From Cyclo-Static Process Networks to Code Generation for Multidimensional Software Pipelining. (Des réseaux de processus cyclo-statiques à la génération de code pour le pipeline multi-dimensionnel)

Applications based on streams, ordered sequences of data values, are important targets of program optimization because of their high computational requirements and the diversity of their application domains: communication, embedded systems, multimedia, etc. One of the most important and difficult problems in special purpose stream language design and implementation is how to schedule these applications in a fine-grain way to exploit available machine resources. In this thesis we propose a framework for fine-grain scheduling of streaming applications and nested loops in general. First, we try to pipeline steady state phases (inner loops), by finding the repeated kernel pattern, and executing actor occurrences in parallel as much as possible. Then we merge the kernel prolog and epilog of pipelined phases to move them out of the outer loop. Merging the kernel prolog and epilog means that we shift actor occurrences, or instructions, from one phase iteration to another and from one outer loop iteration to another, a multidimensional shifting. Experimental shows that our framework can improve performance, parallelism extraction without increasing the code size, in streaming applications and nested loops in general. te l-0 06 83 22 4, v er si on 1 28 M ar 2 01 2