AMD STUDENT CONSULTANT • Co-advising a team of UM students and engineers to accelerate bioinformatics solutions on AMD GPUs. NVIDIA RESEARCH INTERN FOR 15 MONTHS • Accelerated Dynamic Time Warping (compute-bound) on GPUs to get ∼3.7X sequencing time & cost savings using nanopore Read Until. • Accelerated Minimap2’s chaining step (memory bound) on GPUs to get upto 4.1X speedup: costup over SIMD-CPUs for genome mapping. SAMSUNG R& D SR. ENGINEER, MEMORY SOLUTIONS TEAM • Data center storage solutions: Architected the SV-UVM testbench for Non-Volatile Memory Express over Fabric (NVMEoF) and RDMA over Converged Ethernet (RoCE) VIPs.
University of Michigan
UNIVERSITY OF MICHIGAN, ANN ARBOR ’18- ’23 FINAL YEAR CSE PHD CANDIDATE ADVISED BY PROF. SATISH NARAYANASAMY UNIVERSITY OF MICHIGAN, ANN ARBOR
MS IN COMPUTER SCIENCE & ENGINEERING NATIONAL INSTITUTE OF TECHNOLOGY KARNATAKA, INDIA
BACHELOR OF TECHNOLOGY IN ELECTRONICS & COMMUNICATION ENG.
GPU-accelerated Dynamic Time Warping for Selective Nanopore Sequencing. Under review at Nature Scientific Reports.
Accelerating Minimap2 for Accurate Long Read Alignment on GPUs. Journal of Biotechnology and Biomedicine 6 (2023): 13-23.
Squigglefilter: An accelerator for portable virus detection. In MICRO-54: 54th Annual IEEE/ACM International Symposium on Microarchitecture (pp. 535-549). (ACM/IEEE MICRO Top Picks w/ Honorable Mention; ACM/IEEE Artefact Badges
Rapid Real-time Squiggle Classification for Read until using RawMap. Archives of Clinical and Biomedical Research 7 (2023): 45-57
A comprehensive solution to road traffic accident detection and ambulance management. IEEE ICAEES, pp. 43-47. IEEE, 2016. (IEEE Best Paper Award)