PhD Student with minor in Entrepreneurship
Department of Computer Science
University of Arizona
Office: Gould-Simpson 718
Phone: 520-360-6778
E-mail:
Biography
I am a PhD candidate in the Department of Computer Science
at the University of Arizona. For my PhD minor I completed a minor in Entrepreneurship from
the McGuire Center for Entrepreneurship at the
Eller College of Management. My advisor is
Dr. Chris Gniady. I am also part of the Dynamic REsource Allocation and Management (DREAM) team.
I received my Bachelors degree and my Masters degree in Computer Science from the Department of Computer Science
at the University of Arizona in December 2005. I have since been working as Senior Software Engineer with the
Thirty Meter Telescope, the National Optical Astronomy Observatory and the Large Synoptic Survey Telescope.
Research
My broad area of research is Big-Data performance and Energy Efficiency. My current research focuses on instrumenting RDBMS's to get performance numbers to see resource usage.Projects
DB over Named Data Network
I am currently exploring ideas on how NDN can be helpful in improving database throughput using NDN features like smart networking.QAMEM: Query Aware Memory Energy Management
I am also working on research using performance counters to see if there is a correlation between queries and memory behavior. This may help in Memory Energy Management.IAMEM: Interaction Aware Memory Energy Management (pdf)
Abstract
Energy efficiency has become one of the most important factors in the development of computer systems. As applications become more data centric and put more pressure on the memory subsystem, managing energy consumption of main memory is becoming critical. Therefore, it is critical to take advantage of all memory idle times by placing memory in low power modes even during the active process execution. However, current solutions only offer energy optimizations on a per process basis and are unable to take advantage of memory idle times when the process is executing. To allow accurate and fine-grained memory management during the process execution, we propose Interaction-Aware Memory Energy Management (IAMEM). IAMEM relies on accurate correlation of user-initiated tasks with the demand placed on the memory subsystem to accurately predict power state transitions for maximal energy savings while minimizing the impact on performance. Through detailed trace-driven simulation, we show that IAMEM reduces the memory energy consumption by as much as 16% as compared to the state-of-the-art approaches, while maintaining the user-perceivable performance comparable to the system without any energy optimizations.Contribution
Worked on previous work by Dr. Mingsong Bi, now at Intel Corporation, and updated the Memory Power Simulator to work with DDR3 memory. I updated the results and presented the paper at Usenix in June 2013.τDOM: Temporal Document Object Model (link)
τDOM is an extension to standard DOM API to support manipulating temporal XML document. Temporal XML documents store temporal information along with data in a single document. τDOM allows users to view the document from different perspectives. Using τDOM, the user can choose to access all the data, the data valid at an instant, or the data valid during a period of applicability in the document. τDOM frees the user from handling temporal data themselves and provides a convenient and robust tool to filter content of the document according to the temporal constraint specified by the user.Publications
Conference
IAMEM: Interaction-Aware Memory Energy ManagementMingsong Bi, Srinivasan Chandrasekharan, and Chris Gniady
USENIX 2013 Annual Technical Conference (ATC), 2013.
Deobfuscation: Improving reverse engineering of obfuscated code
Srinivasan Chandrasekharan and Saumya Debray
Draft Paper, 2005
Undergraduate Honors Thesis
Evaluation of the Efficacy of Control Flow Obfuscation Against Profiling and Intelligent Static Attacksunder Saumya Debray
Fall 2003