Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Institution
Articles 1 - 6 of 6
Full-Text Articles in Systems Architecture
Holistic Performance Analysis And Optimization Of Unified Virtual Memory, Tyler Allen
Holistic Performance Analysis And Optimization Of Unified Virtual Memory, Tyler Allen
All Dissertations
The programming difficulty of creating GPU-accelerated high performance computing (HPC) codes has been greatly reduced by the advent of Unified Memory technologies that abstract the management of physical memory away from the developer. However, these systems incur substantial overhead that paradoxically grows for codes where these technologies are most useful. While these technologies are increasingly adopted for use in modern HPC frameworks and applications, the performance cost reduces the efficiency of these systems and turns away some developers from adoption entirely. These systems are naturally difficult to optimize due to the large number of interconnected hardware and software components that …
A Practical Approach To Automated Software Correctness Enhancement, Aleksandr Zakharchenko
A Practical Approach To Automated Software Correctness Enhancement, Aleksandr Zakharchenko
Dissertations
To repair an incorrect program does not mean to make it correct; it only means to make it more-correct, in some sense, than it is. In the absence of a concept of relative correctness, i.e. the property of a program to be more-correct than another with respect to a specification, the discipline of program repair has resorted to various approximations of absolute (traditional) correctness, with varying degrees of success. This shortcoming is concealed by the fact that most program repair tools are tested on basic cases, whence making them absolutely correct is not clearly distinguishable from making them relatively more-correct. …
Reproducible Application Platforms For Distributed Computing Systems, John Q. Wofford Iii
Reproducible Application Platforms For Distributed Computing Systems, John Q. Wofford Iii
Computer Science ETDs
A scientific conclusion requires falsifiable evidence. Results from distributed systems research are often difficult to reproduce because these systems consist of multiple nodes, each running independent system software and communicating across inter-node devices. This work motivates, describes, and demonstrates a reproducible application platform for distributed computing systems based on a layered, container-based software stack. This system effectively moves all application software dependencies from the host to a portable container. Each layer represents a particular functionality of the software stack. The layers are modular and extensible so that results are not only repeatable, but they can also be built on to …
Adaptive Parallelism For Coupled, Multithreaded Message-Passing Programs, Samuel K. Gutiérrez
Adaptive Parallelism For Coupled, Multithreaded Message-Passing Programs, Samuel K. Gutiérrez
Computer Science ETDs
Hybrid parallel programming models that combine message passing (MP) and shared- memory multithreading (MT) are becoming more popular, especially with applications requiring higher degrees of parallelism and scalability. Consequently, coupled parallel programs, those built via the integration of independently developed and optimized software libraries linked into a single application, increasingly comprise message-passing libraries with differing preferred degrees of threading, resulting in thread-level heterogeneity. Retroactively matching threading levels between independently developed and maintained libraries is difficult, and the challenge is exacerbated because contemporary middleware services provide only static scheduling policies over entire program executions, necessitating suboptimal, over-subscribed or under-subscribed, configurations. In …
Characterizing And Improving Power And Performance In Hpc Networks, Taylor L. Groves
Characterizing And Improving Power And Performance In Hpc Networks, Taylor L. Groves
Computer Science ETDs
Networks are the backbone of modern HPC systems. They serve as a critical piece of infrastructure, tying together applications, analytics, storage and visualization. Despite this importance, we have not fully explored how evolving communication paradigms and network design will impact scientific workloads. As networks expand in the race towards Exascale (1×10^18 floating point operations a second), we need to reexamine this relationship so that the HPC community better understands (1) characteristics and trends in HPC communication; (2) how to best design HPC networks to save power or enhance the performance; (3) how to facilitate scalable, informed, and dynamic decisions within …
A Study Of Improving The Parallel Performance Of Vasp., Matthew Brandon Baker
A Study Of Improving The Parallel Performance Of Vasp., Matthew Brandon Baker
Electronic Theses and Dissertations
This thesis involves a case study in the use of parallelism to improve the performance of an application for computational research on molecules. The application, VASP, was migrated from a machine with 4 nodes and 16 single-threaded processors to a machine with 60 nodes and 120 dual-threaded processors. When initially migrated, VASP's performance deteriorated after about 17 processing elements (PEs), due to network contention. Subsequent modifications that restrict communication amongst VASP processes, together with additional support for threading, allowed VASP to scale up to 112 PEs, the maximum number that was tested. Other performance-enhancing optimizations that were attempted included replacing …