BazTech - Yadda

1

Implementacja metody momentów z wykorzystaniem kart graficznych i architektury CUDA

Topa T., Noga A.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 3

34-40

PL

W artykule omówiono możliwości zastosowania kart graficznych do przyspieszania obliczeń numerycznych bazujących na metodzie momentów. Opisano algorytmy metody momentów implementowane w heterogenicznym środowisku CPU/GPU oraz przeprowadzono szczegółową analizę możliwych do uzyskania przyspieszeń dla różnych generacji architektury CUDA.

EN

The using of GPU to accelerate of the numerical simulations based on the Method of Moments (MoM) is presented in this paper. Implementation of the MoM in heterogeneous CPU/GPU platform and the measured speedups for the three generation of CUDA architecture is also demonstrated.

2

Usage of Digital Image Correlation in Analysis of Cracking Processes

Marciniak B., Marciniak T., Lutowski Z., Bujnowski S.

Image Processing & Communications

|

2012

|

Vol. 17, no. 3

21--28

EN

In this paper, the analysis of the possibilities of using Digital Image Correlation (DIC) based on Graphics Processing Unit (GPU) for strain analysis in fatigue cracking processes is presented. The basic assumption for the discussed displacement and strain measurement method under time variable loads was obtaining high measurement sensitivity by simultaneously minimizing the measurement time consumption. For this purpose special computing procedures based on multiprocessor graphic cards were developed, which significantly reduced the total time of displacement and strain analysis. The developed digital procedure for correlation of images has been used for an example of displacement analysis in the method of fatigue crack propagation testing in airplane riveted joints. In this paper are presented the results of the researches of the team run by professor Antoni Zabłudowski.

3

A Graph-Based Approach to the Segmentation of Images with Mould Filled Foam Matrices

Gocławski J., Sekulska-Nalewajko J.

Image Processing & Communications

|

2012

|

Vol. 17, no. 4

59--70

EN

In the paper a method of MST (minimum spanning tree) graph-based image segmentation supported by parallel GPUprocessing has been presented. It has been applied to images of foam matrices filled with mould fungi of Mucor genus. The aim of the segmentation was to extract the profiles of the matrix objects from image background. Parallel computing methods were used to the initial image filtering, graph edge array building and sorting. The results obtained with graph based method both with and without parallel processing have been compared with conventional analysis in MATLAB environment. It has been verified that GPU processing clearly reduce execution time of the algorithm.

4

Probability Density Functions for Calculating Approximate Aggregates

Gramacki J., Gramacki A.

Foundations of Computing and Decision Sciences

|

2010

|

Vol. 35, No. 4

223-240

EN

In the paper we show how one can use probability density function (PDF) for calculating approximate aggregates. The aggregates can be obtained very quickly and efficiently and there is no need to look through the large amount of data, as well as creating a sort of materialized aggregates (usually implemented as materialized views). Although the final results are only approximate, the method is extremely fast and can be successively used during initial phase of data exploration. We include simple experimental results which proof effectiveness of the method, especially if PDFs are typical, for example similar to Gaussian normal ones. If the PDFs differ from a normal distribution, one can consider making a proper preliminary transformation of the input variables or estimate PDFs by some nonparametric methods, for example using the so called kernel estimators. The later is used in the paper. To accelerate calculations, one can consider a usage of graphics processing unit (GPU). We point out this approach in the last section of the paper and give some preliminary results which are very promising.