Sana Damani
Scholar

Sana Damani

Google Scholar ID: iWmFNQEAAAAJ
NVIDIA
CompilersComputer ArchitectureGPU
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
114
 
H-index
6
 
i10-index
5
 
Publications
20
 
Co-authors
19
list available
Contact
Emailsdamani@gatech.eduCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
4 items
Improving Efficiency of GPU Kernel Optimization Agents using a Domain-Specific Language and Speed-of-Light Guidance
2026
Cited
0
SOL-ExecBench: Speed-of-Light Benchmarking for Real-World GPU Kernels Against Hardware Limits
2026
Cited
0
KernelBlaster: Continual Cross-Task CUDA Optimization via Memory-Augmented In-Context Reinforcement Learning
2026
Cited
0
ProofWright: Towards Agentic Formal Verification of CUDA
2025
Cited
0
Resume (English only)
Research Experience
  • Currently a research scientist at Nvidia, working at the intersection of compilers and microarchitecture.
Education
  • Ph.D. from Georgia Institute of Technology; Advisor: Professor Vivek Sarkar; Focus: Scheduling techniques aimed at optimizing the performance of parallel applications.
Background
  • Research Interests: at the intersection of compilers and microarchitecture. Specialization: Optimizing the performance of parallel applications.
Co-authors
19 total
Steve Keckler
Steve Keckler
Vice President of Architecture Research, NVIDIA
Co-author 2
Co-author 2
Aamer Jaleel
Aamer Jaleel
IEEE Fellow; Principal Research Scientist at NVIDIA Research
Mohamed Tarek Ibn Ziad
Mohamed Tarek Ibn Ziad
Architecture Research Group (ARG), NVIDIA
Co-author 5
Co-author 5
Abhimanyu Bambhaniya
Abhimanyu Bambhaniya
School of Electrical and Computer Engineering, Georgia Institute of Technology
Co-author 7
Co-author 7
Hyesoon Kim
Hyesoon Kim
Georgia Tech