high performance computing on graphics processing units: hgpu.org

Contemporary GPUs allow concurrent execution of small computational kernels in order to prevent idling of GPU resources. Despite the potential concurrency between independent kernels, the order in which kernels are issued to the GPU will significantly influence the application performance. A technique for deriving suitable kernel launch orders is therefore presented, with the aim of […]

Stochastic Gradient Descent, a stochastic optimization of Gradient Descent, is an algorithm that is used in different topics, like for example for linear regression or logistic regression. After the Netflix prize, SGD start to be used also in recommender systems to compute matrix factorization. Considering the large amounts of data that this kind of system […]

Epidemiology computation models are crucial for the assessment and control of public health crises. Agent-based simulations of pandemic influenza are useful for forecasting the infectious disease spreading in order to help public health policy makers during emergencies. In such emergencies decisions are required for public health preparedness in cycles of less than a day, and […]

The High Performance Computing (HPC) field is witnessing a widespread adoption of Graphics Processing Units (GPUs) as co-processors for conventional homogeneous clusters. The adoption of prevalent Single-Program Multiple-Data (SPMD) programming paradigm for GPU-based parallel processing brings in the challenge of resource underutilization, with the asymmetrical processor/co-processor distribution. In other words, under SPMD, balanced CPU/GPU distribution […]

Today, there is no one who disagrees on how important data is in every industry especially in enterprise market. More recently, the key point that decides the survival of a business is the management of their big data, which is defined by the 3V’s: Volume, Velocity, and Variety [1]. While the rate of data generation […]

Mobile applications running on wearable devices and smartphones can greatly benefit from accurate and scalable deep CNN-based machine learning algorithms. While mobile CPU performance does not match the intensive computational requirement of deep CNNs, the embedded GPU which already exists in many mobile platforms can be leveraged for acceleration of CNN computations on the local […]

Pulsar acceleration searches are methods for recovering signals from radio telescopes, that may otherwise be lost due to the effect of orbital acceleration in binary systems. The vast amount of data that will be produced by next generation instruments such as the Square Kilometre Array (SKA) necessitates real-time acceleration searches, which in turn requires the […]

Scene understanding, such as image classification and semantic image segmentation, has been a challenging problem in computer vision. The difficulties mainly come from the feature representation, i.e., how to find a good representation for images. Instead of improving over hand-crafted features such as SIFT or HoG, we focus on learning image representations by generative and […]

We present a parallel algorithm for finding the shortest path whose total weight is smaller than a pre-determined value. The passage times over the edges are assumed to be positive integers. In each step the processing elements are not analyzing the entire graph. Instead they are focusing on a subset of vertices called active vertices. […]

Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging. To deploy deep CNNs on mobile devices, we present a simple and effective scheme to compress the entire CNN, which we call one-shot whole network compression. The […]

Deep learning methods have resulted in significant performance improvements in several application domains and as such several software frameworks have been developed to facilitate their implementation. This paper presents a comparative study of four deep learning frameworks, namely Caffe, Neon, Theano, and Torch, on three aspects: extensibility, hardware utilization, and speed. The study is performed […]

Quantifying simulation uncertainties is a critical component of rigorous predictive simulation. A key component of this is forward propagation of uncertainties in simulation input data to output quantities of interest. Typical approaches involve repeated sampling of the simulation over the uncertain input data, and can require numerous samples when accurately propagating uncertainties from large numbers […]