Evolution of GPUs

Evolution of GPUs
Chris Seitz
PDF created with pdfFactory Pro trial version www.pdffactory.com

Overview
Concepts:
Real-time rendering
Hardware graphics pipeline
Evolution of the PC hardware graphics pipeline:
1995-1998: Texture mapping and z-buffer
1998: Multitexturing
1999-2000: Transform and lighting
2001: Programmable vertex shader
2002-2003: Programmable pixel shader
2004: Shader model 3.0 and 64-bit color support
©2004 NVIDIA Corporation. All rights reserved.

Real-Time Rendering
Graphics hardware enables real-time rendering
Real-time means display rate at more than 10 images per second
3D Scene = Image =
Collection of Array of pixels
3D primitives (triangles, lines, points)

PC Architecture
Motherboard
CPU
System Memory
Bus Port (PCI, AGP, PCIe)
Graphics Board
Video Memory
GPU

Hardware Graphics Pipeline
Application 3D Geometry 2D Rasterization

Pixels
Stage Triangles Stage Triangles Stage
For each For each

triangle vertex: triangle:
Transform Rasterize
position: triangle
3D -> screen
Interpolate
Compute vertex attributes
attributes
Shade
pixels
Resolve
visibility

Real-time Graphics 1997:
RIVA 128 – 3M Transistors

Real-time Graphics 2004:

UnReal Engine 3.0 Images Courtesy of Epic Games

‘95-‘98: Texture Mapping & Z-Buffer
CPU GPU
Application / Rasterization Stage
Geometry Stage
Raster
Texture
Rasterizer Operations
Unit
Unit
2D Triangles Bus
(PCI) Frame
2D Triangles Textures
Buffer
Textures
System Memory Video Memory

Raster Operations Unit (ROP)
Raster
Texture Operations
Rasterizer Fragments
Unit Unit
Scissor Test
Fragment
tested against scissor rectangle
Screen Position Alpha Test
(x, y) Frame Buffer
tested against reference value
Alpha Value Stencil Test Stencil Buffer
a
stencil buffer value at (x, y)
tested against reference value Z-Buffer
Depth Z Test
z
Color Buffer
tested against z-buffer value at (x, y)
Color Alpha Blending Pixels
(Visibility test)
(r, g, b)
blended with color buffer value at (x, y)

Ksrc * Colorsrc + Kdst * Colorsrc
(src = fragment, dst = color buffer)

Texture Mapping
Triangle Mesh Base Texture

(with UV coordinates)
+ =
Sampling
Magnification, Minification
Filtering
Bilinear, Trilinear, Anisotropic
Mipmapping
Perspective Correct Interpolation

Texture Mapping: Mipmapping & Filtering
or
Bilinear Filtering Trilinear Filtering

Filtering Examples
Point
Bilinear
Trilinear
Anisotropic
(4X) & Trilinear

Incoming

Riva TNT – 7M Transistors - 1998
Multitexture

1998: Multitexturing
CPU GPU
Application / Rasterization Stage
Geometry Stage
Multi Raster
Rasterizer Texture Operations
Unit Unit
2
2D Triangles Bus
(AGP) Frame
Buffer
Textures
System Memory Video Memory

Multitexturing
Base Texture modulated by Light Map
from UT2004 (c)

Epic Games Inc.
Used with permission
=

GeForce 256 – 23M Transistors - 1999
Hardware
Transform &
Lighting

1999-2000: Transform and Lighting
CPU GPU “Fixed Function Pipeline”
Application Geometry Stage Rasterization Stage

Stage
Transform Raster
Register
& Lighting Rasterizer Operations
Texture Combiner
Unit Unit
Unit
3D Bus
Triangles
(AGP) Frame
Buffer
Textures
System
Memory Video Memory

Transform and Lighting Unit (TnL)
Transform and Lighting Unit
Transform Lighting
World Matrix
Model or Object Space Material Properties
World Space
Model-View Matrix Light Properties
View Matrix
Vertex Color
Camera or Eye Space
Projection Matrix
Projection or Clip Space
Perspective Division &

Viewport Matrix
Vertex Diffuse &
Screen or Window Space Specular Color

Wanda and Bubble

GeForce 2
Pixel Shading
Multitexture


GeForce 3
Programmable
Vertex Shading

2001: Programmable Vertex Shader
CPU GPU

Stage
Vertex Raster
Shader Rasterizer Register
w/ Z-Cull
Texture Operations
(no flow Combiner
control)
Unit Unit
(4 Textures)
3D Bus
Triangles
(AGP)
Frame
Buffer
Textures
System
Memory Video Memory

Vertex Shader
A programmable processor for any
per-vertex computation
void VertexShader(
// Input per vertex
in float4 positionInModelSpace,
in float2 textureCoordinates,
in float3 normal,
// Input per batch of triangles

uniform float4x4 modelToProjection,
uniform float3 lightDirection,
// Output per vertex

out float4 positionInProjectionSpace,
out float2 textureCoordinatesOutput,
out float3 color
)
{
// Vertex transformation
positionInProjectionSpace = mul(modelToProjection, positionInModelSpace);
// Texture coordinates copy

textureCoordinatesOutput = textureCoordinates;
// Vertex color computation

color = dot(lightDirection, normal);
}

Bump Mapping
Bump mapping involves fetching the per-pixel normal from a
normal map texture (instead of using the interpolated vertex
normal) in order to compute lighting at a given pixel
+ =
Diffuse light Normal Map Diffuse light with bumps

Cubic Texture Mapping
Cubemap
z Environment Mapping
Reflection vector
(x , y y is used to lookup
,z )
x into the cubemap
Cubemap lookup
in direction (x, y, z)


Projective Texture Mapping
Projected Texture
(x, y, z, w)
Texture Projection
(x/w, y/w)
Projective Texture lookup

Volume Texture Mapping
z
(x,y,z)
y
Volume Texture x
Solid Textures
3D Noise Noise Perturbation
Volume Texture lookup

with position (x, y, z)

Hardware Shadow Mapping
Shadow Map Computation
z/w
The shadow map contains the depth
(z/w) of the 3D points visible from (x, y, z, w)
Spot
the light’s point of view: (x/w, y/w)
light
Shadow Rendering shadow

map
A 3D point (x, y, z, w) is in shadow if: value
(x, y, z, w)
z/w < value of shadow map at (x/w, y/w)
Spot
(x/w, y/w)
A hardware shadow map lookup light
returns the value of this comparison

between 0 and 1

Antialiasing: Examples

Antialiasing: Supersampling & Multisampling
Supersampling:
Compute color and Z at higher
resolution and display averaged
color to smooth out the visual
artifacts
Multisampling:
Same thing except only Z is
computed at higher resolution
Multisampling performs
antialiasing on primitive
edges only

X-Isle: Dinosaur Isle

Image courtesy of Crytek

GeForce 4
Multiple
Vertex and
Pixel Shaders

Wolfman

GeForce FX - >100M Transistors
Programmable
Pixel Shading
(DirectX 9.0)
Scalable
Architecture

‘02- ‘03: Programmable Pixel Shader
CPU GPU

Stage
Vertex Pixel Raster
Shader Rasterizer
(static & Texture Shader Operations
w/ Z-Cull (static flow
dynamic Unit control)
Unit
flow control) (16 textures)
3D Bus
Triangles
(AGP)
Frame
Buffer
Textures
System
Memory Video Memory


PC Graphics Software Architecture
CPU GPU
Application
BUS
Commands
Vertex Pixel Frame
Shader Shader Buffer
3D API
Programs
(OpenGL or DirectX)
Geometry
Textures Vertex Pixel

Driver Program Program
The application, 3D API and driver are written in C or C++

The vertex and pixel programs are written in a high-level shading
language (DirectX HLSL, OpenGL Shading Language, Cg)
Pushbuffer: Contains the commands to be executed on the GPU

Pixel Shader
A programmable processor for any per-pixel computation
void PixelShader(
// Input per pixel
in float2 textureCoordinates,
in float3 normal,

uniform sampler2D baseTexture,
// Output per pixel

out float3 color
)
{
// Texture lookup
float3 baseColor = tex2D(baseTexture,
textureCoordinates);
// Light computation
float light = dot(lightDirection, normal);
// Pixel color computation

color = baseColor * light;
}

Shader: Static vs. Dynamic Flow Control
void Shader(
...
// Input per vertex or per pixel
in float3 normal,

uniform bool computeLight,
Static Flow Control
...
(condition varies )
per batch of triangles) {
...
if (computeLight) {
...
if (dot(lightDirection, normal)) {
Dynamic Flow Control ...
(condition varies }
per vertex or pixel) ...
}
...
}

GeForce 6800 – 220M Transistors
Shader Model
3.0
FP64 & High

Dynamic
Range

2004: Shader Model 3.0 & 64-Bit Color Support
CPU GPU

Stage
Vertex Pixel
Rasterizer Raster
Shader Shader
(static &
w/ Z-Cull (static & Operations
Texture
dynamic dynamic flow Unit
flow control) Unit control)
64-Bit
Color
3D Bus
Triangles
(PCIe)
Frame
Buffer
Textures
System
Memory Video Memory

Shader Model 3.0
Longer shaders → More complex shading
Pixel shader:
Dynamic flow control → Better performance
Derivative instructions → Shader antialiasing
Support for 32-bit floating-point precision →
Fewer artifacts
Face register → Faster two-sided lighting
Vertex shader: Lord of the Rings™
The Battle for Middle-earth™
Texture access → Simulation on GPU,
displacement mapping
Geometry Instancing → Better performance
Far Cry

The GeForce 6 Series
Amazing Real-time Effects


Shader Model 3.0 / 64-bit Floating Point Processing
Unreal Engine 3.0 Running On GeForce 6 Series
2 Million Triangle Detail Mesh Models

High Dynamic Range Rendering
Fully Customizable Shaders


Shader Model 3.0 / 64-bit Floating Point Processing
Unreal Engine 3.0 Running On GeForce 6 Series
100 Million Triangle Source Content Scene

High Dynamic Range Rendering

High Dynamic Range Imagery
The dynamic range of a scene is the ratio of the highest to the lowest luminance
Real-life scenes can have high dynamic ranges of several millions
Display and print devices have a low dynamic range of around 100
Tone mapping is the process of displaying high dynamic range images on those
low dynamic range devices
High dynamic range images use floating-point colors
OpenEXR is a high dynamic range image format that is compatible with NVIDIA’s
64-bit color format
HDR Rendering Engine -

Compute surface reflectance, save in HDR buffer
Contributions from multiple lights are additive (blended)
Add image-space special effects & Post to HDR buffer
AA, Glow, Depth of Field, Motion Blur

Real-Time Tone Mapping
The image is entirely computed in 64-bit
color and tone-mapped for display
Renderings of the same scene, from low to high exposure

Evolution of Performance
10000 CPU Frequency (GHz)
Bus Bandwidth (GB/sec)

a te
l Fill R
1000 Pix e Pixel Fill Rate
(MPixels/sec)
Vertex Rate (MVerts/sec)
100 e
x Rat Graphics Bandwidth
te
Ver
(GB/sec)
h
nd widt
s Ba
10 phic
Gra
idth
nd w
Bu s Ba
1 re qu en cy
C PU F
0.1 1994 2004
4 MB 32 MB 64 MB 128 MB 256 MB 512 MB
DirectX 6 DirectX 7 DirectX 8 DirectX 9
OpenGL 1.1 OpenGL 1.4 OpenGL 1.5

Looking Ahead: Now + 10 years
CPU Frequency (GHz)
1000000 127 Gvertx
Bus Bandwidth (GB/sec)
Pixel Fill Rate (MPixels/sec)
100000 Vertex Rate (MVerts/sec)
Graphics flops (GFlops/sec)
10000 Graphics Bandwidth (GB/sec)
1000 R ate lo ps
Fill sf
Pix
e l hic
e ap
at Gr
100 xR
rte
Ve
dth 100 GHz

10 dw i
S B an cy
BU q uen
.5 Mverts Fr e
C PU
1
0.1
1994 2004 2014
100 MHz

NVIDIA SLI Multi-GPU

Progression of Graphics
Virtual Fighter Wanda Wolfman

NV1 NV1x NV2x
1Mtrans 22Mtrans 63Mtrans
Dawn Nalu
NV3x NV4x
130Mtrans 222M

Thank You

Evolution of GPUs

Enviado por

Dados do documento

Descrição original:

Direitos autorais

Formatos disponíveis

Compartilhar este documento

Compartilhar ou incorporar documento

Opções de compartilhamento

Você considera este documento útil?

Este conteúdo é inapropriado?

Direitos autorais:

Formatos disponíveis

Evolution of GPUs

Enviado por

Direitos autorais:

Formatos disponíveis

Evolution of GPUs

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Bus Port (PCI, AGP, PCIe)

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Application 3D Geometry 2D Rasterization

For each For each

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

System Memory Video Memory

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

blended with color buffer value at (x, y)

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Triangle Mesh Base Texture

PDF created with pdfFactory Pro trial version www.pdffactory.com

Bilinear Filtering Trilinear Filtering

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

System Memory Video Memory

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

from UT2004 (c)

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Application Geometry Stage Rasterization Stage

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Camera or Eye Space

Projection or Clip Space

Perspective Division &

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

PDF created with pdfFactory Pro trial version www.pdffactory.com

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

Application Geometry Stage Rasterization Stage

©2004 NVIDIA Corporation. All rights reserved.

PDF created with pdfFactory Pro trial version www.pdffactory.com

// Input per batch of triangles

// Output per vertex

// Texture coordinates copy

// Vertex color computation

PDF created with pdfFactory Pro trial version www.pdffactory.com