I'm a sixth year Ph.D. student in Computer Science at University of Washington, working with Prof. Arvind Krishnamurthy and Dr. Matthai Philipose. I'm generally interest at deep learning system, distributed system, mobile system, and computer networks. Previously I worked with Prof. David Wetherall and Prof. Aruna Balasumbramanian. I received my bachelor degree in Institute for Theoretical Computer Science (supervised by Prof. Andrew Yao) at Tsinghua University.
I'll join AWS AI team at Amazon this fall.
- Nexus: is a serving system for neural network inferences on GPU clusters. Nexus analyzes and schedules the DNN models at the level of linear algebra operations, which motivates several new ways to batch these operations and a batching-aware cluster resource allocation and scheduling framework to improve GPU utilization.
- TVM: aims to bridge the gap between deep learning systems, which are optimized for productivity, and the multitude of programming, performance and efficiency constraints enforced by different types of hardware. TVM provides a common representation for deep learning computation workloads, and enables optimizations for CPUs, GPUs and other specialized hardware such as FPGAs.
- Sequential Model Specialization: aims to accelerate the speed of recognizing entities such as objects, people, scenes and activities in every frame of video footage of day-to-day life, by exploiting "specialized" convolutional neural networks (CNNs) under highly skewed distribution. When applied to recognizing faces in TV shows and movies we realized end-to-end classification speedups of 2.4-7.8x/2.6-11.2x (on GPU/CPU) relative to a state-of-the-art convolutional neural network, at competitive accuracy.
- MCDNN: an approximation-based execution framework for applying computer vision to video on cloud-backed mobile devices using Deep Neural Networks(DNNs). The computational demands of DNNs are high enough that, without careful resource management, such applications strain device battery, and cloud cost budgets. MCDNN allows each request to be served approximately, by systematically trading off DNN classification accuracy for resource use.
- Metasync: a secure and reliable file synchronization service that uses multiple cloud synchronization services as untrusted storage providers. We devised a novel variant of Paxos that provides efficient and consistent updates on top of the unmodified APIs exported by existing services.
- Mobile Hub: leverages heterogeneous hardware, such as sensor hubs, to improve the power efficiency of always-on sensing applications on mobile phones. MobileHub rewrites the binary of a given application without programmer effort to make it more power efficient.
Cloud-based file synchronization services, such as Dropbox, are a worldwide resource for many millions of users. However, individual services often have tight resource limits, suffer from temporary outages or even shutdowns, and sometimes silently corrupt or leak user data.
We design, implement, and evaluate MetaSync, a secure and reliable file synchronization service that uses multiple cloud synchronization services as untrusted storage providers. To make MetaSync work correctly, we devise a novel variant of Paxos that provides efficient and consistent updates on top of the unmodified APIs exported by existing services. Our system automatically redistributes files upon reconfiguration of providers.
Our evaluation shows that MetaSync provides low update latency and high update throughput while being more trustworthy and available. MetaSync outperforms its underlying cloud services by 1.2-10× on three realistic workloads.
Enabling flexible spectrum access (FSA) in existing wireless networks is challenging due to the limited spectrum programmability – the ability to change spectrum properties of a signal to match an arbitrary frequency allocation. This paper argues that spectrum programmability can be separated from general wireless physical layer (PHY) modulation. Therefore, we can support flexible spectrum programmability by inserting a new spectrum virtualization layer (SVL) directly below traditional wireless PHY, and enable FSA for wireless networks without changing their PHY designs.
SVL provides a virtual baseband abstraction to wireless PHY, which is static, contiguous, with a desirable width defined by the PHY. At the sender side, SVL reshapes the modulated baseband signals into waveform that matches the dynamically allocated physical frequency bands – which can be of different width, or non-contiguous – while keeping the modulated information unchanged. At the receiver side, SVL performs the inverse reshaping operation that collects the waveform from each physical band, and reconstructs the original modulated signals for PHY. All these reshaping operations are performed at the signal level and therefore SVL is agnostic and transparent to upper PHY. We have implemented a prototype of SVL on a software radio platform, and tested it with various wireless PHYs. Our experiments show SVL is flexible and effective to support FSA in existing wireless networks.
Last update: Jan. 2018