R. Barriuso and A. Knies (1994), "SHMEM User's Guide for Fortran, Rev. 2.2", Cray Research, Inc. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Analyzing Data Structures for Parallel Sparse.. - Tourino, Doallo.. (1996) (Correct)
....stored from the beginning of such buffer. Note that we have to dimension the ring buffer to a size long enough to preserve, during the k iteration, the k column of Q until the updating of the last column of Q (see Figure 1) This parallel algorithm was coded in Fortran 77 and the Cray T3D SHMEM [5] native shared memory library was used for communication. With these routines we can minimize the communication overhead at the expense of a very careful programming due to possible synchronization and cache coherence problems. It only has three communication operations per iteration (say, k) a ....
....of the switch operations is negligible and the reduced dense submatrix appears distributed in a regular cyclic manner. Figure 10 (b) presents the parallel execution times for the BCS based right looking LU algorithm. This time the parallel algorithm was coded in Fortran 77 and the Cray T3D SHMEM [5] native shared memory library was used for communication. The factorization numerical errors of our parallel algorithm are similar to those of the MA48 routine, and they can be reduced by applying a previous scaling to the matrix. Besides, the fill in of our algorithm is also similar to that of ....
R. Barriuso, A. Knies (1994), "SHMEM User's Guide for Fortran, Rev. 2.2", Cray Research, Inc.
Iterative And Direct Sparse Solvers On Parallel Computers - Asenjo, Bandera.. (1996) (Correct)
No context found.
R. Barriuso and A. Knies (1994), "SHMEM User's Guide for Fortran, Rev. 2.2", Cray Research, Inc.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC