Parallelization of Linearized Applications in Fortran D

The Fortran D language extends Fortran by permitting the user to specify the distribution of array variables across the processors of a parallel computer system. This information can then be used by the compiler to derive a multidimensional parallelization. For programs in which multidimensional arrays have been linearized for optimal performance on vector processors, this strategy will not produce the best results because in those programs Fortran D is limited to a one-dimensional parallelization, which yields less e cient communication than multidimensional parallelization because of surface-to-volume e ects. This paper proposes Fortran D extensions and associated compiler technology to support natural topology parallelization of applications' codes with linearized arrays. Experimental results are presented to illustrate the improvement in performance of this new approach over the performance of currently available methods such as Fortran D and the PARTI inspector/executor strategy.