Results 1  10
of
11
Automatic Mapping Tasks to Cores Evaluating AMTHA Algorithm in Multicore Architectures
"... The AMTHA (Automatic Mapping Task on Heterogeneous Architectures) algorithm for tasktoprocessors assignment and the MPAHA (Model of Parallel Algorithms on Heterogeneous Architectures) model are presented. The use of AMTHA is analyzed for multicore processorbased architectures, considering the com ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The AMTHA (Automatic Mapping Task on Heterogeneous Architectures) algorithm for tasktoprocessors assignment and the MPAHA (Model of Parallel Algorithms on Heterogeneous Architectures) model are presented. The use of AMTHA is analyzed for multicore processorbased architectures, considering the communication model among processes in use. The results obtained in the tests carried out are presented, comparing the real execution times on multicores of a set of synthetic applications with the predictions obtained with AMTHA. Finally current lines of research are presented, focusing on clusters of multicores and hybrid programming paradigms.
INCLUDING IMPROVEMENT OF THE EXECUTION TIME IN A SOFTWARE ARCHITECTURE OF LIBRARIES WITH SELFOPTIMISATION
"... autotuning, performance modelling, selfoptimisation, hierarchy of libraries The design of hierarchies of libraries helps to obtain modular and efficient sets of routines to solve problems of specific fields. An example is ScaLAPACK’s hierarchy in the field of parallel linear algebra. To facilitate ..."
Abstract
 Add to MetaCart
autotuning, performance modelling, selfoptimisation, hierarchy of libraries The design of hierarchies of libraries helps to obtain modular and efficient sets of routines to solve problems of specific fields. An example is ScaLAPACK’s hierarchy in the field of parallel linear algebra. To facilitate the efficient execution of these routines, the inclusion of selfoptimization techniques in the hierarchy has been analysed. The routines at a level of the hierarchy use information generated by routines from lower levels. But sometimes, the information generated at one level is not accurate enough to be used satisfactorily at higher levels, and a remodelling of the routines is necessary. A remodelling phase is proposed and analysed with a Strassen matrix multiplication. 1
Using metaheuristics in a parallel computing course ⋆
"... Abstract. In this paper the use of metaheuristics techniques in a parallel computing course is explained. In the practicals of the course different metaheuristics are used in the solution of a mapping problem in which processes are assigned to processors in a heterogeneous environment, with heteroge ..."
Abstract
 Add to MetaCart
Abstract. In this paper the use of metaheuristics techniques in a parallel computing course is explained. In the practicals of the course different metaheuristics are used in the solution of a mapping problem in which processes are assigned to processors in a heterogeneous environment, with heterogeneity in computation and in the network. The parallelization of the metaheuristics is also considered. 1
CONCURRENCY AND COMPUTATION: PRACTICE AND EXPERIENCE Concurrency Computat.: Pract. Exper. 2000; 00:1–6
"... Prepared using cpeauth.cls [Version: 2002/09/19 v2.02] Optimizing process allocation of parallel programs for heterogeneous clusters ..."
Abstract
 Add to MetaCart
Prepared using cpeauth.cls [Version: 2002/09/19 v2.02] Optimizing process allocation of parallel programs for heterogeneous clusters
Heterogeneous PBLAS: A Set of Parallel Basic Linear Algebra Subprograms for Heterogeneous Computational Clusters
"... We present a package, called Heterogeneous PBLAS (HeteroPBLAS), which is built on top of PBLAS and provides optimized parallel basic linear algebra subprograms for Heterogeneous Computational Clusters. We present the user interface and the software hierarchy of the first research implementation of H ..."
Abstract
 Add to MetaCart
We present a package, called Heterogeneous PBLAS (HeteroPBLAS), which is built on top of PBLAS and provides optimized parallel basic linear algebra subprograms for Heterogeneous Computational Clusters. We present the user interface and the software hierarchy of the first research implementation of HeteroPBLAS. This is the first step towards the development of a parallel linear algebra package for Heterogeneous Computational Clusters. We demonstrate the efficiency of the HeteroPBLAS programs on a homogeneous computing cluster and a
A Model for the Automatic Mapping of Tasks to Processors in Heterogeneous Multicluster Architectures *
, 2007
"... This paper discusses automatic mapping methods for concurrent tasks to processors applying graph analysis for the relation among tasks, in which processing and communicating times are incorporated. Starting by an analysis in which processors are homogeneous and data transmission times do not depend ..."
Abstract
 Add to MetaCart
This paper discusses automatic mapping methods for concurrent tasks to processors applying graph analysis for the relation among tasks, in which processing and communicating times are incorporated. Starting by an analysis in which processors are homogeneous and data transmission times do not depend on the processors that are communicating (a typical case in homogeneous clusters), we progress to extend the model to heterogeneous processors having the possibility of different communication levels, applicable to a multicluster. Some results obtained with the model and future work lines are presented, particularly, the possibility of obtaining the required optimal number of processors, keeping a constant efficiency level.
HETEROPBLAS: A SET OF PARALLEL BASIC LINEAR ALGEBRA SUBPROGRAMS OPTIMIZED FOR HETEROGENEOUS COMPUTATIONAL CLUSTERS ∗
"... Abstract. This paper presents a software library, called Heterogeneous PBLAS (HeteroPBLAS), which provides optimized parallel basic linear algebra subprograms for Heterogeneous Computational Clusters. This library is written on the top of HeteroMPI and PBLAS whose building blocks, the de facto stand ..."
Abstract
 Add to MetaCart
Abstract. This paper presents a software library, called Heterogeneous PBLAS (HeteroPBLAS), which provides optimized parallel basic linear algebra subprograms for Heterogeneous Computational Clusters. This library is written on the top of HeteroMPI and PBLAS whose building blocks, the de facto standard kernels for matrix and vector operations (BLAS) and message passing communication (BLACS), are optimized for heterogeneous computational clusters. This is the first step towards the development of a parallel linear algebra package for Heterogeneous Computational Clusters. We show that the efficiency of the parallel routines is due to the most important feature of the library, which is the automation of the difficult optimization tasks of parallel programming on heterogeneous computing clusters. They are the determination of the accurate values of the platform parameters such as the speeds of the processors and the latencies and bandwidths of the communication links connecting different pairs of processors, the optimal values of the algorithmic parameters such as the data distribution blocking factor, the total number of processes, the 2D process grid arrangement, and the efficient mapping of the processes executing the parallel algorithm to the executing nodes of the heterogeneous computing cluster. We present the user interface and the software hierarchy of the first research implementation of HeteroPBLAS. We demonstrate the efficiency of the HeteroPBLAS programs on a homogeneous computing cluster and a heterogeneous computing cluster. Key words: parallel linear algebra, ScaLAPACK, HeteroMPI, heterogeneous platforms 1. Introduction. This paper presents a software library, called Heterogeneous PBLAS (HeteroPBLAS),
* This research is partly supported by the program of the Presidium of the Russian Academy of Sciences “Mathematical
"... Optimal mapping of a parallel application processes onto heterogeneous platform * ..."
Abstract
 Add to MetaCart
Optimal mapping of a parallel application processes onto heterogeneous platform *