Optimization of Heterogeneous Systems with AI Planning Heuristics and Machine Learning: A Performance and Energy Aware Approach
Autor: | Suejb Memeti, Sabri Pllana |
---|---|
Jazyk: | angličtina |
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Optimization Computer Science - Machine Learning Computer science Computer Science - Artificial Intelligence Symmetric multiprocessor system Machine learning computer.software_genre Artificial intelligence (AI) Planning heuristics Machine Learning (cs.LG) Theoretical Computer Science Scheduling (computing) Computer Science - Software Engineering Automated planning and scheduling Numerical Analysis business.industry Computer Sciences Machine learning (ML) Computer Science Applications Software Engineering (cs.SE) Computational Mathematics Artificial Intelligence (cs.AI) Datavetenskap (datalogi) Computational Theory and Mathematics Artificial intelligence Heterogeneous computing business Heuristics Host (network) computer Software Energy (signal processing) Xeon Phi Efficient energy use |
Popis: | Heterogeneous computing systems provide high performance and energy efficiency. However, to optimally utilize such systems, solutions that distribute the work across host CPUs and accelerating devices are needed. In this paper, we present a performance and energy aware approach that combines AI planning heuristics for parameter space exploration with a machine learning model for performance and energy evaluation to determine a near-optimal system configuration. For data-parallel applications our approach determines a near-optimal host-device distribution of work, number of processing units required and the corresponding scheduling strategy. We evaluate our approach for various heterogeneous systems accelerated with GPU or the Intel Xeon Phi. The experimental results demonstrate that our approach finds a near-optimal system configuration by evaluating only about 7% of reasonable configurations. Furthermore, the performance per Joule estimation of system configurations using our machine learning model is more than 1000x faster compared to the system evaluation by program execution. Preprint |
Databáze: | OpenAIRE |
Externí odkaz: |