Plamenka Borovska

Comparison of parallel metaheuristics for solving the TSP

The paper compares the efficiency of several metaheuristics for solving the travelling salesman problem. Parallel computational models are suggested for ant colony optimization, simulated annealing and genetic algorithm. The models utilize multiple independent runs on multicomputer platform. The performance parameters and parallelism profiling of the metaheuristics are made based on hybrid (MPI+OpenMP) implementations of the suggested models for solving several instances of TSP from the TSPLIB.

Data protection utilizing trusted platform module

Data protection has become a major requirement for computer systems which process sensitive information especially in daily commercial activities. It is mainly achieved through encryption based on software protections measures that have constantly shown lacks of security against attacks or malicious codes. In this paper we present and explore a real scenario for data encryption utilizing trusted computing technology and its core named trusted platform module (TPM). This new technology, which assists with encryption at the hardware level instead of the software, makes more difficult for intruders and attackers to break into the system and compromise the data stored there. The processes from activation of TPM to the encryption of data are investigated. At the end, an analysis of the advantages and limitations of protection has been made in respect to the functions of TPM and some other models as well.

Parallel models for sequence alignment on CPU and GPU

The paper presents parallel computational models of Smith-Waterman algorithm for CPU and GPU. An investigation is made of the performance parameters of computing similarity indexes between query sequences and a reference sequence using the suggested parallel programming models. Implementations for GPU based sequence alignment using nVIDIA CUDA and OpenCL as well as CPU based sequence alignment using OpenMP multithreaded implementation are presented. The experimental analyses are aimed at searching for similarities of the human gamma interferon protein and influenza virus.

Parallel performance evaluation of multithreaded local sequence alignment

Bioniformatics is area, demanding knowledge and skills for acquisition, storing, management, analysis, interpretation and dissemination of biological information. This scientific area requires powerful computing resources for exploring large sets of biological data. Biological sequence processing is a key for molecular biology. Smith-Waterman algorithm, based on dynamic programming has become the most fundamental in bioinformatics. The goal of this paper is to investigate the efficiency of parallel multithreaded implementation based on Smith-Waterman algorithm. Performance parameters have been estimated by the experiments using various data sets on two parallel computer platforms.

Massively parallel algorithm for multiple biological sequences alignment

In silico biological sequence processing is a key for molecular biology. This scientific area requires powerful computing resources for exploring large sets of biological data. Multiple sequence alignment is widely used method for biological sequence processing. The goal of this method is DNA and protein sequences alignment. This paper presents an innovative parallel algorithm MSA BG for multiple alignment of biological sequences that is highly scalable and locality aware. The designed MSABG algorithm is iterative and is based on the concept of Artificial Bee Colony metaheuristics and the concept of algorithmic and architectural spaces correlation. The metaphor of the ABC metaheuristics has been constructed and the functionalities of the agents have been defined. The conceptual parallel model of computation has been designed. The algorithmic framework of the designed parallel algorithm has been constructed.

αΩHighway interconnection network architecture for high performance computing

The interconnection network is a crucial part of high-performance computer systems. It significantly determines parallel system performance as well as the development and the operating cost. In this paper we suggest efficient and scalable hierarchical multi-ring interconnection network architecture. For building up the interconnection network we have designed adequate switch architecture and implemented “step-back-on-blocking” flow control algorithm. The architectural model has been verified and communicational performance parameters have been evaluated on the basis of numerous simulation experiments conducted in the OMNeT++ simulation environment.

Parallel performance evaluation and profiling of multiple sequence nucleotide alignment on the supercomputer BlueGene/P

Biological sequence processing is a key of information technology for molecular biology. This scientific area requires powerful computing resources for exploring large sets of biological data. Multiple sequence alignment is an important method in the DNA and protein analysis. ClustalW has become the most popular tool and implements a progressive method for multiple sequence alignment. The goal of this paper is to propose the performance evaluation of the efficiency of parallel multiple alignment on the supercomputer BlueGene/P for the case study of investigating viral nucleotide sequences and finding out consensus motifs and variable domains in the different segments of influenza virus A genome. Parallel performance evaluation and profiling of multiple sequence alignment have been performed on the basis of parallel program implementation based on ClustalW method and a local mirror database of all available isolates of the 8 segments of the influenza virus A. The molecular biology outcome of the experiments is that the consensus and the variable domains in Influenza virus A under investigation have been determined and output by utilizing the biological sequence alignment editor UGENE UniPro.

Token-based adaptive load balancing for dynamically parallel computations on multicomputer platforms

The paper suggests an algorithm for token-based adaptive load balancing for dynamically parallel computations on multicomputer platforms. The proposed algorithm for load balance is initiated and performed by the idle or under-loaded processes and requires token message circulating among the parallel processes and bearing information about the load distribution throughout the system. The efficiency of the algorithm is estimated for the case study of Sam Loyds puzzle utilizing parallel version of branch-and-bound search algorithm with depth-first search strategy. The experimental study is based on flat parallel program implementations. Speedup and efficiency of the parallel system are estimated as well as scalability of the application workload and the multicomputer size.

PARMETAOPT — Parallel metaheuristics framework for combinatorial optimization problems

The paper presents an experimental parallel metaheuristics framework for solving combinatorial optimization of grand challenge scientific and engineering problems that has been developed based on biologically inspired metaheuristics, modeling of social behavior and cultural evolution as well as trajectory-based methods. A prototype class library for metaheuristics is developed and several parallel computational models of metaheuristics for solving combinatorial optimization problems are implemented. The library contains implementations in C++ of parallel computational models for both population based and trajectory based metaheuristics. Some improvements in the parallel models are suggested and implemented in the library PARMETAOPT. The influence of the parameters on the performance of some of the parallel algorithms is analyzed using the developed parallel metaheuristics framework and performance tuning rules are suggested. The implementations are based on message passing with MPICH2 for the flat programming models and OpenMP API is used for multithreading in the hybrid programming models.

Efficiency of parallel metaheuristics for solving combinatorial problems

The paper investigates the speedup and quality of solution of parallel metaheuristics on multicomputer platform for the case studies of parallel genetic computation for solving the TSP and solving the room assignment problem by parallel simulated annealing. Parallel computational models have been suggested for solving the TSP by genetic approach with chromosome migration (SPMD paradigm) and for solving the room assignment problem by simulated annealing (manager/workers paradigm). The experimental study is based on flat (MPI-based) parallel program implementations on multicomputer platform. Performance and scalability analysis have been made in respect to the application size and multicomputer size. The impact of various factors on the quality of solutions have been investigated and presented.