- Feb 8, 2011
- 3,536
- 0
- 0
I came across this great article on AMD's next gpu architecture that suggested within a few years we may see accelerated physics and parallel processing in general done on AMD bulldozer and capable of working in tandem with discrete graphics cards. Many of us suspected this was coming, but now we have a clearer indication of when that might become available and how it will likely be implemented.
From what I can understand of the article the idea is to create an architecture that is flexible enough to be incorporated into chips specifically as an integrated graphics solution or as a parallel processor for any number of uses. Many might say this is the first real step towards central processors becoming more like the human brain with both specialized circuitry and flexible parallel processing capabilities. A mixture of both vector and scalar approaches adaptable to the needs of the system.
http://www.pcper.com/reviews/Graphic...PUs-and-Beyond
"In Closing
We will see the first generation of parts come out in Q4 2011. These will be discrete GPUs. The current Llano CPUs are based on the older VLIW-5 architecture, and it looks like Trinity (Bulldozer + iGPU) will be based on the VLIW-4 architecture. After that though, we can expect the integrated parts to use this new architecture. This opens up a new realm of possibilities for AMD. One scenario discussed was that of physics acceleration. Instead of the dGPU doing both rendering and physics/compute work, the iGPU on the CPU would handle those. The iGPU would have the advantage of being located on the CPU, sharing the same memory controller, and accessing the main memory very quickly, as well as greater memory localization of the data. This would reduce latency by a significant degree as compared to the dGPU doing the same thing over the PCI-E bus. By taking care of this business, the dGPU would better handle other operations such as geometry and pixel shading or tessellation."
From what I can understand of the article the idea is to create an architecture that is flexible enough to be incorporated into chips specifically as an integrated graphics solution or as a parallel processor for any number of uses. Many might say this is the first real step towards central processors becoming more like the human brain with both specialized circuitry and flexible parallel processing capabilities. A mixture of both vector and scalar approaches adaptable to the needs of the system.
http://www.pcper.com/reviews/Graphic...PUs-and-Beyond
"In Closing
We will see the first generation of parts come out in Q4 2011. These will be discrete GPUs. The current Llano CPUs are based on the older VLIW-5 architecture, and it looks like Trinity (Bulldozer + iGPU) will be based on the VLIW-4 architecture. After that though, we can expect the integrated parts to use this new architecture. This opens up a new realm of possibilities for AMD. One scenario discussed was that of physics acceleration. Instead of the dGPU doing both rendering and physics/compute work, the iGPU on the CPU would handle those. The iGPU would have the advantage of being located on the CPU, sharing the same memory controller, and accessing the main memory very quickly, as well as greater memory localization of the data. This would reduce latency by a significant degree as compared to the dGPU doing the same thing over the PCI-E bus. By taking care of this business, the dGPU would better handle other operations such as geometry and pixel shading or tessellation."
Facebook
Twitter