GSOC24

[ankitmrj]

Greetings!

Respected SU2 team,

Personal Details
Name Ankit Srivastav
Email [email protected]
Mobile +91 6388335320
Time Zone UTC +5:30
GitHub Handle @​ankitmrj

University Madan Mohan Malviya University of Technology Gorakhpur, India.
Education: Bachelor of Technology (Computer Science and Engineering).
Code Experience: Proficient in C, C++, Python, Web Development (MERN), Database (MongoDB), and Problem solving skills.

Project-5

### Feasibility of GPU acceleration in CU2

About the SU2 Foundation
The SU2 Foundation is an educational and scientific not-for-profit that will bring together computational scientists and engineers through the SU2 Foundation platform. The SU2 Foundation develops, maintains, and supports a collection of C++ and Python-based software tools for performing Partial Differential Equation (PDE) analysis and solving PDE-constrained optimization problems.

About the Project
The Graphics Processing Unit (GPU) improves performance because it integrates a more significant number of cores than the CPU. It is very useful for solving problems using several processes in parallel.
The goal of this project is to explore a straightforward adaptation of the existing SU2 code using NVBLAS, verify the potential speed-up in existing test cases, identify bottlenecks, and explore the potential for future work.

Why this feature is needed?
To create NVBLAS-enabled SU2 version. The NVBLAS Library is a GPU-accelerated Library that implements BLAS (Basic Linear Algebra Subprograms). It can accelerate most BLAS Level-3 routines by dynamically routing BLAS calls to one or more NVIDIA GPUs present in the system, when the characteristics of the call make it speed up on a GPU.

I am eager to be part and work on developing a code to generate discretized meshes with gradient information, coupling it with SU2, and benchmarking the new method against traditional approaches. I am confident in my skills in C++,feasibility analysis of the use of GPU to improve the efficiency of metaheuristics optimization algorithms.

I am undergraduate student, I have classes for approximately 5-7 hours a day. However, I am committed to dedicating at least 20-25 hours per week to this project from the start of April. During my summer upcoming vacation months in May, June and July, I will be able to allocate 5-6 hours daily to the project, which should provide adequate time to tackle the challenges posed by this easy / medium.

I am thrilled to get opportunity to contribute to the SU2 project and believe that my skills and wholeheartedness make me a appropriate candidate for this project. I am looking forward to the possibility of working with mentor @leonardo Cavanha and the SU2 team during the Google Summer of Code program.

I would be cognizant of if you could connect me with the project mentor to further discuss the project details and establish a timeline. I am eager to collaborate closely with the mentor to ensure the successful completion of the project.

Thank you for taking into account my application. I am available for any further discussions or elucidation you may require.
I look forward to hearing from you.

Thank you!