TGEX: a Tool for Portable Parallel and Distributed Execution of Unstructured Problems

نویسندگان

  • Hai-Xiang Lin
  • Arjan J. C. van Gemund
  • Johan Meijdam
  • Pier Nauta
چکیده

There exist a large number of scientiic and industrial applications with inherently unstructured parallelism which cannot be solved eeectively using a data parallel approach. In this paper we present TGEX, a generic tool for the parallel execution of unstructured problems on distributed memory computers. A general computational problem is rst expressed in terms of a computation task graph which serves as a machine-independent representation of the parallel program. TGEX then executes the task graph in a macro data ow style on the target distributed-memory machine. Thus TGEX simpliies parallel programming by freeing the application programmer from the burden of low level task synchro-nisation and communication. TGEX is implemented using PVM and is therefore portable on a large number of distributed memory systems.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Scalability analysis and parallel execution of unstructured problems

Unstructured parallelism is the hardest problem to analyze and to program. In this paper we present a generic approach TGEX for analyzing and executing unstructured problems. It separates the speciication of a computational problem from the control of the parallel execution. A computational problem is rst partitioned in terms of a computation task graph which serves as a machine-independent rep...

متن کامل

Scalability analysis and parallel execution of unstructured problemsHai

Unstructured parallelism is the hardest problem to analyze and to program. In this paper we present a generic approach TGEX for analyzing and executing unstructured problems. It separates the speciication of a computational problem from the control of the parallel execution. A computational problem is rst partitioned in terms of a computation task graph which serves as a machine-independent rep...

متن کامل

Design and initial performance of a high-level unstructured mesh framework on heterogeneous parallel systems

OP2 is a high-level domain specific library framework for the solution of unstructured mesh-based applications. It utilizes source-to-source translation and compilation so that a single application code written using the OP2 API can be transformed into multiple parallel implementations for execution on a range of back-end hardware platforms. In this paper we present the design and performance o...

متن کامل

Parallel Agglomeration Strategies for Industrial Unstructured Solvers

An industrial aerospace code has been parallelised for execution on shared memory and distributed memory architectures. The flow solver uses an explicit time integration approach and utilises an agglomeration multigrid strategy to accelerate the convergence. A novel method has been used to efficiently parallelise the multigrid solver that also minimised any intrusion into the flow solver. The p...

متن کامل

The "Annai" environment for portable distributed parallel programming

We are currently developing a portable integrated tool environment for distributed-memory parallel processors (DMPPs) as part of the Joint CSCS–ETH/NEC Collaboration in Parallel Processing. As we design and implement a sequence of tool prototypes these are used and evaluated by a team of application developers. This close interaction allows rapid feedback, as requests from the applicationdevelo...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1996