput gains. However, trans-precision FMA (e.g.,…

Hardware Architecture · Computer Science 2026-05-11 Jiayi Wang , Maohua Nie , Sin-Chen Lin , C. -J. Richard Shi , Ang Li

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…

Hardware Architecture · Computer Science 2025-02-11 Shantian Qin , Ziqing Qiang , Zhihua Fan , Wenming Li , Xuejun An , Xiaochun Ye , Dongrui Fan

Spiking Neural Networks (SNNs) are increasingly favored for deployment on resource-constrained edge devices due to their energy-efficient and event-driven processing capabilities. However, training SNNs remains challenging because of the…

Hardware Architecture · Computer Science 2025-07-22 Haoxiong Ren , Yangu He , Kwunhang Wong , Rui Bao , Ning Lin , Zhongrui Wang , Dashan Shang

We present a shared memory implementation of a parallel algorithm, called delta-stepping, for solving the single source shortest path problem for directed and undirected graphs. In order to reduce synchronization costs we make some…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-02-21 M. Kranjčević , D. Palossi , S. Pintarelli

The drive towards exascale computing is opening an enormous opportunity for more realistic and precise simulations of natural phenomena. The process of simulation, however, involves not only the numerical computation of predictions but also…

Distributed, Parallel, and Cluster Computing · Computer Science 2018-05-21 Allan Santos , Hermano Lustosa , Fabio Porto , Bruno Schulze

Large language models (LLMs) excel at capturing global token dependencies via self-attention but face prohibitive compute and memory costs on lengthy inputs. While sub-quadratic methods (e.g., linear attention) can reduce these costs, they…

Machine Learning · Computer Science 2025-06-18 Yeonju Ro , Zhenyu Zhang , Souvik Kundu , Zhangyang Wang , Aditya Akella

Transformers have shown dominant performance across a range of domains including language and vision. However, their computational cost grows quadratically with the sequence length, making their usage prohibitive for resource-constrained…

Computation and Language · Computer Science 2023-10-24 Yinghan Long , Sayeed Shafayet Chowdhury , Kaushik Roy

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Yong He , Hongshan Yu , Chaoxu Mu , Mingtao Feng , Tongjia Chen , Zechuan Li , Anwaar Ulhaq , Ajmal Mian

Near-data accelerators (NDAs) that are integrated with main memory have the potential for significant power and performance benefits. Fully realizing these benefits requires the large available memory capacity to be shared between the host…

Hardware Architecture · Computer Science 2020-12-02 Benjamin Y. Cho , Yongkee Kwon , Sangkug Lym , Mattan Erez

Synaptic delay parameterization of neural network models have remained largely unexplored but recent literature has been showing promising results, suggesting the delay parameterized models are simpler, smaller, sparser, and thus more…

Increasing investment in computing technologies and the advancements in silicon technology has fueled rapid growth in advanced driver assistance systems (ADAS) and corresponding SoC developments. An ADAS SoC represents a heterogeneous…

Hardware Architecture · Computer Science 2022-09-14 Hao Luan , Yu Yao , Chang Huang

Modern autoregressive models rely on attention, yet the Softmax full attention in Transformers scales quadratically with sequence length. Sliding Window Attention (SWA) achieves linear-time encoding/decoding by constraining the attention…

Machine Learning · Computer Science 2026-01-08 Jiaxu Liu , Yuhe Bai , Xiangyu Yin , Christos-Savvas Bouganis

Machine comprehension is a representative task of natural language understanding. Typically, we are given context paragraph and the objective is to answer a question that depends on the context. Such a problem requires to model the complex…

Computation and Language · Computer Science 2018-03-28 Zia Hasan , Sebastian Fischer

Attention mechanisms, which enable a neural network to accurately focus on all the relevant elements of the input, have become an essential component to improve the performance of deep neural networks. There are mainly two attention…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Qing-Long Zhang Yu-Bin Yang