Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. An overview of the Fortran-D programming system. In Proceedings of the Fourth Workshop on Languages and Compilers for Parallel Computing, 1991. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Optimization of Array Redistribution for Distributed Memory.. - Akiyoshi Wakatani (1995) (6 citations) (Correct)
....important for applications where the parallelism alternates between dimensions of the data, as in the alternating direction implicit (ADI) method [2] for partial differential equations. Even when redistribution isn t apparent, some communication patterns are equivalent to redistribution [1]. For instance, the assignment statement in the following HPF fragment generates a communication pattern that is essentially the same as redistributing A. real 8,dimension(n,n) A, B c hpf distribute (block,block) A c hpf distribute ( block) B B = A This paper proposes a spiral mapping of ....
Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. Compiling Fortran D for distributedmemory machines. Communications of ACM, 35(8):66--80, August 1992.
Implementing Data-Parallel Software on Dataflow Hardware - Shaw (1993) (2 citations) (Correct)
....both SIMD and MIMD. For SIMD computers, the data parallel programming model maps directly to the architecture, and is usually the only programming model available; for MIMD architectures, there has been work to compile data parallel languages to various MIMD architectures [13] 45] 34] 27] [31]. Although the work in compiling data parallel languages to MIMD machines is still in its early stages, the data parallel programming model is clearly effective: even without compilers for data parallel languages, programmers tend to write parallel programs in a Single Program Multiple Data (SPMD) ....
....assumptions we made, and then we describe the general data mapping and work distribution strategies. 3. 1 Objectives Data mapping and work distribution are intimately related in the data parallel programming model, because work is distributed with the data to minimize communications costs in [31], this is called the owner computes rule . Therefore, the choice of data mapping is especially important because it determines load balance as well as costs of communication. Assumptions about locality. We make no assumptions about spatial locality in the communications network. In the previous ....
[Article contains additional citation context not shown here]
Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. Compiling Fortran-D. Communications of the ACM, 35(8):66--80, August 1992.
Composites: Trees for Data Parallel Programming - Carroll, Pollock (1994) (1 citation) (Correct)
....written under control (or MIMD style) parallelism. Debugging is much easier because race conditions and deadlocks are avoided through single threaded execution. These advantages have led to numerous implementations of data parallel languages, such as C [27, 30] Dataparallel C [16] Fortran D [20], and High Performance Fortran [1] Unfortunately, the usefulness of data parallel programming for non scientific applications is limited in many ways by its basic assumptions. Data parallel programming languages, which normally exhibit fine grained parallelism with synchronization between each ....
....a separate model of parallel programming originated with CmLisp[18] and C [27, 30] the first data parallel languages from Thinking Machines. The success of C led to the design and implementation of a large number of other data parallel languages, including High Performance Fortran [1] Fortran D[20], DINO[28] and Dataparallel C[16] As data parallel programming came into wider use, a number of researchers started to investigate ways of applying the data parallel model to a broader class of architectures. A number of these have taken a similar approach to ours, starting by merging the data ....
[Article contains additional citation context not shown here]
Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. An overview of the Fortran-D programming system. In Proceedings of the Fourth Workshop on Languages and Compilers for Parallel Computing, 1991.
Compiling and Optimizing Dynamic Parallel Programs - Mark Chu-Carroll Carroll (Correct)
No context found.
Seema Hiranandani, Ken Kennedy, and Chau-Wen Tseng. An overview of the Fortran-D programming system. In Proceedings of the Fourth Workshop on Languages and Compilers for Parallel Computing, 1991.
Adaptive Data Placement for Distributed-Memory Machines - Lowenthal, Andrews (1995) (2 citations) (Correct)
No context found.
Seema Hiranandani, Ken Kennedy, Charles Koelbel, Ulrich Kremer, and Chau-Wen Tseng. An overview of the Fortran-D programming system. Report TR91121, CRPC, March 1991.
Adaptive Data Placement for Distributed-Memory Machines - Lowenthal, Andrews (1995) (2 citations) (Correct)
No context found.
Seema Hiranandani, Ken Kennedy, Charles Koelbel, Ulrich Kremer, and Chau-Wen Tseng. An overview of the Fortran-D programming system. Report TR91121, CRPC, March 1991.
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