[[abstract]]Two-dimensional mesh-connected computers with multiple broadcasting (2-MCCMBs) are studied. Previously, only square 2-MCCMBs with N processing elements (PEs) were considered for semigroup computations of N data items, and O(N1/6) time was required. The authors propose three approaches to achieve a better performance. With fewer PEs, first, an O(N1/7) time algorithm is derived on a square 2-MCCMB. Then it is found that square machines are not the best form for semigroup computations, and an O(N1/8) time algorithm is thus derived on a rectangular 2-MCCMB with N PEs. This time complexity can be further reduced to O(N1/9) if fewer PEs are used. Semigroup computations on k-dimensional MCCMBs are discussed.[[department]]資訊工程學
We present lower bounds on the amount of communication that matrix multiplication algorithms must pe...
AbstractThe problem of broadcasting in grid graphs is discussed. Two algorithms for broadcasting m m...
Maximising the performance of parallel systems requires matching message-passing algorithms and appl...
[[abstract]]Semigroup and prefix computations on two-dimensional mesh-connected computers with multi...
[[abstract]]For parallel algorithms, their execution time consists of two parts: the computation tim...
[[abstract]]©1992 Elsevier-The paper considers 2-dimensional mesh-connected computers with multiple ...
©2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish thi...
The mesh-connected computer architecture has emerged as a natural choice for solving a large number ...
AbstractSuppose we have a completely-connected network of random-access machines which communicate b...
Randomized selection algorithms on k-dimensional mesh-connected computers with multiple broadcasting...
Multiselection is the problem of selecting multiple elements at specified ranks from a set of arbitr...
On a mesh-connected computer, moving data across the mesh is the most time-consuming operation in ma...
Multiselection is the problem of selecting multiple elements at specified ranks from a set of arbitr...
A new methodology named CALMANT (CC-cube Algorithms on Meshes and Tori) for mapping a type of algori...
Sorting is a fundamental problem with applications in all areas of computer science and engineering....
We present lower bounds on the amount of communication that matrix multiplication algorithms must pe...
AbstractThe problem of broadcasting in grid graphs is discussed. Two algorithms for broadcasting m m...
Maximising the performance of parallel systems requires matching message-passing algorithms and appl...
[[abstract]]Semigroup and prefix computations on two-dimensional mesh-connected computers with multi...
[[abstract]]For parallel algorithms, their execution time consists of two parts: the computation tim...
[[abstract]]©1992 Elsevier-The paper considers 2-dimensional mesh-connected computers with multiple ...
©2001 IEEE. Personal use of this material is permitted. However, permission to reprint/republish thi...
The mesh-connected computer architecture has emerged as a natural choice for solving a large number ...
AbstractSuppose we have a completely-connected network of random-access machines which communicate b...
Randomized selection algorithms on k-dimensional mesh-connected computers with multiple broadcasting...
Multiselection is the problem of selecting multiple elements at specified ranks from a set of arbitr...
On a mesh-connected computer, moving data across the mesh is the most time-consuming operation in ma...
Multiselection is the problem of selecting multiple elements at specified ranks from a set of arbitr...
A new methodology named CALMANT (CC-cube Algorithms on Meshes and Tori) for mapping a type of algori...
Sorting is a fundamental problem with applications in all areas of computer science and engineering....
We present lower bounds on the amount of communication that matrix multiplication algorithms must pe...
AbstractThe problem of broadcasting in grid graphs is discussed. Two algorithms for broadcasting m m...
Maximising the performance of parallel systems requires matching message-passing algorithms and appl...