CSR: Small: Storage Architecture for the Next Generation of Smart
Mobile Platforms: Award CSR-1218520
Principal Investigators:
- Umakishore Ramachandran
- Moinuddin K. Qureshi
Graduate Students:
- Wonhee Cho (current)
- Yeonju Jeong (current)
- Moonkyung Ryu (graduated)
Funding:
- NSF Award CSR-1218520
- Period of Funding (3 years): August 1, 2012 - July 31, 2015
Abstract:
Mobile computing is sweeping the world. According to recent
statistics, there are up to 4 billion mobile users (more than
half of the world's population), with accelerated penetration
in regions such as India and Africa. This trend is even more
significant in the light of predictions about mobile devices
dominating most personal computing landscape in the near
future. Recent studies are pointing to the permanent storage
in such devices being a weak link. Due to considerations of
power and physical footprint, flash has been the storage
technology of choice hitherto in mobile platforms. Newer
storage technologies such as PCM, and STT-RAM are on the
horizon as a competitor to flash. Each of these technologies
have their own idiosyncracies both from the point of view of
architecting them (from a hardware perspective) and integrating
them in the operating system (OS) stack (from a system software
perspective). It is time to take a critical look at the OS
software stack and architect it to plan for future evolutions
of the storage technologies. In this proposal, we focus on the
system software and hardware issues, in an integrated fashion,
in the construction of high-performance storage architecture
for mobile platforms.
The goals of the project are summarized below:
-
We will collect traces of applications (both
current and futuristic) for mobile platforms and
conduct detailed storage-centric measurements of
their performance on current and emerging mobile
storage technologies.
-
We will analyze the source of storage-related
performance bottlenecks on mobile platforms at
different levels of the software stack (application,
system software, and hardware) using a combination of
measurement, simulation, and real implementation on
existing and emerging mobile platforms.
-
We will propose solutions both at the system
software and architecture levels, in an integrated
manner, for advancing the state-of-the-art in storage
for mobile platforms.
-
We will conduct detailed quantitative evaluation of
our solutions both via simulation and implementation
of research prototypes. In addition to validating our
research ideas, this effort in of itself may lead to
new insights on how to perform quantitative studies
that are closer to real implementation.
Graduated PhD Students:
-
Moonkyung Ryu
Date: May 2014
Thesis:
TOWARDS A SCALABLE DESIGN OF VIDEO CONTENT DISTRIBUTION OVER THE INTERNET
(currently with Google, Mounain View, CA)
Annual Reports:
Return to Kishore's Homepage