INTEL 80386 MICROPROCESSOR, Study notes of Architecture

memory and 64Terabytes of Virtual memory. ▻ It has pipeline architecture which allows simultaneous instruction fetching, decoding, and executing and memory ...

Typology: Study notes

2021/2022

Uploaded on 09/07/2022

adnan_95
adnan_95 🇮🇶

4.3

(39)

918 documents

1 / 10

Toggle sidebar

This page cannot be seen from the preview

Don't miss anything!

bg1
FEATURES OF 80386:
Two versions of 80386 are commonly available:
1) 80386DX
2)80386SX
80386DX 80386SX
1) 32 bit address bus
32bit data bus
2) Packaged in 132 pin ceramic
pin grid array(PGA)
3) Address 4GB of memory
1) 24 bit address bus 16 bit
data bus
2) 100 pin flat package
3) 16 MB of memory
INTEL 80386 MICROPROCESSOR
pf3
pf4
pf5
pf8
pf9
pfa

Partial preview of the text

Download INTEL 80386 MICROPROCESSOR and more Study notes Architecture in PDF only on Docsity!

FEATURES OF 80386 :

Two versions of 80386 are commonly available:

  1. 80386DX 2)80386SX 80386DX

80386SX

  1. 32 bit address bus 32bit data bus
  2. Packaged in 132 pin ceramic pin grid array(PGA)
  3. Address 4GB of memory
  4. 24 bit address bus 16 bit data bus
  5. 100 pin flat package
  6. 16 MB of memory

INTEL 80386 MICROPROCESSOR

 32 bit processor, it has 32 bit ALU which allows to process 32 bit data at a time.  32 bit address bus, therefore it can access 4 GB physical memory and 64 Terabytes of Virtual memory.  It has pipeline architecture which allows simultaneous instruction fetching, decoding, and executing and memory management. Because of instruction pipelining higher bus bandwidth & on chip address translation mechanism, the average execution time has been significantly reduced.  It allows user to switch between different OS such as DOS and UNIX  Operates in Real, Protected and Virtual 8086 mode.

 It contains dedicated hardware for

performing

calculation,

high speed

logical to linear

address

address

translation and protection check.

 It contain translation lookside

(TLB) that store recently used

directory and page table entries.

buffer

page

This

buffer consists of 32 sets of table entries

which allow direct access of 128 kbyts of

paged memory

  • ARCHITECTURE OF INTEL

1 Central processing unit(CPU)

a) Execution Unit : Reads the instruction instruction queue and execute the instruction. from the Consists of three subunits : control, data and protection test unit I) Control Unit: It contains microcode and special hardware allows processor to reduce time required for execution of multiply and divide instruction. It also speeds the effective address calculation. II) Data Unit: Responsible for data operations requested by the control unit. It contains ALU, eight 32 bit general purpose registers and 64 bit barrel shifter. The barrel shifter is used for multiple bit shifts in one clock. Thus it increases the speed of all shift and rotate operations.

III) Protection Test Unit: checks for segmentation violations under the control of the microcode. b) Instruction Decode Unit : Takes instruction byte from the code prefetch queue and translates them in to microcode. The decoded instructions are then stored in the instruction queue.

2 ) Memory Management Unit

a) Segmentation Unit: Translate logical address to linear addresses at the request of execution unit. Compares the effective address for the length limit specified in the segment descriptor. Adds the segment base and the effective address to generate linear address. Before calculation of linear address it also checks access rights. It provides a 4 level protection mechanism for protecting and isolating the system code and data from those of the application program

ii)It send address, data and control signals to communicate with memory and I/O devices iii)It controls the interface to external bus masters and coprocessors. iv)It also provides the address relocation facility. Instruction Prefetch Unit Fetches sequentially the instruction byte stream from the memory. It uses bus control unit to fetch instruction bytes when it is not performing bus cycles. These prefetched instruction bytes are stored in 16 bytes code queue. When jump or call instructions are executed, the contents of the prefetched and decode queues are cleared out