GRAPHICS PROCESSING

UNIT(GPU)

BY
Bivekananda
ELECTRONICS &
COMMUNICATION
ENGINEERING

INTRODUCTION
What is GPU?
It is a processor optimized for 2D/3D graphics, video,
visual computing, and display.
It is highly parallel, highly multithreaded
multiprocessor optimized for visual computing.
Its uses parallel archetecture.It is also
called Visual processing unit
It serves as both a programmable graphics
processor and a scalable parallel
computing platform.
It works along with CPU

CPU VERSUS GPU

A SIMPLE WAY TO UNDERSTAND THE
DIFFERENCE BETWEEN A CPU ANDGPU IS
TO COMPARE HOW THEY PROCESS TASKS.
A CPU CONSISTS OF A FEW CORES
OPTIMIZED FOR SEQUENTIAL SERIAL
PROCESSING WHILE A GPU HAS A
MASSIVELY PARALLEL ARCHITECTURE
CONSISTS OF THOUSANDS OF SMALLER,
MORE EFFICIENT CORES DESIGNED FOR
HANDLING MULTIPLE TASKS
SIMULTANEOUSLY

GPU vs CPU
A GPU is tailored for highly parallel operation
while a CPU executes programs serially
For this reason, GPUs have many parallel
execution units and higher transistor counts,
while CPUs have few execution units and higher
clockspeeds
GPUs have much deeper pipelines (several
thousand stages vs 10-20 for CPUs)
GPUs have significantly faster and more
advanced memory interfaces as they need to
shift around a lot more data than CPUs

CPU VERSUS GPU

PHYSICAL VIEW
OF A GPU

COMPONENTS OF
A GPU
*

MOTHERBOARD

GRAPHICS PROCESSOR

MEMORY

DISPLAY CONNECTOR

Working
The images you see on your monitor are
made of tiny dots called pixels. At most
common resolution settings, a screen
displays over a million pixels, and the
computer has to decide what to do with
every one in order to create an image. To do
this, it needs a translator something to take
binary data from the CPU and turn it into a
picture you can see. Unless a computer has
graphics
capability
built
into
the
motherboard, that translation takes place on
the graphics card

Working Continues
The CPU sends information about the image to
the graphics card. The graphics card decides
how to use the pixels on the screen to create
the image. It then sends that information to
the monitor through a cable
To make a 3Dimage,the graphics card first
creates a wire frame out of straight lines. Then,
it rasterizes the image (fills in the remaining
pixels). It also adds lighting, texture and
color. For fastpaced games,the computer has
to go through this process about sixty times
per second. Without a graphics card to perform
the necessary calculations, the workload would

The graphics card accomplishes this

task using four main components:
A motherboard connection for data
and power
A processor to decide what to do
with each pixel on the screen
Memory to hold information about
each pixel and to temporarily store
completed pictures

GRAPHICS PROCESSOR
A graphics card's processor, called a graphics
processing unit (GPU), is similar to a computer's
CPU. A GPU is designed specifically for performing
the complex mathematical and geometric
calculations that are necessary for graphics
rendering. Some of the fastest GPUs have more
transistors than the average CPU. A GPU
produces a lot of heat, so it is usually located
under a heat sink or a fan.

RAM
As the GPU creates images, it needs somewhere to
hold information and completed pictures. It uses
the card's RAM for this purpose, storing data

PCI Connection
Graphics cards connect to the computer
through the motherboard. The motherboard
supplies power to the card and lets it
communicate with the CPU. PCI Express is the
newest form of connection and provides the
fastest transfer rates between the graphics
card and the motherboard

Specifications
A

good

overall

measurement

of

card's

performance

is its frame
rate,
measured in frames per second (FPS). The frame
rate describes how many complete images the
card can display per second. The human eye can
process about 25 frames every second, but fast
action games require a frame rate of at least 60
FPS to provide smooth animation and scrolling
The graphics card's hardware directly affects its
speed. These are the hardware specifications that
most affect the card's speed and the units in
which they are measured:

GPU clock speed (MHz)

Size of the memory bus (bits)
Amount of available memory (MB)
Memory clock rate (MHz)

Modern GPU
Architecture

The GPU pipeline

The GPU receives geometry

information(mainly triangles in
3D) from the CPU as an input and
provides a picture as an output
Lets see how that happens
host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Host Interface
The host interface is the communication bridge
between the CPU and the GPU
It receives commands from the CPU and also pulls

geometry information from system

memory
It outputs a stream of vertices in object space
with all their associated information (normals,
texture coordinates, per vertex color etc)
host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Vertex Processing
*A vertex processing is a graphics processing
function that maps vertices onto the screen
and adds special effects to objects in a 3D
environment.
One of its purposes is to transform each vertex's
3D position in virtual space to the 2D coordinate
at which it appears on the screen.
Vertex pipelines also eliminate unneeded
geometry by detecting parts of the scene that are
hidden by other parts and simply discarding those
triangle
host
vertex
pixel
memory
parts
setup
interface
processing
processing
interface

Triangle setup
Rasterization
It is the process of determining which screenspace
pixel locations are covered by each triangle. Each
triangle generates a primitive called a fragment
at each screenspace pixel location that it covers.

host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Triangle Setup (cont)

A fragment is generated if and only
if its center is inside the triangle

host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Fragment Processing Or Pixel

processing
Each fragment provided by triangle setup is fed
into fragment processing as a set of attributes
(position, normal, texcoord etc), which are used
to compute the final color for this pixel
The computations taking place here include
texture mapping and math operations

host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Memory Interface
Fragment colors provided by the previous stage
are written to the framebuffer
Before the final write occurs, some fragments are
rejected by the zbuffer, stencil and alpha tests
The final pixels are processed and are provided as
picture

host
interface

vertex
processing

triangle
setup

pixel
processing

memory
interface

Diagram of a modern GPU

Input from CPU

Host interface

Vertex processing

Triangle setup

Pixel processing

Memory Interface
64bits to
memory

64bits to
memory

64bits to
memory

64bits to
memory

GPU
MANUFACTURERS:
*NVIDIA
*ATI/AMD
*INTEL

APPLICATIONS

LATEST GPU TECHNLOGY

CUDA Parallel Computing
CUDA IS NVIDIAS PARALLEL COMPUTING
ARCHITECTURE THAT ENABLES DRAMATIC INCREASES
IN COMPUTING PERFORMANCE BY HARNESSING THE
POWER OF THE GPU (GRAPHICS PROCESSING UNIT).

PHYSX TECHNOLOGY
NVIDIA PHYSX TECHNOLOGY HELPS GAMES PLAY
BETTER AND FEEL BETTER BY MAKING INTERACTION
WITH ENVIRONMENTS AND
CHARACTERS FAR MORE REALISTIC THAN EVER
BEFORE. BY MAKING BEHAVIOR MORE REALISTIC, THE
GRAPHICS LOOK AND FEELBETTER

NVIDIA 3D Vision Technology

NVIDIA
3D
VISION
TECHNOLOGY
DELIVERS
STEREOSCOPIC 3D IMAGES FOR GAMERS, MOVIE
LOVERS AND PHOTO ENTHUSIASTS
WHEN CONFIGURED WITH NVIDIA GPUS, NVIDIA 3D
VISION ACTIVE SHUTTER GLASSES, AND 3D VISION
READY DISPLAY/PROJECTOR.

LATEST GPU AVAILABLE IN

MARKET Gtx
NVIDIA GEFORCE
980 Ti

It supports:

CUDA
3D Vision
PhysX
4k

GTX 980 TI Memory

Specs:
Memory Clock :1753 MHZ
Memory size:6GB
MemoryBandwidth(GB/sec):
336.5

AMD Radeon R9
290X

Memory Clock :1250

MHZ
Memory size:4GB
MemoryBandwidth(GB/se
c):345.6
GPU Clock speed:1000
MHZ

THANK YOU