Electronic Thesis and Dissertation Repository


Doctor of Philosophy


Computer Science


Marc Moreno Maza


Parallel programming is gaining ground in various domains due to the tremendous computational power that it brings; however, it also requires a substantial code crafting effort to achieve performance improvement. Unfortunately, in most cases, performance tuning has to be accomplished manually by programmers. We argue that automated tuning is necessary due to the combination of the following factors. First, code optimization is machine-dependent. That is, optimization preferred on one machine may be not suitable for another machine. Second, as the possible optimization search space increases, manually finding an optimized configuration is hard. Therefore, developing new compiler techniques for optimizing applications is of considerable interest. This thesis aims at generating new techniques that will help programmers develop efficient algorithms and code targeting hardware acceleration technologies, in a more effective manner. Our work is organized around a compilation framework, called MetaFork, for concurrency platforms and its application to automatic parallelization. MetaFork is a high-level programming language extending C/C++, which combines several models of concurrency including fork-join, SIMD and pipelining parallelism. MetaFork is also a compilation framework which aims at facilitating the design and implementation of concurrent programs through four key features which make MetaFork unique and novel: (1) Perform automatic code translation between concurrency platforms targeting multi-core architectures. (2) Provide a high-level language for expressing concurrency as in the fork-join model, the SIMD paradigm and the pipelining parallelism. (3) Generate parallel code from serial code with an emphasis on code depending on machine or program parameters (e.g. cache size, number of processors, number of threads per thread block). (4) Optimize code depending on parameters that are unknown at compile-time.