In this article, we introduce CURRENNT, an open-source parallel implementation of deep recurrent neural networks (RNNs) supporting graphics processing units (GPUs) through NVIDIA’s Computed Unified Device Architecture (CUDA). CURRENNT supports uni- and bidirectional RNNs with Long Short-Term Memory (LSTM) memory cells which overcome the vanishing gradient problem. To our knowledge, CURRENNT is the first publicly […]

October 8, 2015 by hgpu

The 2D Least Median of Squares (LMS) is a popular tool in robust regression because of its high breakdown point: up to half of the input data can be contaminated with outliers without affecting the accuracy of the LMS estimator. The complexity of 2D LMS estimation has been shown to be $Omega(n^2)$ where $n$ is […]

October 8, 2015 by hgpu

With large-scale Integral Field Spectroscopy (IFS) surveys of thousands of galaxies currently under-way or planned, the astronomical community is in need of methods, techniques and tools that will allow the analysis of huge amounts of data. We focus on the kinematic modelling of disc galaxies and investigate the potential use of massively parallel architectures, such […]

October 8, 2015 by hgpu

Array-based languages such as MATLAB and Python (with NumPy) have become very popular for scientific computing. However, the performance of the implementations of these languages is often lacking. For example, some of the implementations are interpreted. Further, these languages were not designed with multi-core CPUs and GPUs in mind and thus don’t take full advantage […]

October 6, 2015 by hgpu

Embedded computing, not only in large systems like drones and hybrid vehicles, but also in small portable devices like smart phones and watches, gets more extreme to meet ever increasing demands for extended and improved functionalities. This, combined with the typical constrains for low power consumption and small sizes, makes the design of numerical libraries […]

October 6, 2015 by hgpu

We discuss an approach for solving sparse or dense banded linear systems ${bf A} {bf x} = {bf b}$ on a Graphics Processing Unit (GPU) card. The matrix ${bf A} in {mathbb{R}}^{N times N}$ is possibly nonsymmetric and moderately large; i.e., $10000 leq N leq 500000$. The ${it split and parallelize}$ (${tt SaP}$) approach seeks […]

September 30, 2015 by hgpu

Data-efficient learning in continuous state-action spaces using high-dimensional observations remains an elusive challenge in developing fully autonomous systems. An instance of this challenge is the pixels to torques problem, which identifies key elements of an autonomous agent: autonomous thinking and decision making using sensor measurements only, learning from mistakes, and applying past experiences to novel […]

September 26, 2015 by hgpu

We present a GPU accelerated CUDA-C implementation of the Barnes Hut (BH) tree code for calculating the gravita- tional potential on octree adaptive meshes. The tree code algorithm is implemented within the FLASH4 adaptive mesh refinement (AMR) code framework and therefore fully MPI parallel. We describe the algorithm and present test results that demonstrate its […]

September 26, 2015 by hgpu

This paper presents a framework that supports the implementation of parallel solutions for the widespread parametric maximum flow computational routines used in image segmentation algorithms. The framework is based on supergraphs, a special construction combining several image graphs into a larger one, and works on various architectures (multi-core or GPU), either locally or remotely in […]

September 24, 2015 by hgpu

This work presents CLTune, an auto-tuner for OpenCL kernels. It evaluates and tunes kernel performance of a generic, user-defined search space of possible parametervalue combinations. Example parameters include the OpenCL workgroup size, vector data-types, tile sizes, and loop unrolling factors. CLTune can be used in the following scenarios: 1) when there are too many tunable […]

September 17, 2015 by hgpu

We introduce a parallel GPU implementation of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Using a single graphic card, our implementation achieves speedups of up to 83x from the standard sequential implementation. Our implementation is fully compatible with the standard sequential implementation and the software is now available online and is open source.

September 17, 2015 by hgpu

Syntactic parsing is one of the core tasks of natural language processing, with many appli- cations in downstream NLP tasks, from machine translation and summarization to relation extraction and coreference resolution. Parsing performance on English texts, particularly well-edited newswire text, is generally regarded as quite good. However, state-of-the-art constituency parsers produce incorrect parses for more […]

September 15, 2015 by hgpu