English
Related papers

Related papers: ReFloat: Low-Cost Floating-Point Processing in ReR…

200 papers

Recent advances in vision transformers (ViTs) have demonstrated the advantage of global modeling capabilities, prompting widespread integration of large-kernel convolutions for enlarging the effective receptive field (ERF). However, the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-31 Mingshu Zhao , Yi Luo , Yong Ouyang

This paper introduces channel gating, a dynamic, fine-grained, and hardware-efficient pruning scheme to reduce the computation cost for convolutional neural networks (CNNs). Channel gating identifies regions in the features that contribute…

Machine Learning · Computer Science 2019-10-30 Weizhe Hua , Yuan Zhou , Christopher De Sa , Zhiru Zhang , G. Edward Suh

Flow matching has emerged as a promising generative approach that addresses the lengthy sampling times associated with state-of-the-art diffusion models and enables a more flexible trajectory design, while maintaining high-quality image…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Arnela Hadzic , Franz Thaler , Lea Bogensperger , Simon Johannes Joham , Martin Urschler

Today, almost all computer systems use IEEE-754 floating point to represent real numbers. Recently, posit was proposed as an alternative to IEEE-754 floating point as it has better accuracy and a larger dynamic range. The configurable…

Hardware Architecture · Computer Science 2021-04-13 Varun Gohil , Sumit Walia , Joycee Mekie , Manu Awasthi

Processing-in-memory (PIM) has emerged as an enabler for the energy-efficient and high-performance acceleration of deep learning (DL) workloads. Resistive random-access memory (ReRAM) is one of the most promising technologies to implement…

Hardware Architecture · Computer Science 2024-03-29 Harsh Sharma , Gaurav Narang , Janardhan Rao Doppa , Umit Ogras , Partha Pratim Pande

In recent years, half precision floating-point arithmetic has gained wide support in hardware and software stack thanks to the advance of artificial intelligence and machine learning applications. Operating at half precision can…

Numerical Analysis · Mathematics 2024-09-19 Longfei Gao , Kevin Harms

Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Shivam Aggarwal , Hans Jakob Damsgaard , Alessandro Pappalardo , Giuseppe Franco , Thomas B. Preußer , Michaela Blott , Tulika Mitra

Deformable Attention Transformers (DAT) have shown remarkable performance in computer vision tasks by adaptively focusing on informative image regions. However, their data-dependent sampling mechanism introduces irregular memory access…

Computer Vision and Pattern Recognition · Computer Science 2025-07-29 Wendong Mao , Mingfan Zhao , Jianfeng Guan , Qiwei Dong , Zhongfeng Wang

Modern high-performance computing (HPC) increasingly relies on GPUs, but integrating GPU acceleration into complex scientific frameworks like OpenFOAM remains a challenge. Existing approaches either fully refactor the codebase or use…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-10-10 Gregor Olenik , Marcel Koch , Hartwig Anzt

As large language models (LLMs) grow in parameter size and context length, computation precision has been reduced from 16-bit to 4-bit to improve inference efficiency. However, this reduction causes accuracy degradation due to activation…

Artificial Intelligence · Computer Science 2025-06-02 Janghwan Lee , Jiwoong Park , Jinseok Kim , Yongjik Kim , Jungju Oh , Jinwook Oh , Jungwook Choi

Computational Fluid Dynamics (CFD) simulations are often constrained by the memory-bound nature of sparse matrix-vector operations, which eventually limits performance on modern high-performance computing (HPC) systems. This work introduces…

Residual neural networks are widely used in computer vision tasks. They enable the construction of deeper and more accurate models by mitigating the vanishing gradient problem. Their main innovation is the residual block which allows the…

Hardware Architecture · Computer Science 2023-11-03 Filippo Minnella , Teodoro Urso , Mihai T. Lazarescu , Luciano Lavagno

The present paper investigates high performance computing abilities of OpenFOAM for a low Reynolds number ($Re_D=2000$) axisymmetric jet subject to multiple zero net mass flux (ZNMF) actuators. First, parallel performance of OpenFOAM is…

Fluid Dynamics · Physics 2014-06-30 Asim Önder , Johan Meyers

This paper investigates the relationship between mapping style and device roadmap in Resistive Random Access Memory (ReRAM) architectures for neuromorphic computing. The study leverages simulations using DNN+NeuroSim to evaluate the impact…

Emerging Technologies · Computer Science 2023-07-17 Enrico F. Persico

With the staggering increase of edge compute applications like Internet-of-Things (IoT) and artificial intelligence (AI), the demand for fast, energy-efficient on-chip memory is growing. While the fast and mature static random-access memory…

Emerging Technologies · Computer Science 2026-03-30 Albi Mema , Simon Thomann , Narendra Singh Dhakad , Hussam Amrouch

The increasing need for compact and low-power computing solutions for machine learning applications has triggered significant interest in energy-efficient neuromorphic systems. However, most of these architectures rely on spiking neural…

Neural and Evolutionary Computing · Computer Science 2019-12-23 Manu V Nair , Giacomo Indiveri

Residual block is a very common component in recent state-of-the art CNNs such as EfficientNet or EfficientDet. Shortcut data accounts for nearly 40% of feature-maps access in ResNet152 [8]. Most of the previous DNN compilers, accelerators…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-03-08 Duy Thanh Nguyen , Hyeonseung Je , Tuan Nghia Nguyen , Soojung Ryu , Kyujoong Lee , Hyuk-Jae Lee

This paper describes REAP, a software-hardware approach that enables high performance sparse linear algebra computations on a cooperative CPU-FPGA platform. REAP carefully separates the task of organizing the matrix elements from the…

Distributed, Parallel, and Cluster Computing · Computer Science 2020-04-30 Mohammadreza Soltaniyeh , Richard P. Martin , Santosh Nagarakatte

Resistive Random Access Memory (ReRAM) based Processing In Memory (PIM) Accelerator has emerged as a promising computing architecture for memory intensive applications, such as Deep Neural Networks (DNNs). However, due to its immaturity,…

Emerging Technologies · Computer Science 2023-12-19 Je-Woo Jang , Thai-Hoang Nguyen , Joon-Sung Yang

Efficient and accurate algorithms are necessary to reconstruct particles in the highly granular detectors anticipated at the High-Luminosity Large Hadron Collider and the Future Circular Collider. We study scalable machine learning models…

Data Analysis, Statistics and Probability · Physics 2024-07-17 Joosep Pata , Eric Wulff , Farouk Mokhtar , David Southwick , Mengke Zhang , Maria Girone , Javier Duarte