Kocoloski, Brian
(2018)
Scalability in the Presence of Variability.
Doctoral Dissertation, University of Pittsburgh.
(Unpublished)
This is the latest version of this item.
Abstract
Supercomputers are used to solve some of the world’s most computationally demanding
problems. Exascale systems, to be comprised of over one million cores and capable of 10^18
floating point operations per second, will probably exist by the early 2020s, and will provide
unprecedented computational power for parallel computing workloads. Unfortunately,
while these machines hold tremendous promise and opportunity for applications in High
Performance Computing (HPC), graph processing, and machine learning, it will be a major
challenge to fully realize their potential, because to do so requires balanced execution across
the entire system and its millions of processing elements. When different processors take different
amounts of time to perform the same amount of work, performance imbalance arises,
large portions of the system sit idle, and time and energy are wasted. Larger systems incorporate
more processors and thus greater opportunity for imbalance to arise, as well as larger
performance/energy penalties when it does. This phenomenon is referred to as performance
variability and is the focus of this dissertation.
In this dissertation, we explain how to design system software to mitigate variability
on large scale parallel machines. Our approaches span (1) the design, implementation, and
evaluation of a new high performance operating system to reduce some classes of performance
variability, (2) a new performance evaluation framework to holistically characterize
key features of variability on new and emerging architectures, and (3) a distributed modeling
framework that derives predictions of how and where imbalance is manifesting in order to
drive reactive operations such as load balancing and speed scaling. Collectively, these efforts
provide a holistic set of tools to promote scalability through the mitigation of variability.
Share
| Citation/Export: |
|
| Social Networking: |
|
Details
| Item Type: |
University of Pittsburgh ETD
|
| Status: |
Unpublished |
| Creators/Authors: |
|
| ETD Committee: |
|
| Date: |
31 January 2018 |
| Date Type: |
Publication |
| Defense Date: |
22 September 2017 |
| Approval Date: |
31 January 2018 |
| Submission Date: |
23 October 2017 |
| Access Restriction: |
No restriction; Release the ETD for access worldwide immediately. |
| Number of Pages: |
127 |
| Institution: |
University of Pittsburgh |
| Schools and Programs: |
Dietrich School of Arts and Sciences > Computer Science |
| Degree: |
PhD - Doctor of Philosophy |
| Thesis Type: |
Doctoral Dissertation |
| Refereed: |
Yes |
| Uncontrolled Keywords: |
performance variability; supercomputing; high performance computing; operating systems |
| Date Deposited: |
31 Jan 2018 17:37 |
| Last Modified: |
31 Jan 2018 17:37 |
| URI: |
http://d-scholarship.pitt.edu/id/eprint/33294 |
Available Versions of this Item
-
Scalability in the Presence of Variability. (deposited 31 Jan 2018 17:37)
[Currently Displayed]
Metrics
Monthly Views for the past 3 years
Plum Analytics
Actions (login required)
 |
View Item |
![[feed]](/images/feed-icon-32x32.png){kind=icon}