Analysis of large deviations behavior of multi-GPU memory access in deep learning

Tamizharasan, P. S.; Ramasubramanian, N.

doi:10.1007/s11227-018-2246-4

Cited by 3 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergence of CUDA as a programming model marked the beginning of the widespread use of GPUs in general-purpose computing. Currently, GPUs are widely used in the area of scientific computing, such as molecular dynamics (MD), direct simulation Monte Carlo (DSMC), CFD, weather forecast (WF), and artificial intelligence (AI) [13][14][15][16][17]. The development of GPU-based parallelization brings increased opportunities and challenges for high-performance computing.…”

Section: Introductionmentioning

confidence: 99%

A Multi‐GPU Parallel Algorithm in Hypersonic Flow Computations

Lai

Tian

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

Computational fluid dynamics (CFD) plays an important role in the optimal design of aircraft and the analysis of complex flow mechanisms in the aerospace domain. The graphics processing unit (GPU) has a strong floating-point operation capability and a high memory bandwidth in data parallelism, which brings great opportunities for CFD. A cell-centred finite volume method is applied to solve three-dimensional compressible Navier–Stokes equations on structured meshes with an upwind AUSM+UP numerical scheme for space discretization, and four-stage Runge–Kutta method is used for time discretization. Compute unified device architecture (CUDA) is used as a parallel computing platform and programming model for GPUs, which reduces the complexity of programming. The main purpose of this paper is to design an extremely efficient multi-GPU parallel algorithm based on MPI+CUDA to study the hypersonic flow characteristics. Solutions of hypersonic flow over an aerospace plane model are provided at different Mach numbers. The agreement between numerical computations and experimental measurements is favourable. Acceleration performance of the parallel platform is studied with single GPU, two GPUs, and four GPUs. For single GPU implementation, the speedup reaches 63 for the coarser mesh and 78 for the finest mesh. GPUs are better suited for compute-intensive tasks than traditional CPUs. For multi-GPU parallelization, the speedup of four GPUs reaches 77 for the coarser mesh and 147 for the finest mesh; this is far greater than the acceleration achieved by single GPU and two GPUs. It is prospective to apply the multi-GPU parallel algorithm to hypersonic flow computations.

show abstract

Section: Introductionmentioning

confidence: 99%

A Multi‐GPU Parallel Algorithm in Hypersonic Flow Computations

Lai

Tian

et al. 2019

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

Design possibilities and challenges of DNN models: a review on the perspective of end devices

2022

View full text Add to dashboard Cite

Research on Classroom Teaching Behavior Analysis and Evaluation System Based on Deep Learning Face Recognition Technology

Yang

2021

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

With the continuous enrichment of educational resources, how to analyze and evaluate classroom teaching behavior has become one of the important indicators to measure teaching quality. Based on this, this article builds a classroom teaching behavior analysis and evaluation system based on deep learning face recognition technology, and conducts professional course classroom behavior analysis, from three perspectives: the concentration of the student’s side face, the concentration of the student’s head down, and the concentration of the eyes. Make judgments. The experimental results show that face recognition technology based on deep learning can effectively judge students’ classroom behavior and facilitate teaching management and implementation.

show abstract

Analysis of large deviations behavior of multi-GPU memory access in deep learning

Cited by 3 publications

References 21 publications

A Multi‐GPU Parallel Algorithm in Hypersonic Flow Computations

A Multi‐GPU Parallel Algorithm in Hypersonic Flow Computations

Design possibilities and challenges of DNN models: a review on the perspective of end devices

Research on Classroom Teaching Behavior Analysis and Evaluation System Based on Deep Learning Face Recognition Technology

Contact Info

Product

Resources

About