Big data technologies have been successfully applied to many disciplines for knowledge discovery and decision making, but the further growth and adoption of the big data paradigm face several critical challenges. First, it is challenging to meet the performance needs of modern big data problems which are inherently more difficult, e.g., learning of heterogeneous and imprecise data, and have more stringent performance requirements, e.g., real-time analysis of dynamic data. Second, power consumption is becoming a serious limiting factor to the further scaling of big data systems and the applications that it can support. These challenges demand a new type of big data systems that incorporate unconventional hardware capable of accelerating data processing and accesses while lowering the system's power consumption. This project has addressed this need by developing GEARS (an enerGy-Efficient big-datA Research System), a unique infrastructure for studying heterogeneous and dynamic data using heterogeneous computing and storage resources. GEARS is a one-of-kind, energy-efficient big-data research infrastructure based on cohesively co-designed software and hardware components. It has enabled a variety of important studies on heterogeneous and dynamic data and advances the scientific knowledge in computer science as well as other data-driven disciplines. It has enhanced the training of a large body of undergraduate and graduate students, including many from underrepresented groups, by offering unique research and education activities. Finally, it has also benefitted the society by contributing new open-source solutions and with potential commercial applications in support of heterogeneous and dynamic data analysis.

Specifically, GEARS has contributed the designs and implementations of hardware infrastructure that makes extensive use heterogeneous processors and storage devices and software infrastructure for heterogenous computing across CPUs, GPUs, and FPGAs and data access across a deep storage hierarchy integrating DRAM, NVM, SSD, and HDD. GEARS has enabled novel computer systems and algorithms research on learning heterogeneous and dynamic data, including (1) new algorithm partitioning and scheduling schemes for using heterogeneous accelerators and optimizing the performance and energy efficiency of big data tasks; (2) new I/O scheduling and data staging strategies for performance and energy efficiency of the deep big-data storage hierarchy; (3) multi-phase, out-of-core decomposition techniques for large-scale tensors; (4) real-time visual analytics system that links streaming media with simulations for anticipatory analytics; (5) multi-modal deep learning methods with heterogeneous social data; (6) new computational tools for real-time analysis of social unrest using social media; (7) scalable, adaptive, and interactive team detection and assemble system for designing high-performing teams using big network data; (8) rare category analysis and heterogeneous learning algorithms for fast and accurate rare event discoveries with large and heterogeneous social data; and (9) new distributed machine learning framework for learning semantic knowledge from Web-scale images/videos with incomplete/noisy textual annotations. GEARS has also contributed to important research in many other disciplines, including (1) biological science: analyzing the genomes of wheat leaf rust pathogen for durable rust resistance and sustained rust control; (2) neuroscience: multimodal brain network fusion for learning the latent representations of brain networks; (3) geographical science: automatic terrain feature detection and classification using a mixed set of optimal remote sensing and natural images; (4) medicine: detecting prostate cancer in sequential contrast-enhanced ultrasound (CEUS) images; (5) emergency management: scalable analysis of sparse and noisy disaster data; (6) security: development of techniques and automated tools for identification and analysis of digital disinformation and propaganda; (7) finance: real-time financial fraud detection; (8) sustainability: spatiotemporal visual analytics for exploring the relationship between global trade networks and regional instability; and (9) transportation: monocular 3D object localization in real-time for autonomous driving. All project results have been shared with the broader community via the project website, journal and conference publications, and open-source software.

Last Modified: 02/08/2022
Modified by: Ming Zhao