Pranav Bhandarkar
Senior Member Of Technical Staff, Compilers at AMD
Austin, Texas, United States
Summary
🤩
Rockstar🎓
Top SchoolPranav Bhandarkar is a senior compiler engineer with nearly 13 years of deep experience across target-independent and target-dependent compiler development, having worked extensively with both GCC and LLVM. He has led an engineering team building the Halide compiler backend for Qualcomm’s proprietary processors and now works on compilers at AMD from Austin, Texas. His contributions to the LLVM project include nuanced OpenMP fixes and MLIR-to-LLVMIR translations for offloading and private clauses, reflecting expertise in parallelism and code-generation for heterogeneous targets. Comfortable across DSP, ARM, and custom accelerators, he combines systems-level optimization experience with hands-on backend implementation and team leadership. An understated strength is his ability to bridge frontend IR transformations and low-level target-specific code generation to deliver performant, maintainable toolchains.
2 years of coding experience
18 years of employment as a software developer
Masters Computer Science, Masters Computer Science at The University of Texas at AustinHSC, HSC at St. Vincents High SchoolBachelor of Engineering Computer Engineering, Bachelor of Engineering Computer Engineering at Savitribai Phule Pune University
Hindi, Marathi
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (8)
openmp10
c-language10
cprogramming-language10
compiler-construction10
mlr10
llvm10
parallel-computing9
llvm-ir9
Programming languages (2)
Github contributions (5)
llvm/llvm-project
Dec 2023 - Mar 2025
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:94 reviews, 30 PRs, 10 pushes in 1 year 3 months
Contributions summary:Pranav primarily contributed to the LLVM project by implementing and fixing code related to OpenMP. Their work involved modifying the OpenMPIRBuilder to correctly handle dependencies within the `omp.task` and `omp.target` constructs, specifically addressing scenarios where the if clause of a task construct evaluates to false and the nowait and/or depend clauses are in place. They also combined existing functionalities within the OpenMPIRBuilder to streamline the process of generating offloading pointer arrays. Furthermore, they added support for translating private clauses on `omp.target` operations from MLIR to LLVMIR, including the correct handling of deallocation.
compilerstechnologiesclangsubmittoolchain
bhandarkar-pranav/llvm-project
Dec 2023 - Mar 2025
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Contributions:138 pushes, 30 branches in 1 year 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.