Click Here to
Order this information in Print

Click Here to
Order this information on CD-ROM

Click Here to
Download this information in PDF Format

 

Click here to make tpub.com your Home Page

Page Title: CONTROL MEMORY
Back | Up | Next

Click here for a printable version

Google


Web
www.tpub.com

Home


   
Information Categories
.... Administration
Advancement
Aerographer
Automotive
Aviation
Combat
Construction
Diving
Draftsman
Engineering
Electronics
Food and Cooking
Math
Medical
Music
Nuclear Fundamentals
Photography
Religion
USMC
   
Products
  Educational CD-ROM's
Printed Manuals
Downloadable Books

   
Back
Terminate Current Program Execution
Up
Fire Controlman Volume 03-Digital Data Systems
Next
CACHE MAPPING TECHNIQUES

CONTROL MEMORY Control  memory  is  a  random  access  memory (RAM) consisting of addressable storage registers. It is primarily used in mini and mainframe computers. It is used as a temporary storage for data. Access to control memory data requires less time than to main memory; this speeds up CPU operation by reducing the number of memory references for data storage and retrieval. Access  is  performed  as  part  of  a  control  section sequence while the master clock oscillator is running. The control memory addresses are divided into two groups: a task mode and an executive  (interrupt)  mode. Addressing words stored in control memory is via the address select logic for each of the register groups. There can be up to five register groups in control memory. These groups select a register for fetching data for programmed  CPU operation or for maintenance console or equivalent display or storage of data via a maintenance   console   or   equivalent.   During programmed  CPU  operations,  these  registers  are accessed directly by the CPU logic. Data routing circuits  are  used  by  control  memory  to  interconnect  the registers used in control memory. Some  of  the  registers  contained  in  a  control memory that operate in the task and the executive modes include the following: Accumulators Indexes Monitor clock status indicating registers Interrupt data registers CACHE MEMORY Cache memory is a small, high-speed RAM buffer located between the CPU and main memory. Cache memory buffers or holds a copy of the instructions (instruction cache) or data (operand or data cache) currently being used by the CPU. The instructions and data are copies of those in main memory. Cache memory provides two benefits. One, the average access time for CPU’s memory requests is reduced, increasing the CPU’s speed by providing rapid access  to  currently  used  instructions  and  data.  Two,  the CPU’s use of the available memory bandwidth is reduced. This allows other devices on the system bus to use the memory without interfering with the CPU. Therefore, cache memory is used to speed up the flow of  instructions  and  data  into  the  CPU  from  main memory. This cache function is important because the main memory cycle time is typically slower than the CPU clocking rates. To accomplish this rapid data transfer, cache  memories  are  usually  built  from  the  faster bipolar   RAM  devices  rather  than  the  slower metal-oxide-semiconductor  (MOS)  RAM  devices. The RAMs used for cache memory may be either dynamic RAMs (DRAMs) or static RAMs (SRAMs). Cache memories are not part of the memory section and they are transparent to programmers (i.e., not accessible by machine instruction). Their size varies with the type of computer, usually they are no more than 64K. PROPERTIES  OF  CACHE  MEMORY.  —All caches share the following properties: A buffered memory or cache memory consists of a  small  high-speed  memory  with  main  memory information. This information may be addresses, data, or instructions. The speed of the small memory is usually on the order of one magnitude faster than main memory, and its capacity is typically one or two orders of magnitude less than main memory. A cache memory system requires an identifier or tag store to indicate which entries of main memory have been copied into it. Such an area is usually referred to as the directory or tag store. A cache memory requires a logical network and method of replacing old entries. A cache memory uses timing and control. CACHE PROCESS. —The cache process takes place when a CPU with a cache initiates a memory reference. The address of the needed item is generated and the cache is searched. The method of search depends on the type of cache mapping  used  by  the computer system. We can generalize the cache process into three areas as follows: Searches —Reads from the cache directory with a hit indicating that the data from the requested address is present, while a miss indicates that the data is not present. Updates —Writes to the cache data as well as to the directories with new information. Invalidates —Writes only to the directories; this effectively removes an address that previously resided in  cache. 5-15

Privacy Statement - Press Release - Copyright Information. - Contact Us - Support Integrated Publishing