cv

This is a description of the page. You can modify it in '_pages/cv.md'. You can also change or remove the top pdf download button.

Basics

Name Chaitanya Mamatha Ananda
Label Ph.D. Candidate in Computer Science
Email cmama002@ucr.edu
Phone 951-907-8519
Summary My research interests lie in the areas of compiler optimization, machine learning and deep learning. My doctoral research has involved (i) building optimized memory layouts for heap segment in x86 binaries, (ii) devising techniques for reducing code size in x86/Arm binaries and (iii) AI-driven techniques for improving code layout.

Education

  • 2022.09 - Present
    Ph.D. Candidate
    University of California, Riverside
    Computer Science
    • Artificial Intelligence (2024 Winter)
    • Introduction to Deep Learning (2023 Fall)
    • Advanced Computer Architecture (2023 Spring)
    • Advanced Operating Systems (2023 Winter)
    • High Performance Computing (2022 Fall)
    • Compiler Construction (2022 Fall)
  • 2017.08 - 2021.06
    B.E.
    Bangalore Institute of Technology, Bengaluru, India
    Computer Science and Engineering

Work

  • 2025.09 - 2026.05
    Student Researcher
    Google, Sunnyvale
    Exploring AI-driven approaches for improving code layout optimization. Designing techniques to improve memory layout on warehouse scale workloads.
  • 2023.06 - 2025.09
    Graduate Research Assistant
    University of California, Riverside
    Conducted research to improve memory layouts. Designed techniques to reduce code size in binaries.
  • 2021.01 - 2021.06
    Project Trainee
    Robert Bosch Engineering and Business Solutions (RBEI), Bengaluru, India
    Developed scripts to synchronize video and radar data from automated test driving.
  • 2019.01 - 2022.12
    Research Intern
    Indian Institute of Science, Bengaluru, India
    Developed a parallel programming model for solving partial differential equations using Regent/Legion. Designed an anomaly detector for scientific data using statistical and neural network based methods.

Projects

  • PreFix
    Developed PreFix, a novel optimization technique for heap-intensive applications that achieves near perfect separation of hot objects, improving spatial locality and application performance. PreFix employs profiling-guided hot object identification, preallocated memory regions, and object recycling, resulting in an average execution time reduction of 21.7% (up to 74%), significantly outperforming existing solutions like HDS and HALO. [CGO '25]
  • DeduBB
    Developed a framework for reducing the size of production binaries on x86 and Arm architectures at the post-link stage. [LCTES '26]

Publications

Skills

Programming
Python
C/C++
Frameworks
LLVM (BOLT)
Tools
Vim
Linux/Unix
Git

Awards