processor register

​

In  computer architecture , a processor register is a small amount of  storage  available as part of a  CPU  or other digital processor. Such registers are (typically) addressed by mechanisms other than  main memory  and can be accessed more quickly. Almost all computers,  load-store architecture  or not, load data from a larger memory into registers where it is used for arithmetic, manipulated, or tested, by some machine instruction . Manipulated data is then often stored back in main memory, either by the same instruction or a subsequent one. Modern processors use either  static  or  dynamic   RAM  as main memory, the latter often being implicitly accessed via one or more  cache levels . A common property of  computer programs  is  locality of reference : the same values are often accessed repeatedly and frequently used values held in registers improves performance. This is what makes fast registers (and caches) meaningful.

 

Processor registers are normally at the top of the  memory hierarchy , and provide the fastest way to access data. The term normally refers only to the group of registers that are directly encoded as part of an instruction, as defined by the  instruction set . However, modern high performance CPUs often have duplicates of these "architectural registers" in order to improve performance via  register renaming , allowing parallel and  speculative execution . Modern  x86  is perhaps the most well known example of this technique.^[1]

Allocating frequently used variables to registers can be critical to a program's performance. This  register allocation  is either performed by a  compiler , in the  code  generation  phase, or manually, by an assembly language  programmer

 

 

 

来源： <http://en.wikipedia.org/wiki/Processor_register>