Address phase - computer architecture, Computer Engineering

Address phase:

A PCI bus transaction starts having an address phase. The initiator,  after seeing that it has GNT# and the bus is inactive, drives the target address onto the AD[31:0] lines, the associated command (for example: I/O write or memory read,) on the C/BE[3:0]# lines, and pulls FRAME# low.

Each other device inspect the address and command & decides whether to respond as the target by asserting DEVSEL#. Device has to respond by asserting DEVSEL# within 3 cycles. Devices which promise to respond within one or two cycles are said to have "fast DEVSEL" or "medium DEVSEL", respectively. (In fact, the time to respond is 2.5 cycles, since PCI devices have to transmit all signals half a cycle early so that they can be retaining3 cycles later.)Note that a device have to latch the address on the first cycle; the initiator is needed to remove the address and command from the bus on the following cycle, even before retaining a DEVSEL# response. The extra time is available only for interpreting the address and command after it is captured. On the fifth cycle of the address phase (or earlier if all other devices have medium DEVSEL or faster), a catch-all "subtractive decoding" is permitted for some address ranges. It is generally used by an ISA bus bridge for addresses within its particular range (16 bits for I/O and 24 bits for memory).

On the sixth cycle, if there has been no response, the initiator can abort the transaction by deserting FRAME#. It is known as master abort termination and it is customary for PCI bus bridges to return all- ones data (0xFFFFFFFF) in this particular case. PCI devices therefore are generally designed to ignore by using the all-ones value in essential status registers, so that such type of error may be easily detected by software.


Posted Date: 10/13/2012 7:29:10 AM | Location : United States

Related Discussions:- Address phase - computer architecture, Assignment Help, Ask Question on Address phase - computer architecture, Get Answer, Expert's Help, Address phase - computer architecture Discussions

Write discussion on Address phase - computer architecture
Your posts are moderated
Related Questions
Q. What do you mean by Segment numbers? There is a good reason for not leaving determination of segment numbers up to assembler. It permits programs written in 8086 assembly

Hypothesis ... since the Hebrew language is a Numerical language meaning that each letter in their alphabet has a numerical value. I believe, that the Hebrew-language based on a r

What is state and state diagram? A state is an abstraction of values and links of an object. Set of values and links are grouped together into a state according to the group be

What is a reference string? An algorithm is evaluated by running it on a exacting string of memory references and computing the number of page faults. The string of memory refe

When a switch capacity is full, calls coming into that switch are said to be                 . (A)  open                                            (B)  shorted (C) bloc

Q. Explain Micro-operations performed by CPU? The micro-operations performed by CPU can be categorized as:    Micro-operations for data transfer from register-memory, re

Q. Explain salient points about indirect addressing? A number of salient points about this scheme are:  In this addressing scheme effective address EA and contents of th

More complicated logic circuits can be made byconnecting a number of simple logic gates.How do we decide how to connect the gates togive a particular function e.g. output Y?We need

Error handling in Hard disk in computer architecture : Modern drives also make widespread use of Error Correcting Codes (ECCs), specifically Reed-Solomon error correction.

The bandwidth requirement of a telephone channel is (A)  3 KHz                                      (B)  15 KHz (C)  5 KHz                                      (D)  25 KH