English
Related papers

Related papers: Serving DNN Models with Multi-Instance GPUs: A Cas…

200 papers

NVIDIA MIG (Multi-Instance GPU) allows partitioning a physical GPU into multiple logical instances with fully-isolated resources, which can be dynamically reconfigured. This work highlights the untapped potential of MIG through moldable…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-07-21 Jorge Villarrubia , Luis Costero , Francisco D. Igual , Katzalin Olcoz

Deep learning training is an expensive process that extensively uses GPUs, but not all model training saturates modern powerful GPUs. Multi-Instance GPU (MIG) is a new technology introduced by NVIDIA that can partition a GPU to better-fit…

Machine Learning · Computer Science 2023-04-25 Ties Robroek , Ehsan Yousefzadeh-Asl-Miandoab , Pınar Tözün

Modern GPU workloads increasingly demand efficient resource sharing, as many jobs do not require the full capacity of a GPU. Among sharing techniques, NVIDIA's Multi-Instance GPU (MIG) offers strong resource isolation by enabling…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-12-19 Hsu-Tzu Ting , Jerry Chou , Ming-Hung Chen , I-Hsin Chung

The explosive growth of AI applications has created unprecedented demand for GPU resources. Cloud providers meet this demand through GPU-as-a-Service platforms that offer rentable GPU resources for running AI workloads. In this context, the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-25 Marco Zambianco , Lorenzo Fasol , Roberto Doriguzzi-Corin

New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This technology provides more flexibility for users to support both…

Machine Learning · Computer Science 2023-01-03 Huaizheng Zhang , Yuanming Li , Wencong Xiao , Yizheng Huang , Xing Di , Jianxiong Yin , Simon See , Yong Luo , Chiew Tong Lau , Yang You

Efficient power management in cloud data centers is essential for reducing costs, enhancing performance, and minimizing environmental impact. GPUs, critical for tasks like machine learning (ML) and GenAI, are major contributors to power…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-15 Tirth Vamja , Kaustabha Ray , Felix George , UmaMaheswari C Devi

GPU technology has been improving at an expedited pace in terms of size and performance, empowering HPC and AI/ML researchers to advance the scientific discovery process. However, this also leads to inefficient resource usage, as most GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-10-10 Baolin Li , Tirthak Patel , Siddarth Samsi , Vijay Gadepally , Devesh Tiwari

The extensive use of GPUs in cloud computing and the growing need for multitenancy have driven the development of innovative solutions for efficient GPU resource management. Multi-Instance GPU (MIG) technology from NVIDIA enables shared GPU…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-05 Ahmad Siavashi , Mahmoud Momtazpour

In cloud machine learning (ML) inference systems, providing low latency to end-users is of utmost importance. However, maximizing server utilization and system throughput is also crucial for ML service providers as it helps lower the…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-03-01 Yunseong Kim , Yujeong Choi , Minsoo Rhu

Recent years have witnessed increasing interest in machine learning inferences on serverless computing for its auto-scaling and cost effective properties. Existing serverless computing, however, lacks effective job scheduling methods to…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-04-26 Xinning Hui , Yuanchao Xu , Zhishan Guo , Xipeng Shen

GPU clusters in multi-tenant settings often suffer from underutilization, making GPU-sharing technologies essential for efficient resource use. Among them, NVIDIA Multi-Instance GPU (MIG) has gained traction for providing hardware-level…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-14 Myeongsu Kim , Ikjun Yeom , Younghoon Kim

Giant Deep Neural Networks (DNNs), have become indispensable for accurate and robust support of large-scale cloud based AI services. However, serving giant DNNs is prohibitively expensive from an energy consumption viewpoint easily…

Machine Learning · Computer Science 2025-05-20 Leyang Xue , Yao Fu , Luo Mai , Mahesh K. Marina

Advances in GPU compute throughput and memory capacity brings significant opportunities to a wide range of workloads. However, efficiently utilizing these resources remains challenging, particularly because diverse application…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-10 Gabin Schieffer , Ruimin Shi , Jie Ren , Ivy Peng

NVIDIA's Multi-Instance GPU (MIG) is a feature that enables system designers to reconfigure one large GPU into multiple smaller GPU slices. This work characterizes this emerging GPU and evaluates its effectiveness in designing…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-12-02 Gwangoo Yeo , Jiin Kim , Yujeong Choi , Minsoo Rhu

The increasing size of input graphs for graph neural networks (GNNs) highlights the demand for using multi-GPU platforms. However, existing multi-GPU GNN systems optimize the computation and communication individually based on the…

Distributed, Parallel, and Cluster Computing · Computer Science 2023-06-28 Yuke Wang , Boyuan Feng , Zheng Wang , Tong Geng , Kevin Barker , Ang Li , Yufei Ding

As edge computing expands, serving multiple deep neural network (DNN) models on a single shared GPU has become a common yet challenging scenario, where each scheduling decision affects the tail latency of all concurrent queues. Existing…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-08 Jiahe Cao , Xiaomeng Li , Qiang Liu , Tao Han , Ning Zhang , Weisong Shi

GPU-based heterogeneous architectures are now commonly used in HPC clusters. Due to their architectural simplicity specialized for data-level parallelism, GPUs can offer much higher computational throughput and memory bandwidth than CPUs in…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-05-15 Urvij Saroliya , Eishi Arima , Dai Liu , Martin Schulz

With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-11-30 Fuxun Yu , Shawn Bray , Di Wang , Longfei Shangguan , Xulong Tang , Chenchen Liu , Xiang Chen

We investigate scaling and efficiency of the deep neural network multigrid method (DNN-MG). DNN-MG is a novel neural network-based technique for the simulation of the Navier-Stokes equations that combines an adaptive geometric multigrid…

Numerical Analysis · Mathematics 2021-06-16 Nils Margenberg , Robert Jendersie , Thomas Richter , Christian Lessig

There is an urgent and pressing need to optimize usage of Graphical Processing Units (GPUs), which have arguably become one of the most expensive and sought after IT resources. To help with this goal, several of the current generation of…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-09-11 Bekir Turkkan , Pavankumar Murali , Pavithra Harsha , Rohan Arora , Gerard Vanloo , Chandra Narayanaswami
‹ Prev 1 2 3 10 Next ›