Matches in SemOpenAlex for { <https://semopenalex.org/work/W1951139325> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W1951139325 abstract "There is a stage in the GPU computing pipeline where a grid of thread-blocks is mapped to the problem domain. Normally, this grid is a k-dimensional bounding box that covers a k-dimensional problem no matter its shape. Threads that fall inside the problem domain perform computations, otherwise they are discarded at runtime. For problems with non-square geometry, this is not always the best idea because part of the space of computation is executed without any practical use. Two- dimensional triangular domain problems, alias td-problems, are a particular case of interest. Problems such as the Euclidean distance map, LU decomposition, collision detection and simula- tions over triangular tiled domains are all td-problems and they appear frequently in many areas of science. In this work, we propose an improved GPU mapping function g(lambda), that maps any lambda block to a unique location (i, j) in the triangular domain. The mapping is based on the properties of the lower triangular matrix and it works at a block level, thus not compromising thread organization within a block. The theoretical improvement from using g(lambda) is upper bounded as I < 2 and the number of wasted blocks is reduced from O(n^2) to O(n). We compare our strategy with other proposed methods; the upper-triangular mapping (UTM), the rectangular box (RB) and the recursive partition (REC). Our experimental results on Nvidias Kepler GPU architecture show that g(lambda) is between 12% and 15% faster than the bounding box (BB) strategy. When compared to the other strategies, our mapping runs significantly faster than UTM and it is as fast as RB in practical use, with the advantage that thread organization is not compromised, as in RB. This work also contributes at presenting, for the first time, a fair comparison of all existing strategies running the same experiments under the same hardware." @default.
- W1951139325 created "2016-06-24" @default.
- W1951139325 creator A5085139932 @default.
- W1951139325 creator A5088815725 @default.
- W1951139325 date "2013-08-06" @default.
- W1951139325 modified "2023-10-01" @default.
- W1951139325 title "Improving the GPU space of computation under triangular domain problems" @default.
- W1951139325 cites W2000335122 @default.
- W1951139325 cites W2011777324 @default.
- W1951139325 cites W2040583861 @default.
- W1951139325 cites W2060104647 @default.
- W1951139325 cites W2101779504 @default.
- W1951139325 cites W2116511687 @default.
- W1951139325 cites W2182846020 @default.
- W1951139325 cites W2295862081 @default.
- W1951139325 cites W2498568530 @default.
- W1951139325 hasPublicationYear "2013" @default.
- W1951139325 type Work @default.
- W1951139325 sameAs 1951139325 @default.
- W1951139325 citedByCount "1" @default.
- W1951139325 countsByYear W19511393252014 @default.
- W1951139325 crossrefType "posted-content" @default.
- W1951139325 hasAuthorship W1951139325A5085139932 @default.
- W1951139325 hasAuthorship W1951139325A5088815725 @default.
- W1951139325 hasConcept C111919701 @default.
- W1951139325 hasConcept C11413529 @default.
- W1951139325 hasConcept C114614502 @default.
- W1951139325 hasConcept C115961682 @default.
- W1951139325 hasConcept C121332964 @default.
- W1951139325 hasConcept C134306372 @default.
- W1951139325 hasConcept C135628077 @default.
- W1951139325 hasConcept C138101251 @default.
- W1951139325 hasConcept C147037132 @default.
- W1951139325 hasConcept C154945302 @default.
- W1951139325 hasConcept C173608175 @default.
- W1951139325 hasConcept C187691185 @default.
- W1951139325 hasConcept C198880260 @default.
- W1951139325 hasConcept C2524010 @default.
- W1951139325 hasConcept C2777210771 @default.
- W1951139325 hasConcept C2781302577 @default.
- W1951139325 hasConcept C33923547 @default.
- W1951139325 hasConcept C34388435 @default.
- W1951139325 hasConcept C36503486 @default.
- W1951139325 hasConcept C41008148 @default.
- W1951139325 hasConcept C45374587 @default.
- W1951139325 hasConcept C97355855 @default.
- W1951139325 hasConceptScore W1951139325C111919701 @default.
- W1951139325 hasConceptScore W1951139325C11413529 @default.
- W1951139325 hasConceptScore W1951139325C114614502 @default.
- W1951139325 hasConceptScore W1951139325C115961682 @default.
- W1951139325 hasConceptScore W1951139325C121332964 @default.
- W1951139325 hasConceptScore W1951139325C134306372 @default.
- W1951139325 hasConceptScore W1951139325C135628077 @default.
- W1951139325 hasConceptScore W1951139325C138101251 @default.
- W1951139325 hasConceptScore W1951139325C147037132 @default.
- W1951139325 hasConceptScore W1951139325C154945302 @default.
- W1951139325 hasConceptScore W1951139325C173608175 @default.
- W1951139325 hasConceptScore W1951139325C187691185 @default.
- W1951139325 hasConceptScore W1951139325C198880260 @default.
- W1951139325 hasConceptScore W1951139325C2524010 @default.
- W1951139325 hasConceptScore W1951139325C2777210771 @default.
- W1951139325 hasConceptScore W1951139325C2781302577 @default.
- W1951139325 hasConceptScore W1951139325C33923547 @default.
- W1951139325 hasConceptScore W1951139325C34388435 @default.
- W1951139325 hasConceptScore W1951139325C36503486 @default.
- W1951139325 hasConceptScore W1951139325C41008148 @default.
- W1951139325 hasConceptScore W1951139325C45374587 @default.
- W1951139325 hasConceptScore W1951139325C97355855 @default.
- W1951139325 hasLocation W19511393251 @default.
- W1951139325 hasOpenAccess W1951139325 @default.
- W1951139325 hasPrimaryLocation W19511393251 @default.
- W1951139325 hasRelatedWork W1507779820 @default.
- W1951139325 hasRelatedWork W1585537637 @default.
- W1951139325 hasRelatedWork W1988338706 @default.
- W1951139325 hasRelatedWork W1994125313 @default.
- W1951139325 hasRelatedWork W2027917757 @default.
- W1951139325 hasRelatedWork W2041454931 @default.
- W1951139325 hasRelatedWork W2083463614 @default.
- W1951139325 hasRelatedWork W2094444265 @default.
- W1951139325 hasRelatedWork W2276132393 @default.
- W1951139325 hasRelatedWork W2481847753 @default.
- W1951139325 hasRelatedWork W2747828031 @default.
- W1951139325 hasRelatedWork W2757156397 @default.
- W1951139325 hasRelatedWork W2808515206 @default.
- W1951139325 hasRelatedWork W2809452033 @default.
- W1951139325 hasRelatedWork W2886168566 @default.
- W1951139325 hasRelatedWork W2886926130 @default.
- W1951139325 hasRelatedWork W2922111169 @default.
- W1951139325 hasRelatedWork W3040878860 @default.
- W1951139325 hasRelatedWork W3137858876 @default.
- W1951139325 hasRelatedWork W3210059317 @default.
- W1951139325 isParatext "false" @default.
- W1951139325 isRetracted "false" @default.
- W1951139325 magId "1951139325" @default.
- W1951139325 workType "article" @default.