Hybrid Heuristics for Mapping Task Problem on Large Scale Heterogeneous Platforms

2016 ◽  
Author(s):  
Ania Kaci ◽  
Huy-Nam Nguyen ◽  
Amir Nakib ◽  
Patrick Siarry
Keyword(s):  
Large Scale ◽  
Heterogeneous Platforms ◽  
Hybrid Heuristics ◽  
Mapping Task

Interpretive MPI for Parallel Computing

2008 ◽  
Author(s):  
Yu-Cheng Chou ◽  
Harry H. Cheng
Keyword(s):  
Parallel Computing ◽  
Programming Languages ◽  
Message Passing ◽  
Large Scale ◽  
Message Passing Interface ◽  
Rapid Development ◽  
Web Based ◽  
Heterogeneous Platforms ◽  
C Programs ◽  
Computation Speedup

Message Passing Interface (MPI) is a standardized library specification designed for message-passing parallel programming on large-scale distributed systems. A number of MPI libraries have been implemented to allow users to develop portable programs using the scientific programming languages, Fortran, C and C++. Ch is an embeddable C/C++ interpreter that provides an interpretive environment for C/C++ based scripts and programs. Combining Ch with any MPI C/C++ library provides the functionality for rapid development of MPI C/C++ programs without compilation. In this article, the method of interfacing Ch scripts with MPI C implementations is introduced by using the MPICH2 C library as an example. The MPICH2-based Ch MPI package provides users with the ability to interpretively run MPI C program based on the MPICH2 C library. Running MPI programs through the MPICH2-based Ch MPI package across heterogeneous platforms consisting of Linux and Windows machines is illustrated. Comparisons for the bandwidth, latency, and parallel computation speedup between C MPI, Ch MPI, and MPI for Python in an Ethernet-based environment comprising identical Linux machines are presented. A Web-based example is given to demonstrate the use of Ch and MPICH2 in C based CGI scripting to facilitate the development of Web-based applications for parallel computing.

scholarly journals Broadcasting on Large Scale Heterogeneous Platforms under the Bounded Multi-Port Model

2014 ◽  
Vol 25 (10) ◽  
pp. 2520-2528 ◽  
Author(s):  
Olivier Beaumont ◽  
Nicolas Bonichon ◽  
Lionel Eyraud-Dubois ◽  
Przemyslaw Uznanski ◽  
Shailesh Kumar Agrawal
Keyword(s):  
Large Scale ◽  
Heterogeneous Platforms

scholarly journals Virtual/Real Transfer in a Large-Scale Environment: Impact of Active Navigation as a Function of the Viewpoint Displacement Effect and Recall Tasks

2013 ◽  
Vol 2013 ◽  
pp. 1-7 ◽  
Author(s):  
Grégory Wallet ◽  
Hélène Sauzéon ◽  
Florian Larrue ◽  
Bernard N'Kaoua
Keyword(s):  
Spatial Learning ◽  
Large Scale ◽  
Ground Level ◽  
Sorting Task ◽  
Environment Impact ◽  
Displacement Effect ◽  
Egocentric Frame ◽  
Mapping Task ◽  
Navigation Mode ◽  
Better Than

The purpose of this study was to examine the effect of navigation mode (passive versus active) on the virtual/real transfer of spatial learning, according to viewpoint displacement (ground: 1 m 75 versus aerial: 4 m) and as a function of the recall tasks used. We hypothesize that active navigation during learning can enhance performances when route strategy is favored by egocentric match between learning (ground-level viewpoint) and recall (egocentric frame-based tasks). Sixty-four subjects (32 men and 32 women) participated in the experiment. Spatial learning consisted of route learning in a virtual district (four conditions: passive/ground, passive/aerial, active/ground, or active/aerial), evaluated by three tasks:wayfinding,sketch-mapping,andpicture-sorting. In thewayfinding task, subjects who were assigned the ground-level viewpoint in the virtual environment (VE) performed better than those with the aerial-level viewpoint, especially in combination with active navigation. In thesketch-mapping task, aerial-level learning in the VE resulted in better performance than the ground-level condition, while active navigation was only beneficial in the ground-level condition. The best performance in thepicture-sorting taskwas obtained with the ground-level viewpoint, especially with active navigation. This study confirmed the expected results that the benefit of active navigation was linked with egocentric frame-based situations.

scholarly journals ON THE COMPLEXITY OF MAPPING LINEAR CHAIN APPLICATIONS ONTO HETEROGENEOUS PLATFORMS

2009 ◽  
Vol 19 (03) ◽  
pp. 383-397 ◽  
Author(s):  
ANNE BENOIT ◽  
YVES ROBERT ◽  
ERIC THIERRY
Keyword(s):  
Large Scale ◽  
Broad Class ◽  
Linear Chain ◽  
Real Life ◽  
Interval Mapping ◽  
Constant Factor ◽  
Data Set ◽  
Heterogeneous Platforms ◽  
Mapping Problem ◽  
One To One

In this paper, we explore the problem of mapping linear chain applications onto large-scale heterogeneous platforms. A series of data sets enter the input stage and progress from stage to stage until the final result is computed. An important optimization criterion that should be considered in such a framework is the latency, or makespan, which measures the response time of the system in order to process one single data set entirely. For such applications, which are representative of a broad class of real-life applications, we can consider one-to-one mappings, in which each stage is mapped onto a single processor. However, in order to reduce the communication cost, it seems natural to group stages into intervals. The interval mapping problem can be solved in a straightforward way if the platform has homogeneous communications: the whole chain is grouped into a single interval, which in turn is mapped onto the fastest processor. But the problem becomes harder when considering a fully heterogeneous platform. Indeed, we prove the NP-completeness of this problem. Furthermore, we prove that neither the interval mapping problem nor the similar one-to-one mapping problem can be approximated in polynomial time by any constant factor (unless P=NP).

Techniques for Solving Large-Scale Graph Problems on Heterogeneous Platforms

2016 ◽  
pp. 318-332
Author(s):  
Ilya Afanasyev ◽  
Alexander Daryin ◽  
Jack Dongarra ◽  
Dmitry Nikitenko ◽  
Alexey Teplov ◽  
...  
Keyword(s):  
Large Scale ◽  
Heterogeneous Platforms ◽  
Graph Problems
Sign in / Sign up

Export Citation Format

Share Document