Atjaunināt sīkdatņu piekrišanu

History of the GPU - Eras and Environment 1st ed. 2022 [Mīkstie vāki]

  • Formāts: Paperback / softback, 332 pages, height x width: 235x155 mm, weight: 659 g, 194 Illustrations, color; 15 Illustrations, black and white; XXX, 332 p. 209 illus., 194 illus. in color., 1 Paperback / softback
  • Izdošanas datums: 02-Jan-2023
  • Izdevniecība: Springer International Publishing AG
  • ISBN-10: 3031135806
  • ISBN-13: 9783031135804
  • Mīkstie vāki
  • Cena: 36,20 €*
  • * ši ir gala cena, t.i., netiek piemērotas nekādas papildus atlaides
  • Standarta cena: 42,59 €
  • Ietaupiet 15%
  • Grāmatu piegādes laiks ir 3-4 nedēļas, ja grāmata ir uz vietas izdevniecības noliktavā. Ja izdevējam nepieciešams publicēt jaunu tirāžu, grāmatas piegāde var aizkavēties.
  • Daudzums:
  • Ielikt grozā
  • Piegādes laiks - 4-6 nedēļas
  • Pievienot vēlmju sarakstam
  • Formāts: Paperback / softback, 332 pages, height x width: 235x155 mm, weight: 659 g, 194 Illustrations, color; 15 Illustrations, black and white; XXX, 332 p. 209 illus., 194 illus. in color., 1 Paperback / softback
  • Izdošanas datums: 02-Jan-2023
  • Izdevniecība: Springer International Publishing AG
  • ISBN-10: 3031135806
  • ISBN-13: 9783031135804
This is the second book in a three-part series that traces the development of the GPU, which is defined as a single chip with an integrated transform and lighting (T&L) capability. This feature previously was found in workstations as a stand-alone chip that only performed geometry functions. Enabled by Moores law, the first era of GPUs began in the late 1990s.

Silicon Graphics (SGI) introduced T&L first in 1996 with the Nintendo 64 chipset with integrated T&L but didnt follow through. ArtX developed a chipset with integrated T&L but didnt bring it to market until November 1999.

The need to integrate the transform and lighting functions in the graphics controller was well understood and strongly desired by dozens of companies. Nvidia was the first to produce a PC consumer level single chip with T&L in October 1999. All in all, fifteen companies came close, they had designs and experience, but one thing or another got in their way to prevent them succeeding.

All the forces and technology were converging; the GPU was ready to emerge. Several of the companies involved did produce an integrated GPU, but not until early 2000.





This is the account of those companies, the GPU and the environment needed to support it. The GPU has become ubiquitous and can be found in every platform that involves a computer and a user interface.
1 Introduction
1.1 Nvidia's NV10---First Integrated PC GPU (September 1999)
2(12)
1.1.1 Nvidia's Non GPU GPU
9(1)
1.1.2 The S3 Nvidia Patent Suit and Silicon Valley Gossip
10(1)
1.1.2.1 Meanwhile, Back in Reality?
11(1)
1.1.2.2 Nvidia and S3 Enter into a Cross-Licensing Agreement
12(2)
1.2 Summary and Conclusion
14(1)
1.3 Epilog---All the Others
15(1)
References
16(3)
2 The GPUs' Functions
19(44)
2.1 The Pipeline
20(11)
2.1.1 The Meaning of Real Time
21(1)
2.1.2 Binning and Branding
22(1)
2.1.3 The Frame Buffer
23(2)
2.1.3.1 GPUs and Memory
25(1)
2.1.3.2 Resizable Base Address Register (2010)
26(1)
2.1.4 Object-Level Clipping
27(1)
2.1.4.1 Looking Back at the Geometry Processor's Origins
27(3)
2.1.4.2 Digital Signal Processors Used for Geometry
30(1)
2.2 The Rendering Equation
31(1)
2.3 The Geometry Creation
32(4)
2.4 The Software Story: The All-Important APIs
36(5)
2.4.1 The Triangle Setup
37(1)
2.4.2 Drawing and Shading
37(1)
2.4.3 Triangle Sorting
37(1)
2.4.4 Texture Mapping
38(3)
2.4.4.1 3D Texture Filtering
41(1)
2.5 Fill Rate, Rendering Pipelines, and Triangle Size
41(15)
2.5.1 Rendering Techniques
43(2)
2.5.1.1 Polygon Rendering
45(1)
2.5.1.2 Scan-Line Rendering
45(1)
2.5.1.3 Immediate Mode Rendering
45(1)
2.5.1.4 Tile Rendering
46(1)
2.5.1.4.1 Tile-Based Deferred Rendering
46(2)
2.5.1.4.2 Immediate Mode Tile Rendering
48(1)
2.5.1.5 Ray-Traced Rendering
49(1)
2.5.2 Instancing
50(1)
2.5.3 Aliasing
50(3)
2.5.4 Scaling
53(2)
2.5.5 Environment Mapping
55(1)
2.6 Generating the Image: Hardware Issues
56(2)
2.6.1 VPU---Visual Processing Unit
57(1)
2.6.2 Multi-display
57(1)
2.7 Crypto GPU
58(1)
2.8 Audio, In, Out, In Again
58(1)
2.9 Conclusions
59(1)
References
60(3)
3 The Major GPU Eras
63(42)
3.1 The First Era---Transform and Lighting---DirectX 7 (1999)
66(6)
3.1.1 Shading and Shaders
66(2)
3.1.1.1 Shading
68(2)
3.1.2 Geometry Processing
70(2)
3.2 The Second Era---Programmable Shaders---DirectX 8 and 9 (2001--2006)
72(3)
3.2.1 Pixel (Fragment) Shader Stage
73(1)
3.2.2 How Many Shaders? Is There a Limit?
74(1)
3.3 The Third Era---The Unified Shader---DirectX 10 and 11 (2006--2009)
75(4)
3.3.1 Geometry Shader (2006)
78(1)
3.4 The Fourth Era---Compute Shaders---DirectX 11 (2009--2015)
79(4)
3.4.1 Tessellation Shader (October 2009)
80(3)
3.4.2 Summary
83(1)
3.5 The Fifth Era---Ray Tracing and AI---DirectX 12 (2015--2020)
83(8)
3.5.1 Ray Tracing Shaders
84(3)
3.5.2 Real-Time Ray Tracing with AI
87(2)
3.5.3 Variable Rate Shading---2019
89(2)
3.6 The Sixth Era---Mesh Shaders---DirectX 12 Ultimate (2020)
91(2)
3.6.1 Primitive and Mesh Shaders---2017--2020
92(1)
3.6.2 Sampler Feedback
93(1)
3.7 Summary on Shading
93(3)
3.7.1 Mobile
93(1)
3.7.1.1 GPU Sources for Mobile Devices
94(2)
3.7.2 GPU-Compute
96(1)
3.8 FLOPS Versus Fraps: Cars and GPUs
96(4)
3.8.1 Why Good Enough is Not
98(2)
3.9 Conclusion
100(1)
References
101(4)
4 The First Era of GPUs
105(46)
4.1 The Golden Age---Transform, and Lighting Changes the Industry (1999--2001)
107(1)
4.1.1 On Being First
108(1)
4.2 First Era Discrete PC-Based GPUs
108(27)
4.2.1 Glaze3D Bitboys 2.0 (1999--2001)
109(3)
4.2.1.1 Infineon
112(2)
4.2.1.2 Bitboys Gets the Axe
114(1)
4.2.1.3 Bitboys Gets Hammered
115(1)
4.2.1.4 The Final Blow
116(1)
4.2.2 S3 Savage 2000 (November 1999)
116(3)
4.2.2.1 S3 Chrome
119(1)
4.2.2.2 Epilogue: The Curious Trail to Zhaoxin
120(1)
4.2.3 ATI and Nvidia: First Era GPUs (1999--2002)
121(1)
4.2.4 ATI Radeon R100---256 (April 2000)
121(4)
4.2.4 Pixel Tapestry Architecture
125(3)
4.2.5 Nvidia's NV15---GeForce 2 GTS (April 2000)
128(1)
4.2.6 STMicroelectronics---Imagination Technologies Kyro II (2001--2002)
128(4)
4.2.6.1 PowerVR3 STG4000 Kyro---2001
132(1)
4.2.6.2 PowerVR3 STG4500 Kyro II---2001
132(2)
4.2.6.3 The End
134(1)
4.2.6.4 Summary
134(1)
4.3 The Development and History of the Integrated GPU (1999--)
135(11)
4.3.1 ArtX
136(1)
4.3.1.1 ArtX: First Company to Announce a PC-Based iGPU
137(3)
4.3.1.2 ATI Acquires ArtX (February 2000)
140(1)
4.3.2 ATI's First IGP (March 2000)
141(1)
4.3.3 SiS' First PC-Based IGP (December 2000)
142(3)
4.3.4 Nvidia's nForce 220 IGP (June 2001)
145(1)
4.3.5 ATI's IGP 320 (2002)
146(1)
4.4 IGP Conclusion
146(1)
4.5 The Expansion Years (2001-2016)
147(2)
4.5.1 The Collapse and the Rise of Graphics Chip Companies
148(1)
4.6 Conclusion
149(1)
References
149(2)
5 The GPU Environment---Hardware
151(50)
5.1 It Takes a Village to Build a GPU
151(1)
5.2 Semiconductor Technology
152(13)
5.2.1 Intel Introduces Angstroms
153(2)
5.2.1.1 Fins to Sheets
155(1)
5.2.1.2 GPU Memory
156(2)
5.2.1.2.1 Shared Versus Private Memory
158(1)
5.2.1.3 Memory Type and GPU
159(1)
5.2.2 Chiplets
160(5)
5.3 PC Bus Architectures
165(12)
5.3.1 Industry Standard Architecture: 1981
167(1)
5.3.2 Micro Channel Architecture: 1987
168(1)
5.3.3 Extended ISA: 1988 T
168(1)
5.3.4 VESA Local Bus: 1992
169(1)
5.3.5 Peripheral Component Interconnect: 1992
169(3)
5.3.6 Accelerated Graphics Port: 1997
172(1)
5.3.7 Peripheral Component Interconnect Express: 2003
172(4)
5.3.8 Other I/O
176(1)
5.4 GPU Video Outputs
177(17)
5.4.1 VGA: 1987
179(1)
5.4.2 DVI (1999--)
179(1)
5.4.3 HDMI (2002--)
179(2)
5.4.4 High Dynamic Range (2015)
181(1)
5.4.5 DisplayPort
182(1)
5.4.6 Seeing More
183(1)
5.4.7 Virtual Reality Headsets
183(1)
5.4.8 Augmented Reality Glasses
184(1)
5.4.9 Mixed Reality Headsets
185(1)
5.4.10 Monitor Synchronization: 2013-2015
186(6)
5.4.10.1 Those Damn Scalers
192(1)
5.4.10.2 Flickering
193(1)
5.4.10.3 Adaptive Sync, FreeSync, and G-Sync
194(1)
5.5 Multiple AIBs in a System
194(5)
5.5.1 Multi-GPIs (1996)
196(3)
5.6 Conclusion
199(1)
References
199(2)
6 Application Program Interface (API)
201(50)
6.1 Application Program Interface
202(45)
6.1.1 APIs and OSs
203(4)
6.1.1.1 Chaos in the Mobile Market
207(1)
6.1.1.2 DirectX Shaders
207(2)
6.1.1.3 Comparison of Vertex Shaders
209(1)
6.1.2 History of DirectX
209(5)
6.1.2.1 Hardware Feature Levels
214(1)
6.1.2.2 Microsoft's Japanese Bigotry
214(1)
6.1.3 The History of OpenGL
215(1)
6.1.4 The Fahrenheit Project
215(2)
6.1.5 Low-Level APIs
217(1)
6.1.5.1 Mantle
218(1)
6.1.5.2 Metal
219(1)
6.1.5.3 Vulkan
220(1)
6.1.5.3.1 Cross-Platform Support
220(2)
6.1.6 WebGPU
222(1)
6.1.7 DirectX 12
223(1)
6.1.7.1 Ultimate
223(1)
6.1.7.1.1 Ray Tracing
224(1)
6.1.7.1.2 Variable Rate Shading
225(1)
6.1.7.1.3 Getting to Mesh Shaders
226(1)
6.1.7.1.4 HW T&L Engines, 1981 to 1996: IRIS GL to Direct X 7.0
226(1)
6.1.7.1.5 Vertex and Pixel Shaders, 1997 to 2008: Direct3D 10
227(2)
6.1.7.1.6 Tessellation
229(1)
6.1.7.1.7 The Pipeline Expands
230(2)
6.1.7.1.8 Unified Shader, 2006--2010: DirectX 9.0 and OpenGL 3.3
232(1)
6.1.7.1.9 Getting to Compute: Task Shaders 2016--2017 (DirectX 12, Vulkan 2)
233(1)
6.1.8 Microsoft DirectX Shader Model 4.0: Enhancements
234(1)
6.1.8.1 Geometry Shaders
234(1)
6.1.8.1.1 Mesh Shaders, 2018--2020: DirectX 12 Ultimate, Vulkan Extension
235(2)
6.1.8.1.2 Meshlets
237(5)
6.1.8.1.3 Benchmarking
242(1)
6.1.8.1.4 Interactive Mode
242(1)
6.1.8.1.5 Mesh Demo
243(4)
6.2 Conclusion
247(1)
References
248(3)
7 The GPU Environment---Software Extensions and Custom Features
251(32)
7.1 Software Libraries and Tools
251(10)
7.1.1 Ambient Occlusion
252(1)
7.1.2 Nvidia's DLSS (February 2019)
253(4)
7.1.3 AMD's Fidelity FX Super Resolution (May 2021)
257(2)
7.1.4 Intel's XeSS (March 2022)
259(2)
7.2 More Than a Driver
261(5)
7.2.1 SYCL
261(1)
7.2.2 GLSL
262(1)
7.2.3 HLSL
262(1)
7.2.4 SPIR-V
263(1)
7.2.5 Textures
263(3)
7.3 Summary
266(1)
7.4 Software Development Kits for Developers
266(13)
7.4.1 Nvidia's GameWorks (2014--)
267(3)
7.4.2 AMD's FX Library (2014)
270(1)
7.4.3 AMD's GPUOpen (2015-) Tr.u
271(2)
7.4.4 Application Enhancement Software
273(1)
7.4.5 AMD's Gaming Evolved
274(2)
7.4.6 Nvidia's GeForce Experience
276(3)
7.5 Conclusion
279(1)
7.6 Summary
279(1)
References
280(3)
Appendix A Acronyms 283(4)
Appendix B Definitions 287(40)
Index 327
Dr. Jon Peddie is a recognized pioneer in the graphics industry, President of Jon Peddie Research, and named one of the worlds most influential analysts. Peddie has been an ACM distinguished speaker and is currently an IEEE Distinguished visitor. He lectures at numerous conferences and universities on topics about graphics technology and the emerging trends in digital media technology. Former President of Siggraph Pioneers, he serves on the advisory boards of several conferences, organizations, and companies and contributes articles to numerous publications. In 2015, he was given the Life Time Achievement award from the CAAD society. Peddie has published hundreds of papers to date; and authored and contributed to eleven books, His most recent books are, Augmented Reality, where we all will live", Ray Tracing, a Tool for all.