Welcome!
We perform research in the broadly defined area of
computer engineering. We design new hardware
architectures for emerging platforms, spanning
datacenters to mobile devices. Moreover, we
propose new hardware management strategies to
ensure service quality for diverse users in
complex systems. In design and management, we
navigate fundamental relationships between
performance, energy-efficiency, and fairness.
Computer Systems and Machine Learning
We adapt and invent methods in statistical machine
learning to understand and optimize distributed
systems. We focus on interpretable frameworks such
as causal inference and natural-language
processing
[SIGMETRICS'18]
[MICRO'12] . We also focus on dynamic
frameworks that learn and make decisions across
time
[MICRO'19]
[SIGMETRICS'18].
We also apply statistical inference to capture
broad relationships within parameter spaces for
hardware architectures. Inference defines a design
space, simulates sparsely sampled designs, and
derives predictive models to act as surrogates for
more expensive simulation and measurement. We
pioneered these strategies for processor design
[ISCA'10]
[HPCA'07]
[ASPLOS'06].
And we seek to extend these strategies to
accelerator design and high-level synthesis
[DATE'20]
[Micro'10].
Computer Systems and Algorithmic Economics
With the democratization of cloud computing,
diverse users demand computation from complex
datacenters. In this setting, we study mechanisms
for hardware allocation and scheduling. Our
interdisciplinary research spans computer
architecture, economic mechanism design, and game
theory
[IEEE'20].
For example, we examine design markets in which
autonomic agents bid for hardware on behalf of
users
[HPCA'18]
[HPCA'13].
We also investigate fairness and algorithms that
equitably divide hardware among strategic agents
[HPCA'17]
[ASPLOS'16]
[ASPLOS'14].
Finally, we balance trade-offs between performance
and fairness.
Computer Architecture and Energy Efficiency
Energy efficiency is imperative for scalable performance and environmental sustainability. We design efficient processors and memory systems [MICRO'12] [ISCA'12] [ISCA'10]. Hardware heterogeneity balances performance and efficiency [HPCA'14] while hardware specialization tailors resources to software needs [ISCA'10] [ASPLOS'08] [HPCA'07]. Moreover, the proliferation of computing requires holistic sustainability strategies [MLSys'22]. Our research links fundamental technology, business management, and public policy [StGallen'08] [StGallen'07].
Memory Architecture and Scalable Technology
We coordinate architecture and circuit design and identify new system capabilities enabled by emerging technologies [ISCA'10]. We study phase change memory (PCM), which relies on programmable resistance to provide qualitatively better scaling trajectories than today's DRAM [ISCA'09]. Our research spans the hardware-software interface, from links to file systems [HPCA'13] [SOSP'09].
