Comparison of AMD Graphics Processing Units - Field Explanations

Field Explanations

The fields in the table listed below describe the following:

• Model – The marketing name for the processor assigned by ATi. Note that the ATi trademark has been replaced by AMD trademark starting with the Radeon HD 6000 series graphics processing units. Professional graphics processing units will switch to the AMD trademark as well.
• Launch – Date of release for the processor.
• Model number – Mobility VPUs are based on technology from several technology families. ATi assigns codenames based on an "MXX" model string, which does not relate to the actual technological base of the processor (represented by the R-number). Additionally, ATi is the sole supplier for all Mobility Radeon parts. For this reason, except for the Mobility Radeon 2000 series, all Mobility processors are listed on the same table.
• Code name – The internal engineering codename for the processor (typically designated by an RNXX name where N is the series number and XX is the market segment for which the product is designed. Additionally, a codename may follow the RVNXX format where "V" typically signifies a processor intended for a mainstream or value market segment).
• 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 PCIe).
• Memory – The reference amount of memory used by the processor.
• Core clock – The reference core clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
• Memory clock – The reference memory clock frequency (used as some manufacturers adjust clocks lower and higher, this number will always be that listed by ATi).
• 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.
• Performance subsection
  • Shader operations - How many operations the pixel shaders (or unified shaders in DirectX 10 and newer GPUs) can perform. Measured in MOperations/s or GOperations/s.
  • Pixel fillrate - The number of pixels the raster operators can render to a display in one second. Measured in MPixels/s or GPixels/s.
  • Texture fillrate - The rate at which a texture can be mapped by the texture mapping units onto a polygon mesh in one second. Measured in MTextels/s or GTextels/s.
  • Vertex operations - The amount of geometry operations that can be processed on the vertex shaders in one second (only applies to DirectX 9.0c and older GPUs). Measured in MVertices/s.
• Memory subsection
  • Bandwidth – Maximum theoretical bandwidth for the processor at factory clock with factory bus width. GB=109 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.
• API compliance section
  • DirectX – Highest version of DirectX with which the hardware is fully compliant.
  • OpenGL – Highest version of OpenGL with which the hardware is fully compliant.
• Features – Additional features that are not standard as a part of the two graphics libraries.