high performance computing on graphics processing units: hgpu.org

hgpu.org » Neural networks

Optimization of Spatial Convolution in ConvNets on Intel KNL

Sangamesh Nagashattappa Ragate

View

Download (PDF)

Tags: Computer science, Deep learning, Image recognition, Intel Xeon Phi, Neural networks, Thesis

September 9, 2017 by hgpu

Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization

Viacheslav Khomenko, Oleg Shyshkov, Olga Radyvonenko, Kostiantyn Bokhan

View

Download (PDF)

Tags: Algorithms, Computer science, Deep learning, LSTM, Neural networks, nVidia, Tesla K40, Theano

September 7, 2017 by hgpu

Towards On-Chip Optical FFTs for Convolutional Neural Networks

Jonathan George, Hani Nejadriahi, Volker Sorger

View

Download (PDF)

Tags: CNN, Computer science, Deep learning, FFT, Neural networks, nVidia, Tesla P100

September 3, 2017 by hgpu

Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes

Yuriy Kochura, Sergii Stirenko, Oleg Alienin, Michail Novotarskiy, Yuri Gordienko

View

Download (PDF)

Tags: Computer science, CUDA, Deep learning, Image recognition, Java, Machine learning, Neural networks, nVidia, nVidia GeForce GTX Titan, Performance, TensorFlow, Tesla K40

September 3, 2017 by hgpu

Scaling Deep Learning on GPU and Knights Landing clusters

Yang You, Aydin Buluc, James Demmel

View

Download (PDF)

Source codes

Tags: Cloud, Computer science, Deep learning, GPU cluster, Intel Xeon Phi, Machine learning, Neural networks, nVidia, Package, PC cluster, Tesla K80, Tesla M100

August 17, 2017 by hgpu

Scalability Study of Deep Learning Algorithms in High Performance Computer Infrastructures

Francesc Sastre Cabot

View

Download (PDF)

Tags: Algorithms, Computer science, Computer vision, CUDA, Deep learning, GPU cluster, Machine learning, Neural networks, nVidia, Tesla K80, Tesla M2090, Thesis

July 22, 2017 by hgpu

Deep neural networks for direct, featureless learning through observation: the case of 2d spin models

K. Mills, I. Tamblyn

View

Download (PDF)

Tags: Condensed matter, CUDA, Deep learning, Ising model, Materials Science, Neural networks, nVidia, Phase transition, Physics, Tesla K40

July 2, 2017 by hgpu

Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras

Keunwoo Choi, Deokjin Joo, Juho Kim

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Keras, Neural networks, nVidia, nVidia GeForce GTX 1080, nVidia GeForce GTX Titan X, Package, Python, Signal processing, Tesla K80, Tesla M60

June 21, 2017 by hgpu

Device Placement Optimization with Reinforcement Learning

Azalia Mirhoseini, Hieu Pham, Quoc V. Le, Benoit Steiner, Rasmus Larsen, Yuefeng Zhou, Naveen Kumar, Mohammad Norouzi, Samy Bengio, Jeff Dean

View

Download (PDF)

Tags: Artificial intelligence, Computer science, CUDA, Deep learning, Heterogeneous systems, Neural networks, nVidia, TensorFlow, Tesla K80

June 17, 2017 by hgpu

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

Priya Goyal, Piotr Dollar, Ross Girshick, Pieter Noordhuis, Lukasz Wesolowski, Aapo Kyrola, Andrew Tulloch, Yangqing Jia, Kaiming He

View

Download (PDF)

Source codes

Tags: Computer science, Computer vision, CUDA, Deep learning, Neural networks, nVidia, Package, Tesla P100

June 10, 2017 by hgpu

MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU

Qingqing Cao, Niranjan Balasubramanian, Aruna Balasubramanian

View

Download (PDF)

Source codes

Tags: Computer science, CUDA, Deep learning, Java, Neural networks, nVidia, Package, RNN, TensorFlow

June 10, 2017 by hgpu

Neneta: Heterogeneous Computing Complex-Valued Neural Network Framework

Vladimir Lekic, Zdenka Babic

View

Download (PDF)

Tags: ATI, ATI Radeon HD 5770, Computer science, Deep learning, Heterogeneous systems, Neural networks, OpenCL

June 5, 2017 by hgpu

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

Profile Util library: A quick and easy way to get MPI, OpenMP and GPU runtime information

MaC: Mamba CPU performance predictor

MambaCPU: Enhanced Correlation Mining with State Space Models for CPU Performance Prediction

Mixed-precision finite element kernels

Mixed-precision finite element kernels and assembly: Rounding error analysis and hardware acceleration

SHMT: The Simultaneous and Heterogenous Multithreading project

General-Purpose Computing on Tensor Processors

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Online Energy Optimization in GPUs: A Multi-Armed Bandit Approach

See all packages

* * *

high performance computing on graphics processing units: hgpu.org

Optimization of Spatial Convolution in ConvNets on Intel KNL

Accelerating recurrent neural network training using sequence bucketing and multi-GPU data parallelization

Towards On-Chip Optical FFTs for Convolutional Neural Networks

Performance Analysis of Open Source Machine Learning Frameworks for Various Parameters in Single-Threaded and Multi-Threaded Modes

Scalability Study of Deep Learning Algorithms in High Performance Computer Infrastructures

Deep neural networks for direct, featureless learning through observation: the case of 2d spin models

Kapre: On-GPU Audio Preprocessing Layers for a Quick Implementation of Deep Neural Network Models with Keras

Device Placement Optimization with Reinforcement Learning

Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour

MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU

Neneta: Heterogeneous Computing Complex-Valued Neural Network Framework

Recent source codes

Kokkidio: Kokkos+Eigen - write fast, readable multi-platform code

LLaMA-Inference-Bench

MATAR

Over-synchronization in GPU Programs

profile_util: simple C++ library to report memory, timing, thread affinity

MaC: Mamba CPU performance predictor

Mixed-precision finite element kernels

SHMT: The Simultaneous and Heterogenous Multithreading project

Superpipeline: A Universal Approach for Reducing GPU Memory Usage in Large Models

EnergyUCB-Bandit

Most viewed papers (last 30 days)