Application processors and memory architecture for wireless applications

• US 20040024955A1
• Filed: 04/01/2003
• Published: 02/05/2004
• Est. Priority Date: 06/27/2002
• Status: Active Grant

• Current Assignee: Nazomi Communications Incorporated
• Original Assignee: Nazomi Communications Incorporated
• Inventors: Patel, Mukesh K.
• Granted Patent: US 7,290,080 B2
• Time in Patent Office: Days
• US Class Current: 711/100
• CPC Class Codes: G06F 13/4234 being a memory bus
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

In one embodiment, the invention provides a method for accessing memory. The method comprises sending memory transactions to a memory sub-system for a first processor to an intermediate second processor interposed on a communication path between the first processor and the memory sub-system; and controlling when the memory transactions are allowed to pass through the second processor to reach the memory sub-system.

Claims

1. A method for accessing memory, the method comprising:

sending memory transactions to a memory sub-system for a first processor to an intermediate second processor interposed on a communication path between the first processor and the memory sub-system; and

controlling when the memory transactions are allowed to pass through the second processor to reach the memory sub-system.

2. The method of claim 1, wherein the controlling comprises delaying the pass through of the memory transactions.

3. The method of claim 2, wherein the delaying the pass through of the memory transactions comprises asserting a WAIT signal or de-asserting a READY signal to the first processor by the second processor.

4. The method of claim 2, wherein the delaying is for a period sufficient to allow a current memory cycle of the memory sub-system initiated by the second processor to complete.

5. The method of claim 1, wherein the controlling comprises aborting the current memory cycle of the memory sub-system initiated by the second processor.

6. The method of claim 5, wherein the aborting is only performed if the current memory cycle can be safely aborted without a loss of data.

7. The method of claim 6, wherein the aborting is only performed if the memory sub-system comprises memory devices that maintain data integrity when a memory access is pre-maturely terminated.

8. The method of claim 7, wherein the controlling comprises passing address, data, and control signals from the first processor through a multiplexer mechanism in the second processor set to select the address, data, and control signals when a chip select signal from the first processor is asserted, to the memory sub-system.

9. The method of claim 8, wherein the multiplexer mechanism is set to select address, data, and control signals generated by a memory controller of the second processor if a chip select signal from the second processor is asserted.

10. The method of claim 8, further comprising synchronizing an assertion of one or more chip select signals from the first processor to indicate when the memory transactions are being passed through to the memory sub-system.

11. The method of claim 10, further comprising saving information relating to an aborted current memory cycle.

12. The method of claim 11, wherein the aborted current memory cycle is resumed after the passed through memory transactions complete.

13. The method of claim 1, wherein the second processor executes platform independent intermediate language instructions.

14. The method of claim 1, further comprising disabling asynchronous refresh requests produced internally with the memory devices of the memory sub-system;

and generating an external refresh request signal to indicate to the memory devices when to perform a refresh.

15. The method of claim 14, wherein the external refresh request signal is generated by the second processor when the second processor is not accessing in memory.

16. The method of claim 1, wherein the first processor is a baseband processor for a mobile communications device.

17. The method of claim 1, wherein the second processor is an applications processor for the mobile communications device.

18. A system, comprising:

a first processor;

a memory sub-system;

a communications path between the first processor and the memory sub-system to allow the first processor to access the memory sub-system; and

a second processor interposed between the first processor and the memory sub-system and defining an intermediate point in the communications path, the second processor including a memory controller to control access to the memory sub-system by the first and second processors.

19. The system of claim 18, wherein the communications path comprises a first bus between the first and second processors and a second bus between the second processor and the memory sub-system.

20. The system of claim 18, wherein the second bus comprises separate address and control lines coupling the second processor to first and second groups of memory devices within the memory sub-system, respectively.

21. The system of claim 20, wherein the first group of memory devices is accessible on demand by the first processor;

and the second group of memory devices is accessible to the first processor only when the second group is not being accessed by the second processor.

22. The system of claim 21, wherein non-volatile memory devices within the first group of memory components are accessible to the second processor only when not being accessed by the first processor.

23. The system of claim 18, wherein the second bus comprises two separate busses, each coupling the second processor to first and second groups of memory devices within the memory sub-system, respectively.

24. The system of claim 18, wherein the second processor comprises a detection mechanism to detect when the first processor generates memory cycle signals to the memory sub-system.

25. The system of claim 24, wherein the second processor includes a pass-through mechanism to allow detected memory cycle signals from the first processor to pass through the second processor.

26. The system of claim 25, wherein the pass-through mechanism allows a detected memory cycle signal to pass through to the memory sub-system, immediately, if the second processor is not accessing the memory sub-system.

27. The system of claim 26, wherein the pass-through mechanism delays the pass through of a detected memory cycle signal to the memory sub-system, until a current memory access of the memory sub-system by the second processor can be aborted without data loss.