I have graduated and joined Intel as a Deep Learning Compiler Engineer!
I obtained my PhD in the Electrical and Computer Engineering from Purdue University. I was a member of Purdue Programming Languages Group (PurPL). My PhD research focused on developing targeted compiler transformations to improve performance and reliability of programs with irregular control-flow. I also have experience in using program analysis techniques (e.g. Fuzzing, Symbolic Execution) to improve Performance Test Generation.
I am fortunate to be advised by Prof. Milind Kulkarni.
Publications
- HyBF: A Hybrid Branch Fusion Strategy for Code Size Reduction
Rodrigo C. O. Rocha *, Charitha Saumya *, Kirshanthan Sundararajah, Pavlos Petoumenos, Milind Kulkarni, Michael O’Boyle ( * equal contributions )
CC 2023 (Acceptance rate = 40%) - UniRec: A Unimodular-like Framework for Nested Recursions and Loops
Kirshanthan Sundararajah, Charitha Saumya, Milind Kulkarni
OOPSLA 2022 (Acceptance rate = 31%) - Cornucopia: A Framework for Feedback Guided Generation of Binaries
Vidush Singhal, Akul Abhilash Pillai, Charitha Saumya, Milind Kulkarni, Aravind Machiry
ASE 2022 (Acceptance rate = 22%) - SparseLNR: Accelerating Sparse Tensor Computations Using Loop Nest Restructuring
Adhitha Dias, Kirshanthan Sundararajah, Charitha Saumya, Milind Kulkarni
ICS 2022 (Acceptance rate = 24%)
Best Paper Award - DARM: Control-Flow Melding for SIMT Thread Divergence Reduction
Charitha Saumya, Kirshanthan Sundararajah, Milind Kulkarni
CGO 2022 (Acceptance rate = 27%) - ADDS-EVS: An Agent-Based Deployment Decision-Support System for Electric Vehicle Services
Zengxiang Lei, Jiawei Xue, Xiaowei Chen, Charitha Saumya, Xinwu Qian, Mingyi He, Stanislav Sobolevsky, Satish V Ukkusuri
ITSC 2021 - XSTRESSOR: Automatic Generation of Large-Scale Worst-Case Test Inputs by Inferring Path Conditions
Charitha Saumya, Jinkyu Koo, Milind Kulkarni, Saurabh Bagchi
ICST 2019 (Acceptance rate = 28%)
Distinguished Paper Award - PySE: Automatic Worst-Case Test Generation by Reinforcement Learning
Jinkyu Koo, Charitha Saumya, Milind Kulkarni, Saurabh Bagchi
ICST 2019 (Acceptance rate = 28%) - Inertial Measurement Units based Wireless Sensor Network for Real Time Gait Analysis
Imesh Lihinikaduarachchi, Sajith Rajapaksha, Charitha Saumya, Viraj Senevirathne, Pujitha Silva
IEEE Region 10 Conference 2015
Technical Talks
- Merging Similar Control-Flow Regions in LLVM for Performance and Code Size Benefits
2022 LLVM Developers’ Meeting, San Jose, CA
Education
| PhD in Electrical and Computer Engineering | Purdue University (August 2023) |
|---|---|
| MS in Electrical and Computer Engineering | Purdue University (December 2020) |
| BS in Electronic and Telecommunication Engineering | University of Moratuwa, Sri Lanka (May 2015) |
Work Experience
| Research Intern | Adobe Research, San Jose, CA (Summer 2020) |
|---|---|
| Software Engineering Intern | Bigstream, Mountian View, CA (Summer 2019) |
| Associate Software Engineer | Paraqum Technologies, Colombo, Sri Lanka (2015 - 2016) |
| Software Engineering Intern | MillenniumIT Software, Colombo, Sri Lanka (2013 - 2014) |
Professional Service
- Artifact Evaluation Committee: CGO 2023
- Student Volunteer: SPLASH 2021
- External Reviewer: ISSRE 2017, 2018, DSN 2021
- Undergraduates Advised: Pranavi Bajjuri, Ganesh Varnekar, Vidush Singhal