Optimizing Irregular HPF Applications using Halos

نویسنده

  • Siegfried Benkner
چکیده

This paper presents language features for High Performance Fortran (HPF) to specify non-local access patterns of distributed arrays, called halos, and to control the communication associated with these non-local accesses. Using these features crucial optimization techniques required for an e cient parallelization of irregular applications may be applied. The information provided by halos is utilized by the compiler and runtime system to optimize the management of distributed arrays and the computation of communication schedules. High-level communication primitives for halos enable the programmer to avoid redundant communication, to reuse communication schedules, and to hide communication overheads by overlapping communication with computation. Performance results of a kernel from a crash simulation code on the NEC Cenju-4, the IBM SP2, and on the NEC SX-4 show that by using the proposed extensions a performance close to hand-coded message-passing codes can be achieved for irregular problems.

برای دانلود رایگان 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

HPF Library, Language and Compiler Support for Shadow Edges in Data Parallel Irregular Computations

On distributed memory architectures data parallel compilers emulate the global address space by distributing the data onto the processors according to the mapping directives of the user and by generating explicit inter-processor communication automatically. A shadow is additionally allocated local memory to keep on one processor also non-local values of the data that is accessed or deened by th...

متن کامل

A Tracing Protocol for Optimizing Data Parallel Irregular Computations

High Performance Fortran (HPF) is the de facto standard language for writing data parallel programs. In case of applications that use indirect addressing on distributed arrays, HPF compilers have limited capabilities for optimizing such codes on distributed memory architec-tures, especially for optimizing communication and reusing communication schedules between subroutine boundaries. This pape...

متن کامل

Multiple Data Parallelism with HPF and KeLP

Abs t r ac t . High Performance Fortran (HPF) is an effective language for implementing regular data parallel applications on distributed memory architectures, but it is not well suited to irregular, block-structured applications such as multiblock and adaptive mesh methods. A solution to this problem is to use a non-HPF SPMD program to coordinate multiple concurrent HPF tasks, each operating o...

متن کامل

Parallelizing Irregular Applications with the Vienna HPF+ Compiler VFC

Applications based on highly irregular, dynamically changing data structures cannot be handled eeciently with current High Performance Fortran and available HPF compilers. In order to support such applications, extensions of the language as well as sophisticated analysis and parallelization techniques are required. In this paper we introduce the Vienna HPF+ Compiler (VFC), a new source-to-sourc...

متن کامل

Which Applications Can Use High Performance Fortran and Fortran-D: Industry Standard Data Parallel Languages?

In this paper, we present the first, preliminary results of HPF/Fortran-D language analysis based on compiling and running benchmark applications using a prototype implementation of HPF/Fortran-D compiler. The analysis indicate that the HPF is a very convenient tool for programming many applications on massively parallel and/or distributed systems. In addition, we cumulate experience on how to ...

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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1999