Search

Although automated empirical performance optimization and tuning is well-studied for kernels and domain-specific libraries, a current research grand challenge is how to extend these methodologies and tools to significantly larger sequential and parallel applications. In this context, we present the ROSE source-to-source outliner, which addresses the problem of extracting tunable kernels out of whole programs, thereby helping to convert the challenging whole-program tuning problem into a set of more manageable kernel tuning tasks. Our outliner aims to handle large scale C/C++, Fortran and OpenMP applications. A set of program analysis and transformation techniques are utilized to enhance the portability, scalability, and interoperability of source-to-source outlining. More importantly, the generated kernels preserve performance characteristics of tuning targets and can be easily handled by other tools. Preliminary evaluations have shown that the ROSE outliner serves as a key component within an end-to-end empirical optimization system and enables a wide range of sequential and parallel optimization opportunities. [ABSTRACT FROM AUTHOR]

Optimizing the performance of HPC software requires a high-level understanding of communication patterns as well as their relation to source code structures. We describe an algorithm to detect communication patterns in parallel traces and show how these patterns can guide static code analysis. First, we detect patterns that identify potential bottlenecks in MPI communication traces. Next, we associate the patterns with the corresponding nodes in an abstract syntaxtree using the ROSE compiler framework. Finally we perform static analysis on the annotated control flow and system dependence graphs to guide transformations such as code motion or the automatic introduction of MPI collectives. [ABSTRACT FROM AUTHOR]