English
Related papers

Related papers: Toward matrix multiplication for deep learning inf…

200 papers

General matrix-vector multiplication (GeMV) remains a critical latency bottleneck in large language model (LLM) inference, even with quantized low-bit models. Processing-Using-DRAM (PUD), an analog in-DRAM computing technique, has the…

Hardware Architecture · Computer Science 2025-09-24 Tatsuya Kubo , Daichi Tokuda , Tomoya Nagatani , Masayuki Usui , Lei Qu , Ting Cao , Shinya Takamaeda-Yamazaki

Large Language Model (LLM) inference requires substantial computational resources, yet CPU-based inference remains essential for democratizing AI due to the widespread availability of CPUs compared to specialized accelerators. However,…

Hardware Architecture · Computer Science 2025-10-01 Jingyao Zhang , Jaewoo Park , Jongeun Lee , Elaheh Sadredini

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…

Extreme learning machine (ELM), proposed by Huang et al., has been shown a promising learning algorithm for single-hidden layer feedforward neural networks (SLFNs). Nevertheless, because of the random choice of input weights and biases, the…

Neural and Evolutionary Computing · Computer Science 2014-09-16 Yuguang Wang , Feilong Cao , Yubo Yuan

Dense linear algebra kernels are critical for wireless applications, and the oncoming proliferation of 5G only amplifies their importance. Many such matrix algorithms are inductive, and exhibit ample amounts of fine-grain ordered…

Distributed, Parallel, and Cluster Computing · Computer Science 2019-05-16 Jian Weng , Vidushi Dadu , Tony Nowatzki

Optical and optoelectronic approaches of performing matrix-vector multiplication (MVM) operations have shown the great promise of accelerating machine learning (ML) algorithms with unprecedented performance. The incorporation of…

Emerging Technologies · Computer Science 2020-12-04 Weilu Gao , Cunxi Yu , Ruiyang Chen

With unprecedented demand for generative AI (GenAI) inference, acceleration of primitives that dominate GenAI such as general matrix-vector multiplication (GEMV) is receiving considerable attention. A challenge with GEMVs is the high memory…

Hardware Architecture · Computer Science 2024-04-02 Mohamed Assem Ibrahim , Mahzabeen Islam , Shaizeen Aga

General Matrix Multiplication or GEMM kernels take centre place in high performance computing and machine learning. Recent NVIDIA GPUs include GEMM accelerators, such as NVIDIA's Tensor Cores. Their exploitation is hampered by the…

Mathematical Software · Computer Science 2021-11-23 Thomas Faingnaert , Tim Besard , Bjorn De Sutter

Sliding Window Sum algorithms have been successfully used for training and inference of Deep Neural Networks. We have shown before how both pooling and convolution 1-D primitives could be expressed as sliding sums and evaluated by the…

Machine Learning · Computer Science 2023-10-10 Roman Snytsar

Extreme Learning Machine (ELM) is an efficient and effective least-square-based learning algorithm for classification, regression problems based on single hidden layer feed-forward neural network (SLFN). It has been shown in the literature…

Machine Learning · Computer Science 2020-11-05 Ramesh Ragala , Bharadwaja kumar

Among ML operators today, GEneralMatrix Multiplication (GEMM)-based operators are known to be key operators that build the main backbone of ML models. As their computational overhead dominates the overall execution time (e.g., 42.8% - 96.6%…

Hardware Architecture · Computer Science 2025-04-17 Rachid Karami , Sheng-Chun Kao , Hyoukjun Kwon

Extreme Learning Machines (ELM) provide a fast alternative to traditional gradient-based learning in neural networks, offering rapid training and robust generalization capabilities. Its theoretical basis shows its universal approximation…

Machine Learning · Computer Science 2024-06-27 Ergun Biçici

With the rapid growth of deep neural networks (DNNs), compute-in-memory (CIM) has emerged as a promising energy-efficient paradigm for accelerating multiply-and-accumulate (MAC) operations. Yet, current CIM architectures are largely limited…

Hardware Architecture · Computer Science 2026-04-16 Subhradip Chakraborty , Ankur Singh , Akhilesh R. Jaiswal

One of the most important and commonly used operations in many linear algebra functions is matrix-matrix multiplication (GEMM), which is also a key component in obtaining high performance of many scientific codes. It is a computationally…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-03-18 Nenad Mijić , Davor Davidović

The inherent diversity of computation types within the deep neural network (DNN) models often requires a variety of specialized units in hardware processors, which limits computational efficiency, increasing both inference latency and power…

Machine Learning · Computer Science 2024-08-21 Ruiqi Sun , Siwei Ye , Jie Zhao , Xin He , Jianzhe Lin , Yiran Li , An Zou

Deep Neural Networks (DNNs) and Large Language Models (LLMs) have revolutionized artificial intelligence, yet their deployment faces significant memory and computational challenges, especially in resource-constrained environments.…

Hardware Architecture · Computer Science 2025-04-24 Cong Guo , Chiyue Wei , Jiaming Tang , Bowen Duan , Song Han , Hai Li , Yiran Chen

Deep learning frameworks commonly implement convolution operators with GEMM-based algorithms. In these algorithms, convolution is implemented on top of matrix-matrix multiplication (GEMM) functions, provided by highly optimized BLAS…

Computer Vision and Pattern Recognition · Computer Science 2019-07-05 Marat Dukhan

Generalized sparse matrix-matrix multiplication (or SpGEMM) is a key primitive for many high performance graph algorithms as well as for some linear solvers, such as algebraic multigrid. Here we show that SpGEMM also yields efficient…

Distributed, Parallel, and Cluster Computing · Computer Science 2015-03-19 Aydin Buluc , John Gilbert

Matrix multiplication (GEMM) is a core operation to numerous scientific applications. Traditional implementations of Strassen-like fast matrix multiplication (FMM) algorithms often do not perform well except for very large matrix sizes, due…

Mathematical Software · Computer Science 2016-11-04 Jianyu Huang , Leslie Rice , Devin A. Matthews , Robert A. van de Geijn

Optical architectures have been emerging as an energy-efficient and high-throughput hardware platform to accelerate computationally intensive general matrix-matrix multiplications (GEMMs) in modern machine learning (ML) algorithms. However,…

Emerging Technologies · Computer Science 2022-04-01 Jichao Fan , Yingheng Tang , Weilu Gao