Pradeep Rao
Principal Member Of Technical Staff at AMD
Bengaluru, Karnataka, India
Summary
👤
Senior🎓
Top SchoolPradeep Rao is a Principal Member of Technical Staff at AMD with over a decade of experience optimizing software for modern CPU and GPU architectures, including deep expertise in high-performance computing, linear algebra, and low-level C/OpenCL development. He has a strong track record of shipping and optimizing compute kernels and libraries—contributing to open-source projects like BLIS and clFFT where he implemented and refined single-precision triangular solves and advanced FFT precallback support for multi-dimensional transforms. Previously he led GPU and HPC efforts using OpenCL and CUDA and built enterprise-grade Microsoft-stack solutions, giving him a rare combination of systems-level performance tuning and application-layer engineering. Based in Bengaluru, he pairs rigorous microkernel optimization skills with practical framework and tooling experience, and often bridges developer adoption and SDK enablement at platform scale. An engineer comfortable in both algorithmic math and production ecosystems, he brings a pragmatic focus on accuracy, testability, and cross-platform consistency.
10 years of coding experience
12 years of employment as a software developer
Bachelor Of Engineering, Mechanical, Bachelor Of Engineering, Mechanical at RV College Of Engineering
Github Skills (12)
opencl10
fft10
dft10
c-language10
blas10
cprogramming-language10
optimization10
testing10
c119
c179
assembly8
x86-648
Programming languages (5)
Github contributions (5)
clMathLibraries/clFFT
Jul 2015 - Jan 2016
a software library containing FFT functions written in OpenCL
Role in this project:
Back-end Developer
Back-end DeveloperContributions:51 commits, 3 pushes in 5 months
Contributions summary:Pradeep's contributions are primarily focused on implementing and testing pre-callback functionalities within the clFFT library. The commits demonstrate adding support for 2D and 3D complex-to-complex (C2C) and real-to-complex (R2C) transforms, and enhancing the existing capabilities. The user addressed existing test failures related to precallback with a particular focus on improving the accuracy and reliability of the pre-callback feature, including tests involving mixed-radix FFT transforms, and ensuring consistency with reference outputs from the FFTW library. Furthermore, the user refactored and improved existing test cases within the library, including documentation updates.
cudalibrary-softwaregpufftgpgpu
flame/blis
Sep 2016 - May 2019
BLAS-like Library Instantiation Software Framework
Role in this project:Back-end Developer
Back-end DeveloperContributions:10 commits in 2 years 8 months
Contributions summary:Pradeep contributed to the BLIS library by implementing single-precision trsm for lower triangular matrices, adding related files, and modifying existing ones. They were involved in optimizing microkernels and testing trsm single precision. The user also fixed merge conflicts and updated the license file. Furthermore, the user worked on refactoring and updating code within the framework.
software-frameworklinear-algebra-librarylinear-algebramatrix-multiplicationblis
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.