Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Martin Griebl"'
Publikováno v:
Concurrency and Computation: Practice and Experience. 16:221-246
Tiling is a well-known technique for sequential compiler optimization, as well as for automatic program parallelization. However, in the context of parallelization, tiling should not be considered as a stand-alone technique, but should be applied aft
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::06e8bad1db5238a8b66ae4c24e017282
https://doi.org/10.1002/cpe.772
https://doi.org/10.1002/cpe.772
Publikováno v:
International Journal of Parallel Programming. 28:607-631
There are many algorithms for the space-time mapping of nested loops. Some of them even make the optimal choices within their framework. We propose a preprocessing phase for algorithms in the polytope model, which extends the model and yields space-t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::353e8670d58bdf4bb85237a30a4995bd
https://doi.org/10.1023/a:1007516818651
https://doi.org/10.1023/a:1007516818651
Publikováno v:
Parallel Computing. 25:1489-1510
One central problem in the execution of parallel nested loops with non-affine bounds is the precise scanning (i.e., enumeration) of the points in their iteration space and the detection of their termination. Scanning schemes have been proposed for bo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a1016598b90ab22171fd7c8a7300d277
https://doi.org/10.1016/s0167-8191(99)00063-0
https://doi.org/10.1016/s0167-8191(99)00063-0
Autor:
Martin Griebl, Jean-Francois Collard
Publikováno v:
Parallel Processing Letters. :117-131
This paper describes a dataflow analysis of array data structures for data-parallel and/or control- (or task-) parallel imperative languages. This analysis departs from previous work because it 1) simultaneously handles both parallel programming para
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e122d2a44aa9aa0189cd96a1d346d87a
https://doi.org/10.1142/s0129626497000140
https://doi.org/10.1142/s0129626497000140
Autor:
Martin Griebl, Christian Lengauer
Publikováno v:
International Journal of Parallel Programming. 23:471-496
The mathematical model for the parallelization, or “space-time mapping,” of loop nests is the polyhedron model. The presence ofwhile loops in the nest complicates matters for two reasons: (1) the parallelized loop nest does not correspond to a po
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2eb934a93f7cd562e28d71a16f7b918b
https://doi.org/10.1007/bf02577774
https://doi.org/10.1007/bf02577774
Autor:
Martin Griebl, Christian Lengauer
Publikováno v:
Parallel Processing Letters. :221-232
A WHILE-loop can be viewed as a FOR-loop with a dynamic upper bound. The computational model of polytopes is useful for the automatic parallelization of FOR-loops. We investigate its potential for the parallelization of WHILE-loops.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0efd94fde874a3d7251705af01c8c9ff
https://doi.org/10.1142/s0129626494000223
https://doi.org/10.1142/s0129626494000223
Publikováno v:
Euro-Par 2003 Parallel Processing ISBN: 9783540407881
Euro-Par
Euro-Par
Loop-carried code placement (LCCP) is able to remove redundant computations that cannot be recognized by traditional code motion techniques. However, this comes possibly at the price of increased communication time. We aim at minimizing the communica
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a58d5167570ac85f290ff5c504276b33
https://doi.org/10.1007/978-3-540-45209-6_45
https://doi.org/10.1007/978-3-540-45209-6_45
Autor:
Martin Griebl, Christian Lengauer
Publikováno v:
Proceedings the First Aizu International Symposium on Parallel Algorithms/Architecture Synthesis.
Recently, efforts have been made to devise automatic methods, based on a mathematical model, for the parallelization of loop nests with while loops. These methods are extensions of methods for the parallelization of nested for loops. As we present th
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::df6b706caf607ceb847b33daae5654d7
https://doi.org/10.1109/aispas.1995.401360
https://doi.org/10.1109/aispas.1995.401360
Autor:
Martin Griebl
Publikováno v:
SPAA
Automatic parallelization of loop programs based on space-time mapping typically aims at maximal parallelism. In order to obtain reasonable performance, the granularity of the parallelism must be coarsened, e.g., by applying tiling techniques.In cont
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::26b4632299d6c6fcf6755524ab709809
https://doi.org/10.1145/378580.378740
https://doi.org/10.1145/378580.378740
Publikováno v:
Euro-Par 2001 Parallel Processing ISBN: 9783540424956
Euro-Par
Euro-Par
Traditional code optimization techniques treat loops as nonpredictable structures and do not consider expressions containing array accesses for optimization. We show that the polyhedron model can be used to implement code placement techniques that ex
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::50210b6ee1c046ff322448de20872b18
https://doi.org/10.1007/3-540-44681-8_34
https://doi.org/10.1007/3-540-44681-8_34