Comprehensive techniques of multi-GPU memory optimization for deep learning acceleration
Sign Up to like & getrecommendations! Published in 2019 at "Cluster Computing"
DOI: 10.1007/s10586-019-02974-6
Abstract: This paper presents a comprehensive suite of techniques for optimized memory management in multi-GPU systems to accelerate deep learning application execution. We employ a hybrid utilization of GPU and CPU memories in a multi-GPU environment… read more here.
Keywords: comprehensive techniques; deep learning; optimization; multi gpu ... See more keywords
Towards an optimized distributed deep learning framework for a heterogeneous multi-GPU cluster
Sign Up to like & getrecommendations! Published in 2020 at "Cluster Computing"
DOI: 10.1007/s10586-020-03144-9
Abstract: This paper presents a novel “Distributed Deep Learning Framework” for a heterogeneous multi-GPU cluster that can effectively improve overall resource utilization without sacrificing training accuracy. Specifically, we employ a hybrid aggregation approach using a parameter-server… read more here.
Keywords: heterogeneous multi; framework; deep learning; multi gpu ... See more keywords
Harnessing the Power of Multi-GPU Acceleration into the Quantum Interaction Computational Kernel Program.
Sign Up to like & getrecommendations! Published in 2021 at "Journal of chemical theory and computation"
DOI: 10.1021/acs.jctc.1c00145
Abstract: We report a new multi-GPU capable ab initio Hartree-Fock/density functional theory implementation integrated into the open source QUantum Interaction Computational Kernel (QUICK) program. Details on the load balancing algorithms for electron repulsion integrals and exchange… read more here.
Keywords: computational kernel; gpu; interaction computational; quantum interaction ... See more keywords
Multinode Multi-GPU Two-Electron Integrals: Code Generation Using the Regent Language.
Sign Up to like & getrecommendations! Published in 2022 at "Journal of chemical theory and computation"
DOI: 10.1021/acs.jctc.2c00414
Abstract: The computation of two-electron repulsion integrals (ERIs) is often the most expensive step of integral-direct self-consistent field methods. Formally it scales as O(N4), where N is the number of Gaussian basis functions used to represent… read more here.
Keywords: multi gpu; multinode; using regent; multinode multi ... See more keywords
A data relocation approach for terrain surface analysis on multi-GPU systems: a case study on the total viewshed problem
Sign Up to like & getrecommendations! Published in 2021 at "International Journal of Geographical Information Science"
DOI: 10.1080/13658816.2020.1844207
Abstract: ABSTRACT Digital Elevation Models (DEMs) are important datasets for modelling the line of sight, such as radio signals, sound waves and human vision. These are commonly analyzed using rotational sweep algorithms. However, such algorithms require… read more here.
Keywords: multi; total viewshed; case; multi gpu ... See more keywords
Priority-Based PCIe Scheduling for Multi-Tenant Multi-GPU Systems
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Computer Architecture Letters"
DOI: 10.1109/lca.2019.2955119
Abstract: Multi-GPU systems are widely used in data centers to provide significant speedups to compute-intensive workloads such as deep neural network training. However, limited PCIe bandwidth between the CPU and multiple GPUs becomes a major performance… read more here.
Keywords: based pcie; pcie scheduling; multi gpu; multi ... See more keywords
GPU-NEST: Characterizing Energy Efficiency of Multi-GPU Inference Servers
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Computer Architecture Letters"
DOI: 10.1109/lca.2020.3023723
Abstract: Cloud inference systems have recently emerged as a solution to the ever-increasing integration of AI-powered applications into the smart devices around us. The wide adoption of GPUs in cloud inference systems has made power consumption… read more here.
Keywords: energy efficiency; inference; gpu inference; multi gpu ... See more keywords
Multi-GPU Efficient Indexing For Maximizing Parallelism of High Dimensional Range Query Services
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Services Computing"
DOI: 10.1109/tsc.2021.3079580
Abstract: Numerous research efforts have been proposed for efficient processing of range queries in high-dimensional space by either redesigning R-tree access structure for exploring massive parallelism on single GPU or exploring distributed framework of R-tree. However,… read more here.
Keywords: multi gpu; parallelism; gpu; range ... See more keywords
Towards the Simulation of a Realistic Large-Scale Spiking Network on a Desktop Multi-GPU System
Sign Up to like & getrecommendations! Published in 2022 at "Bioengineering"
DOI: 10.3390/bioengineering9100543
Abstract: The reproduction of the brain ’sactivity and its functionality is the main goal of modern neuroscience. To this aim, several models have been proposed to describe the activity of single neurons at different levels of… read more here.
Keywords: multi gpu; network; large scale; simulation ... See more keywords