Wyniki wyszukiwania - BazTech

1

FPGA-Based high speed two ways parallel histogram computation for grey image

Mahmood Riyadh Zaghlool, Abdullah Hiba-Allah Tariq

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 1

120--123

EN

In this paper approaches to the parallel architecture for local parallel histogram computation is studied. In this method, has been used many number of block RAM in FPGA based, each of them to perform a specific function must use a dual-ported of BRAM memory. These hardware techniques need one array of image and another one array for histogram. To reduce number of cycles in the FPGA implementation of our proposed technique read two operation memories at the same time.

PL

W tym artykule badane są podejścia do architektury równoległej do obliczania lokalnego histogramu równoległego. W metodzie tej wykorzystano wiele bloków pamięci RAM w układzie FPGA, każdy z nich do wykonywania określonej funkcji musi wykorzystywać dwuportową pamięć BRAM. Te techniki sprzętowe wymagają jednej tablicy obrazu i drugiej tablicy dla histogramu. Aby zredukować liczbę cykli w implementacji FPGA proponowanej przez nas techniki odczytujemy jednocześnie dwie pamięci operacyjne.

2

Comparison of multi-frontal and alternating direction parallel hybrid memory iGRM direct solver for non-stationary simulations

Woźniak Maciej, Bukowska Anna

Computer Science

|

2020

|

T. 21 (4)

419-439

EN

Three-dimensional isogeometric analysis (IGA-FEM) is a modern method for simulation. The idea is to utilize B-splines or NURBS basis functions for both computational domain descriptions and engineering computations. Refined isogeometric analysis (rIGA) employs a mixture of patches of elements with B-spline basis functions and C 0 separators between them. This enables a reduction in the computational cost of direct solvers. Both IGA and rIGA come with challenging sparse matrix structures that are expensive to generate. In this paper, we show a hybrid parallelization method using hybrid-memory parallel machines. The two-level parallelization includes the partitioning of the computational mesh into sub-domains on the first level (MPI) and loop parallelization on the second level (OpenMP). We show that the hybrid parallelization of the integration reduces the contribution of this phase significantly. We compare the multi-frontal solver and alternating direction solver, including the integration and the factorization phases.

3

Naturally parallel measuring system based on FPGA hardware

Długopolski Jacek, Richert Maria

Journal of Machine Construction and Maintenance - Problemy Eksploatacji

|

2019

|

no. 2

113--119

EN

The FPGA (Field Programmable Gate Array) technology, usually a little unnoticeable, almost from the very beginning is developed simultaneously with the microprocessor technology. The possibility for the system designer or end user to influence the internal structure of the integrated circuit gives unattainable possibilities of building plastic and fully massively parallel systems that fit in almost one integrated circuit. This fact allows, among others for building fully parallel multi-point measuring systems. This manuscript presents the architecture proposal for such an FPGA-based exemplary multichannel measurement system and presents the results of its practical use to study the functioning of a tubular heat exchanger in automotive airconditioning.

PL

Technologia programowalnych układów scalonych FPGA (Field Programmable Gate Array), zwykle trochę niezauważana, niemal od samego początku rozwija się równolegle z technologią mikroprocesorową. Możliwość wpływania przez projektanta systemów lub użytkownika końcowego na wewnętrzną strukturę układu scalonego daje nieosiągalne w przypadku zwykłych procesorów możliwości budowania plastycznych i w pełni masywnie równoległych systemów mieszczących się niemal w jednym układzie scalonym. Fakt ten pozwala m.in. na budowanie w pełni równoległych wielopunktowych systemów pomiarowych. W artykule tym pokazano właśnie propozycję architektury takiego bazującego na FPGA przykładowego wielokanałowego systemu pomiarowego oraz przedstawiono wyniki jego praktycznego wykorzystania do badania funkcjonowania rurowego wymiennika ciepła w klimatyzacji samochodowej.

4

Wpływ zastosowania programowania równoległego na wydajność algorytmów kryptograficznych

Kraska M., Kozieł P.

Journal of Computer Sciences Institute

|

2016

|

Vol. 2

120--126

PL

W artykule zostały porównane możliwości zrównoleglenia dwóch algorytmów z dziedziny kryptografii: szyfrowania XOR oraz wyszukiwania kolizji funkcji skrótu MD5. Prezentowane rozwiązania zostały zaimplementowane w taki sposób, by używały wybraną przez użytkownika liczbę rdzeni procesora. Wydajność algorytmów została sprawdzona na różnych procesorach i przedstawiona na wykresach.

EN

Paper compares possibility to parallelize two cryptographic algorithms: Xor cipher and MD5 collision search. Presented solutions allows user to specify number of used processors. Performance of algorithms where tested on a different types of processors and visualized on graphs.

5

Application of projection-based interpolation algorithm for non-stationary problem

Woźniak M., Paszyński M.

Computer Science

|

2016

|

Vol. 17 (3)

297--319

EN

In this paper, we present a solver for non-stationary problems using L 2 projec- tion and h -adaptations. The solver utilizes the Euler time integration scheme for time evolution mixed with projection-based interpolation techniques for solving the L 2 projection problem at every time step. The solver is tested on the model problem of a heat transfer in an L-shape domain. We show that our solver delivers linear computational cost at every time step.

6

Topology optimization of carbon based flat structures using parallel computing

Kuś W., Mrozek A.

Computer Methods in Materials Science

|

2016

|

Vol. 16, No. 3

163--168

EN

The optimization algorithms based on global techniques like evolutionary algorithms tend to be time consuming due to a very high number of objective function evaluations. The computational effort can be reduced when the parallel approach is used. The paper is devoted to parallel versions of optimization algorithm developed for a multicore computer, manycore coprocessor and a supercomputer. The idea of dividing tasks between available cores is described. The optimization of carbon based flat structures problem is used as a test problem in the paper. The paper is focused mainly on the efficiency and scalability of the proposed algorithms.

PL

W artykule przedstawiono metodę oraz algorytm równoległej optymalizacji mimetycznej w zastosowaniu do optymalizacji płaskich struktur atomowych opartych na węglu. W artykule wykorzystano trzy rodzaje zasobów obliczeniowych, typowy komputer wieloprocesowy z wieloma rdzeniami, superkomputer IBM BlueGene/Q oraz koprocesor Intel PHI. Obliczenia przeprowadzono dla problemu optymalizacji rozkładu atomów węgla przy użyciu funkcji celu związanej z energią struktury. W pracy porównano skalowalność przedstawionego algorytmu optymalizacji dla różnych platform sprzętowych.

7

Torus-connected cycles: A simple and scalable topology for interconnection networks

Bossard A., Kaneko K.

International Journal of Applied Mathematics and Computer Science

|

2015

|

Vol. 25, no. 4

723--735

EN

Supercomputers are today made up of hundreds of thousands of nodes. The interconnection network is responsible for connecting all these nodes to each other. Different interconnection networks have been proposed; high performance topologies have been introduced as a replacement for the conventional topologies of recent decades. A high order, a low degree and a small diameter are the usual properties aimed for by such topologies. However, this is not sufficient to lead to actual hardware implementations. Network scalability and topology simplicity are two critical parameters, and they are two of the reasons why modern supercomputers are often based on torus interconnection networks (e.g., Fujitsu K, IBM Sequoia). In this paper we first describe a new topology, torus-connected cycles (TCCs), realizing a combination of a torus and a ring, thus retaining interesting properties of torus networks in addition to those of hierarchical interconnection networks (HINs). Then, we formally establish the diameter of a TCC, and deduce a point-to-point routing algorithm. Next, we propose routing algorithms solving the Hamiltonian cycle problem, and, in a two dimensional TCC, the Hamiltonian path one. Correctness and complexities are formally proved. The proposed algorithms are time-optimal.

8

Zachowanie akumulatorów trakcyjnych zamontowanych w pojeździe elektrycznym

Bakun B.

Przegląd Elektrotechniczny

|

2014

|

R. 90, nr 2

152--155

PL

W niniejszym artykule przedstawiono problem eksploatacji pojazdu elektrycznego z zastosowaniem akumulatorów kwasowoołowiowych, połączonych w szereg i równolegle, bez systemu zarządzania stanem akumulatorów (BMS). Przedstawiony jest charakterystyczny i powtarzalny - w swoim sposobie - stan rozładowania akumulatorów.

EN

This paper presents the problem of using an electric vehicle using lead-acid batteries connected in series and in parallel, without Battery Management System (BMS). There is shown a characteristic and reproducible - in his way – battery state of charge.

9

Collecting Polish-German parallel corpora in the Web

Rosińska M.

Systems Science

|

2008

|

Vol. 34, no 4

41-45

EN

Parallel corpus has recently become an indispensable resource in multilingual natural language processing. Manual preparation of a bilingual corpus is a laborious task. Therefore methods for the automated creation of parallel corpus are currently a topic of concern for many researchers. A number of sophisticated and effective algorithms for collecting parallel texts from the Web have already been created. Unfortunately, none of them have been used in the process of Polish-German corpus creation. That is why the aim of the research has been to verify the efficiency of existing algorithms for the collecting of Polish-German parallel corpus, intended as a reference source for a Machine Translation system, to propose a new algorithm and present results achieved by the new algorithm.

10

Calculation of Clothing Insulation by Serial and Parallel Methods: Effects on Clothing Choice by IREQ and Thermal Responses in the Cold

Kuklane K., Gao C., Holmer I., Giedraityte L., Brode P., Candas V., Hartog den E., Meinander H., Richards M., Havenith G.

International Journal of Occupational Safety and Ergonomics

|

2007

|

Vol. 13, No. 2

103--116

EN

Cold protective clothing was studied in 2 European Union projects. The objectives were (a) to examine different insulation calculation methods as measured on a manikin (serial or parallel), for the prediction of cold stress (IREQ); (b) to consider the effects of cold protective clothing on metabolic rate; (c) to evaluate the movement and wind correction of clothing insulation values. Tests were carried out on 8 subjects. The results showed the possibility of incorporating the effect of increases in metabolic rate values due to thick cold protective clothing into the IREQ model. Using the higher thermal insulation value from the serial method in the IREQ prediction, would lead to unacceptable cooling of the users. Thus, only the parallel insulation calculation method in EN 342:2004 should be used. The wind and motion correction equation (No. 2) gave realistic values for total resultant insulation; dynamic testing according to EN 342:2004 may be omitted.