The article describes the process of computing the Z-transform neural network on the basis of input and output signals of analyzed object. parallel algorithms for performing these calculations are presented and differ...
详细信息
The article describes the process of computing the Z-transform neural network on the basis of input and output signals of analyzed object. parallel algorithms for performing these calculations are presented and different parallel architectures with different number of processors showing their advantages and limitations are analyzed. (C) 2019 Elsevier B.V. All rights reserved.
The programming process for modern parallel processors including multi-core CPUs and many-core GPUs (Graphics Processing Units) represents a significant challenge for application developers. We propose to use the wide...
详细信息
In this research, we compare the computational productivity of several different popular approaches and libraries for parallel computing, both CPU-based and GPU-based. As a model benchmarking task, the Computational F...
详细信息
There are many paradigms available to address the unique and complex problems introduced with parallel programming. These complexities have implications for computer science education as ubiquitous multi-core computer...
详细信息
There are many paradigms available to address the unique and complex problems introduced with parallel programming. These complexities have implications for computer science education as ubiquitous multi-core computers drive the need for programmers to understand parallelism. One major obstacle to student learning of parallel programming is that there is very little human factors evidence comparing the different techniques to one another, so there is no clear direction on which techniques should be taught and how. We performed a randomized controlled trial using 88 university-level computer science student participants performing three identical tasks to examine the question of whether or not there are measurable differences in programming performance between two paradigms for concurrent programming: threads compared to process-oriented programming based on Communicating Sequential Processes. We measured both time on task and programming accuracy using an automated token accuracy map (TAM) technique. Our results showed trade-offs between the paradigms using both metrics and the TAMs provided further insight about specific areas of difficulty in comprehension.
The use of a Phase Field method for medical image segmentation is proposed in this paper. The Allen-Cahn equation, a mathematical model equation, is used in this method. The Finite Difference method is used for numeri...
详细信息
The use of a Phase Field method for medical image segmentation is proposed in this paper. The Allen-Cahn equation, a mathematical model equation, is used in this method. The Finite Difference method is used for numerical discretization of model equations and semi-algebraic equations integrated over time using the second-order Runge-Kutta method. Numerical algorithms are implemented into computer programming using the serial and parallel C programming language based on GPU CUDA. Based on image segmentation calculations, the Phase Field method has high accuracy. It is indicated by the Jaccard Index and Dice Similarity values that are close to one. The range of Jaccard Index values is 0.859 - 0.952, while the Dice Similarity value range is 0.926 - 0.976. In addition, it is shown that parallel programming with GPU CUDA can accelerate 45.72 times compared to serial programming.
Today, almost every computer has at least one multicore processor. To remain in stride with hardware developments, numerous university faculties oriented towards computer science have introduced parallel programming a...
详细信息
Today, almost every computer has at least one multicore processor. To remain in stride with hardware developments, numerous university faculties oriented towards computer science have introduced parallel programming as an integral part of their courses. The question is, given the availability of parallel architectures, and considering future trends in programming, whether it is time for parallel programming to also become an integral part of the informatics curriculum in secondary schools? This paper presents research conducted in three schools in Croatia over several school years. A total of 162 students from the science-mathematic high schools participated in the research. The results, based on student evaluations, suggest that this course content is equally interesting and somewhat more difficult, and perceived as equally useful as other course content taught to students. Moreover, the findings indicate that students can understand and later apply some of the fundamental concepts of parallel programming.
Contribution This study reveals that the programming paradigm is relevant to obtain advanced programming skills. Background parallel computing has become mandatory for computer science students. The increasing amount ...
详细信息
Contribution This study reveals that the programming paradigm is relevant to obtain advanced programming skills. Background parallel computing has become mandatory for computer science students. The increasing amount of computational resources required by emerging applications need experienced programmers that fully exploit hardware resources. However, the hardware platforms and programming languages to leverage them evolve at a dizzying pace, making very challenging for students the successful learning of the continuously changing high-performance computing concepts. Research Questions (a) Is the learning curve of the programming language too steep to begin learning parallel programming fundamentals? (b) Are emergent learning methodologies making even more difficult to learn parallel programming in general? Methodology It is analyzed the main challenges for succeeding in parallel programming courses at the undergraduate level in two different learning modalities, namely on-campus and online. It is analyzed the main tools available within a learning management system, showing their impact on online studies. Findings Our results reveal that the steep learning curve for parallel programming is one of the main barriers to student success, leading to an early drop out of the subject. On-campus studies mitigate this problem through a close relationship between students and educators. Online studies, however, do not have this tight relationship by its definition.
Due to the current scenario in which multi-core architectures are predominant in most personal computers and servers, the knowledge of parallel programming content becomes fundamental for computer students to develop ...
详细信息
Due to the current scenario in which multi-core architectures are predominant in most personal computers and servers, the knowledge of parallel programming content becomes fundamental for computer students to develop software capable of obtaining the best performance of these architectures. Considering the importance of this context, this paper presents the results of a systematic mapping of the literature related to the teaching-learning process of parallel programming in the computing programmes in three important databases: ACM, IEEE and Science Direct. The results obtained showed that in order to solve the challenges and differences found in teaching-learning parallel programming, reorganization is necessary in the undergraduate programmes. A standard for parallel programming teaching is important. This can be established by defining where and how to insert parallelism in the courses, adopting a methodology to teach the contents of parallelism in several different courses, beginning the study in the first year. The main languages, libraries, difficulties encountered and methods of classroom and distance teaching for parallel programming are presented in this paper. Distance learning is still little explored in this area of knowledge, but it can support the teaching and study of these contents.
In the direction of arrival (DoA) estimation, typically sensor arrays are used where the number of required sensors can be large depending on the application. With the help of compressed sensing (CS), hardware complex...
详细信息
In the direction of arrival (DoA) estimation, typically sensor arrays are used where the number of required sensors can be large depending on the application. With the help of compressed sensing (CS), hardware complexity of the sensor array system can be reduced since reliable estimations are possible by using the compressed measurements where the compression is done by measurement matrices. After the compression, DoAs are reconstructed by using sparsity promoting algorithms such as alternating direction method of multipliers (ADMM). For the given procedure, both the measurement matrix design and the reconstruction algorithm may include computationally intensive operations, which are addressed in this study. The presented simulation results imply the feasibility of the system in real-time processing with energy efficient implementations. We propose employing parallel programming to satisfy the real-time processing requirements. While the measurement matrix design has been accelerated 16x with CPU based parallel version with respect to the fastest serial implementation, ADMM based DoA estimation has been improved 1.1x with GPU based parallel version compared to the fastest CPU parallel implementation. In addition, we achieved, to the best of our knowledge, the first energy-efficient real-time DoA estimation on embedded Jetson GPGPUs in 15 W power consumption without affecting the DoA accuracy performance.
Bioinformatics allows and encourages the application of many different parallel programming approaches. This special issue brings together high-quality state-of-the-art contributions about parallel programming in bioi...
详细信息
Bioinformatics allows and encourages the application of many different parallel programming approaches. This special issue brings together high-quality state-of-the-art contributions about parallel programming in bioinformatics, from some interesting points of view or perspectives. The special issue collects considerably extended and improved versions of the best papers, accepted and presented in PBio 2017 (5th International Workshop on parallelism in Bioinformatics, and part of ICA3PP 2017). The domains and topics covered in these 2 papers are timely and important, and the authors have done an excellent job of presenting the material.
暂无评论