中文
相关论文

相关论文: GREENER: A Tool for Improving Energy Efficiency of…

200 篇论文

This paper introduces a distributed, GPU-centric experience replay system, GEAR, designed to perform scalable reinforcement learning (RL) with large sequence models (such as transformers). With such models, existing systems such as Reverb…

机器学习 · 计算机科学 2023-10-10 Hanjing Wang , Man-Kit Sit , Congjie He , Ying Wen , Weinan Zhang , Jun Wang , Yaodong Yang , Luo Mai

Over the lifetime of a computing task, determining the maximum usage of random-access memory (RAM) on both the motherboard and on a graphical processing unit (GPU), as well as the utilization percentage of the central processing unit (CPU)…

性能 · 计算机科学 2025-06-27 Erik D. Huckvale , Hunter N. B. Moseley

Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as…

分布式、并行与集群计算 · 计算机科学 2016-06-15 Javier Prades , Blesson Varghese , Carlos Reano , Federico Silla

GPUs are the most popular platform for accelerating HPC workloads, such as artificial intelligence and science simulations. However, most microarchitectural research in academia relies on GPU core pipeline designs based on architectures…

硬件体系结构 · 计算机科学 2025-10-30 Rodrigo Huerta , Mojtaba Abaie Shoushtary , José-Lorenzo Cruz , Antonio González

Energy-efficiency is a key concern for neural network applications. To alleviate this issue, hardware acceleration using FPGAs or GPUs can provide better energy-efficiency than general-purpose processors. However, further improvement of the…

分布式、并行与集群计算 · 计算机科学 2021-06-29 Seyed Morteza Nabavinejad , Behzad Salami

Registers are the fastest memory components within the GPU's complex memory hierarchy, accessed by names rather than addresses. They are managed entirely by the compiler through a process called register allocation, during which the…

分布式、并行与集群计算 · 计算机科学 2025-01-28 Deniz Elbek , Kamer Kaya

Future computing systems, from handhelds to supercomputers, will undoubtedly be more parallel and heterogeneous than todays systems to provide more performance and energy efficiency. Thus, GPUs are increasingly being used to accelerate…

分布式、并行与集群计算 · 计算机科学 2019-10-18 Saeed Taheri , Apan Qasem , Martin Burtscher

GPUs have become indispensable in high-performance computing, machine learning, and many other domains. Efficiently utilizing the memory subsystem on GPUs is critical for maximizing computing power through massive parallelism. Analyzing…

分布式、并行与集群计算 · 计算机科学 2025-07-28 Yanbo Zhao , Jinku Cui , Zecheng Li , Shuyin Jiao , Xu Liu , Jiajia Li

Developing efficient GPU kernels can be difficult because of the complexity of GPU architectures and programming models. Existing performance tools only provide coarse-grained suggestions at the kernel level, if any. In this paper, we…

性能 · 计算机科学 2020-11-25 Keren Zhou , Xiaozhu Meng , Ryuichi Sai , John Mellor-Crummey

The energy requirements of current natural language processing models continue to grow at a rapid, unsustainable pace. Recent works highlighting this problem conclude there is an urgent need for methods that reduce the energy needs of NLP…

计算与语言 · 计算机科学 2023-05-03 Joseph McDonald , Baolin Li , Nathan Frey , Devesh Tiwari , Vijay Gadepally , Siddharth Samsi

Modern GPU applications, such as machine learning (ML), can only partially utilize GPUs, leading to GPU underutilization in cloud environments. Sharing GPUs across multiple applications from different tenants can improve resource…

分布式、并行与集群计算 · 计算机科学 2024-10-17 Manos Pavlidakis , Giorgos Vasiliadis , Stelios Mavridis , Anargyros Argyros , Antony Chazapis , Angelos Bilas

Graph neural networks (GNNs) start to gain momentum after showing significant performance improvement in a variety of domains including molecular science, recommendation, and transportation. Turning such performance improvement of GNNs into…

硬件体系结构 · 计算机科学 2021-07-20 Zhihui Zhang , Jingwen Leng , Shuwen Lu , Youshan Miao , Yijia Diao , Minyi Guo , Chao Li , Yuhao Zhu

The Long-Short-Term-Memory Recurrent Neural Networks (LSTM RNNs) are a popular class of machine learning models for analyzing sequential data. Their training on modern GPUs, however, is limited by the GPU memory capacity. Our profiling…

机器学习 · 计算机科学 2019-12-02 Bojian Zheng , Abhishek Tiwari , Nandita Vijaykumar , Gennady Pekhimenko

In recent years, the energy consumption of computing systems has increased and a large fraction of this energy is consumed in main memory. Towards this, researchers have proposed use of non-volatile memory, such as phase change memory…

硬件体系结构 · 计算机科学 2013-09-17 Sparsh Mittal

Graph Neural Networks (GNNs) show strong promise for circuit analysis, but scaling to modern large-scale circuit graphs is limited by GPU memory and training cost, especially for deep models. We revisit deep GNNs for circuit graphs and show…

机器学习 · 计算机科学 2026-03-31 Yuebo Luo , Shiyang Li , Yifei Feng , Vishal Kancharla , Shaoyi Huang , Caiwen Ding

GPGPU architectures have become established as the dominant parallelization and performance platform achieving exceptional popularization and empowering domains such as regular algebra, machine learning, image detection and self-driving…

硬件体系结构 · 计算机科学 2022-03-17 Albert Segura , Jose-Maria Arnau , Antonio Gonzalez

Recent advances in multi and many-core processors have led to significant improvements in the performance of scientific computing applications. However, the addition of a large number of complex cores have also increased the overall power…

分布式、并行与集群计算 · 计算机科学 2023-02-23 Akash Dutta , Jee Choi , Ali Jannesari

The GPU programming model is primarily aimed at the development of applications that run one GPU. However, this limits the scalability of GPU code to the capabilities of a single GPU in terms of compute power and memory capacity. To scale…

分布式、并行与集群计算 · 计算机科学 2022-03-03 Stijn Heldens , Pieter Hijma , Ben van Werkhoven , Jason Maassen , Rob. V. van Nieuwpoort

In the future, embedded processors must process more computation-intensive network applications and internet traffic and packet-processing tasks become heavier and sophisticated. Since the processor performance is severely related to the…

硬件体系结构 · 计算机科学 2012-05-10 Mehdi Alipour , Mostafa E. Salehi , Hesamodin shojaei baghini

The energy efficiency of neural processing units (NPU) is playing a critical role in developing sustainable data centers. Our study with different generations of NPU chips reveals that 30%-72% of their energy consumption is contributed by…

硬件体系结构 · 计算机科学 2025-10-07 Yuqi Xue , Jian Huang