Pranati Majhi

Ph.D. Student
Texas A&M University
pmajhi@tamu.edu

About Me

I am currently a fourth year PhD student at Texas A&M University, working in the field of Computer Architecture.

Research Interests

High Performance Computing: interconnection networks, deep learning accelerators
Data Compression: quantization, lossless compression, hardware based compression techniques
Efficient LLM Inference: LLM accelerators, KV Cache Management

Experience

[August 2022 - Present] Research Assistant - Texas A&M University
[August 2024 - December 2024] Research Scientist Intern - Meta
[Spring 2023/2024/2025, Fall 2025] Teaching Assistant - Texas A&M University
[June 2021 - July 2021] Summer Analyst - Goldman Sachs

Publications

HPCA

(To be presented) Compression-Aware Gradient Splitting for Collective Communications in Distributed Training

P. Majhi, S. Laskar, A. Muzahid, E. Kim

IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2026.
MICRO

SuperMesh: Energy-Efficient Collective Communications for Accelerators

S. Laskar, P. Majhi, A. Muzahid, E. Kim

IEEE/ACM International Symposium on Microarchitecture (MICRO), 2025.

PDF Code BibTex
HPCA

Enhancing Collective Communication in MCM Accelerator for Deep Learning Training

S. Laskar, P. Majhi, S. Kim, F. Mahmud, A. Muzahid, E. Kim

IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2024.

PDF Code BibTex

Education

[August 2022 - Present]
[July 2018 - May 2022]

Powered by Jekyll and Minimal Light theme.