Scribd
Upload
4 views

Graphics Processing

The document provides an overview of Graphics Processing Units (GPUs), detailing their definition, components, architecture, and comparison with Central Processing Units (CPUs). It highlights the GPU's efficiency in processing graphics and parallel tasks, as well as its advantages and disadvantages. The conclusion emphasizes the GPU's significant performance capabilities, particularly in artificial intelligence applications.

Uploaded by

thumuphaninder150
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
4 views

Graphics Processing

The document provides an overview of Graphics Processing Units (GPUs), detailing their definition, components, architecture, and comparison with Central Processing Units (CPUs). It highlights the GPU's efficiency in processing graphics and parallel tasks, as well as its advantages and disadvantages. The conclusion emphasizes the GPU's significant performance capabilities, particularly in artificial intelligence applications.

Uploaded by

thumuphaninder150
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 12

GRAPHICS

PROCESSIN
G
UNIT
AN ELECTRONIC CIRCUIT THAT PERFORMS
MATHEMATICAL CALCULATIONS AT HIGH SPEED

PRESENTED BY :
Gummadi Sharath
21QP1A0543
CSE - A
CONTENTS :
1.Introduction
2.Definition
3.Components of GPU
4.Architecture
5.Comparison with CPU
6.GPU Pipeline
7.Conclusion
INTRODUCTION :
• the term was
popularized by
Nvidia in 1999,who
marketed the geforce
256 as “the world’s
first GPU”.
• GPU is designed
especially for the
processing of 3D
graphic
• GPU’S form the heart
of modern graphics
cards
DEFINITION :
• A Graphics Processing Unit is called as
Visual Processing Unit(VPU)

• It is a dedicated processor efficient at


manipulating and displaying computer
graphics.

• Like a CPU it is a single chip processor.


COMPONENTS OF GPU :
The components of a Graphics processing unit are:
1.Graphical processor:
It performs graphical computations
2.Memory:
It is used to store images and list of coordinates
3.Multiprocessors:
It contains multi processors ,each with a shared
memoryblock,processors and register
4.Cores:
It is used to divide processing tasks
5.Fan:
It is used to cool it down
6.Connector:
It has connectors for graphics outputs
ARCHITECTURE :

• Control hardware dominates processors


• Complex,difficult to build and verify
• Takes substaintal fraction of die scales poorly
• Quadratic dependency checking
• Control hardware doesn’t do any math!
COMPARISON BETWEEN GPU
AND CPU :

GPU CPU
• Graphics • central processing
processing unit unit

• 100’s or 1000’s of • 4 – 8 cores


cores

• High throughput • low latency

• good for parallel • good for serial


processing processing

• Break jobs into • quickly process


separate tasks to task that require
process interactivity
simultaneously
The GPU Pipeline :

• The GPU receives geometry information from the CPU


as an input and provides a picture as an output
• Let’s see how that happens…

Vertex Triangle Pixel


Host Memory
processin processin
interface setup interface
g g
CHARACTERISTICS OF GRAPHICS IN GPU:

• Large computational requirements


• Massive parallelism
• Long latencies tolerable
• Deep,feed-forward pipelines
ADAVANTGES : DISADVANTAGES :

8x as many operations  GPU executes some types


executed per sec of code fast
4x as many bytes  need lot of data
transferred per sec parallelism,data reuse and
regularity
29x as much performance
 GPU’s are harder to
per dollar program and tune than
6x as much performance CPU’s
per watt  poor tools support for
irregular codes
Conclusion :
• GPU 157X FASTER for 400 nodes
• Lots of improvement can be made
• GPU is well suited for A.I
Do You Have Any Questions ?

THANK YOU

You might also like