论文信息 - A message segmentation technique to minimize task completion time

A message segmentation technique to minimize task completion time

Optimal partitioning of multiprocessor programs is a trade-off: as the granularity of subtasks of a parallel task increases, the communication overhead decreases but so does the total parallelism. The authors propose a new technique to determine the optimal segment size of messages between a producer and a consumer to minimize the overall execution time, and apply it to allocation of DOACROSS loops.<<ETX>>

[1] Sun-Yuan Kung,et al. On supercomputing with systolic/wavefront array processors , 1984 .

[2] D. Sorensen,et al. A pipelined givens method for computing the QR factorization of a sparse matrix , 1986 .

[3] Bowen Liu,et al. Programming in VS Fortran on the IBM 3090 for maximum vector performance , 1988, Computer.

[4] Anne Rogers,et al. Process decomposition through locality of reference , 1989, PLDI '89.

[5] Michael T. Heath,et al. Parallel solution of triangular systems on distributed-memory multiprocessors , 1988 .

[6] Dianne P. O'Leary,et al. Data-flow algorithms for parallel matrix computation , 1985, CACM.

[7] Edward F. Gehringer,et al. B-HIVE: hardware and software for an experimental multiprocessor , 1990, Twenty-Third Annual Hawaii International Conference on System Sciences.