Syllabus
Unit 1
Introduction to basic architecture and OS concepts – multi-core CPUs – high-speed interconnects – overview of High-Performance Computing (HPC) and its importance – hardware and software requirements for HPC – parallel programming and their applications (MPI/OpenMP) – brief introduction to workload manager and job schedulers.
Unit 2
Overview of GPU architecture and its evolution – comparison of CPU and GPU architecture – introduction to CUDA programming and its basic concepts – optimizing CUDA kernels for maximum performance – advanced CUDA programming techniques, such as shared memory, constant memory, and texture memory – introduction to cuBLAS and cuDNN libraries for linear algebra and deep learning – case studies of GPU: accelerated applications in scientific computing, data analytics, and machine learning.
Unit 3
Definition of cloud computing and its importance – Benefits and challenges of cloud computing – types of cloud services (IaaS, PaaS, SaaS) and their characteristics – cloud computing architecture and its components – cloud storage and its types – cloud networking and its challenges – cloud security and its importance – cloud application – benefits and challenges of HPC and AI – synergy between HPC and AI – training and inference of AI models using HPC.
Objectives and Outcomes
Course Objectives
- Familiarize student with architectural overview of modern HPC and GPU based heterogeneous architectures, focusing on its computing power versus data movement needs.
- Familiarise the students working with cloud platforms and services to configure and use computational resources and storage.
- To educate students how to write efficient parallel programming and GPU programming.
- To discuss various application of HPC computational techniques in computational science.
Course Outcomes
After completing this course, students will be able to
CO1
|
Apply high-performance computing in different research field.
|
CO2
|
Design OpenMPI programme and CUDA programme
|
CO3
|
Simulate on cloud computing system.
|
CO4
|
Evaluate how the convergence of HPC and AI is transforming the data science.
|
CO-PO Mapping
PO/PSO
|
PO1
|
PO2
|
PO3
|
PO4
|
PO5
|
PO6
|
PO7
|
PO8
|
PO9
|
PO10
|
PO11
|
PO12
|
PSO1
|
PSO2
|
PSO3
|
CO
|
CO1
|
3
|
2
|
–
|
2
|
2
|
3
|
2
|
–
|
–
|
2
|
1
|
3
|
1
|
1
|
–
|
CO2
|
2
|
3
|
3
|
3
|
3
|
–
|
1
|
–
|
2
|
1
|
2
|
3
|
3
|
3
|
1
|
CO3
|
2
|
2
|
3
|
2
|
3
|
1
|
1
|
–
|
2
|
1
|
2
|
3
|
2
|
2
|
1
|
CO4
|
2
|
2
|
1
|
2
|
3
|
2
|
1
|
1
|
2
|
1
|
2
|
3
|
3
|
3
|
3
|
Text Books / References
Text Books / References
“High Performance Computing: Modern Systems and Practices” by Thomas Sterling and Matthew Anderson
“CUDA by Example: An Introduction to General-Purpose GPU Programming” by Jason Sanders and Edward Kandrot
“Parallel Programming with MPI” by Peter S. Pacheco
Comer, D. (2021). The Cloud Computing Book: The Future of Computing Explained. CRC Press