In this work we present a multi-level parallel framework for the Optical Flow computation on a GPUs cluster, equipped with a scientific computing middleware (the PetSc library). Starting from a flow-driven isotropic method, which models the optical flow problem through a parabolic partial differential equation (PDE), we have designed a parallel algorithm and its software […]

June 24, 2015 by hgpu

Finite Element Methods are techniques for estimating solutions to boundary value problems for partial differential equations from an approximating subspace. These methods are based on weak or variational forms of the BVP that require less of the problem functions than what the original PDE would suggest in terms of order of differentiability and continuity. In […]

June 7, 2015 by hgpu

This thesis, entitled "High Performance Computing for solving large sparse systems. Optical Diffraction Tomography as a case of study" investigates the computational issues related to the resolution of linear systems of equations which come from the discretization of physical models described by means of Partial Differential Equations (PDEs). These physical models are conceived for the […]

March 30, 2015 by hgpu

In the near future, massively parallel computing systems will be necessary to solve computation intensive applications. The key bottleneck in massively parallel implementation of numerical algorithms is the synchronization of data across processing elements (PEs) after each iteration, which results in significant idle time. Thus, there is a trend towards relaxing the synchronization and adopting […]

March 18, 2015 by hgpu

In this thesis we present the first, to our knowledge, implementation and performance analysis of Hermite methods on GPU accelerated systems. We give analytic background for Hermite methods; give implementations of the Hermite methods on traditional CPU systems as well as on GPUs; give the reader background on basic CUDA programming for GPUs; discuss performance […]

February 2, 2015 by hgpu

In an ideal world, scientific applications are computationally efficient, maintainable and composable and allow scientists to work very productively. We argue that these goals are achievable for a specific application field by choosing suitable domain-specific abstractions that encapsulate domain knowledge with a high degree of expressiveness. This thesis demonstrates the design and composition of domain-specific […]

February 1, 2015 by hgpu

The High Performance Conjugate Gradient (HPCG) benchmark has been recently proposed as a complement to the High Performance Linpack (HPL) benchmark currently used to rank supercomputers in the Top500 list. This new benchmark solves a large sparse linear system using a multigrid preconditioned conjugate gradient (PCG) algorithm. The PCG algorithm contains the computational and communication […]

November 29, 2014 by hgpu

In view of the rapid rise of the number of cores in modern supercomputers, time-parallel methods that introduce concurrency along the temporal axis are becoming increasingly popular. For the solution of time-dependent partial differential equations, these methods can add another direction for concurrency on top of spatial parallelization. The paper presents an implementation of the […]

October 3, 2014 by hgpu

As parallel and heterogeneous computing becomes more and more a necessity for implementing high performance simulators, it becomes increasingly harder for scientists and engineers without experience in high performance computing to achieve good performance. Even for those who knows how to write efficient code the process for doing so is time consuming and error prone, […]

September 8, 2014 by hgpu

A model of a multilayer device with non-trivial geometrical and material structure and its working process is suggested. The thermal behavior of the device as one principle characteristic is simulated. The algorithm for solving the non-stationary heat conduction problem with a time-dependent periodical heating source is suggested. The algorithm is based on finite difference explicit–implicit […]

August 27, 2014 by hgpu

Multiresolution Analysis (MRA) is a mathematical method that is based on working on a problem at different scales. One of its applications is medical imaging where processing at multiple scales, based on the concept of Gaussian and Laplacian image pyramids, is a well-known technique. It is often applied to reduce noise while preserving image detail […]

August 23, 2014 by hgpu

The last decade saw the long tradition of frequency scaling of processing units grind to a halt, and efforts were re-focused on maintaining computational growth by other means; such as increased parallelism, deep memory hierarchies and complex execution logic. After a long period of "boring productivity", a host of new architectures, accelerators, programming languages and […]

July 24, 2014 by hgpu