I am an assistant professor of Computer Science and Electrical and Computer Engineering at Duke University. I received my doctoral degree at Columbia University where I was advised by Professor Martha Kim. Prior to joining Duke, I was a postdoctoral researcher at UC Berkeley under the sponsorship and advisement of Professor Krste Asanović and the mentorship of Professor David Patterson. In my former life, I was an architect at Intel and then a research scientist at Intel Labs.
I enjoy solving difficult problems surrounding computations with the goal to process large volumes of data efficiently. My research interests include computer architecture and microarchitecture, hardware-software co-designs, accelerators, and emerging application domains ― especially those in big data analytics such as genomics, graphs, and databases. One of my research goals is to greatly simplify the design, deployment, and usage of custom hardware and to leverage this research in hardware acceleration to advance state-of-the-art research in the healthcare domain as well as other natural sciences.
Our paper "PyTFHE: An End-to-End Compilation and Execution Framework for Fully Homomorphic Encryption Applications" won ISPASS best paper award in Raleigh!
Mason Ma will tell you about PyTFHE, a highly productive end-to-end framework for FHE application development. PyTFHE achieves orders of magnitude more efficient FHE application execution compared to other SOTA frameworks.
Our paper "SNS’s not a Synthesizer: A Deep-Learning-Based Synthesis Predictor" will be presented at ISCA in NYC!
Entropy Xu will tell you how to predict the area, power, and timing physical characteristics of a broad range of designs at two to three orders of magnitude faster than the Synopsys Design Compiler!
Our paper "ProSE: The Architecture and Design of a Protein Discovery Engine" will be presented at ASPLOS in Lausanne!
APEX Lab welcomes its third graduate researcher Mason Ma! Mason is a first year CS PhD student at Duke.
Mason has a B.S. from UC Irvine. His research interests are in homomorphic encryption, hardware specialization, and computer architecture.
"Effectuating Hardware-Accelerated Systems with Domain-Specific Primitives" is selected for the NSF Faculty Early Career Development Program (CAREER) Award!
The CAREER Program is a Foundation-wide activity that offers the National Science Foundation's most prestigious awards in support of early-career faculty.
Selected for the Google "Rising" Systems Faculty Award!
Google SysInfra recognizes and supports the next stage of rising scholars' careers in research, teaching, and mentoring. Collectively, the 7 awardees represent 14+ universities in their advanced studies and faculty positions. Thank you Google!!
APEX Lab welcomes its second graduate researcher Entropy Xu! Entropy is a first year CS PhD student at Duke.
Entropy has a B.S. from UC Irvine. His research interests are in microarchitecture, hardware agile development, stochastic computing, and accelerator architecture.
CS/ECE Undergraduate Course:
Checkout the Fall 2020 CS/ECE 250 Course Website!
Our paper at ISCA 2020 showcases a project that accelerates the genomic secondary analysis pipeline (part of GATK4) using a framework called Genesis.
Genesis is a framework for accelerating genomic data manipulation operations. Genesis has a SQL-esque frontend and a hardware library of composable components.
Selected for the Systems for ML Facebook Research Award! Project: "Accelerating and Deploying Natural Language Processing Systems in Data Centers"
Along with Isaac Robson, a master's student at UNC, we will explore how accelerated NLP systems can help with drug discovery and more.
APEX Lab welcomes its first graduate researcher Phyllis Ang!
Phyllis is a first year CS PhD student at Duke.
Phyllis is from Houston, TX and she has a B.S. from UT Austin. Her research interests are in computer architecture, AI, and systems.
Chisel Bootcamp Sponsored by APEX Lab @ Duke:
Open to Students and Industry Hardware Architects
Check out the Chisel Bootcamp hosted at Duke on Friday, September 6!
Register for the event here! Space is limited.
New CS/ECE Graduate Course:
Computer Architecture and Hardware Acceleration
Check out the Fall 2019 CS/ECE 590 course website!