Evolutionary algorithms for compiler-enabled program autotuning

• Main Author: Pacula, Maciej
• Other Authors: Una-May O'Reilly.
• Format: Others
• Language: English
• Published: Massachusetts Institute of Technology 2011
• Subjects: Electrical Engineering and Computer Science.
• Online Access: http://hdl.handle.net/1721.1/66313

Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2011. === This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections. === Cataloged from student submitted PDF version of thesis. === Includes bibliographical references (p. 116-122). === PetaBricks [4, 21, 7, 3, 5] is an implicitly parallel programming language which, through the process of autotuning, can automatically optimize programs for fast QoS-aware execution on any hardware. In this thesis we develop and evaluate two PetaBricks autotuners: INCREA and SiblingRivalry. INCREA, based on a novel bottom-up evolutionary algorithm, optimizes programs offline at compile time. SiblingRivalry improves on INCREA by optimizing online during a program's execution, dynamically adapting to changes in hardware and the operating system. Continuous adaptation is achieved through racing, where half of available resources are devoted to always-on learning. We evaluate INCREA and SiblingRivalry on a large number of real-world benchmarks, and show that our autotuners can significantly speed up PetaBricks programs with respect to many non-tuned and mis-tuned baselines. Our results indicate the need for a continuous learning loop that can optimize efficiently by exploiting online knowledge of a program's performance. The results leave open the question of how to solve the online optimization problem on all cores, i.e. without racing. === by Maciej Pacula. === M.Eng.