There are several parallel programming models available for numerical computations at different levels of expressibility and ease of use. For the development of new domainspecific programming models, a splitting into...
详细信息
ISBN:
(纸本)9783540681052
There are several parallel programming models available for numerical computations at different levels of expressibility and ease of use. For the development of new domainspecific programming models, a splitting into a distributed data container and parallel data iterators is proposed. Data distribution is implemented in application specific libraries. Data iterators are directly analysed and compiled automatically into parallel code. Target architectures of the source-to-source translation include shared (pthreads, Cell SPE), distributed memory (MPI) and hybrid programming styles. A model applications for grid based hierarchical numerical methods and an auto-parallelizing compiler are introduced.
暂无评论