GRAPHICS PROCESSING UNIT

PRESENTED BY LEKSHMI P A ROLL NO:19

2/2/2013 1

Presentation Overview
Definition Comparison with CPU Architecture GPU-CPU Interaction GPU Memory

2/2/2013

Why GPU?
To provide a separate dedicated graphics
resources including a graphics processor and memory. To relieve some of the burden of the main system resources, namely the Central Processing Unit, Main Memory, and the System Bus, which would otherwise get saturated with graphical operations and I/O requests.

2/2/2013

There comes

GPU

2/2/2013

What is a GPU?
A Graphics Processing Unit or GPU (also occasionally called Visual Processing Unit or VPU) is a dedicated processor efficient at manipulating and displaying computer graphics . Like the CPU (Central Processing Unit), it is a single-chip processor.

2/2/2013

HOWEVER,
The abstract goal of a GPU, is to enable
a representation of a 3D world as realistically as possible. So these GPUs are designed to provide additional computational power that is customized specifically to perform these 3D tasks.

2/2/2013

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 , while CPUs have few execution units . GPUs have singificantly faster and more advanced memory interfaces as they need to shift around a lot more data than CPUs. GPUs have much deeper pipelines (several thousand stages vs 10-20 for CPUs).
2/2/2013 7

BRIEF HISTORY
First-Generation GPUs
Up to 1998; Nvidias TNT2, ATis Rage, and 3dfxs Voodoo3;DX6 feature set.

Second-Generation GPUs Third-Generation GPUs

1999 -2000; Nvidias GeForce256 and GeForce2, ATis Radeon7500, and S3s Savage3D; T&L; OpenGL and DX7;Configurable.

2001; GeForce3/4Ti, Radeon8500, MSs Xbox; OpenGL ARB, DX7/8; Vertex Programmability + ASM

Fourth-Generation GPUs

Fifth-Generation GPUs - GeForce 8X:DirectX10.

2002 onwards; GeForce FX family, Radeon 9700; OpenGL+extensions, DX9; Vertex/Pixel Programability + HLSL; 0.13 Process, 125M T/C, 200M T/S.

2/2/2013

GPU Architecture
How many processing units?
How many ALUs? Do you need a cache? What kind of memory?
2/2/2013 9

GPU Architecture
How many processing units?
Lots.

How many ALUs? Do you need a cache? What kind of memory?

2/2/2013 10

GPU Architecture
How many processing units?
Lots.

How many ALUs?

Hundreds.

Do you need a cache? What kind of memory?

2/2/2013 11

GPU Architecture
How many processing units?
Lots.

How many ALUs?

Hundreds.

Do you need a cache?

Sort of.

What kind of memory?

2/2/2013 12

GPU Architecture
How many processing units?
Lots.

How many ALUs?

Hundreds.

Do you need a cache?

Sort of.

What kind of memory?

very fast.
2/2/2013 13

The difference.

Without GPU
2/2/2013

With GPU

14

The GPU pipeline

The GPU receives geometry information
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

2/2/2013

15

Details..

2/2/2013

16

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 (texture coordinates, per vertex color etc) .
host interface vertex processing triangle setup pixel processing memory interface

2/2/2013

17

Vertex Processing
The vertex processing stage receives vertices
from the host interface in object space and outputs them in screen space This may be a simple linear transformation, or a complex operation involving morphing effects No new vertices are created in this stage, and no vertices are discarded (input/output has 1:1 mapping)

host interface

vertex processing

triangle setup

pixel processing

memory interface

2/2/2013

18

Triangle setup
In this stage geometry information becomes
raster information (screen space geometry is the input, pixels are the output) Prior to rasterization, triangles that are backfacing or are located outside the viewing frustrum are rejected

host interface

vertex processing

triangle setup

pixel processing

memory interface

2/2/2013

19

Triangle Setup (cont..)

A pixel is generated if and only if its center is inside
the triangle Every pixel generated has its attributes computed to be the perspective correct interpolation of the three vertices that make up the triangle

2/2/2013

20

Pixel Processing
Each pixel provided by triangle setup is fed into
pixel processing as a set of attributes 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

2/2/2013

21

Memory Interface
Pixel colors provided by the previous stage are
written to the framebuffer Used to be the biggest bottleneck before pixel processing took over Before the final write occurs, some pixels are rejected by the zbuffer .On modern GPUs z is compressed to reduce framebuffer bandwidth (but not size).
host interface vertex processing triangle setup pixel processing memory interface

2/2/2013

22

Programmability in GPU pipeline

In current state of the art GPUs, vertex and
pixel processing are now programmable The programmer can write programs that are executed for every vertex as well as for every pixel This allows fully customizable geometry and shading effects that go well beyond the generic look and feel of older 3D applications
host interface vertex processing triangle setup pixel processing memory interface

2/2/2013

23

GPU Pipelined Architecture

(simplified view)
GPU
110010100100

C P U

Vertex Setup

Vertex Shader

Rasterizer

Pixel Shader

Frame buffer

Texture Storage + Filtering

Vertices
2/2/2013

Pixels
24

GPU Pipelined Architecture

(simplified view)
GPU
C P U

Vertex Setup

Vertex Shader

Rasterizer

Pixel Shader

Frame buffer

Texture Storage + Filtering

One unit can limit the speed of the pipeline

2/2/2013 25

CPU/GPU interaction
The CPU and GPU inside the PC work in
parallel with each other There are two threads going on, one for the CPU and one for the GPU, which communicate through a command buffer:
GPU reads commands from here

Pending GPU commands

CPU writes commands here

2/2/2013 26

CPU/GPU interaction (cont)

If this command buffer is drained empty,
we are CPU limited and the GPU will spin around waiting for new input. All the GPU power in the universe isnt going to make your application faster! If the command buffer fills up, the CPU will spin around waiting for the GPU to consume it, and we are effectively GPU limited
2/2/2013 27

Synchronization issues
In the figure below, the CPU must not
overwrite the data in the yellow block until the GPU is done with the black command, which references that data:

GPU reads commands from here

CPU writes commands here

2/2/2013

data
28

Inlining data One way to avoid these problems is to

inline all data to the command buffer and avoid references to separate data:
GPU reads commands from here

CPU writes commands here

However, this is also bad for performance, since we may need to copy several Mbytes passing around a pointer

2/2/2013

29

GPU readbacks
The output of a GPU is a rendered image on the
screen, what will happen if the CPU tries to read it? GPU reads commands from here
Pending GPU commands

CPU writes commands here

GPU must be synchronized with the CPU, ie it must drain its entire command buffer, and the CPU must wait while this happens
2/2/2013 30

GPU readbacks (cont)

We lose all parallelism, since first the CPU
waits for the GPU, then the GPU waits for the CPU (because the command buffer has been drained) Both CPU and GPU performance take a nosedive Bottom line: the image the GPU produces is for your eyes, not for the CPU (treat the CPU -> GPU highway as a one way street)
2/2/2013 31

About GPU memory..

2/2/2013

32

Memory Hierarchy
CPU and GPU Memory Hierarchy
Disk
CPU Main Memory GPU Video Memory CPU Caches GPU Caches GPU Constant Registers

CPU Registers
2/2/2013

GPU Temporary Registers

33

Where is GPU Data Stored?

Vertex buffer Frame buffer Texture

Texture

Vertex Buffer

Vertex Processor

Rasterizer

Fragment Processor

Frame Buffer(s)
34

2/2/2013

CPU memory vs GPU memory

CPU
Registers Local Mem Global Mem
Read/write Read/write stack Read/write heap

GPU
Read/write None Read-only during computation. Write-only at end (to pre-computed address) None

Disk
2/2/2013

Read/write disk

35

It looks like..

2/2/2013

36

Some applications..
Computer generated holography using a
graphics processing unit Improve the performance of CAD tools. Computer graphics in games

2/2/2013

37

New..
NVIDIA's new graphics processing unit,
the GeForce 8X ULTRA, said to represent the very latest in visual effects technologies.

2/2/2013

38

THANK YOU

2/2/2013

39