Parallelization of linearized applications in Fortran D

摘要

Fortran D extends Fortran to parallel computers via specification of the distribution of array variables across processors. When multidimensional arrays have been linearized for optimal performance on vector processors, Fortran D cannot produce the best parallelization because it is limited to one-dimensional distribution, which is less efficient due to surface-to-volume effects. We propose Fortran D extensions and compiler technology to support natural topology parallelization of such codes. Experimental results are presented to illustrate the improvement in performance of this approach over the performance of currently available methods.