Bio

I am a Ph.D. student in Computer Science at Purdue University, advised by Professor Vamsi Addanki, where my research spans hardware/software co-design, computer architecture, accelerators, networking, and AI systems. My work focuses on building high-performance, scalable systems by bridging low-level architectural mechanisms with emerging workloads in distributed training and large-scale data processing. I am particularly interested in accelerator-centric architectures, photonic and high-bandwidth interconnects, collective communication optimization, and end-to-end system design for next-generation AI and HPC platforms. My research integrates analytical modeling, simulation, and real-system experimentation to explore new design spaces that push the boundaries of performance, efficiency, and system programmability.

Recent Publications

1. arXiv
   

   Harvest: Adaptive Photonic Switching Schedules for Collective Communication in Scale-up Domains
   Mahir Rahman, Samuel Joseph, Nihar Kodkani, Behnaz Arzani, and Vamsi Addanki.
   CoRR, 2026.
   PDF  Abstract  BibTeX

   Click here to close the dropdown!

   As chip-to-chip silicon photonics gain traction for their bandwidth and energy efficiency, their circuit-switched nature raises a fundamental question for collective communication: when and how should the interconnect be reconfigured to realize these benefits? Establishing direct optical paths can reduce congestion and propagation delay, but each reconfiguration incurs non-negligible overhead, making naive per-step reconfiguration impractical.
        We present Harvest, a systematic approach for synthesizing topology reconfiguration schedules that minimize collective completion time in photonic interconnects. Given a collective communication algorithm and its fixed communication schedule, Harvest determines how the interconnect should evolve over the course of the collective, explicitly balancing reconfiguration delay against congestion and propagation delay. We reduce the synthesis problem into a dynamic program with an underlying topology optimization subproblem and show that the approach applies to arbitrary collective communication algorithms. Furthermore, we exploit the algorithmic structure of a well-known AllReduce algorithm (Recursive Doubling) to synthesize optimal reconfiguration schedules without using any optimizers. By parameterizing the formulation using reconfiguration delay, Harvest naturally adapts to various photonic technologies. Using packet-level and flow-level evaluations, as well as hardware emulation on commercial GPUs, we show that the schedules synthesized by Harvest significantly reduce collective completion time across multiple collective algorithms compared to static interconnects and reconfigure-every-step baselines.

   Click here to close the dropdown!

   @article{rahman2026harvestadaptivephotonicswitching,
     journal = {CoRR},
     title = {Harvest: Adaptive Photonic Switching Schedules for Collective Communication in Scale-up Domains},
     author = {Rahman, Mahir and Joseph, Samuel and Kodkani, Nihar and Arzani, Behnaz and Addanki, Vamsi},
     year = {2026},
     eprint = {2602.09188},
     archiveprefix = {arXiv},
     primaryclass = {cs.NI},
     url = {https://arxiv.org/abs/2602.09188}
   }