Abstract | ||
---|---|---|
We present two implementations of dense matrix multiplication based on two different non-canonical array layouts: one based on a hypermatrix data structure (HM) where data submatrices are stored using a recursive layout; the other based on a simple block data layout with square blocks (SB) where blocks are arranged in column-major order. We show that the iterative code using SB outperforms a recursive code using HM and obtains competitive results on a variety of platforms. |
Year | Venue | Keywords |
---|---|---|
2006 | parallel computing | data submatrices,hypermatrix data structure,simple block data layout,different non-canonical array layout,iterative code,recursive code,recursive layout,column-major order,dense matrix multiplication,obtains competitive result,dense matrix operation |
Field | DocType | Volume |
Data structure,Memory hierarchy,Computer science,Parallel computing,Algorithm,Block (data storage),Theoretical computer science,Multiplication,Matrix multiplication,Block matrix,Recursion,Sparse matrix | Conference | 4699 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-75754-6 | 1 |
PageRank | References | Authors |
0.42 | 3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
José R. Herrero | 1 | 1 | 0.42 |
Juan J. Navarro | 2 | 323 | 42.90 |