Charalampos Chelmis, Ph.D. - US grants

Semiconductor technology is facing fundamental physical limits creating an increased demand for acceleration of data-intensive applications on architectures that bring memory much closer to reconfigurable compute logic. Three dimensional integrated circuits (3DIC) appear to be the most prominent technology towards memory-driven computing by enabling large amounts of memory stacked in layers to be accessed by a logic unit using high bandwidth vertical interconnects. Software-defined technologies can provide the framework for harnessing the potential breakthrough performance of 3D and other advanced memory technologies in a holistic but dynamic manner, while at the same time hiding their internal complexity. This project focuses on developing a novel software paradigm to perform algorithmic exploration of memory-driven computing on new memory architectures and facilitate the development of massively parallel algorithms for memory-unconstrained computing with the potential for breakthrough performance levels.

The project will develop Software-Defined 3D Memory (SD3DM) as a transformative layer for memory-driven computing that will not simply virtualize 3D memory but will holistically address the oncoming reality of massive on-chip 3D Memory for accelerating data-intensive applications while jointly optimizing energy consumption. Memory access optimizations will be developed at the algorithm level to meet application performance objectives of throughput, latency, and energy efficiency. Specifically, the optimizations will be designed to fully exploit the characteristics of target architectures by (i) carefully defining application-specific dynamic data layouts, (ii) developing application-specific memory controllers for runtime support, and (iii) designing novel in-memory data permutation mechanisms to accelerate inter-stage communication. Integer Linear Programming (ILP) and Stochastic Programming (SP) based dynamic data layouts that exploit the interlayer pipelining and parallel vault access features of 3D memory for throughput and energy-optimal mapping of data to different memory components will be developed. Data layout algorithms will be developed in in conjunction with application-specific memory controllers to provide maximum pipeline execution efficiency for any given application.

The proposed optimizations will be demonstrated on widely used signal processing and machine learning algorithms with diverse data access and logic use requirements. Successful completion of this project will directly lead to a significant increase in the size of signal processing and machine learning problems that can be solved on emerging 3DIC platforms at speeds that were not possible before. The developed work will potentially influence multiple application domains. The investigators will encourage the participation by women, minorities, and under-represented groups in the project through USC's Minority Opportunities in Research (MORE) Programs.

Those in need of help often do not know how to locate or access service providers. Likewise, service-providing agencies often work in silos. The lack of communication also applies to volunteers; people do not know who to help and how they can be resourceful. Response becomes even more problematic when a problem demands the coordination of service providers, volunteers, and government structures, and after business hours, when the communication channels that can aid people in need become sparse. This project will (i) simplify the discovery and use of services, (ii) enable two-way communication between stakeholders (e.g., residents and service providers), (iii) deploy resources more efficiently, and (iv) assist stakeholders in assessing and promoting the wellbeing of their communities. The end result will be directly applicable to communities across the US, and has the potential to be influential beyond the human and physical services domain. It will advance computer science, electrical and computer engineering, and social and behavioral sciences to collectively address the challenges associated with this problem, and will create educational opportunities to encourage students to cross disciplinary boundaries. Women and underrepresented groups will be encouraged to participate in this project by collaborating with community-based organizations, and via programs at the University at Albany.

This multidisciplinary project takes a community-wide approach that will integrate people and data with analytics and engineering using social and behavioral sciences to maximize the efficiency of delivering human and physical services, and also improve the sense of connectedness of residents with service providers and government structures. The project will study the limitations of extant services, which will in turn inform the development of novel decision-making mechanisms with sufficient behavioral realism. The outcome will be an integrated "one-stop" service of services. This project will (i) develop new data mining methods for uncovering complex interdependencies within a dynamic sociotechnical system, (ii) devise novel information processing, machine learning, and control methods to dynamically optimize delivery of human and physical services under uncertainty with humans in the decision-making loop, and (iii) shed light on the ability of communities to integrate emerging technologies to become more connected in human interactions.