Journal
PROCEEDINGS OF 2019 5TH IEEE/ACM WORKSHOP ON MACHINE LEARNING IN HIGH PERFORMANCE COMPUTING ENVIRONMENTS (MLHPC 2019)
Volume -, Issue -, Pages 75-87Publisher
IEEE COMPUTER SOC
DOI: 10.1109/MLHPC49564.2019.00013
Keywords
-
Funding
- Intel(R)
- Intel(R) Big Data Center
- U.S. Army Research Laboratory
- U.S. Army Research Office [W911NF-13-1-0390, W911NF-18-1-0028]
- Office of Science of the U.S. Department of Energy [DE-AC02-05CH11231]
Ask authors/readers for more resources
Extracting actionable insight from complex unlabeled scientific data is an open challenge and key to unlocking data-driven discovery in science. Complementary and alternative to supervised machine learning approaches, unsupervised physics-based methods based on behavior-driven theories hold great promise. Due to computational limitations, practical application on real-world domain science problems has lagged far behind theoretical development. We present our first step towards bridging this divide - DisCo - a high-performance distributed workflow for the behavior-driven local causal state theory. DisCo provides a scalable unsupervised physics-based representation learning method that decomposes spatiotemporal systems into their structurally relevant components, which are captured by the latent local causal state variables. Complex spatiotemporal systems are generally highly structured and organize around a lower-dimensional skeleton of coherent structures, and in several firsts we demonstrate the efficacy of DisCo in capturing such structures from observational and simulated scientific data. To the best of our knowledge, DisCo is also the first application software developed entirely in Python to scale to over 1000 machine nodes, providing good performance along with ensuring domain scientists' productivity. We developed scalable, performant methods optimized for Intel many-core processors that will be upstreamed to open-source Python library packages. Our capstone experiment, using newly developed DisCo workflow and libraries, performs unsupervised spacetime segmentation analysis of CAM5.1 climate simulation data, processing an unprecedented 89.5 TB in 6.6 minutes end-to-end using 1024 Intel Haswell nodes on the Cori supercomputer obtaining 91% weak-scaling and 64% strong-scaling efficiency.
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