ludecomposition is widely used in the field of numerical analysis and engineering to solve large-scale sparse linear *** complex data dependency makes it difficult to parallelize the lu *** this paper,an architecture...
详细信息
ISBN:
(纸本)9781509066261;9781509066254
ludecomposition is widely used in the field of numerical analysis and engineering to solve large-scale sparse linear *** complex data dependency makes it difficult to parallelize the lu *** this paper,an architecture with an efficientcache for parallelsparseludecompositionusingfpga is *** proposed architecture is based on the Gilbert-Peierls(GP) *** using the elimination graph,we find the column dependency of the lu *** is thus possible to exploit the *** a dependency table,a simple but efficientcache strategy and its corresponding architecture are *** proposed cache strategy avoids the cache miss and reduces the size of cache used to store all the intermediate data on *** experiment demonstrates that,our design can achieve speedup of 2.85 x-10.27 x,compared with UMFPACK running on general purpose *** cache size can be reduced by 50.93% on average with the proposed cache strategy.
暂无评论