An Accelerated Processing Unit (APU) is a processing system that includes additional processing capability designed to accelerate one or more types of computations outside of a CPU. This may include a graphics processing unit (GPU), a field-programmable gate array (FPGA), or similar specialized processing system. Variations on the usage of this term include a marketing based variation in which APU describes a processing device which integrates a CPU and a GPU on the same die thus improving data transfer rates between these components while reducing power consumption. APUs can also include video processing and other application-specific accelerators. Examples: AMD Fusion, Intel HD Graphics and NVIDIA's Project Denver.
The term Accelerated Processing Unit or APU was first used in a public context with respect to accelerated computing on theScalability.or blog, and prior to that in various presentations and business plans written by Joe Landman of Scalable Informatics. Other uses include Xilinx using the term for an Auxiliary Processor Unit.
Anandtech.com reports that in 2011, AMD will be coming out with an Accelerated Processing Unit (APU). What is an APU exactly? Try four CPU cores married to a single GPU. The four CPU cores will be based on the existing Phenom II microarchitecture. The one GPU will be a DirectX 11 class GPU. The APU will be manufactured on a 32nm process at GlobalFoundaries, and is scheduled to arrive in 2011. The code name for the APU is Llano.
Intel is also coming our with their own version of the APU, with the code name Sandy Bridge. Sandy Bridge will use a new microarchitecture for the CPU, and an updated integrated graphics core. Sandy Bridge will be manufactured on a 32nm process, and is due in early 2011.
If one was to handicap this race, then it would be expected that Intel will have a faster CPU with Sandy Bridge. Historically, Intel’s graphics have not always been the best. Thus one could expect that AMD will have a better integrated GPU than Intel
Link
ไม่มีความคิดเห็น:
แสดงความคิดเห็น