ROPs are still aligned with L2 cache slices and Memory Controllers. The GM107 GPU contains one GPC, five Maxwell Streaming Multiprocessors (SM), and two 64-bit memory controllers (128-bit total). Maxwell implements multiple SM units within a GPC (Graphics Processing Cluster), and each SM includes a Polymorph Engine and Texture Units, while each GPC includes a Raster Engine. With more cache located on-chip, fewer requests to the graphic card's DRAM are needed, thus reducing overall board power and improving performance. Maxwell also has a larger L2 cache design 2048KB in GM107 versus 256KB in GK107. The new Maxwell SM architecture now has five SMs in GM107, compared to two in GK107, with only a 25% increase in die area. Because of GM107’s architectural efficiency, at 1080p resolution a GeForce GTX 750 Ti will have a TDP hovering at merely 60 Watts.įor Maxwell Nvidia applied a new design Streaming Multiprocessor (SM) with the focus on improving overall performance per watt. The first graphics card that is based on the GM107 GPU is the GeForce GTX 750 Ti. The first Maxwell-based GPU is codenamed “GM107” and designed for use in power-limited environments like notebooks and small form factor (SFF) PCs. NVIDIA’s first-generation “Maxwell” GPU architecture implements a number of architectural enhancements designed to extract even more performance and more power efficiency per watt consumed. The product however is using the GM107 which is based on a 28nm fabrication process. ![]() The GeForce GTX 750 and 750 Ti are based on Maxwell GPU architecture. In this segment of the article we will look at the reference (original design) based specs and architecture. ![]() The Technology and Specs Reference technology and specs
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |