A methodology for the development and the support of massively parallel programs

Danelutto, Marco; Meglio, Robert Di; Orlando, Salvatore; Pelagatti, Susanna; Vanneschi, Marco

doi:10.1016/0167-739x(92)90040-i

Cited by 47 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compare And Swap) [2]. This approach groups TBB in a family of solutions for parallel programming aimed at enabling programmers to explicitly define parallel behaviour via parametric exploitation patterns (skeletons, actually) that have been widely explored over the last two decades for parallel computing [11], [13], [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Efficient Smith-Waterman on Multi-core with FastFlow

Aldinucci

Meneghin

Torquati

2010

2010 18th Euromicro Conference on Parallel, Distributed and Network-Based Processing

View full text Add to dashboard Cite

Abstract-Shared memory multiprocessors have returned to popularity thanks to rapid spreading of commodity multi-core architectures. However, little attention has been paid to supporting effective streaming applications on these architectures. In this paper we describe FastFlow, a low-level programming framework based on lock-free queues explicitly designed to support high-level languages for streaming applications. We compare FastFlow with state-of-theart programming frameworks such as Cilk, OpenMP, and Intel TBB. We experimentally demonstrate that FastFlow is always more efficient than them on a given real world application: the speedup of FastFlow over other solutions may be substantial for fine grain tasks, for example +35% over OpenMP, +226% over Cilk, +96% over TBB for the alignment of protein P01111 against UniProt DB using the Smith-Waterman algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%

Efficient Smith-Waterman on Multi-core with FastFlow

Aldinucci

Meneghin

Torquati

2010

2010 18th Euromicro Conference on Parallel, Distributed and Network-Based Processing

View full text Add to dashboard Cite

show abstract

“…This includes initial formulations of certain task-parallel skeletons such as farm [37,195], pipeline [124], divide and conquer [130], and branch and bound [100] and some early work on data-parallel skeletons [139] such as scan [38]. Initially, the main focus of skeleton programming was on achieving high abstraction [175], either by usage of activity graphs [59] or by a high-level coordination language [71,72,40,26,81,108,68].…”

Section: Skeleton Programmingmentioning

confidence: 99%

Performance-aware component composition for GPU-based systems

Dastgeer¹

2014

View full text Add to dashboard Cite

This thesis adresses issues associated with efficiently programming modern heterogeneous GPU-based systems, containing multicore CPUs and one or more programmable Graphics Processing Units (GPUs). We use ideas from component-based programming to address programming, performance and portability issues of these heterogeneous systems. Specifically, we present three approaches that all use the idea of having multiple implementations for each computation; performance is achieved/retained either a) by selecting a suitable implementation for each computation on a given platform or b) by dividing the computation work across different implementations running on CPU and GPU devices in parallel.In the first approach, we work on a skeleton programming library (SkePU) that provides high-level abstraction while making intelligent implementation selection decisions underneath either before or during the actual program execution. In the second approach, we develop a composition tool that parses extra information (metadata) from XML files, makes certain decisions offline, and, in the end, generates code for making the final decisions at runtime. The third approach is a framework that uses source-code annotations and program analysis to generate code for the runtime library to make the selection decision at runtime. With a generic performance modeling API alongside program analysis capabilities, it supports online tuning as well as complex program transformations.These approaches differ in terms of genericity, intrusiveness, capabilities and knowledge about the program source-code; however, they all demonstrate usefulness of component programming techniques for programming GPU-based systems. With experimental evaluation, we demonstrate how all three approaches, although different in their own way, provide good performance on different GPU-based systems for a variety of applications.This work has been supported by two EU FP7 projects (PEP-PHER, EXCESS) and by SeRC. Populärvetenskaplig sammanfattningAtt få varje generation av datorer att fungera snabbareär viktigt för samhä-llets utveckling och tillväxt. Traditionellt hade de flesta datorer bara en general-purpose processor (den så kallade CPU:n) som bara kunde exekvera en beräkningsuppgift i taget. Under det senasteårtiondet har dock flerkärniga och mångkärniga processorer blivit vanliga, och datorer har också blivit mer heterogena. Ett modernt datorsystem innehåller vanligtvis flerän en CPU, tillsammans med specialprocessorer såsom grafikprocessorer (GPU:er) som ar anpassade för att kunna exekvera vissa typer av beräkningar effektivarë an CPU:er. Vi kallar ett sådant system med en eller flera GPU:er för ett GPU-baserat system. GPU:er i sådana system har sitt eget separata minne, och för att kunna köra en beräkning på en GPU så behöver man vanligtvis flytta all indata till GPU:ns minne och sedan hämta tillbaka resultatet när beräkningenär klar.Programmeringen av GPU-baserade systemär icke-trivialt av flera anledningar: (1) CPU:er och GPU:er kräver olika programmeringsexper...

show abstract

“…Other works [12] use algorithmic skeleton approach mainly to separate the communication/synchronization structure from the application-specific computation in order to optimize the mapping of skeletons on different underlying distributed architectures. Similarly many programming environments [3,9,11], based on functional or OOP languages, have been developed to provide, through skeletons, implicit parallel programming mechanisms. A mobile agent based approach for Paradigm-Oriented Distributed Computing is described in paper [6].…”

Section: Introductionmentioning

confidence: 99%

A Skeleton Based Programming Paradigm for Mobile Multi‐Agents on Distributed Systems and Its Realization within the MAGDA Mobile Agents Platform

Aversa

Martino

Mazzocca

et al. 2008

Mobile Information Systems

View full text Add to dashboard Cite

Abstract. Parallel programming effort can be reduced by using high level constructs such as algorithmic skeletons. Within the MAGDA toolset, supporting programming and execution of mobile agent based distributed applications, we provide a skeleton-based parallel programming environment, based on specialization of Algorithmic Skeleton Java interfaces and classes. Their implementation include mobile agent features for execution on heterogeneous systems, such as clusters of WSs and PCs, and support reliability and dynamic workload balancing. The user can thus develop a parallel, mobile agent based application by simply specialising a given set of classes and methods and using a set of added functionalities.

show abstract

A methodology for the development and the support of massively parallel programs

Cited by 47 publications

References 4 publications

Efficient Smith-Waterman on Multi-core with FastFlow

Efficient Smith-Waterman on Multi-core with FastFlow

Performance-aware component composition for GPU-based systems

A Skeleton Based Programming Paradigm for Mobile Multi‐Agents on Distributed Systems and Its Realization within the MAGDA Mobile Agents Platform

Contact Info

Product

Resources

About