Tag Archives: multithreading

Experimental Studies on the Performance of Algorithms for CFA Interpolation

Iva Nikolova

Abstract: This paper deals with the challenging task of reconstructing a full three-color representation of color images captured by a single image sensor – CCD or CMOS, which samples the image according to a color filter array (CFA). The output images feature a certain kind of pattern in which every pixel has only single-color information. The process of modifying the raw image sensor data to obtain full RGB color information at each pixel is called demosaicing or CFA interpolation. Seven popular algorithms CFA interpolation are regarded. The results of timing performance analysis of their sequential implementations are presented and discussed. The performance speedup analysis and scalability tests with multithreading and CUDA-based GPU implementations are analyzed.
Keywords: Bayer pattern, CFA interpolation, GPU, Image sensors, Multithreading, Parallel computations, Performance and speedup analysis.

Download article

Hybrid Parallel Programming Model for Solving the Travelling Salesman Problem

Atanas Hristov

Abstract: The modern high-performance computing systems (HPCS) are composed of hundreds of thousand computational nodes. An effective resource allocation in HPCS is a subject for many scientific research investigations. Many programming models for effectively resources allocation have been proposed. The main purpose of those models is to increase the parallel performance of the HPCS. The paper investigates the efficiency of parallel computing for solving the Travelling Salesman Problem (TSP). Hybrid parallel model is proposed based on the flat parallel programing model with message passing for communication between the computational nodes in the platform and parallel programming model of multithreading for communication between the cores inside the computational node. Parallel communications profiling is made and parallel performance parameters are evaluated on the basis of experimental results.

Key words: travelling salesman problem, NP-complete, “mater-workers” paradigm, multithreading, message passing interface, intel threading building blocks, parallel performance.

Download Article

New Generation of Programming Languages and Models for High Performance Computing Systems

Atanas Hristov, Plamenka Borovska

Abstract: The effective resource utilization of the modern high performance computing (HPC)
systems is subject for many scientific research investigations. In this paper, a new generation
programming languages and models for high performance computing systems have been
systematized and presented. The motives for development of modern methods for multithreading
and vector parallelization have been analyzed. The focuse is on the four main attributes of the
modern high performance computing systems: performance, programmability, portability and
robustness, because they are fundamental for developing of new generation of programming
languages.

Key words: high performance computing systems, multithreading, multicore systems, parallel
performance, parallel programming languages.

Download Article