S. Gorlatch and Ch. Lengauer. Abstraction and performance in the design of parallel programs: An overview of the SAT approach. Acta Informatica, 36(9-10):761-803, May 2000. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Lifting Sequntial Functions to Parallel Skeletons - Nitsche (Correct)
.... skeletons to a xed set as in HOPP [23,24] P3L [2,21,7] or SCL [9,8] This means some restrictions for the programmer, but allows optimizing transformations on the skeletons [26,1] While these transformations can be applied automatically within the compiler, transformational approaches like SAT [12,13], APM [20] or work within BMF do not have the restriction of a xed skeleton set, but rely on additional information from the user to apply the appropriate transformations. Other systems like Skil [4,3] allow arbitrary skeletons to be used, but require that a library programmer implements the ....
S. Gorlatch and Ch. Lengauer. Abstraction and performance in the design of parallel programs: An overview of the SAT approach. Acta Informatica, 36(9-10):761-803, May 2000.
Towards Formally-Based Design of Message Passing Programs - Gorlatch (2000) (3 citations) Self-citation (Gorlatch) (Correct)
.... broad research on parallel models and languages: at the high level end of the spectrum, there are formallybased approaches that use abstract parallel constructs for ensuring correctness and portability, e.g. the BirdMeertens formalism (BMF) 1] and the transformational SAT approach based on it [2], skeletons [3] 4] and abstract parallel machines [5] The current research concentrates on yet not well understood issues, e.g. how should abstract constructs be composed together to build a parallel program, and how can the most cost e ective design alternative be chosen [6] at the ....
.... scan, which we have used in (7) to model MPI program (1) Although the notion of homomorphism seems to be quite restrictive, many practically relevant functions have been shown to be adjustable to the homomorphic format by introducing auxiliary function (s) i.e. at the price of extra computations [2], 13] Homomorphisms can be computed in parallel by partitioning the input list into an arbitrary concatenation of segments (blocks) as expressed by the promotion property: h red ( red ( map h (9) Programs in BMF, like (7) can be transformed by applying, step by step, ....
[Article contains additional citation context not shown here]
S. Gorlatch, \Abstraction and performance in the design of parallel programs," Habilitation Thesis. Universitat Passau. MIP9802, 1998.
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