Designing Zero-Copy Message Passing Interface Derived Datatype Communication Over Infiniband: Alternative Approaches and Performance Evaluation

2005 ◽  
Vol 19 (2) ◽  
pp. 129-142 ◽  
Author(s):  
Gopalakrishnan Santhanaraman ◽  
Jiesheng Wu ◽  
Wei Huang ◽  
Dhabaleswar K. Panda
Keyword(s):  
Performance Evaluation ◽  
Message Passing ◽  
Message Passing Interface ◽  
Zero Copy ◽  
Alternative Approaches ◽  
And Performance

scholarly journals A parallelization scheme to simulate reactive transport in the subsurface environment with OGS#IPhreeqc

2015 ◽  
Vol 8 (3) ◽  
pp. 2369-2402
Author(s):  
W. He ◽  
C. Beyer ◽  
J. H. Fleckenstein ◽  
E. Jang ◽  
O. Kolditz ◽  
...  
Keyword(s):  
Message Passing ◽  
Reactive Transport ◽  
Message Passing Interface ◽  
Transport Processes ◽  
Coupled Processes ◽  
Scientific Software ◽  
Geochemical Reactions ◽  
Optimized Allocation ◽  
And Performance ◽  
The One

Abstract. This technical paper presents an efficient and performance-oriented method to model reactive mass transport processes in environmental and geotechnical subsurface systems. The open source scientific software packages OpenGeoSys and IPhreeqc have been coupled, to combine their individual strengths and features to simulate thermo-hydro-mechanical-chemical coupled processes in porous and fractured media with simultaneous consideration of aqueous geochemical reactions. Furthermore, a flexible parallelization scheme using MPI (Message Passing Interface) grouping techniques has been implemented, which allows an optimized allocation of computer resources for the node-wise calculation of chemical reactions on the one hand, and the underlying processes such as for groundwater flow or solute transport on the other hand. The coupling interface and parallelization scheme have been tested and verified in terms of precision and performance.

The MPI and OpenMP Implementation of Parallel Algorithm for Generating Mandelbrot Set

2014 ◽  
Vol 571-572 ◽  
pp. 26-29
Author(s):  
Xiang Wei Duan ◽  
Wei Chang Shen ◽  
Jun Guo
Keyword(s):  
Parallel Algorithm ◽  
Shared Memory ◽  
Message Passing ◽  
Message Passing Interface ◽  
Algorithm Design ◽  
Performance Testing ◽  
Mandelbrot Set ◽  
The Difference ◽  
And Performance

The paper introduce the Mandelbrot Set and the message passing interface (MPI) and shared-memory (OpenMP), analyses the characteristic of algorithm design in the MPI and OpenMP environment, describes the implementation of parallel algorithm about Mandelbrot Set in the MPI environment and the OpenMP environment, conducted a series of evaluation and performance testing during the process of running, then the difference between the two system implementations is compared.

scholarly journals MPI to Coarray Fortran: Experiences with a CFD Solver for Unstructured Meshes

2017 ◽  
Vol 2017 ◽  
pp. 1-12 ◽  
Author(s):  
Anuj Sharma ◽  
Irene Moulitsas
Keyword(s):  
High Resolution ◽  
Message Passing ◽  
Message Passing Interface ◽  
Parallel Implementation ◽  
Unstructured Meshes ◽  
Navier Stokes ◽  
Performance Measurements ◽  
Partitioned Global Address Space ◽  
Computational Fluid Dynamics Cfd ◽  
And Performance

High-resolution numerical methods and unstructured meshes are required in many applications of Computational Fluid Dynamics (CFD). These methods are quite computationally expensive and hence benefit from being parallelized. Message Passing Interface (MPI) has been utilized traditionally as a parallelization strategy. However, the inherent complexity of MPI contributes further to the existing complexity of the CFD scientific codes. The Partitioned Global Address Space (PGAS) parallelization paradigm was introduced in an attempt to improve the clarity of the parallel implementation. We present our experiences of converting an unstructured high-resolution compressible Navier-Stokes CFD solver from MPI to PGAS Coarray Fortran. We present the challenges, methodology, and performance measurements of our approach using Coarray Fortran. With the Cray compiler, we observe Coarray Fortran as a viable alternative to MPI. We are hopeful that Intel and open-source implementations could be utilized in the future.

scholarly journals VISUAL PROGRAMMING FOR MESSAGE-PASSING SYSTEMS

1999 ◽  
Vol 09 (04) ◽  
pp. 397-423 ◽  
Author(s):  
NENAD STANKOVIC ◽  
KANG ZHANG
Keyword(s):  
Message Passing ◽  
Message Passing Interface ◽  
Direct Interaction ◽  
Visual Programming ◽  
Levels Of Abstraction ◽  
Concrete Objects ◽  
Real Objects ◽  
And Performance ◽  
Flow Graphs ◽  
Parallel Debugging

The attractiveness of visual programming stems in large part from the direct interaction with program elements as if they were real objects, since people deal better with concrete objects than with the abstract. This paper describes a new graph based software visualization tool for parallel message-passing programming named Visper that combines the levels of abstraction at which message-passing parallel programs are expressed and makes use of compositional programming. Central to the tool is the Process Communication Graph that correlates both the control and data flow graphs into a single graph formalism, without a need for complex textual annotation. The graph can express static and runtime communication and replication structures, as found in Message Passing Interface (MPI) and Parallel Virtual Machine (PVM). It also forms the basis for visualizing parallel debugging and performance.

scholarly journals Porting the AVS/Express scientific visualization software to Cray XT4

2011 ◽  
Vol 369 (1949) ◽  
pp. 3398-3412 ◽  
Author(s):  
George W. Leaver ◽  
Martin J. Turner ◽  
James S. Perrin ◽  
Paul M. Mummery ◽  
Philip J. Withers
Keyword(s):  
Performance Analysis ◽  
Message Passing ◽  
Large Scale ◽  
Message Passing Interface ◽  
Materials Science ◽  
Scientific Visualization ◽  
Visualization Software ◽  
Science Community ◽  
Interactive Application ◽  
And Performance

Remote scientific visualization, where rendering services are provided by larger scale systems than are available on the desktop, is becoming increasingly important as dataset sizes increase beyond the capabilities of desktop workstations. Uptake of such services relies on access to suitable visualization applications and the ability to view the resulting visualization in a convenient form. We consider five rules from the e-Science community to meet these goals with the porting of a commercial visualization package to a large-scale system. The application uses message-passing interface (MPI) to distribute data among data processing and rendering processes. The use of MPI in such an interactive application is not compatible with restrictions imposed by the Cray system being considered. We present details, and performance analysis, of a new MPI proxy method that allows the application to run within the Cray environment yet still support MPI communication required by the application. Example use cases from materials science are considered.

MPI-FT: PORTABLE FAULT TOLERANCE SCHEME FOR MPI

2000 ◽  
Vol 10 (04) ◽  
pp. 371-382 ◽  
Author(s):  
SOULLA LOUCA ◽  
NEOPHYTOS NEOPHYTOU ◽  
ADRIANOS LACHANAS ◽  
PARASKEVAS EVRIPIDOU
Keyword(s):  
Message Passing ◽  
Message Passing Interface ◽  
Fault Tolerant ◽  
Detection Mechanism ◽  
First Case ◽  
Monitoring Process ◽  
Replacement Process ◽  
The Dead ◽  
And Performance ◽  
Process Solutions

In this paper, we propose the design and development of a fault tolerant and recovery scheme for the Message Passing Interface (MPI). The proposed scheme consists of a detection mechanism for detecting process failures, and a recovery mechanism. Two different cases are considered, both assuming the existence of a monitoring process, the Observer which triggers the recovery procedure in case of failure. In the first case, each process keeps a buffer with its own message traffic to be used in case of failure, while the implementor uses periodical tests for notification of failure by the Observer. The recovery function simulates all the communication of the processes with the dead one by re-sending to the replacement process all the messages destined for the dead one. In the second case, the Observer receives and stores all message traffic, and sends to the replacement all the buffered messages destined for the dead process. Solutions are provided to the dead communicator problem caused by the death of a process. A description of the prototype developed is provided along with the results of the experiments performed for efficiency and performance.

Performance Evaluation of a Multiprocessor Cluster for a Thermohydrodynamic Lubrication Analysis

2005 ◽  
Author(s):  
Nenzi Wang ◽  
Chih-Ming Tsai
Keyword(s):  
Performance Evaluation ◽  
Message Passing ◽  
Message Passing Interface ◽  
Cost Effective ◽  
Parallel Applications ◽  
Single System ◽  
Fine Grain ◽  
Effective Manner ◽  
Single System Image ◽  
Programming Paradigms

This study presents a performance evaluation of two parallel programming paradigms, OpenMP and message-passing interface (MPI), for thermohydrodynamic lubrication analysis. In this study the performance of parallel computing in MPI cluster is equivalent to a similarly configured single-system image cluster. For a reasonable parallel efficiency (75%) the experimentally determined minimum execution times for the tasks to be conducted in parallel are approximate 0.5 and 5.0 seconds for OpenMP and MPI parallelism, respectively. It is noted that OpenMP programming allows parallel applications to be developed incrementally and supports fine-grain communication in a very cost effective manner. A computer program written in part to perform two or more tasks simultaneously may well be a computation norm in future tribological study.

Sign in / Sign up

Export Citation Format

Share Document