With the advent of exascale architectures maximizing performance while maintaining energy consumption within reasonable limits has become one of the most critical design constraints. This constraint is particularly significant in light of the power budget of 20 MWatts set by the U.S. Department of Energy for exascale supercomputing facilities. Therefore, understanding an application's characteristics, execution pattern, energy footprint, and the interactions of such aspects is critical to improving the application's performance as well as its utilization of the underlying resources.
With conventional methods of analyzing performance and energy consumption trends scientists are forced to limit themselves to a manageable number of design parameters. While these modeling techniques have catered to the needs of current high-performance computing systems, the complexity and scale of exascale systems demands that large-scale design-space-exploration techniques are developed to enable comprehensive analysis and evaluations.
In this dissertation we present research on performance and energy modeling of current high performance computing and future exascale systems. Our thesis is focused on the design space exploration of current and future architectures, in terms of their reconfigurability, application's sensitivity to hardware characteristics (e.g., system clock, memory bandwidth), application's execution patterns, application's communication behavior, and utilization of resources. Our research is aimed at understanding the methods by which we may maximize performance of exascale systems, minimize energy consumption, and understand the trade offs between the two.
We use analytical, statistical, and machine-learning approaches to develop accurate, portable and scalable performance and energy models. We develop application and machine abstractions using Aspen (a domain specific language) to implement and evaluate our modeling techniques. As part of our research we develop and evaluate system-level performance and energy-consumption models that form part of an automated modeling framework, which analyzes application signatures to evaluate sensitivity of reconfigurable hardware components for candidate exascale proxy applications. We also develop statistical and machine-learning based models of the application's execution patterns on heterogeneous platforms. We also propose a communication and computation modeling and mapping framework for exascale proxy architectures and evaluate the framework for an exascale proxy application. These models serve as external and internal extensions to Aspen, which enable proxy exascale architecture implementations and thus facilitate design space exploration of exascale systems. / Ph. D. / Performance monitoring and modeling has been an extensively researched topic over the last decade. The traditional approaches of manually modeling performance and energy worked well for previous generation computers. With the prevalence of complex high-performance computers, clusters and the anticipation of future exascale architectures, the conventional modeling approaches will not be sufficient. A number of reasons limit the conventional modeling approaches, e.g, complexity of current and future architectures, increase in number of performance parameters to monitor, diversity in the architecture etc. This issue will worsen with the advent of exascale architectures that encompasses complex micro-architectures along with the increases in scale that have never been encountered in the computing industry before.
In this dissertation, we focus on two primary aspects of performance and energy modeling in the context of current high performance computing and future exascale architectures. We focus on adapting conventional modeling approaches to comprise the properties of accuracy, scalability, portability and independence of architectures. Centered around performance and energy improvements, we also develop design space exploration techniques that study the effects of application performance improvement in terms of reconfigurable hardware. We also quantitatively measure the effects of application performance sensitivity with changing hardware configurations – using analytical and machine learning modeling techniques. We explore theoretical exascale architecture, and validate it for performance limits. We develop a communication and computation model for the proxy exascale architecture and test it for strong and weak scaling for co-design for molecular dynamics.
| Identifer | oai:union.ndltd.org:VTETD/oai:vtechworks.lib.vt.edu:10919/95563 |
| Date | 25 May 2018 |
| Creators | Umar, Mariam |
| Contributors | Computer Science, Cameron, Kirk W., Tilevich, Eli, Vetter, Jeffrey S., Ribbens, Calvin J., Jung, Changhee |
| Publisher | Virginia Tech |
| Source Sets | Virginia Tech Theses and Dissertation |
| Detected Language | English |
| Type | Dissertation |
| Format | ETD, application/pdf |
| Rights | In Copyright, http://rightsstatements.org/vocab/InC/1.0/ |
Page generated in 0.0025 seconds