Efficient task migration is an important feature in parallel and distributed programs, in particular to support checkpointing and recovery for fault tolerance. It is also very useful in distributed environments like networks of workstations where external loads are often unpredictable and dynamic in nature. We propose simple language extensions (ELMO) to existing sequential programming languages like C, Fortran or C++, that provide a object-based task-parallel execution model. Tasks may be dynamically created, are location transparent, and may be migrated or checkpointed transparently by the system. In this paper, ELMO's language features together with the requisite compiler support is presented. 1 Introduction Networks of workstations...
Coarse-grained task parallelism exists in sequential code and can be leveraged to boost the use of ...
Abstract. In this paper, we propose an approach to automatic compiler parallelization based on langu...
It is well known that parallelization of software is a difficult problem to solve. This project aime...
The programming of parallel and distributed applications is difficult. The proliferation of net wor...
International audience[Excerpt from the introduction] The spreading of Distributed Memory Parallel C...
This paper demonstrates how parallel programming language features can be specified as composable la...
Parallel computing is notoriously challenging due to the difficulty in developing correct and effici...
Associated research group: Minnesota Extensible Language ToolsThis paper describes parallelizing com...
Efficiently using multicore architectures demands an increasing degree of fluency in parallel progra...
Gardens is an integrated programming language and system which supports efficient parallel computati...
The definition of High Performance Fortran (HPF) is a significant event in the maturation of paralle...
The paper addresses dynamic allocation of objects in a distributed object-oriented (OO for short) pr...
This paper presents an source-level software system, PMT, which performs task migrations for long-ru...
Migration is a fundamental mechanism for achieving load balancing and locality of references in para...
Object-oriented programming has been very successful for general purpose programming tasks for almos...
Coarse-grained task parallelism exists in sequential code and can be leveraged to boost the use of ...
Abstract. In this paper, we propose an approach to automatic compiler parallelization based on langu...
It is well known that parallelization of software is a difficult problem to solve. This project aime...
The programming of parallel and distributed applications is difficult. The proliferation of net wor...
International audience[Excerpt from the introduction] The spreading of Distributed Memory Parallel C...
This paper demonstrates how parallel programming language features can be specified as composable la...
Parallel computing is notoriously challenging due to the difficulty in developing correct and effici...
Associated research group: Minnesota Extensible Language ToolsThis paper describes parallelizing com...
Efficiently using multicore architectures demands an increasing degree of fluency in parallel progra...
Gardens is an integrated programming language and system which supports efficient parallel computati...
The definition of High Performance Fortran (HPF) is a significant event in the maturation of paralle...
The paper addresses dynamic allocation of objects in a distributed object-oriented (OO for short) pr...
This paper presents an source-level software system, PMT, which performs task migrations for long-ru...
Migration is a fundamental mechanism for achieving load balancing and locality of references in para...
Object-oriented programming has been very successful for general purpose programming tasks for almos...
Coarse-grained task parallelism exists in sequential code and can be leveraged to boost the use of ...
Abstract. In this paper, we propose an approach to automatic compiler parallelization based on langu...
It is well known that parallelization of software is a difficult problem to solve. This project aime...