Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications
KAUST DepartmentComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Extreme Computing Research Center
KAUST Supercomputing Laboratory (KSL)
Supercomputing, Computational Scientists
Permanent link to this recordhttp://hdl.handle.net/10754/622145
MetadataShow full item record
AbstractThe performance optimization of scientific applications usually requires an in-depth knowledge of the hardware and software. A performance tuning mechanism is suggested to automatically tune OpenACC parameters to adapt to the execution environment on a given system. A historic learning based methodology is suggested to prune the parameter search space for a more efficient auto-tuning process. This approach is applied to tune the OpenACC gang and vector clauses for a better mapping of the compute kernels onto the underlying architecture. Our experiments show a significant performance improvement against the default compiler parameters and drastic reduction in tuning time compared to a brute force search-based approach.
CitationSiddiqui S, AlZayer F, Feki S (2015) Historic Learning Approach for Auto-tuning OpenACC Accelerated Scientific Applications. High Performance Computing for Computational Science -- VECPAR 2014: 224–235. Available: http://dx.doi.org/10.1007/978-3-319-17353-5_19.
Conference/Event name11th International Conference on High Performance Computing for Computational Science, VECPAR 2014