Scribd
Upload
52 views

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
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
52 views

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
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