I am interested in working at the intersection of Machine Learning and High-Performance computing.
I am experienced in working on MLIR, Torch-MLIR and Glow compiler infrastructures. I have worked on optimizing machine learning models for inferences and training. I have also worked on projects related to automated code generation for GPUs.
- Programming: C++, C, Python, HTML, CSS, MySQL, PHP
- Technologies: MLIR, Torch-MLIR, LLVM, Clang, Pytorch, Linux, Git, Wordpress
- Libraries: CUDA, Numpy, Keras, Pandas, Scikit-learn, Matplotlib, OpenAI Gym & Baselines
I am working on adding support and optimizations for deep learning models in the torch-mlir.
I also actively contribute to the open-source torch-mlir framework. Link to the contributions..
July 2021 - October 2021
I worked on optimizing Machine Learning models on Qualcomm processors for inferences using Glow compiler infrastructure.
August 2019 - June 2021
INDIAN INSTITUTE OF SCIENCE, BANGALORE
Computer Science and Engineering. GPA: 8.5/10
Courses: Computer Architecture, Compiler Design, Theory and Practice of Computer Systems Security, Deep Learning for Natural Language Processing, Machine Learning, Practical Data Science, Linear Algebra and Probability, Design and Analysis of Algorithms, Cryptography.
August 2015 - May 2019
MADHAV INSTITUTE OF TECHNOLOGY AND SCIENCE
Computer Science and Engineering
GPA: 7.77
PUBLISHED IN THE 31ST ACM SIGPLAN INTERNATIONAL CONFERENCE ON COMPILER CONSTRUCTION (CC’22)
The work presents an MLIR based code-generation pipeline for Tensor Cores on NVIDIA GPUS, which achieves performance comparable to that of hand-tuned libraries like cuBLAS, cuBLASLt, and cuTensor.
- GATE 2019, All India Rank - 45 (78.33 marks out of 100)
- Flipkart Grid, Secured position in Top 150 out of 22.5K teams from Top 100 colleges of India
Address
Gwalior, M.P., India - 474011
Phone
+91 7879835123
vivekkhandelwal1424@gmail.com