ChipAdvisor: A Machine Learning Approach for Mapping Applications to Heterogeneous Systems

Hiwot Tadese Kassa, Tarunesh Verma, Todd Austin, Valeria Bertacco
University of Michigan


While hardware accelerators provide significant performance and energy improvements over general-purpose processors, their limited reusability incurs high design costs. It is thus impractical to have a unique accelerator for each application. Hence, it is critical to develop solutions that can leverage the accelerators available to the best of their capabilities for a wide range of applications. In this paper, we note the common computation, data access, and communication patterns of applications, and based on these patterns, we identify significant intrinsic properties across applications. We then correlate these properties with the unique microarchitectural properties of the compute platforms available and develop a framework, ChipAdvisor, to predict the platform that provides the best performance and energy efficiency for an application. We evaluate ChipAdvisor for applications from several domains, targeting CPUs, GPUs, and FPGAs as example compute platforms. ChipAdvisor achieves an accuracy of up to 98% in predicting the best performing platform, and 94% in predicting the most energy efficiency one, compared to an oracle analysis, that is, one which always selects the best platform for all applications.