Journal
PROCEEDINGS OF THE 2019 46TH INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA '19)
Volume -, Issue -, Pages 39-52Publisher
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3307650.3326633
Keywords
Machine learning; real-time systems; energy; heterogeneous architectures; resource allocation
Categories
Funding
- NSF [CCF-1439156, CNS-1526304, CCF-1823032, CNS-1764039]
- Proteus project under the DARPA BRASS program
- DOE
Ask authors/readers for more resources
Machine learning and artiicial intelligence are invaluable for computer systems optimization: as computer systems expose more resources for management, ML/AI is necessary for modeling these resources' complex interactions. The standard way to incorporate ML/AI into a computer system is to irst train a learner to accurately predict the system's behavior as a function of resource usage-e.g., to predict energy eiciency as a function of core usage-and then deploy the learned model as part of a system-e-g., a scheduler. In this paper, we show that (1) continued improvement of learning accuracy may not improve the systems result, but (2) incorporating knowledge of the systems problem into the learning process improves the systems results even though it may not improve overall accuracy. Speciically, we learn application performance and power as a function of resource usage with the systems goal of meeting latency constraints with minimal energy. We propose a novel generative model which improves learning accuracy given scarce data, and we propose a multi-phase sampling technique, which incorporates knowledge of the systems problem. Our results are both positive and negative. The generative model improves accuracy, even for state-of-the-art learning systems, but negatively impacts energy. Multi-phase sampling reduces energy consumption compared to the state-of-the-art, but does not improve accuracy. These results imply that learning for systems optimization may have reached a point of diminishing returns where accuracy improvements have little efect on the systems outcome. Thus we advocate that future work on learning for systems should de-emphasize accuracy and instead incorporate the system problem's structure into the learner.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available