A Survey of Parallel Programming Models and Tools in the Multi and Many-Core Era

Díaz, Javier; Muñoz‐Caro, Camelia; Niño, Alfonso

doi:10.1109/tpds.2011.308

Cited by 222 publications

(159 citation statements)

References 66 publications

Supporting

Mentioning

151

Contrasting

Unclassified

Order By: Relevance

“…En este contexto, el término multicore hace referencia a aquellas arquitecturas en las que en un procesador se integran varios cores, usualmente entre dos y diez (Rivoire, 2010). Este tipo de procesador no mejora por sí sólo el desempeño de algoritmos secuenciales, pero si puede mejorar ostensiblemente el desempeño de algoritmos paralelos, siempre y cuando se dé una coordinación apropiada entre los diferentes cores cuando atienden tareas concurrentes (Díaz et al, 2012). Es importante mencionar que este tipo de procesadores, trabaja con un esquema de memoria compartida, teniendo en cuenta que los cores comparten un mismo espacio de memoria.…”

Section: Metodologíaunclassified

Desempeño de los Paradigmas Funcional y Orientado a Objetos en Arquitecturas Multicore: Caso de Estudio Haskell-Java

Hoyos

Puertas

2017

Inf. tecnol.

View full text Add to dashboard Cite

ResumenEn este trabajo se describe la implementación de paralelismo multicore en los lenguajes de programación Haskell y Java, utilizado dos paradigmas de programación diferentes, el funcional y el orientado a objetos. Se parte de una implementación ya existente del algoritmo solucionador de sudokus, desarrollada en Haskell con un enfoque funcional, a la que se incorporaron elementos de paralelización básica. Luego se construyó su equivalente desde la programación orientada a objetos en el lenguaje Java. Finalmente se realizaron diferentes mediciones para analizar y contrastar el desempeño de las dos implementaciones. De acuerdo al análisis realizado, se llegó a la conclusión que Haskell hace una utilización más óptima que Java de la arquitectura multicore.Palabras clave: arquitectura multicore; Haskell; Java; programación funcional, programación orientada a objetos Performance of Functional and Object-Oriented Paradigms in Multicore Architecture: Case Study Haskell-Java AbstractThis paper describes how multicore parallelism is implemented in the Haskell and Java programming languages, using two different programming paradigms, functional and object oriented. The starting point is an existing implementation of the sudokus solver algorithm, developed in Haskell with a functional approach, to which elements of basic parallelization were incorporated. After that, an equivalent version was constructed from object-oriented programming in the Java language. Finally, different measurements were taken to analyze and contrast the performance of the two implementations. According to the analysis, it was concluded that Haskell makes a more optimal use than Java of multicore architecture.

show abstract

Section: Metodologíaunclassified

Desempeño de los Paradigmas Funcional y Orientado a Objetos en Arquitecturas Multicore: Caso de Estudio Haskell-Java

Hoyos

Puertas

2017

Inf. tecnol.

View full text Add to dashboard Cite

show abstract

“…ARMCI annoyed as Aggregate Remote Copy Interface is one of the model that make it possible to allow a programming model between shared memory and message passing [15]. A standardize form of this model was introduced as Message Passing Interface (MPI).…”

Section: Mpimentioning

confidence: 99%

Empirical Analysis of HPC Using Different Programming Models

Ashraf¹,

Fouz²,

Eassa³

2016

IJMECS

View full text Add to dashboard Cite

Abstract-During the last decade, Heterogeneous systems are emerging for high performance computing [1]. In order to achieve high performance computing (HPC), existing technologies and programming models aims to see rapid growth toward intra-node parallelism [2]. The current high computational system and applications demand for a massive level of computation power. In last few years, Graphical processing unit (GPU) has been introduced an alternative of conventional CPU for highly parallel computing applications both for general purpose and graphic processing. Rather than using the traditional way of coding algorithms in serial by single CPU, many multithreading programming models has been introduced such as CUDA, OpenMP, and MPI to make parallel processing by using multicores. These parallel programming models are supportive to data driven multithreading (DDM) principle [3]. In this paper, we have presented performance based preliminary evaluation of these programming models and compared with the conventional single CPU serial processing system. We have implemented a massive computational operation for performance evaluation such as complex matrix multiplication operation. We used data driven multithreaded HPC system for performance evaluation and presented the results with a comprehensive analysis of these parallel programming models for HPC parallelism.

show abstract

“…Parallel computing has been proposed for decades [23] [24]. It can decrease the execution time of applications by executing them on multiple processors [25].…”

Section: Introductionmentioning

confidence: 99%

A scalable community detection algorithm for large graphs using stochastic block models

Peng

Zhang

Wong

et al. 2017

IDA

View full text Add to dashboard Cite

A Survey of Parallel Programming Models and Tools in the Multi and Many-Core Era

Cited by 222 publications

References 66 publications

Desempeño de los Paradigmas Funcional y Orientado a Objetos en Arquitecturas Multicore: Caso de Estudio Haskell-Java

Desempeño de los Paradigmas Funcional y Orientado a Objetos en Arquitecturas Multicore: Caso de Estudio Haskell-Java

Empirical Analysis of HPC Using Different Programming Models

A scalable community detection algorithm for large graphs using stochastic block models

Contact Info

Product

Resources

About