Stephen Lien Harrell

Stephen Lien Harrell

Auto-generated profile, based on publicly available information

Stephen Lien Harrell

Texas Advanced Computing Center, University of Texas at Austin, Austin, TX, USA

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 May 2021 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Open access
RBRobert Bird
Robert Bird
NTNigel Tan
Nigel Tan
SLScott V. Luedtke
Scott V. Luedtke
SHStephen Lien Harrell
Stephen Lien Harrell
MTMichela Taufer
Michela Taufer
BABrian Albright
Brian Albright
VPIC is a general purpose particle-in-cell simulation code for modeling plasma phenomena such as magnetic reconnection, fusion, solar weather, and laser-plasma interaction in three dimensions using large numbers of particles. VPIC's capacity in both fidelity and scale makes it particularly well-suited for plasma research on pre-exascale and exascale platforms. In this article, we demonstrate the unique challenges involved in preparing the VPIC code for operation at exascale, outlining important optimizations to make VPIC efficient on accelerators. Specifically, we show the work undertaken in adapting VPIC to exploit the portability-enabling framework Kokkos and highlight the enhancements to VPIC's modeling capabilities to achieve performance at exascale. We assess the achieved performance-portability trade-off through a suite of studies on nine different varieties of modern pre-exascale hardware. Our performance-portability study includes weak-scaling runs on three of the top ten TOP500 supercomputers, as well as a comparison of low-level system performance of hardware from four different vendors.

1 November 2010
Verified
Conference Paper
Closed access
ACAdam G. Carlyle
Adam G. Carlyle
SHStephen L. Harrell
Stephen L. Harrell
PSPreston M. Smith
Preston M. Smith
The increasing availability of commercial cloud computing resources in recent years has caught the attention of the high-performance computing (HPC) and scientific computing community. Many researchers have subsequently examined the relative computational performance of commercially available cloud computing offerings across a number of HPC application bench-marks and scientific workflows, but the analogous cost comparisons-i.e., comparisons between the cost of doing scientific computation in traditional HPC environments vs. cloud computing environments-are less frequently discussed and are difficult to make in meaning-ful ways. Such comparisons are of interest to traditional HPC resource providers as well as to members of the scientific research community who need access to HPC resources on a routine basis. This paper is a case study of costs incurred by faculty end-users of Purdue University's HPC “community cluster” program. We develop and present a per node-hour cloud computing equivalent cost that is based upon actual usage patterns of the community cluster participants and is suitable for direct comparison to hourly costs charged by one commercial cloud computing provider. We find that the majority of community cluster participants incur substantially lower out-of-pocket costs in this community cluster program than in purchasing cloud computing HPC products.

1 November 2018
Verified
Conference Paper
Closed access
SHStephen Lien Harrell
Stephen Lien Harrell
JKJoy Kitson
Joy Kitson
RBRobert Bird
Robert Bird
SPSimon John Pennycook
Simon John Pennycook
JSJason Sewall
Jason Sewall
RRRobert Robey
Robert Robey
Exascale computing brings with it diverse machine architectures and programming approaches which challenge application developers. Applications need to perform well on a wide range of architectures while simultaneously minimizing development and maintenance overheads. In order to alleviate these costs, developers have begun leveraging portability frameworks to maximize both the code shared between platforms and the performance of the application. We explore the effectiveness of several such frameworks through applying them to small production codes. Throughout the process, we apply a logging tool to gather data on the development process. We use this information to develop metrics of application development productivity, which can be used to holistically assess how productively a performance-portable application was developed.

15 November 2015
Verified
Conference Paper
Open access
SHStephen Lien Harrell
Stephen Lien Harrell
HNHai Ah Nam
Hai Ah Nam
VLVerónica G. Vergara Larrea
Verónica G. Vergara Larrea
KKKurt Keville
Kurt Keville
DKDan Kamalic
Dan Kamalic
National labs, academic institutions and industry have a strong need for scientists and staff that understand high performance computing (HPC) and the complex interconnections across individual topics in HPC. However, domain science and computer science undergraduate programs are not providing sufficient educational resources, and are far from conveying the interdisciplinary and collaborative nature of the HPC environment. The Student Cluster Competition (SCC) was created as an educational tool to immerse undergraduates in HPC. It is a microcosm of professional HPC centers that teaches and inspires students to pursue careers in the field. The SCC's impact is reflected in new undergraduate curricula and through the experience of the students themselves. The SCC can complement a strong parallel and distributed computing (PDC) curriculum through experiential learning and engagement with the HPC community as a whole, which will prepare graduates for the interdisciplinary nature of work in HPC fields.

1 June 2020
Verified
Conference Paper
Closed access
RKRakesh Kumar
Rakesh Kumar
SJSaurabh Jha
Saurabh Jha
AMAshraf Mahgoub
Ashraf Mahgoub
RKRajesh Kalyanam
Rajesh Kalyanam
SHStephen Harrell
Stephen Harrell
SBSaurabh Bagchi
Saurabh Bagchi
Node downtime and failed jobs in a computing cluster translate into wasted resources and user dissatisfaction. Therefore understanding why nodes and jobs fail in HPC clusters is essential. This paper provides analyses of node and job failures in two university-wide computing clusters at two Tier I US research universities. We analyzed approximately 3.0M job execution data of System A and 2.2M of System B with data sources coming from accounting logs, resource usage for all primary local and remote resources (memory, IO, network), and node failure data. We observe different kinds of correlations of failures with resource usages and propose a job failure prediction model to trigger event-driven checkpointing and avoid wasted work. Additionally, we present user history based resource usage and runtime prediction models. These models have the potential to avoid system related issues such as contention, and improve quality of service such as lower mean queue time, if their predictions are used to make a more informed scheduling decision. As a proof of concept, we simulate an easy backfill scheduler to use predictions of one of these models, i.e., runtime and show the improvements in terms of lower mean queue time. Arising out of these observations, we provide generalizable insights for cluster management to improve reliability, such as, for some execution environments local contention dominates, while for others system-wide contention dominates.

18 July 2011
Verified
Conference Paper
Open access
SHStephen L. Harrell
Stephen L. Harrell
PSPreston M. Smith
Preston M. Smith
DSDoug Smith
Doug Smith
THTorsten Hoefler
Torsten Hoefler
ALAnna A. Labutina
Anna A. Labutina
TOTrinity Overmyer
Trinity Overmyer
This paper aims to describe methods that can be used to create new Student Cluster Competition teams from the standpoint of the team advisors. The purpose is to share these methods in order to create an easier path for organizing a successful team. These methods were gleaned from a survey of advisors that have formed teams in the last four years. Four advisors responded to the survey and those responses fit into five categories: (1) early preparation, (2) coursework specific to the competition, (3) close relationships with the hardware vendors, (4) concentration on the applications over the hardware, and (5) the need to encourage the team members to write papers about their experiences. In addition to these commonalities which may be best practices there are a few divergent but intriguing techniques that may also prove useful for potential advisors. Both will be discussed here and these methods can serve as a primer for anyone looking to start a new Student Cluster Competition team.