Multifold Acceleration of Neural Network Computations Using GPU

被引：0

作者：

Guzhva, Alexander ^{[1
]}

Dolenko, Sergey ^{[1
]}

Persiantsev, Igor ^{[1
]}

机构：

[1] Moscow MV Lomonosov State Univ, DV Skobeltsyn Inst Nucl Phys, Moscow 119991, Russia

来源：

ARTIFICIAL NEURAL NETWORKS - ICANN 2009, PT I | 2009年 / 5768卷

关键词：

GPGPU; neural networks; perceptron; NVIDIA CUDA; parallel computations;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

With emergence of graphics processing units (CPU) of the latest generation, it became possible to undertake neural network based computations using CPU on serially produced video display adapters. In this study, NVIDIA CUDA technology has been used to implement standard back-propagation algorithm for training multiple perceptrons simultaneously on CPU. For the problem considered, CPU-based implementation (on NVIDIA CTX 260 CPU) has lead to a 50x speed increase compared to a highly optimized CPU-based computer program, and more than 150x compared to a commercially available CPU-based software (Neuro Shell 2) (AMD Athlon 64 Dual core 6000+ processor).

引用

页码：373 / 380

页数：8

共 50 条

[1] A Note on the GPU Acceleration of Eigenvalue Computations
Rupp, K.
Tillet, Ph
Smith, B. F.
Grasser, T.
Juengel, A.
11TH INTERNATIONAL CONFERENCE OF NUMERICAL ANALYSIS AND APPLIED MATHEMATICS 2013, PTS 1 AND 2 (ICNAAM 2013), 2013, 1558 : 1536 - 1539
[2] Acceleration of Neural Network Inference for Embedded GPU Systems
Terakura, Kei
Chang, Qiong
Miyazaki, Jun
2024 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING, IEEE BIGCOMP 2024, 2024, : 361 - 362
[3] Neural Acceleration for GPU Throughput Processors
Yazdanbakhsh, Amir
Park, Jongse
Sharma, Hardik
Lotfi-Kamran, Pejman
Esmaeilzadeh, Hadi
PROCEEDINGS OF THE 48TH ANNUAL IEEE/ACM INTERNATIONAL SYMPOSIUM ON MICROARCHITECTURE (MICRO-48), 2015, : 482 - 493
[4] Performance Analysis and Acceleration of Explicit Integration for Large Kinetic Networks using Batched GPU Computations
Haidar, Azzam
Brock, Benjamin
Tomov, Stanimire
Guidry, Michael
Billings, Jay Jay
Shyles, Daniel
Dongarra, Jack
2016 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2016,
[5] TOWARDS AD-HOC GPU ACCELERATION OF PARALLEL EIGENSYSTEM COMPUTATIONS
Garba, Michael T.
Gonzalez-Velez, Horacio
PROCEEDINGS - 25TH EUROPEAN CONFERENCE ON MODELLING AND SIMULATION, ECMS 2011, 2011, : 534 - 538
[6] Exploring GPU acceleration of Deep Neural Networks using Block Circulant Matrices
Dong, Shi
Zhao, Pu
Lin, Xue
Kaeli, David
PARALLEL COMPUTING, 2020, 100 (100)
[7] Poster Abstract: CNN-guardian: Secure Neural Network Inference Acceleration on Edge GPU
Xie, Qipeng
Yang, Hao
Jiang, Linshan
Zhao, Zhihe
Jiang, Siyang
Shen, Shiyu
Khan, Salabat
Liu, Zhe
Wu, Kaishun
PROCEEDINGS OF THE 21ST ACM CONFERENCE ON EMBEDDED NETWORKED SENSOR SYSTEMS, SENSYS 2023, 2023, : 524 - 525
[8] GPU-based acceleration of computations in nonlinear finite element deformation analysis
Mafi, Ramin
Sirouspour, Shahin
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN BIOMEDICAL ENGINEERING, 2014, 30 (03) : 365 - 381
[9] An Analysis of Queuing Network Simulation Using GPU-Based Hardware Acceleration
Park, Hyungwook
Fishwick, Paul A.
ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION, 2011, 21 (03):
[10] Real-time computation of a large-scaled entorhinal-hippocambal spiking neural network using GPU acceleration
Takada, Kensuke
Tateno, Katsumi
IEICE NONLINEAR THEORY AND ITS APPLICATIONS, 2022, 13 (02): : 349 - 354

← 1 2 3 4 5 →