中文
相关论文

相关论文: CompPow: A Case for Component-level GPU Power Mana…

200 篇论文

Three-dimensional integrated circuits promise power, performance, and footprint gains compared to their 2D counterparts, thanks to drastic reductions in the interconnects' length through their smaller form factor. We can leverage the…

Scientists are increasingly exploring and utilizing the massive parallelism of general-purpose accelerators such as GPUs for scientific breakthroughs. As a result, datacenters, hyperscalers, national computing centers, and supercomputers…

分布式、并行与集群计算 · 计算机科学 2022-11-10 Prasoon Sinha , Akhil Guliani , Rutwik Jain , Brandon Tran , Matthew D. Sinclair , Shivaram Venkataraman

Power management is an expensive and important issue for large computational infrastructures such as datacenters, large clusters, and computational grids. However, measuring energy consumption of scalable systems may be impractical due to…

机器学习 · 计算机科学 2017-09-20 Lucas Venezian Povoa , Cesar Marcondes , Hermes Senger

The rapid development in scientific research provides a need for more compute power, which is partly being solved by GPUs. This paper presents a microarchitectural analysis of the modern NVIDIA Blackwell architecture by studying GPU…

分布式、并行与集群计算 · 计算机科学 2025-07-23 Aaron Jarmusch , Nathan Graddon , Sunita Chandrasekaran

Increased reliance on graphics processing units (GPUs) for high-intensity computing tasks raises challenges regarding energy consumption. To address this issue, dynamic voltage and frequency scaling (DVFS) has emerged as a promising…

性能 · 计算机科学 2024-07-19 Qiang Wang , Laiyi Li , Weile Luo , Yijia Zhang , Bingqiang Wang

Evolutionary computing (EC) has proven to be effective in solving complex optimization and robotics problems. Unfortunately, typical Evolutionary Algorithms (EAs) are constrained by the computational capacity available to researchers. More…

分布式、并行与集群计算 · 计算机科学 2025-02-19 Rustam Eynaliyev , Houcen Liu

The growing demand for computational resources in machine learning has made efficient resource allocation a critical challenge, especially in heterogeneous hardware clusters where devices vary in capability, age, and energy efficiency.…

分布式、并行与集群计算 · 计算机科学 2025-10-20 Ahmad Raeisi , Mahdi Dolati , Sina Darabi , Sadegh Talebi , Patrick Eugster , Ahmad Khonsari

Graphics processing units (GPUs) can improve deep neural network inference throughput via batch processing, where multiple tasks are concurrently processed. We focus on novel scenarios that the energy-constrained mobile devices offload…

分布式、并行与集群计算 · 计算机科学 2022-06-14 Wenqi Shi , Sheng Zhou , Zhisheng Niu , Miao Jiang , Lu Geng

GPUs have become the dominant source of computing power for high performance computing and are increasingly being used across the High Energy Physics computing landscape for a wide variety of tasks. Though NVIDIA is currently the main…

GPUs rely on large register files to unlock thread-level parallelism for high throughput. Unfortunately, large register files are power hungry, making it important to seek for new approaches to improve their utilization. This paper…

硬件体系结构 · 计算机科学 2020-12-10 Alexandra Angerd , Erik Sintorn , Per Stenström

Most relatively modern desktop or even laptop computers contain a graphics card useful for more than showing colors on a screen. In this paper, we make a case for why you should learn enough about GPU (graphics processing unit) computing to…

计算物理 · 物理学 2013-05-17 Knut Skogstrand Gjerden

To mitigate the increasingly common underutilization of computational resources in modern GPUs, spatial sharing methods enable multiple applications to use them simultaneously. This work presents a comprehensive evaluation of NVIDIA's…

分布式、并行与集群计算 · 计算机科学 2026-04-30 Jorge Villarrubia , Luis Costero , Francisco D. Igual , Katzalin Olcoz

The unabated growth in AI workload demands is driving the need for concerted advances in compute, memory, and interconnect performance. As traditional semiconductor scaling slows, high-speed interconnects have emerged as the new scaling…

硬件体系结构 · 计算机科学 2025-10-21 Mikhail Bernadskiy , Peter Carson , Thomas Graham , Taylor Groves , Ho John Lee , Eric Yeh

Amid the rapid advancements in large machine learning (ML) models, universities worldwide are investing substantial funds and efforts into GPU clusters. However, managing a shared GPU cluster poses a pyramid of challenges, from hardware…

分布式、并行与集群计算 · 计算机科学 2025-05-15 Kaiqiang Xu , Decang Sun , Hao Wang , Zhenghang Ren , Xinchen Wan , Xudong Liao , Zilong Wang , Junxue Zhang , Kai Chen

Although cloud computing has been transformational to the IT industry, it is built on large data centres that often consume massive amounts of electrical power. Efforts have been made to reduce the energy clouds consume, with certain data…

分布式、并行与集群计算 · 计算机科学 2014-08-28 Francois Rossigneux , Jean-Patrick Gelas , Laurent Lefevre , Marcos Dias de Assuncao

The latest trends in high-performance computing systems show an increasing demand on the use of a large scale multicore systems in a efficient way, so that high compute-intensive applications can be executed reasonably well. However, the…

分布式、并行与集群计算 · 计算机科学 2013-02-25 Juliana M. N. Silva , Cristina Boeres , Lúcia M. A. Drummond , Artur A. Pessoa

Modern LLM serving systems confront inefficient GPU utilization due to the fundamental mismatch between compute-intensive prefill and memory-bound decode phases. While current practices attempt to address this by organizing these phases…

分布式、并行与集群计算 · 计算机科学 2025-09-29 Zejia Lin , Hongxin Xu , Guanyi Chen , Zhiguang Chen , Yutong Lu , Xianwei Zhang

As neural networks (NN) are deployed across diverse sectors, their energy demand correspondingly grows. While several prior works have focused on reducing energy consumption during training, the continuous operation of ML-powered systems…

机器学习 · 计算机科学 2024-01-10 Minghao Yan , Hongyi Wang , Shivaram Venkataraman

Power is increasingly becoming a limiting resource in high-performance, GPU-accelerated computing systems. Understanding the range and sources of power variation is essential in setting realistic bounds on rack and system peak power, and…

分布式、并行与集群计算 · 计算机科学 2022-12-20 Sridutt Bhalachandra , Brian Austin , Samuel Williams , Nicholas J. Wright

Efficient use of energy is essential for today's supercomputing systems, as energy cost is generally a major component of their operational cost. Research into "green computing" is needed to reduce the environmental impact of running these…

性能 · 计算机科学 2022-11-08 Stefano Corda , Bram Veenboer , Emma Tolley