R. Schreiber. High Performance Fortran, Version 2. Parallel Processing Letters, 7(4):437--449, 1997. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Managing Irregular Remote Accesses to Distributed Shared Arrays.. - Kessler (Correct)
....receive is usually sufficient to ensure relative synchronization and data consistency. Where senders and receivers cannot be determined statically, runtime techniques such as inspector executor [10] may be applied. In both cases the single thread of control is an important prerequisite. HPF 2 [12] offers limited task parallelism, which is based on group splitting, but within each group there is still a single thread of control. As NestStep is a more general MIMD language, compiler techniques for HPF can be applied only in special cases. OpenMP [11] allows general MIMD computations and ....
R. Schreiber. High Performance Fortran, Version 2. Parallel Processing Letters, 7(4):437--449, 1997.
NestStep: Nested Parallelism and Virtual Shared Memory for the.. - Keßler (1999) (1 citation) (Correct)
....message passing, although developers of BSP algorithms often use a similar notation. 14] proposes a cost model for nested parallelism in BSP that could immediately be used with NestStep. Distributed arrays. Distribution of arrays has been addressed in various languages, like Split C [5] or HPF [13]. Unfortunately, many compiler techniques to generate and optimize communication are restricted to SIMD languages like HPF. Virtual distributed shared memory. Some virtual shared memory emulations are based on paging and caching. Although this allows to exploit the virtual memory management ....
R. Schreiber. High Performance Fortran, Version 2. Parallel Processing Letters, 7(4):437--449, 1997.
Optimization Rules for Programming with Collective Operations - Gorlatch, Wedler, Lengauer (1999) (7 citations) (Correct)
....parallel computing. They have become an essential part of parallel languages based on various paradigms and targeting various architectures: conventional SPMD programming with run time libraries like MPI [7] and BSP [8] environments for clusters of SMPs like SIMPLE [2] array languages like HPF [11] and ZPL [12] functional languages like NESL [3] high level programming environments like P3L [1] intermediate representations in loop parallelization [10] and others. Collective operations offer several advantages over explicit send receive statements. First, the use of collective operations ....
R. Schreiber. High Performance Fortran, Version 2. Parallel Processing Letters, 7(4):437--449, 1997.
Optimization Rules for Programming with Collective Operations - Gorlatch, Wedler, Lengauer (1999) (7 citations) (Correct)
....computing. They have become an essential part of parallel languages based on various paradigms and targeting various architectures: conventional SPMD programming with MPI [9] and PVM, bulk synchronous BSP libraries [11] environments for clusters of SMPs like SIMPLE [3] array languages like HPF [14] and ZPL [16] functional languages like NESL [4] high level programming environments like P3L [1] intermediate representations in loop parallelization [13] and others. Collective operations ooeer several advantages over lower level constructs like explicit send receive statements. First, the ....
R. Schreiber. High Performance Fortran, Version 2. Parallel Processing Letters, 7(4):437 449, 1997.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC