Experience

 
 
 
 
 
May 2021 – August 2021
Dallas

Software Engineering Intern

Nvidia

Performance Profiling for Deep Learning Frameworks
 
 
 
 
 
May 2020 – August 2020
Houston

Software Engineering Intern

Google

Performance Regression Analysis of Feedback-direct Optimization (FDO) Based Programs
 
 
 
 
 
June 2018 – August 2018
Menlo Park

Research Intern

Facebook

Neural Network Optimization on Mobiles
 
 
 
 
 
April 2017 – July 2017
Beijing

Research Intern

Nvidia

Neural Network Quantization
 
 
 
 
 
October 2013 – February 2014
Beijing

SDE Intern

Baidu

Hadoop Workflow Optimization

Featured Publications

General-purpose GPUs have become common in modern computing systems to accelerate applications in many domains, including machine …
Project Source Document

The US Department of Energys fastest supercomputers and forthcoming exascale systems employ Graphics Processing Units (GPUs) to …
Project Source Document

This paper describes extensions to Rice University’s HPCToolkit performance tools to support measurement and analysis of …
Project Source Document

Projects

*

GPA is a performance advisor for NVIDIA GPUs that suggests potential code optimization opportunities at a hierarchy of levels, including individual lines, loops, and functions. GPA uses data flow analysis to approximately attribute measured instruction stalls to their root causes and uses information about a program’s structure and the GPU to match inefficiency patterns with suggestions for optimization. GPA estimates each optimization’s speedup based on a PC sampling-based performance model.

We implemented GVProf, the first value profiler that locates value redundancy problems in applications running on GPU-based clusters. Our experiments show that GVProf incurs acceptable overhead and scales to large executions. GVProf provides useful insights to guide performance optimization. Under the guidance of GVProf, we optimized several HPC and machine learning workloads, obtaining speedups up to 1.93x.

Our tool provides a profile view and a trace view for GPU-accelerated applications. The profile view identifies where GPU APIs are invoked in CPU calling context, approximates calling context for GPU execution, and analyzes instruction mix for GPU kernels. The tool traces CPU and GPU activities for a large number of processes and threads with minimal overhead.

A fast, memory efficient, and light-weight implementation for gSpan algorithm in data mining. gBolt is up to 100x faster than the original implementation with multi-threading on a single machine. gBolt also reduces more than 200 folds memory usage, running efficiently on personal computers.

Recent Publications

Quickly discover relevant content by filtering publications.

ValueExpert: exploring value patterns in GPU-accelerated applications

Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS’22).

Project Source Document

Measurement and Analysis of GPU-Accelerated OpenCL Computations on Intel GPUs

2021 IEEE/ACM International Workshop on Programming and Performance Visualization Tools (ProTools’21).

Project Source Document

Measurement and analysis of GPU-accelerated applications with HPCToolkit

Parallel Computing (PARCO’21).

Project Source Document

Outcomes of OpenMP Hackathon: OpenMP Application Experiences with the Offloading Model

International Workshop on OpenMP (IWOMP’21).

Source Document

Accelerating High-Order Stencils on GPUs

Concurrency and Computation: Practice and Experience (CCPE’21).

Project Source Document

See all publications

Recent & Upcoming Talks

Presented a talk about our value profiling tool at ASPLOS’22
Mar 2, 2022 12:00 AM — 12:00 AM Lausanne, Switzerland
Project Slides

Presented a poster and a talk about my PhD research at SC’21
Nov 15, 2021 12:00 AM — 12:00 AM St. Louis, Missouri
Project Project Project Poster

Using HPCToolkit to Measure and Analyze the Performance of GPU-accelerated Applications Tutorial, Mar-Apr 2021
Apr 1, 2021 12:00 AM Online
Slides

Presented our CGO’21 work.
Mar 1, 2021 12:00 AM Online
Project Slides

Presented our SC’20 work.
Nov 19, 2020 12:00 AM Online
Project Slides
See all talks

Topics

AMD CPU Calling Context Tree Concurrent Algorithm Data Mining Data Structure Deep Learning Feedback-directed Optimization GPU HPC Instrumentation Intel NVIDIA PC Sampling Parallel Computing Performance Tool Profiler Roofline Stencils Value Analysis Wait-free