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. However, powerful modern supercomputers provide the opportunity to narrow the gap between theory and practical application. 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. This enables us to achieve state-of-the-art unsupervised segmentation of coherent spatiotemporal structures in complex fluid flows.Recently, supervised DL techniques have been applied to address this problem [24], [25], [26] including one of the 2018 Gordon Bell award winners [27]. However, there is an immediate and daunting challenge for these supervised approaches: ground-truth labels do not exist for pixel-level identification of extreme weather events [21]. The DL models used in the above studies are trained using the automated heuristics of TECA [20] for proximate labels. While the results in [24] qualitatively show that DL can improve upon TECA, the results in [26] reach accuracy rates over 97%, essentially reproducing the output of TECA. The supervised learning paradigm of optimizing objective metrics (e.g. training and generalization error) breaks down here [8] since TECA is not ground truth and we do not know how to train a DL model to disagree with TECA in just the right way to get closer to "ground truth".
Abstract-It is well-known that the performance difference between Python and basic C code can be up 200x, but for numerically intensive code another speedup factor of 240x or even greater is possible. The performance comes from software's ability to take advantage of CPU's multiple cores, single instruction multiple data (SIMD) instructions, and high performance caches. The article describes optimizations, included in Intel® Distribution for Python*, aimed to automatically boost performance of numerically intensive code. This paper is intended for Python programmers who want to get the most out of their hardware but do not have time or expertise to re-code their applications using techniques such as native extensions or Cython.
We present a validation and test methodology for a non-deterministic system, namely a True Random Number Generator (TRNG). The TRNG testing methods at Intel have matured over time, and what we present here is the 3rd generation methodology used in our latest chipset products. In addition to well known DFT and DFV techniques, testing of a TRNG requires rigorous statistical analysis to determine its proper operation. Known published works and standards don't address the TRNG testing and validation issues in high volumes or their recommendations are impractical in real manufacturing constraints. We present a practical statistical methodology for TRNG testing in a high volume manufacturing environment. Its validity was proven by testing a 65-nm CMOSbased TRNG design to meet NIST standards. Our methodology can be extended to the testing of similar non-deterministic systems.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.