Deepanjali Mishra

Ph.D. Candidate

Carnegie Mellon University

I am a Ph.D. candidate in the Electrical and Computer Engineering (ECE) Department at Carnegie Mellon University, where I am fortunate to be advised by Prof. Akshitha Sriraman. I also work closely with Prof. Tanvir Ahmed Khan, Dr. Gilles Pokam, and Prof. Heiner Litz, and continue to learn from their distinct styles of thinking.

The overarching vision of my research is to enable data center infrastructure to keep up with (and exceed) the evolving performance and energy requirements of the applications it enables. Emerging applications, such as agentic AI, stress every layer of this infrastructure. To address the challenges they pose, I design techniques that span the entire compute stack, from processor microarchitecture to system software.

Previously, I was a Research Fellow at Microsoft Research India, where I was fortunate to be mentored by Dr. Vivek Seshadri, who introduced me to research and inspired my interest in computer architecture. I also worked closely with Dr. Ashish Panwar and benefited from his technical mentorship. I obtained my bachelor's degree in Electronics and Communication Engineering from Visvesvaraya Technological University, India.

Designing efficient computer systems for emerging applications.

Publications

Journal

Address-Scaling: Architectural Support for Fine-grained Thread-safe Metadata ManagementIEEE Computer Architecture Letters (CAL), 2024
Deepanjali Mishra, Konstantinos Kanellopoulos, Ashish Panwar, Akshitha Sriraman, Vivek Seshadri, Onur Mutlu, and Todd C. Mowry
pdf

Workshops

Speculative Load Micro-op FusionThe Third Workshop on Hot Topics in System Infrastructure (HotInfra’26), ISCA 2026
Deepanjali Mishra, Tanvir Ahmed Khan, Gilles Pokam, Heiner Litz, and Akshitha Sriraman
All venues
- Architecture 2.0: Workshop on AI for Computing Systems Design, ISCA 2026
- Workshop on Cognitive Architectures (CogArch), ISCA 2026
- Workshop on Hot Topics in System Infrastructure (HotInfra’26), ISCA 2026
- EMC2 — Energy Efficient Machine Learning and Cognitive Computing, ASPLOS 2026
- Workshop on Memory-Centric Computing Systems (MCCSys), ASPLOS 2026
- Virtuoso: Ideas and Infrastructures for Novel HW/OS Interfaces, ASPLOS 2026
- International Workshop on Cloud Intelligence / AIOps (AIOps ’26), ASPLOS 2026
- Workshop on Heterogeneous Composable and Disaggregated Systems (HCDS), ASPLOS 2026
Address-Scaling: Architectural Support for Fine-grained Thread-safe Metadata ManagementThe Fourth Young Architect Workshop (YArch), ASPLOS 2022
Deepanjali Mishra, Akshitha Sriraman, and Vivek Seshadri
poster video slides