Scribd
Upload
114 views

GPU Architecture and Programming

Uploaded by

sivasankari.csbs
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
114 views

GPU Architecture and Programming

Uploaded by

sivasankari.csbs
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

Department CSBS Programme: M.Tech.

Semester III Course Category: BS *End Semester Exam Type: TE


Periods / Week Credit Maximum Marks
Course Code L T P C CAM ESE TM
Course Name GPU Architecture and Programming 3 0 0 3 25 75 100
To understand the fundamental principles and engineering trade-offs involved in designing
1)
modern parallel computers
Course 2) Code with GPU programming environments
Objectives 3) Understand GPU computing architecture
4) Develop solutions to solve computationally intensive problems in various fields
5) Design and develop programs that make efficient use of the GPU processing power
BT Mapping
On completion of the course, the students will be able to (Highest Level)
Define terminology commonly used in parallel computing, such as efficiency K1
CO1
and speedup.
CO2 Describe common GPU architectures and programming models. K2
Course Implement efficient algorithms for common application kernels, such as K3
CO3
Outcome matrix multiplication.
CO4 Given a problem, develop an efficient parallel algorithm to solve it. K4
Given a problem, implement an efficient and correct code to solve it,
CO5 K5
analyze its performance,
UNIT-I (9Hrs)
Introduction: The need for parallelism, Forms of parallelism (SISD, SIMD, MISD, MIMD), Moore's Law
and Multi-cores, Fundamentals of Parallel Computers, Communication architecture, Message passing CO1
architecture, Data parallel architecture, Dataflow architecture, Systolic architecture, Performance Issues.
UNIT-II (9Hrs)
Graphics Processing Unit: GPUs as Parallel Computers, Architecture of a modern GPU, Evolution of CO2
Graphics Pipelines, GPGPUs, Scalable GPUs, Architectural characteristics of Future Systems, Implication
of Technology and Architecture for users, Vector addition, Applications of GPU.
UNIT-III (9Hrs)
Graphics Processing Unit: GPUs as Parallel Computers, Architecture of a modern GPU, Evolution of
CO3
Graphics Pipelines, GPGPUs, Scalable GPUs, Architectural characteristics of Future Systems, Implication
of Technology and Architecture for users, Vector addition, Applications of GPU.
UNIT- IV (9Hrs)

Introduction to Parallel Programming: Strategies, Mechanism, Performance theory, Parallel


Programming Patterns: Nesting pattern, Parallel Control Pattern, Parallel Data Management, Map: Scaled
CO4
Vector, Mandelbrot, Collative: Reduce, Fusing Map and Reduce, Scan, Fusing Map and Scan, Data
Recognition: Gather, Scatter, Pack , Stencil and Recurrence, Fork-Join, Pipeline

UNIT- V (9Hrs)
Parallel Programming Languages: Distributed Memory Programming with MPI: trapezoidal rule in MPI,
I/O handling, MPI derived datatype, Collective Communication, Shared Memory Programming with
Pthreads: Conditional Variables, read-write locks, Cache handling, Shared memory programming with CO5
Open MP: Parallel for directives, scheduling loops, Thread Safety, CUDA: Parallel programming in CUDA
C, Thread management, Constant memory and Event, Graphics Interoperability, Atomics, Streams.
Text Books
1. Benedict R Gaster, Lee Howes, David, R. Kaeli, Perhaad Mistry and Dana Schaa, “Heterogeneous Computing
with OpenCL”, Elsevier, 2013.
2. Aaftab Munshi, Benedict Gaster, Timothy G. Mattson, James Fung & Dan Ginsburg, “OpenCL Programming
Guide”, Addison-Wesley Professional, 2011.
3. RyojiTsuchiyama, Takashi Nakamura, TakuroIizuka & Akihiro Asahara, “The OpenCL Programming Book”,
Fixstars Corporation, 2010.
4. Matthew Scarpio, “OpenCL in Action: How to Accelerate Graphics and Computations”, Manning Publications,
2011.
Reference Books
1. P. Pacheco, Parallel Programming with MPI, Elsevier
2. Shane Cook, CUDA programming, Morgan Kaufmann
Web References
1. https://www.nvidia.com/en-us/accelerated-applications/
2. https://forums.developer.nvidia.com/c/nvidia-virtual-gpu-forums/328

* TE – Theory Exam, LE – Lab Exam

COs/POs/PSOs Mapping
Program Specific
Program Outcomes (POs)
COs Outcomes (PSOs)
PO1 PO2 PO3 PO4 PO5 PO6 PO7 PO8 PO9 PO10 PO11 PO12 PSO1 PSO2 PSO3
1
2
3
4
5

Correlation Level: 1 - Low, 2 - Medium, 3 – High

Evaluation Method

Continuous Assessment Marks (CAM) End


Semester
Assessmen Total
CAT CAT Model Examinatio
t Assignment* Attendance Marks
1 2 Exam n (ESE)
Marks
Marks 10 5 5 5 75 100

* Application oriented / Problem solving / Design / Analytical in content beyond the syllabus

You might also like