Parallel hyperspectral coded aperture for compressive sensing on GPUs

The application of compressive sensing (CS) to hyperspectral images is an active area of research over the past few years, both in terms of the hardware and the signal processing algorithms. However, CS algorithms can be computationally very expensive due to the extremely large volumes of data collected by imaging spectrometers, a fact that compromises their use in applications under real-time constraints. This paper proposes four efficient implementations of hyperspectral coded aperture (HYCA) for CS, two of them termed P-HYCA and P-HYCA-FAST and two additional implementations for its constrained version (CHYCA), termed P-CHYCA and P-CHYCA-FAST on commodity graphics processing units (GPUs). HYCA algorithm exploits the high correlation existing among the spectral bands of the hyperspectral data sets and the generally low number of endmembers needed to explain the data, which largely reduces the number of measurements necessary to correctly reconstruct the original data. The proposed P-HYCA and P-CHYCA implementations have been developed using the compute unified device architecture (CUDA) and the cuFFT library. Moreover, this library has been replaced by a fast iterative method in the P-HYCA-FAST and P-CHYCA-FAST implementations that leads to very significant speedup factors in order to achieve real-time requirements. The proposed algorithms are evaluated not only in terms of reconstruction error for different compressions ratios but also in terms of computational performance using two different GPU architectures by NVIDIA: 1) GeForce GTX 590; and 2) GeForce GTX TITAN. Experiments are conducted using both simulated and real data revealing considerable acceleration factors and obtaining good results in the task of compressing remotely sensed hyperspectral data sets.

A framework for scientific computing with GPUs

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Conceção e implementação de um ambiente de baixo custo para processamento de imagens tomográficas

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Optimization of breast tomosynthesis image reconstruction using parallel computing

Breast cancer is the most common cancer among women, being a major public health problem. Worldwide, X-ray mammography is the current gold-standard for medical imaging of breast cancer. However, it has associated some well-known limitations. The false-negative rates, up to 66% in symptomatic women, and the false-positive rates, up to 60%, are a continued source of concern and debate. These drawbacks prompt the development of other imaging techniques for breast cancer detection, in which Digital Breast Tomosynthesis (DBT) is included. DBT is a 3D radiographic technique that reduces the obscuring effect of tissue overlap and appears to address both issues of false-negative and false-positive rates. The 3D images in DBT are only achieved through image reconstruction methods. These methods play an important role in a clinical setting since there is a need to implement a reconstruction process that is both accurate and fast. This dissertation deals with the optimization of iterative algorithms, with parallel computing through an implementation on Graphics Processing Units (GPUs) to make the 3D reconstruction faster using Compute Unified Device Architecture (CUDA). Iterative algorithms have shown to produce the highest quality DBT images, but since they are computationally intensive, their clinical use is currently rejected. These algorithms have the potential to reduce patient dose in DBT scans. A method of integrating CUDA in Interactive Data Language (IDL) is proposed in order to accelerate the DBT image reconstructions. This method has never been attempted before for DBT. In this work the system matrix calculation, the most computationally expensive part of iterative algorithms, is accelerated. A speedup of 1.6 is achieved proving the fact that GPUs can accelerate the IDL implementation.

Towards an algorithmic skeleton framework for programming the Intel R Xeon PhiTM processor

The Intel R Xeon PhiTM is the first processor based on Intel’s MIC (Many Integrated Cores) architecture. It is a co-processor specially tailored for data-parallel computations, whose basic architectural design is similar to the ones of GPUs (Graphics Processing Units), leveraging the use of many integrated low computational cores to perform parallel computations. The main novelty of the MIC architecture, relatively to GPUs, is its compatibility with the Intel x86 architecture. This enables the use of many of the tools commonly available for the parallel programming of x86-based architectures, which may lead to a smaller learning curve. However, programming the Xeon Phi still entails aspects intrinsic to accelerator-based computing, in general, and to the MIC architecture, in particular. In this thesis we advocate the use of algorithmic skeletons for programming the Xeon Phi. Algorithmic skeletons abstract the complexity inherent to parallel programming, hiding details such as resource management, parallel decomposition, inter-execution flow communication, thus removing these concerns from the programmer’s mind. In this context, the goal of the thesis is to lay the foundations for the development of a simple but powerful and efficient skeleton framework for the programming of the Xeon Phi processor. For this purpose we build upon Marrow, an existing framework for the orchestration of OpenCLTM computations in multi-GPU and CPU environments. We extend Marrow to execute both OpenCL and C++ parallel computations on the Xeon Phi. We evaluate the newly developed framework, several well-known benchmarks, like Saxpy and N-Body, will be used to compare, not only its performance to the existing framework when executing on the co-processor, but also to assess the performance on the Xeon Phi versus a multi-GPU environment.

Econometrics on GPUs

A graphical processing unit (GPU) is a hardware device normally used to manipulate computer memory for the display of images. GPU computing is the practice of using a GPU device for scientific or general purpose computations that are not necessarily related to the display of images. Many problems in econometrics have a structure that allows for successful use of GPU computing. We explore two examples. The first is simple: repeated evaluation of a likelihood function at different parameter values. The second is a more complicated estimator that involves simulation and nonparametric fitting. We find speedups from 1.5 up to 55.4 times, compared to computations done on a single CPU core. These speedups can be obtained with very little expense, energy consumption, and time dedicated to system maintenance, compared to equivalent performance solutions using CPUs. Code for the examples is provided.

Calcul en n-dimensions sur GPU

Le code source de la libraire développée accompagne ce dépôt dans l'état où il était à ce moment. Il est possible de trouver une version plus à jour sur github (http://github.com/abergeron).

Logiciel de génération de nombres aléatoires dans OpenCL

clRNG et clProbdist sont deux interfaces de programmation (APIs) que nous avons développées pour la génération de nombres aléatoires uniformes et non uniformes sur des dispositifs de calculs parallèles en utilisant l’environnement OpenCL. La première interface permet de créer au niveau d’un ordinateur central (hôte) des objets de type stream considérés comme des générateurs virtuels parallèles qui peuvent être utilisés aussi bien sur l’hôte que sur les dispositifs parallèles (unités de traitement graphique, CPU multinoyaux, etc.) pour la génération de séquences de nombres aléatoires. La seconde interface permet aussi de générer au niveau de ces unités des variables aléatoires selon différentes lois de probabilité continues et discrètes. Dans ce mémoire, nous allons rappeler des notions de base sur les générateurs de nombres aléatoires, décrire les systèmes hétérogènes ainsi que les techniques de génération parallèle de nombres aléatoires. Nous présenterons aussi les différents modèles composant l’architecture de l’environnement OpenCL et détaillerons les structures des APIs développées. Nous distinguons pour clRNG les fonctions qui permettent la création des streams, les fonctions qui génèrent les variables aléatoires uniformes ainsi que celles qui manipulent les états des streams. clProbDist contient les fonctions de génération de variables aléatoires non uniformes selon la technique d’inversion ainsi que les fonctions qui permettent de retourner différentes statistiques des lois de distribution implémentées. Nous évaluerons ces interfaces de programmation avec deux simulations qui implémentent un exemple simplifié d’un modèle d’inventaire et un exemple d’une option financière. Enfin, nous fournirons les résultats d’expérimentation sur les performances des générateurs implémentés.

NeMo: a platform for neural modelling of spiking neurons using GPUs

Simulating spiking neural networks is of great interest to scientists wanting to model the functioning of the brain. However, large-scale models are expensive to simulate due to the number and interconnectedness of neurons in the brain. Furthermore, where such simulations are used in an embodied setting, the simulation must be real-time in order to be useful. In this paper we present NeMo, a platform for such simulations which achieves high performance through the use of highly parallel commodity hardware in the form of graphics processing units (GPUs). NeMo makes use of the Izhikevich neuron model which provides a range of realistic spiking dynamics while being computationally efficient. Our GPU kernel can deliver up to 400 million spikes per second. This corresponds to a real-time simulation of around 40 000 neurons under biologically plausible conditions with 1000 synapses per neuron and a mean firing rate of 10 Hz.

Using GPUs for beamforming acceleration on SAFT imaging

SAFT techniques are based on the sequential activation, in emission and reception, of the array elements and the post-processing of all the received signals to compose the image. Thus, the image generation can be divided into two stages: (1) the excitation and acquisition stage, where the signals received by each element or group of elements are stored; and (2) the beamforming stage, where the signals are combined together to obtain the image pixels. The use of Graphics Processing Units (GPUs), which are programmable devices with a high level of parallelism, can accelerate the computations of the beamforming process, that usually includes different functions such as dynamic focusing, band-pass filtering, spatial filtering or envelope detection. This work shows that using GPU technology can accelerate, in more than one order of magnitude with respect to CPU implementations, the beamforming and post-processing algorithms in SAFT imaging. ©2009 IEEE.

Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Implementação do algoritmo de Newman para identificação de comunidades em placas gráficas

Communities are present on physical, chemical and biological systems and their identification is fundamental for the comprehension of the behavior of these systems. Recently, available data related to complex networks have grown exponentially, demanding more computational power. The Graphical Processing Unit (GPU) is a cost effective alternative suitable for this purpose. We investigate the convenience of this for network science by proposing a GPU based implementation of Newman community detection algorithm. We showed that the processing time of matrix multiplications of GPUs grow slower than CPUs in relation to the matrix size. It was proven, thus, that GPU processing power is a viable solution for community dentification simulation that demand high computational power. Our implementation was tested on an integrated biological network for the bacterium Escherichia coli

Algorithms hardware implementation for ultrasonic data processing in SHM system

Nowadays, devices that monitor the health of structures consume a lot of power and need a lot of time to acquire, process, and send the information about the structure to the main processing unit. To decrease this time, fast electronic devices are starting to be used to accelerate this processing. In this paper some hardware algorithms implemented in an electronic logic programming device are described. The goal of this implementation is accelerate the process and diminish the information that has to be send. By reaching this goal, the time the processor needs for treating all the information is reduced and so the power consumption is reduced too.

Efficient tool path computation using multi-core GPUs

Tool path generation is one of the most complex problems in Computer Aided Manufacturing. Although some efficient strategies have been developed, most of them are only useful for standard machining. However, the algorithms used for tool path computation demand a higher computation performance, which makes the implementation on many existing systems very slow or even impractical. Hardware acceleration is an incremental solution that can be cleanly added to these systems while keeping everything else intact. It is completely transparent to the user. The cost is much lower and the development time is much shorter than replacing the computers by faster ones. This paper presents an optimisation that uses a specific graphic hardware approach using the power of multi-core Graphic Processing Units (GPUs) in order to improve the tool path computation. This improvement is applied on a highly accurate and robust tool path generation algorithm. The paper presents, as a case of study, a fully implemented algorithm used for turning lathe machining of shoe lasts. A comparative study will show the gain achieved in terms of total computing time. The execution time is almost two orders of magnitude faster than modern PCs.

Studies of turbulent flows in continuous casting of steel with and without magnetic field

This thesis develops and tests various transient and steady-state computational models such as direct numerical simulation (DNS), large eddy simulation (LES), filtered unsteady Reynolds-averaged Navier-Stokes (URANS) and steady Reynolds-averaged Navier-Stokes (RANS) with and without magnetic field to investigate turbulent flows in canonical as well as in the nozzle and mold geometries of the continuous casting process. The direct numerical simulations are first performed in channel, square and 2:1 aspect rectangular ducts to investigate the effect of magnetic field on turbulent flows. The rectangular duct is a more practical geometry for continuous casting nozzle and mold and has the option of applying magnetic field either perpendicular to broader side or shorter side. This work forms the part of a graphic processing unit (GPU) based CFD code (CU-FLOW) development for magnetohydrodynamic (MHD) turbulent flows. The DNS results revealed interesting effects of the magnetic field and its orientation on primary, secondary flows (instantaneous and mean), Reynolds stresses, turbulent kinetic energy (TKE) budgets, momentum budgets and frictional losses, besides providing DNS database for two-wall bounded square and rectangular duct MHD turbulent flows. Further, the low- and high-Reynolds number RANS models (k-ε and Reynolds stress models) are developed and tested with DNS databases for channel and square duct flows with and without magnetic field. The MHD sink terms in k- and ε-equations are implemented as proposed by Kenjereš and Hanjalić using a user defined function (UDF) in FLUENT. This work revealed varying accuracies of different RANS models at different levels. This work is useful for industry to understand the accuracies of these models, including continuous casting. After realizing the accuracy and computational cost of RANS models, the steady-state k-ε model is then combined with the particle image velocimetry (PIV) and impeller probe velocity measurements in a 1/3rd scale water model to study the flow quality coming out of the well- and mountain-bottom nozzles and the effect of stopper-rod misalignment on fluid flow. The mountain-bottom nozzle was found more prone to the longtime asymmetries and higher surface velocities. The left misalignment of stopper gave higher surface velocity on the right leading to significantly large number of vortices forming behind the nozzle on the left. Later, the transient and steady-state models such as LES, filtered URANS and steady RANS models are combined with ultrasonic Doppler velocimetry (UDV) measurements in a GaInSn model of typical continuous casting process. LES-CU-LOW is the fastest and the most accurate model owing to much finer mesh and a smaller timestep. This work provided a good understanding on the performance of these models. The behavior of instantaneous flows, Reynolds stresses and proper orthogonal decomposition (POD) analysis quantified the nozzle bottom swirl and its importance on the turbulent flow in the mold. Afterwards, the aforementioned work in GaInSn model is extended with electromagnetic braking (EMBr) to help optimize a ruler-type brake and its location for the continuous casting process. The magnetic field suppressed turbulence and promoted vortical structures with their axis aligned with the magnetic field suggesting tendency towards 2-d turbulence. The stronger magnetic field at the nozzle well and around the jet region created large scale and lower frequency flow behavior by suppressing nozzle bottom swirl and its front-back alternation. Based on this work, it is advised to avoid stronger magnetic field around jet and nozzle bottom to get more stable and less defect prone flow.