KEMBAR78
Graphics Processing Unit | PDF
Scribd
Upload
128 views9 pages

Graphics Processing Unit

A GPU is a processor optimized for graphics and visual computing. It has thousands of cores that can efficiently process parallel workloads compared to a CPU which has fewer cores for serial processing. A GPU has components like a processor, memory, and display connector. It works by receiving geometry from the CPU, rasterizing it, and providing a picture output through processes like vertex processing and pixel processing. Major GPU manufacturers include NVIDIA, AMD, and Intel.

Uploaded by

Rahul S
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
128 views9 pages

Graphics Processing Unit

A GPU is a processor optimized for graphics and visual computing. It has thousands of cores that can efficiently process parallel workloads compared to a CPU which has fewer cores for serial processing. A GPU has components like a processor, memory, and display connector. It works by receiving geometry from the CPU, rasterizing it, and providing a picture output through processes like vertex processing and pixel processing. Major GPU manufacturers include NVIDIA, AMD, and Intel.

Uploaded by

Rahul S
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/ 9

Graphics

processing unit
By RAHUL S
CONTENT
 WHAT IS GPU?
 DIFFERENCES FROM CPU
 COMPONENTS OF GPU
 WORKING
 MODERN ARCHITECTURE
 GPU TECHNOLOGIES & MAJOR MANUFACTURES
WHAT IS GPU?

 It is processor optimized for 2D/3D graphics, video, visual computing,


and display.
 It is highly parallel, highly multithreaded multiprocessor
optimized for visual computing.
 parallel architecture- visual processing unit
 Works along with cpu.
CPU VERSES GPU

 A CPU consists of a few cores optimised for sequential serial


processing
 GPU have thousands of cores to process parallel workloads efficiently
 Gpu has deeper pipelines
 GPUs have significantly faster and
more advanced memory interfaces
COMPONENTS OF GPU

 A motherboard connections for data and power


 A processor to decide what to do with each pixel
 Memory to hold information
 Display connector for power supply

 DISADVANTAGES
GPU has more transistors, so it produce lot of heat ,so it is usually located
under a hear sink or a fan.
WORIKING OF GPU

 The cpu sends information about the image


 The graphics card decides how to use the pixel
 The graphic card create wire fame
 It rasterizes
 Eg,
for paced games, the computer has to go through this process about sixty
times per second.
MODERN ARCHITECTURE

 The GPU receives geometry information (mainly triangles in 3D) from the CPU
as an input and provides a picture as an output
 Let see how that happens

1. HOST INTERFACE
2. VERTEX PROCESSING
3. TRIANGLE SETUP
4. PIXEL PROCESSING
5. MEMORY
TOP GPU MANUFACTURERS
 NVIDIA
 ATI\AMD
 INTEL

TOP TECHNOLOGIES
 CUDA parallel computing
 PHYSC technology
 NVIDIA 3D vision technology

APPLICATIONS
 COMPUTER GAMES
 DESINGING AUTOMOBILES
 CONSTRUCTION
 MEDICAL SCIENCE
 GRAPHICAL USER INTERFACE
 MOVIES ANIMATION
CONCLUTION

 This paper presents our evaluation and efficiency of GPU computing for data
applications.
 In the future, we will continue this work by investigating the effects of
memory on the GPU performance and efficiency.

Thank you so much !!

You might also like