Comparison of Nvidia graphics processing units

This page contains general information about NVIDIA's GPUs and videocards based on official NVIDIA specifications.

Contents

[hide]

• 1 Direct X version note
• 2 OpenGL version note
• 3 Field Explanations
• 4 Comparison Tables: Desktop GPUs
  • 4.1 Pre-GeForce
  • 4.2 GeForce series
  • 4.3 GeForce 2 series
  • 4.4 GeForce 3 series
  • 4.5 GeForce 4 series
  • 4.6 GeForce FX (5xxx) series
  • 4.7 GeForce 6 (6xxx) series
    • 4.7.1 Features
  • 4.8 GeForce 7 (7xxx) series
    • 4.8.1 Features
  • 4.9 GeForce 8 (8xxx) series
    • 4.9.1 Features
  • 4.10 GeForce 9 (9xxx) series
    • 4.10.1 Features
  • 4.11 GeForce 100 Series
  • 4.12 GeForce 200 Series
    • 4.12.1 Features
  • 4.13 GeForce 300 Series
• 5 Comparison Table: Mobile GPUs
  • 5.1 GeForce Go 7 (Go 7xxx) series
  • 5.2 GeForce 8M (8xxxM) series
  • 5.3 GeForce 9M (9xxxM) series
  • 5.4 GeForce 100M (1xxM) series
  • 5.5 GeForce 200M (2xxM) series
• 6 Comparison Table: Workstation GPUs
  • 6.1 Quadro
  • 6.2 Tesla
• 7 Comparison Table: Miscellaneous
• 8 References
• 9 See also

Direct X version note

Direct X version indicates which graphics acceleration operations the card supports.

• Direct X 6.0 - Multitexturing
• Direct X 7.0 - Hardware Transformation, Clipping and Lighting (TCL/T&L)
• Direct X 8.0 - Shader Model 1.1
• DirectX 8.1 - Pixel Shader 1.3/1.4 & Vertex Shader 1.1
• DirectX 9.0/a - Shader Model 2.0 or Shader Model 2.0 extended
• DirectX 9.0b - Pixel Shader 2.0a/b & Vertex Shader 2.0a/b
• DirectX 9.0c - Shader Model 3.0, GPGPU
• DirectX 9.0L - Windows Vista only, Vista version of DirectX 9.0c, Shader Model 3.0, Windows Graphic Foundation 1.0, DXVA 1.0, GPGPU
• Direct3D 10 - Windows Vista/7, Shader Model 4.0, Windows Graphic Foundation 2.0, DXVA 2.0, GPGPU
• Direct3D 10.1 - Windows Vista/7, Shader Model 4.1, Windows Graphic Foundation 2.1, DXVA 2.1, GPGPU
• DirectX 11 - Windows Vista/7, Shader Model 5.0, Tessellation, Multithreaded rendering, Compute shaders, supported by hardware and software running Direct3D 9/10/10.1, GPGPU

  OpenGL version note

  OpenGL version indicates which graphics acceleration operations the card supports.

• OpenGL 1.1 - Texture objects
• OpenGL 1.2 - 3D textures, BGRA and packed pixel formats ^[1]
• OpenGL 1.3 - Multitexturing, multisampling, texture compression
• OpenGL 1.4 - Depth textures
• OpenGL 1.5 - VBO, Occlusion Querys ^[2]
• OpenGL 2.0 - GLSL 1.1, MRT, Non Power of Two textures, Point Sprites, Two-sided stencil ^[2]
• OpenGL 2.1 - GLSL 1.2, Pixel Buffer Object (PBO), sRGB Textures ^[2]
• OpenGL 3.0 - GLSL 1.3, Texture Arrays, Conditional rendering, FBO ^[3]

Field Explanations

The fields in the table listed below describe the following:

• Model - The Marketing name for the processor assigned by NVIDIA.
• Year - Year of release for the processor.
• Code Name - The internal engineering codename for the processor (typically designated by an NVXY name and later GXY where X is the series number and Y is the schedule of the project for that generation.
• Fab - Fabrication Process. Average feature size of components of the processor.
• Bus interface - Bus by which the Graphics processor is attached to the system (typically an expansion slot, such as PCI, AGP, or PCI-Express).
• Memory max - The maximum amount of memory used by the processor.
• Core Clock max - The maximum factory core clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by NVIDIA).
• Memory Clock max - The maximum factory effective memory clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be the reference clocks used by NVIDIA). All DDR/GDDR memories operate at half this frequency.
• Config Core - The layout of the graphics pipeline, in terms of functional units. Over time the number, type and variety of functional units in the GPU core has changed significantly; before each section in the list there is an explanation as to what functional units are present in each generation of processors. In later models, Shaders are integrated into a Unified Shader Architecture, where any one shader can perform any of the functions listed.
• Fillrate - Maximum theoretical fillrate in Textured Pixels per second. This number is generally used as a "maximum throughput number" for the GPU and generally, a higher fillrate corresponds to a more powerful (and faster) GPU.
• Memory Subsection
  • Bandwidth max - Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GB=10^9 bytes.
  • Bus Type - Type of memory bus or buses utilized.
  • Bus Width - Maximum Bit width of the memory bus or buses utilized. This will always be a factory bus width.
• Graphics Library Support Section
  • DirectX - Maximum version of Direct3D fully supported.
  • OpenGL - Maximum version of OpenGL fully supported.
• Features - Additional features that are not standard as a part of the two Graphics libraries.