Scribd
Upload
12 views1 page

OpenMP and CUDA Programming Questions

The document is a question bank for a Parallel Computing course (BCS702) covering topics in OpenMP and CUDA. It includes questions on differences between PThreads and OpenMP, variable scope, loop-carried dependencies, scheduling, cache coherence, thread safety, GPU architecture, and CUDA programming. Each module contains specific questions aimed at assessing understanding and application of parallel computing concepts.

Uploaded by

Madegowda N
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
12 views1 page

OpenMP and CUDA Programming Questions

The document is a question bank for a Parallel Computing course (BCS702) covering topics in OpenMP and CUDA. It includes questions on differences between PThreads and OpenMP, variable scope, loop-carried dependencies, scheduling, cache coherence, thread safety, GPU architecture, and CUDA programming. Each module contains specific questions aimed at assessing understanding and application of parallel computing concepts.

Uploaded by

Madegowda N
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Parallel Computing (BCS702)

Question Bank Module 4


[Link]. Questions
1 Give the difference between PThreads and OpenMP programming.
Discuss the role of OpenMP pragmas and directives with example
programs.
2 Explain the scope of variables in OpenMP (shared, private, firstprivate,
lastprivate, reduction) with examples.
3 Explain loop-carried dependency in OpenMP and why some loops
cannot be parallelised. Provide examples.
4 What is scheduling in OpenMP? Explain different schedule types in
OpenMP.
5 Explain cache coherence, false sharing, and their impact on OpenMP
performance with diagrams.
6 Discuss the producer-consumer model using OpenMP with suitable
code.
7 What is thread safety in OpenMP? Explain race conditions, locks,
critical sections, and atomic operations
8 Discuss the use of task directives in OpenMP and write a program to
compute Fibonacci numbers using OpenMP tasks.

MODULE 5
[Link]. Questions

1 Discuss the architecture of a GPU with a suitable block diagram.

2 What is the CUDA API? Explain threads, blocks, and grids in CUDA
with threadIdx, blockIdx, blockDim, gridDim usage.
3 Write and explain a complete CUDA program for vector addition with
indexing explanation.
4 Explain CUDA implementation of trapezoidal rule – Version I.

5 Explain performance improvements in CUDA trapezoidal rule –


Version II.
6 Explain blocks with more than one warp in the trapezoidal rule –
Version III.
7 Explain different methods of returning results from CUDA kernels

8 Explain NVIDIA compute capabilities and their effect on GPU


architecture.

You might also like