Real time motion estimation using a neural architecture implemented on GPUs

This work describes a neural network based architecture that represents and estimates object motion in videos. This architecture addresses multiple computer vision tasks such as image segmentation, object representation or characterization, motion analysis and tracking. The use of a neural network architecture allows for the simultaneous estimation of global and local motion and the representation of deformable objects. This architecture also avoids the problem of finding corresponding features while tracking moving objects. Due to the parallel nature of neural networks, the architecture has been implemented on GPUs that allows the system to meet a set of requirements such as: time constraints management, robustness, high processing speed and re-configurability. Experiments are presented that demonstrate the validity of our architecture to solve problems of mobile agents tracking and motion analysis.

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.

Multi-Tenant Virtual GPUs for Optimising Performance of a Financial Risk Application

Graphics Processing Units (GPUs) are becoming popular accelerators in modern High-Performance Computing (HPC) clusters. Installing GPUs on each node of the cluster is not efficient resulting in high costs and power consumption as well as underutilisation of the accelerator. The research reported in this paper is motivated towards the use of few physical GPUs by providing cluster nodes access to remote GPUs on-demand for a financial risk application. We hypothesise that sharing GPUs between several nodes, referred to as multi-tenancy, reduces the execution time and energy consumed by an application. Two data transfer modes between the CPU and the GPUs, namely concurrent and sequential, are explored. The key result from the experiments is that multi-tenancy with few physical GPUs using sequential data transfers lowers the execution time and the energy consumed, thereby improving the overall performance of the application.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Esquemas de volúmenes finitos de alto orden: implementación en GPUs y aplicación a la simulación de flujos geofísicos

En esta tesis doctoral se exponen los fundamentos teóricos necesarios en el diseño de esquemas numéricos de volúmenes finitos para sistemas hiperbólicos no conservativos de una y dos dimensiones. Para el caso unidimensional se repasan los conceptos de esquema camino-conservativo y esquema bien equilibrado, así como la extensión de los esquemas numéricos a alto orden, basados en la reconstrucción de estados. En particular, se presentan los esquemas de tipo PVM (Polynomial Viscosity Matrix), así como diversos esquemas de limitadores de flujo que resultan de la extensión natural del método WAF, utilizando como base algunos esquemas de tipo PVM. Para el caso bidimensional se aborda el diseño de esquemas numéricos camino-conservativos y bien equilibrados de volúmenes finitos para sistemas hiperbólicos no conservativos y su extensión a alto orden, en particular se presenta una reconstrucción de estados de tercer orden compacta y que resulta de la combinación WENO de paraboloides y planos. 
 Se presenta además el desarrollo de métodos numéricos para el sistema de aguas someras bidimensional de una capa. En particular se definen esquemas de primer orden de tipo HLL y FORCE y su extensión a alto orden, un método de limitadores de flujo basado en el esquema HLL-WAF, así como su implementación en arquitecturas de tipo GPU, usando el entorno de programación CUDA. A continuación, se presenta un esquema numérico de orden uno para el sistema de aguas someras de una capa bidimensional en coordenadas esféricas (longitud/latitud), así como la extensión natural del método de limitadores de flujo presentado en el Capítulo 3 a este sistema. Finalmente, se presenta la validación del esquema de limitadores de flujo mediante la simulación de tsunamis reales, y la comparación con datos de campo.

Using multiple GPUs to accelerate string searching for digital forensic analysis

String searching within a large corpus of data is an important component of digital forensic (DF) analysis techniques such as file carving. The continuing increase in capacity of consumer storage devices requires corresponding im-provements to the performance of string searching techniques. As string search-ing is a trivially-parallelisable problem, GPGPU approaches are a natural fit – but previous studies have found that local storage presents an insurmountable performance bottleneck. We show that this need not be the case with modern hardware, and demonstrate substantial performance improvements from the use of single and multiple GPUs when searching for strings within a typical forensic disk image.

Load balancing for constraint solving with GPUs

Solving a complex Constraint Satisfaction Problem (CSP) is a computationally hard task which may require a considerable amount of time. Parallelism has been applied successfully to the job and there are already many applications capable of harnessing the parallel power of modern CPUs to speed up the solving process. Current Graphics Processing Units (GPUs), containing from a few hundred to a few thousand cores, possess a level of parallelism that surpasses that of CPUs and there are much less applications capable of solving CSPs on GPUs, leaving space for further improvement. This paper describes work in progress in the solving of CSPs on GPUs, CPUs and other devices, such as Intel Many Integrated Cores (MICs), in parallel. It presents the gains obtained when applying more devices to solve some problems and the main challenges that must be faced when using devices with as different architectures as CPUs and GPUs, with a greater focus on how to effectively achieve good load balancing between such heterogeneous devices.

Parallel implementation of vertex component analysis for hyperspectral endmember extraction

International Conference with Peer Review 2012 IEEE International Conference in Geoscience and Remote Sensing Symposium (IGARSS), 22-27 July 2012, Munich, Germany

Calculating an upper bound on the finishing time of a group of threads executing on a GPU: a preliminary case study

Graphics processor units (GPUs) today can be used for computations that go beyond graphics and such use can attain a performance that is orders of magnitude greater than a normal processor. The software executing on a graphics processor is composed of a set of (often thousands of) threads which operate on different parts of the data and thereby jointly compute a result which is delivered to another thread executing on the main processor. Hence the response time of a thread executing on the main processor is dependent on the finishing time of the execution of threads executing on the GPU. Therefore, we present a simple method for calculating an upper bound on the finishing time of threads executing on a GPU, in particular NVIDIA Fermi. Developing such a method is nontrivial because threads executing on a GPU share hardware resources at very fine granularity.

Trends Of CPU, GPU and FPGA for high-performance computing

Floating-point computing with more than one TFLOP of peak performance is already a reality in recent Field-Programmable Gate Arrays (FPGA). General-Purpose Graphics Processing Units (GPGPU) and recent many-core CPUs have also taken advantage of the recent technological innovations in integrated circuit (IC) design and had also dramatically improved their peak performances. In this paper, we compare the trends of these computing architectures for high-performance computing and survey these platforms in the execution of algorithms belonging to different scientific application domains. Trends in peak performance, power consumption and sustained performances, for particular applications, show that FPGAs are increasing the gap to GPUs and many-core CPUs moving them away from high-performance computing with intensive floating-point calculations. FPGAs become competitive for custom floating-point or fixed-point representations, for smaller input sizes of certain algorithms, for combinational logic problems and parallel map-reduce problems. © 2014 Technical University of Munich (TUM).

GPU implementation of a hyperspectral coded aperture algorithm for compressive sensing

This paper presents a new parallel implementation of a previously hyperspectral coded aperture (HYCA) algorithm for compressive sensing on graphics processing units (GPUs). HYCA method combines the ideas of spectral unmixing and compressive sensing exploiting the high spatial correlation that can be observed in the data and the generally low number of endmembers needed in order to explain the data. The proposed implementation exploits the GPU architecture at low level, thus taking full advantage of the computational power of GPUs using shared memory and coalesced accesses to memory. The proposed algorithm is evaluated not only in terms of reconstruction error but also in terms of computational performance using two different GPU architectures by NVIDIA: GeForce GTX 590 and GeForce GTX TITAN. Experimental results using real data reveals signficant speedups up with regards to serial implementation.

GPU implementation of the simplex identification via split augmented Lagrangian

Hyperspectral imaging can be used for object detection and for discriminating between different objects based on their spectral characteristics. One of the main problems of hyperspectral data analysis is the presence of mixed pixels, due to the low spatial resolution of such images. This means that several spectrally pure signatures (endmembers) are combined into the same mixed pixel. Linear spectral unmixing follows an unsupervised approach which aims at inferring pure spectral signatures and their material fractions at each pixel of the scene. The huge data volumes acquired by such sensors put stringent requirements on processing and unmixing methods. This paper proposes an efficient implementation of a unsupervised linear unmixing method on GPUs using CUDA. The method finds the smallest simplex by solving a sequence of nonsmooth convex subproblems using variable splitting to obtain a constraint formulation, and then applying an augmented Lagrangian technique. The parallel implementation of SISAL presented in this work exploits the GPU architecture at low level, using shared memory and coalesced accesses to memory. The results herein presented indicate that the GPU implementation can significantly accelerate the method's execution over big datasets while maintaining the methods accuracy.

Parallel GPU architecture for hyperspectral unmixing based on augmented Lagrangian method

Hyperspectral imaging has become one of the main topics in remote sensing applications, which comprise hundreds of spectral bands at different (almost contiguous) wavelength channels over the same area generating large data volumes comprising several GBs per flight. This high spectral resolution can be used for object detection and for discriminate between different objects based on their spectral characteristics. One of the main problems involved in hyperspectral analysis is the presence of mixed pixels, which arise when the spacial resolution of the sensor is not able to separate spectrally distinct materials. Spectral unmixing is one of the most important task for hyperspectral data exploitation. However, the unmixing algorithms can be computationally very expensive, and even high power consuming, which compromises the use in applications under on-board constraints. In recent years, graphics processing units (GPUs) have evolved into highly parallel and programmable systems. Specifically, several hyperspectral imaging algorithms have shown to be able to benefit from this hardware taking advantage of the extremely high floating-point processing performance, compact size, huge memory bandwidth, and relatively low cost of these units, which make them appealing for onboard data processing. In this paper, we propose a parallel implementation of an augmented Lagragian based method for unsupervised hyperspectral linear unmixing on GPUs using CUDA. The method called simplex identification via split augmented Lagrangian (SISAL) aims to identify the endmembers of a scene, i.e., is able to unmix hyperspectral data sets in which the pure pixel assumption is violated. The efficient implementation of SISAL method presented in this work exploits the GPU architecture at low level, using shared memory and coalesced accesses to memory.

Parallel hyperspectral compressive sensing method on GPU

Remote hyperspectral sensors collect large amounts of data per flight usually with low spatial resolution. It is known that the bandwidth connection between the satellite/airborne platform and the ground station is reduced, thus a compression onboard method is desirable to reduce the amount of data to be transmitted. This paper presents a parallel implementation of an compressive sensing method, called parallel hyperspectral coded aperture (P-HYCA), for graphics processing units (GPU) using the compute unified device architecture (CUDA). This method takes into account two main properties of hyperspectral dataset, namely the high correlation existing among the spectral bands 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. Experimental results conducted using synthetic and real hyperspectral datasets on two different GPU architectures by NVIDIA: GeForce GTX 590 and GeForce GTX TITAN, reveal that the use of GPUs can provide real-time compressive sensing performance. The achieved speedup is up to 20 times when compared with the processing time of HYCA running on one core of the Intel i7-2600 CPU (3.4GHz), with 16 Gbyte memory.

Parallel method for sparse semisupervised hyperspectral unmixing

Parallel hyperspectral unmixing problem is considered in this paper. A semisupervised approach is developed under the linear mixture model, where the abundance's physical constraints are taken into account. The proposed approach relies on the increasing availability of spectral libraries of materials measured on the ground instead of resorting to endmember extraction methods. Since Libraries are potentially very large and hyperspectral datasets are of high dimensionality a parallel implementation in a pixel-by-pixel fashion is derived to properly exploits the graphics processing units (GPU) architecture at low level, thus taking full advantage of the computational power of GPUs. Experimental results obtained for real hyperspectral datasets reveal significant speedup factors, up to 164 times, with regards to optimized serial implementation.