Up to 320 texture fetches per clock cycle.Command processor for reduced CPU overhead.128-bit floating point precision for all operations.Dedicated branch execution units and texture address processors.Common instruction set and texture unit access supported for all types of shaders.Dynamic load balancing and resource allocation for vertex, geometry, and pixel shaders.Unified Superscalar Shader Architecture.Read/write multi-sample surfaces with shaders.Independent blend modes per render target.
32-bit floating point texture filtering.512-bit GDDR5 memory interface (ATI Radeon™ HD 4870 X2).512-bit GDDR3 memory interface (ATI Radeon™ HD 4850 X2).1.912 billion processors (956 million transistors per GPU on 55nm fabrication process).
0 kommentar(er)
