high performance computing on graphics processing units: hgpu.org

Sparse matrix vector multiplication (SpMV) is one of the most common operations in scientific and high-performance applications, and is often responsible for the application performance bottleneck. While the sparse matrix representation has a significant impact on the resulting application performance, choosing the right representation typically relies on expert knowledge and trial and error. This paper […]

The integration of graphics processing units (GPUs) on high-end compute nodes has established a new accelerator-based heterogeneous computing model, which now permeates high performance computing. The same paradigm nevertheless has limited adoption in cloud computing or other large-scale distributed computing paradigms. Heterogeneous computing with GPUs can benefit the Cloud by reducing operational costs and improving […]

Convolutional neural networks (CNNs) are widely used in many computer vision applications. Previous FPGA implementations of CNNs are mainly based on the conventional convolutional algorithm. However, the high arithmetic complexity of conventional convolution algorithm for CNNs restricts the performance of accelerators and significantly increases the challenges of design. It has been proved that the Winograd […]

We present a GPU-based Locality Sensitive Hashing (LSH) algorithm to speed up beam search for sequence models. We utilize the winner-take-all (WTA) hash, which is based on relative ranking order of hidden dimensions and thus resilient to perturbations in numerical values. Our algorithm is designed by fully considering the underling architecture of CUDA-enabled GPUs (Algorithm/Architecture […]

This paper presents a novel generative model to synthesize fluid simulations from a set of reduced parameters. A convolutional neural network is trained on a collection of discrete, parameterizable fluid simulation velocity fields. Due to the capability of deep learning architectures to learn representative features of the data, our generative model is able to accurately […]

==================================================== The Third International Workshop on GPU Computing and AI (GCA) http://is-candar.org/GCA18/ to be held in conjunction with The Sixth International Symposium on Computing and Networking (CANDAR’18), Hida Takayama, Japan, November 27-30, 2018 http://is-candar.org/ ==================================================== [Introduction] Built for massive parallelism, General Purpose computing on Graphic Processing Unit (GPGPU) has superseded high-performance CPU in several important […]

Meeting time: September 19-21, 2018 Meeting place: Nagoya University, Japan keynote speakers Prof. Tony C.Y. Chung – Fellow of IEEE University of Saskatchewan, Canada Prof. Hassan Bevrani – University of Kurdistan, Iran Published by All accepted papers after proper registration and presentation, will be published in the CPESE 2018 conference Proceedings. Important dates Paper Submission: […]

Meeting time: September 22-24, 2018 Meeting place: MediaCityUK, Salford Quays, Greater Manchester, England keynote speakers Prof. Sunil Vadera – University of Salford, UK. Prof. Marat Akhmet – Middle East Technical University, Turkey. Published by All the registered and presented papers will published in the International Conference Proceedings Series by ACM, which will be archived in […]

Meeting time: August 21-23, 2018. Meeting place: Huazhong University of Science and Technology of China. No. 1037, Luoyu Road, Hongshan District, Wuhan, China. Published by: Selected and registered papers to be published by IEEE Conference Publication. After a careful reviewing process, all accepted papers after proper registration and presentation, will be published in the conference […]

Meeting time: October 29-31, 2018. Meeting place: Nanyang Executive Centre in Nanyang Technological University, Singapore Host unit: ACM Singapore Chapter. keynote speaker Prof. Latif Ladid, University of Luxembourg, Luxembourg. Prof. Dimitrios Georgakopoulos, Swinburne University of Technology, Australia. Published by: Accepted papers will be published into conference proceedings which is indexed by EI Compendex, Scopus, Thomson […]

Alternating least squares (ALS) has been proved to be an effective solver for matrix factorization in recommender systems. To speed up factorizing performance, various parallel ALS solvers have been proposed to leverage modern multi-cores and many-cores. Existing implementations are limited in either speed or portability. In this paper, we present an efficient and portable ALS […]

CPU has insufficient resources to satisfy the efficient computation of the Convolution Neural Network (CNN), especially for embedded applications. Therefore, heterogeneous computing platforms are widely used to accelerate CNN tasks, such as GPU, FPGA and ASIC. Among these, FPGA can accelerate the computation by mapping the algorithm to the parallel hardware instead of CPU, which […]