Data Distribution Concepts for Parallel Image Processing Data Distribution Concepts for Parallel Image Processing

| Data distributions gained a considerable interest in the eld of data parallel programming. In most cases they are key factors for the eeciency of the implementation. In this paper we analyze data distributions suited for parallel image processing and those deened by some of todays more popular parallel languages (HPF, Vienna Fortran, pC++) and libraries (ScaLAPACK). The majority of them belong to the class of bit permutations. These permutations can eeciently be realized on networks that are based on shuue permutations. As a result we propose to widen the scope of data distributions tolerated by parallel languages and libraries towards classes of distributions. For the large class of the so called normal algorithms we demonstrate that it is possible to implement library functions that can handle a large subclass of distributions thereby avoiding redistributions. At the application level of programming data distributions are to be handled analogously to data types. The concepts introduced are implemented in the parallel image processing system PIPS 1] which is presented brieey.