5
Most read
7
Most read
12
Most read
GRAPHIC PROCESSING UNIT
Presented by KamranAshraf
13-NTU-4009
TOPICS
Advancements
Latest Models
Challenges
Impact on
computing
CONTRIBUTORS
Three main
contributors to
advancement:
Intel AMD/ATI Nvidia
WHAT IS RENDERING
 Rendering is the process of generating an image from a 2D or 3D model by
means of computer programs
 It is the process of add shading, color and lamination in order to create life-like
images on a screen
 A GPU assists a CPU in performing complex rendering calculations
 If a scene is to look relatively realistic and predictable under virtual lighting,
the rendering software should do it
 Rendering is also used to describe the process of calculating effects in a video
editing program to produce final video output
A variety of rendering
techniques applied to a
single 3D scene
WHAT IS GPU RENDERING?
 GPU rendering means, that there is used the power of GPU (Graphics card) for
rendering, instead of CPU (processor).
 Conventional CPUs (Intel, AMD) didn't make such dramatic progress, like GPUs in
last 10 years.
GPU RENDERING
 GPU rendering is definitely the future of rendering as one single GPU has the
same power as the huge and expensive computer clusters with many CPUs
 GPU rendering is incredibly fast and less power hungry
 You will need less computers for the same performance
 Much CHEAPER
THE WORLD'S FASTEST GPU
THEWORLD'S FASTEST GPU
The GTXTitan Z The Radeon R9 295X2
AMD’S R9 295X2
 It joins two of its R9 290X GPUs onto a single board
 Max Resolution: 4096 x 2160, Support 5x Display Monitors
 Memory: 8GB dedicated
 Cores: Powered by 5,632 cores meaning 2,816 cores for each GPU
 The most advanced dual GPU liquid cooling system ever designed
 Ups the power consumption to a scarily large 500 watts
 Cost around $1500
NVIDIA GTXTITAN Z
 5k resolutions supported:This GPU supports multi-monitors and a resolution upto 5k
 Dual GPU architecture:Two Kepler GK110 GPU’s inside,Titan Z generates the same power
as if twoTitan’s were running
 Memory:The card will support a total of 12 GB dedicated memory i.e 6 GB for each GPU.
 CUDA cores:The GTXTitan Z is powered by 5,760 CUDA cores
meaning 2,880 cores for each GPU.
 It won’t make much noise as compared to other powerful GPU’s
 Cost around $3000
CALCULATE IMAGE QUALITY
USING GPU
IMAGE QUALITY CALCULATOR
 The University of Manitoba developed an Image Quality Calculator.
 This utility, which is a plugin for ImageJ, does a great job analyzing the quality
(amount of noise)
COMPARING RESULTS
The GPU (2688 CUDA cores) was 6.2 times faster than the CPU.
IMPACT OF GPU IN
COMPUTING
GPU ACCELERATED COMPUTING
 GPU-accelerated computing is the use of aGPU together with a CPU to accelerate
scientific, analytics, engineering, consumer, and enterprise applications.
 Pioneered by NVIDIA, GPU accelerators now power energy-efficient datacenters
in government labs, universities, enterprises, and small-and-medium businesses
around the world.
 GPUs are accelerating applications in platforms ranging from cars, to mobile
phones and tablets, to drones and robots.
HOW ITWORKS
 Compute-intensive portions of the application are executed by the GPU
 The remainder of the code still runs on the CPU
 From a user's perspective, applications simply run significantly faster
GPUs have thousands of cores to process parallel workloads efficiently
CHALLENGES
THE LIGHTNING CHALLENGE
 One of the most important aspects of creating convincing 3D visuals is
implementing realistic lighting
 The challenge is not having an artist manually animate realistic-looking lighting,
but to simulate how a light reacts with, and bounces off, multiple surfaces in real-
time, otherwise known as path tracing
 In the film industry, path tracing is done offline, because the calculations required
are simply too complex
 Unity global illumination worked on advanced lighting model which supported
indirect lighting but it was very expensive so It's a technology that's not quite
ready.
POWER CHALLENGES
 Biggest, most complex processors on the planet are being made
 The biggest challenge is no longer being able to build a fast GPU
 The biggest challenge is power as Graphics can consume a near infinite amount of
horsepower
 We don't want to have to watercool everything, or have 19 fans and make things
really loud.
ADVANCEMENTS
LATEST ADVANCEMENTS
Nvidia's GameWorks technology
 Nvidia's GamesWorks is a set of visual
effects, physics effects, and tools
designed to give developers more options
when it comes to a game's visuals.
 Effects like HBAO+ and FaceWorks are
part of GameWorks.
 AO can account for the occlusion of light,
creating non-uniform shadows that add
depth to the scene.
 HBAO+ doubles the detail level of the AO
effect, runs three times faster, and uses the
latest DirectX 11 technologies.
 Nvidia's GameWorks is more copyrighted
in nature.
AMD's Mantle technology
 Mantle, allows console-like low-level
access to the CPU and GPU.
 By removing some of the software layers
of the operating system between the
hardware and the software
 With the right programming developers
are able to see an increase in
performance
 AMD claims its Mantle API is open, and
free to use
Thanks

More Related Content

PDF
GPU - Basic Working
PDF
GPU - An Introduction
PPTX
Presentation on graphics processing unit (GPU)
PPTX
GRAPHICS PROCESSING UNIT (GPU)
PPTX
Graphic Processing Unit (GPU)
PPTX
Graphics processing unit (GPU)
PPTX
Nvidia (History, GPU Architecture and New Pascal Architecture)
PPTX
Graphics Processing Unit by Saurabh
GPU - Basic Working
GPU - An Introduction
Presentation on graphics processing unit (GPU)
GRAPHICS PROCESSING UNIT (GPU)
Graphic Processing Unit (GPU)
Graphics processing unit (GPU)
Nvidia (History, GPU Architecture and New Pascal Architecture)
Graphics Processing Unit by Saurabh

What's hot (20)

PPTX
graphics processing unit ppt
PPTX
Graphics processing unit
PPTX
PPTX
CPU vs GPU Comparison
PPT
Graphics Processing Unit - GPU
PDF
Gpu presentation
PDF
CPU vs. GPU presentation
PPTX
Graphics processing unit ppt
PPTX
Tensor Processing Unit (TPU)
PDF
Introduction to GPU Programming
PPTX
GRAPHIC CARD
PPTX
Lec04 gpu architecture
PPT
NVIDIA CUDA
PPT
Graphic card
PDF
PDF
Gpu Systems
PPT
Intel Core i7 Processors
PDF
PDF
Graphic card information search pp
PPTX
Soc lect1
graphics processing unit ppt
Graphics processing unit
CPU vs GPU Comparison
Graphics Processing Unit - GPU
Gpu presentation
CPU vs. GPU presentation
Graphics processing unit ppt
Tensor Processing Unit (TPU)
Introduction to GPU Programming
GRAPHIC CARD
Lec04 gpu architecture
NVIDIA CUDA
Graphic card
Gpu Systems
Intel Core i7 Processors
Graphic card information search pp
Soc lect1
Ad

Similar to Graphic Processing Unit (20)

PPTX
presentaion on graphic process unit.pptx
DOCX
Apu fc & s project
PDF
Graphics Processing Unit: An Introduction
PDF
VisionizeBeforeVisulaize_IEVC_Final
PPSX
APU in nepal 2
PPT
GPU accelerated path rendering fastforward
PPTX
Amd future of gp us - campus party
PDF
The Power of NVIDIA GPUs: Transforming AI, Gaming, & High Performance Computing
PPTX
Graphics Processing Units
PDF
VMworld 2013: Graphics and Users in VDI
DOCX
What is graphic card.docx
PPTX
Introduction to GPU
PPTX
APUs in Nepal
PDF
TECHNICAL PAPER PRESENTATION copy
PDF
Enabling Artificial Intelligence - Alison B. Lowndes
PDF
GPU power consumption and performance trends
PDF
Accelerating Data Science With GPUs
PDF
Fuel your imagination with a Microsoft Surface Laptop Studio
PPTX
presentaion on graphic process unit.pptx
Apu fc & s project
Graphics Processing Unit: An Introduction
VisionizeBeforeVisulaize_IEVC_Final
APU in nepal 2
GPU accelerated path rendering fastforward
Amd future of gp us - campus party
The Power of NVIDIA GPUs: Transforming AI, Gaming, & High Performance Computing
Graphics Processing Units
VMworld 2013: Graphics and Users in VDI
What is graphic card.docx
Introduction to GPU
APUs in Nepal
TECHNICAL PAPER PRESENTATION copy
Enabling Artificial Intelligence - Alison B. Lowndes
GPU power consumption and performance trends
Accelerating Data Science With GPUs
Fuel your imagination with a Microsoft Surface Laptop Studio
Ad

More from Kamran Ashraf (6)

PPTX
The Maximum Subarray Problem
PPTX
Ubiquitous Computing
DOCX
Application programming interface sockets
DOCX
Error Detection types
PPTX
VIRTUAL MEMORY
PPTX
INSTRUCTION LEVEL PARALLALISM
The Maximum Subarray Problem
Ubiquitous Computing
Application programming interface sockets
Error Detection types
VIRTUAL MEMORY
INSTRUCTION LEVEL PARALLALISM

Graphic Processing Unit

  • 1. GRAPHIC PROCESSING UNIT Presented by KamranAshraf 13-NTU-4009
  • 4. WHAT IS RENDERING  Rendering is the process of generating an image from a 2D or 3D model by means of computer programs  It is the process of add shading, color and lamination in order to create life-like images on a screen  A GPU assists a CPU in performing complex rendering calculations  If a scene is to look relatively realistic and predictable under virtual lighting, the rendering software should do it  Rendering is also used to describe the process of calculating effects in a video editing program to produce final video output A variety of rendering techniques applied to a single 3D scene
  • 5. WHAT IS GPU RENDERING?  GPU rendering means, that there is used the power of GPU (Graphics card) for rendering, instead of CPU (processor).  Conventional CPUs (Intel, AMD) didn't make such dramatic progress, like GPUs in last 10 years.
  • 6. GPU RENDERING  GPU rendering is definitely the future of rendering as one single GPU has the same power as the huge and expensive computer clusters with many CPUs  GPU rendering is incredibly fast and less power hungry  You will need less computers for the same performance  Much CHEAPER
  • 8. THEWORLD'S FASTEST GPU The GTXTitan Z The Radeon R9 295X2
  • 9. AMD’S R9 295X2  It joins two of its R9 290X GPUs onto a single board  Max Resolution: 4096 x 2160, Support 5x Display Monitors  Memory: 8GB dedicated  Cores: Powered by 5,632 cores meaning 2,816 cores for each GPU  The most advanced dual GPU liquid cooling system ever designed  Ups the power consumption to a scarily large 500 watts  Cost around $1500
  • 10. NVIDIA GTXTITAN Z  5k resolutions supported:This GPU supports multi-monitors and a resolution upto 5k  Dual GPU architecture:Two Kepler GK110 GPU’s inside,Titan Z generates the same power as if twoTitan’s were running  Memory:The card will support a total of 12 GB dedicated memory i.e 6 GB for each GPU.  CUDA cores:The GTXTitan Z is powered by 5,760 CUDA cores meaning 2,880 cores for each GPU.  It won’t make much noise as compared to other powerful GPU’s  Cost around $3000
  • 12. IMAGE QUALITY CALCULATOR  The University of Manitoba developed an Image Quality Calculator.  This utility, which is a plugin for ImageJ, does a great job analyzing the quality (amount of noise)
  • 13. COMPARING RESULTS The GPU (2688 CUDA cores) was 6.2 times faster than the CPU.
  • 14. IMPACT OF GPU IN COMPUTING
  • 15. GPU ACCELERATED COMPUTING  GPU-accelerated computing is the use of aGPU together with a CPU to accelerate scientific, analytics, engineering, consumer, and enterprise applications.  Pioneered by NVIDIA, GPU accelerators now power energy-efficient datacenters in government labs, universities, enterprises, and small-and-medium businesses around the world.  GPUs are accelerating applications in platforms ranging from cars, to mobile phones and tablets, to drones and robots.
  • 16. HOW ITWORKS  Compute-intensive portions of the application are executed by the GPU  The remainder of the code still runs on the CPU  From a user's perspective, applications simply run significantly faster GPUs have thousands of cores to process parallel workloads efficiently
  • 18. THE LIGHTNING CHALLENGE  One of the most important aspects of creating convincing 3D visuals is implementing realistic lighting  The challenge is not having an artist manually animate realistic-looking lighting, but to simulate how a light reacts with, and bounces off, multiple surfaces in real- time, otherwise known as path tracing  In the film industry, path tracing is done offline, because the calculations required are simply too complex  Unity global illumination worked on advanced lighting model which supported indirect lighting but it was very expensive so It's a technology that's not quite ready.
  • 19. POWER CHALLENGES  Biggest, most complex processors on the planet are being made  The biggest challenge is no longer being able to build a fast GPU  The biggest challenge is power as Graphics can consume a near infinite amount of horsepower  We don't want to have to watercool everything, or have 19 fans and make things really loud.
  • 21. LATEST ADVANCEMENTS Nvidia's GameWorks technology  Nvidia's GamesWorks is a set of visual effects, physics effects, and tools designed to give developers more options when it comes to a game's visuals.  Effects like HBAO+ and FaceWorks are part of GameWorks.  AO can account for the occlusion of light, creating non-uniform shadows that add depth to the scene.  HBAO+ doubles the detail level of the AO effect, runs three times faster, and uses the latest DirectX 11 technologies.  Nvidia's GameWorks is more copyrighted in nature. AMD's Mantle technology  Mantle, allows console-like low-level access to the CPU and GPU.  By removing some of the software layers of the operating system between the hardware and the software  With the right programming developers are able to see an increase in performance  AMD claims its Mantle API is open, and free to use

Editor's Notes

  • #9: Why brute force rendering? The way the brute force rendering works is by looking at the scene which needs to be rendered, then essentially hammering away at the scene by sampling different areas of the shot; calculation information, calculation ray information etc. This was once a very heavy task for older cumputers to deal with. However in the past 10 years computing power has increased substantially and as a result Brute force rendering has become a much more viable option.
  • #10: Why brute force rendering? The way the brute force rendering works is by looking at the scene which needs to be rendered, then essentially hammering away at the scene by sampling different areas of the shot; calculation information, calculation ray information etc. This was once a very heavy task for older cumputers to deal with. However in the past 10 years computing power has increased substantially and as a result Brute force rendering has become a much more viable option.
  • #19: Path tracing is a computer graphics Monte Carlo method of rendering images of three-dimensional scenes such that the global illumination is faithful to reality. Fundamentally, the algorithm is integrating over all the illuminance arriving to a single point on the surface of an object.