@techreport {1138, title = {The Case for Directive Programming for Accelerator Autotuner Optimization}, journal = {Innovative Computing Laboratory Technical Report}, number = {ICL-UT-17-07}, year = {2017}, month = {2017-10}, publisher = {University of Tennessee}, abstract = {In this work, we present the use of compiler pragma directives for parallelizing autotuning of specialized compute kernels for hardware accelerators. A set of constructs, that include prallelizing a source code that prune a generated search space with a large number of constraints for an autotunning infrastructure. For a better performance we studied optimization aimed at minimization of the run time.We also studied the behavior of the parallel load balance and the speedup on four different machines: x86, Xeon Phi, ARMv8, and POWER8.}, author = {Diana Fayad and Jakub Kurzak and Piotr Luszczek and Panruo Wu and Jack Dongarra} }