Electrical computers and digital processing systems: memory – Storage accessing and control – Access timing
Reexamination Certificate
1998-11-03
2001-04-03
Robertson, David L. (Department: 2187)
Electrical computers and digital processing systems: memory
Storage accessing and control
Access timing
C711S154000
Reexamination Certificate
active
06212611
ABSTRACT:
FIELD OF INVENTION
The present invention relates to the field of computer systems, and, in particular, the field of processing memory access requests.
BACKGROUND OF THE INVENTION
A computer system's performance is in part dependent on the speed of accessing the system memory (e.g., the main general-purpose storage region of the computer system.) For example, microprocessors may only execute instructions as fast as the data operands are provided to the microprocessor. Many of the data operands need to be obtained from the system memory.
Therefore, the speed of accessing the system memory has a large impact on the speed at which a microprocessor is able to complete execution of instructions. As a result, there is a continuous need to increase the speed of accessing system memory.
Access to the system memory is commonly controlled by a unit referred to as the memory controller. The memory controller receives memory access requests (e.g., request to read data stored in memory or request to write data to memory) from other units within the computer system (e.g., the Central Processing Unit (CPU), Graphics accelerator, etc.) The memory controller arbitrates the order in which multiple requests will be granted access to memory. Moreover, the memory controller also prepares/translates memory access requests to be transferred to the system memory. For example, the memory controller may decode a memory request into one or more commands (depending upon the protocol of the memory) to be executed by the system memory in order to complete the memory request.
The rate at which the memory controller processes the memory requests is in part dependent on the bandwidth (i.e., rate of transmitting data) of the memory bus (i.e., an electronic pathway) between the memory controller and the system memory. For example, the memory controller typically may only submit requests to the system memory at a rate equal to or less than the rate of transmitting the data/controls on the memory bus. Otherwise, the memory requests will be prepared by the memory controller faster than they can be transmitted and a bottle neck effect will be the result.
In the past, the bandwidth of the memory bus has been relatively slow. As a result, memory controllers have been able to process memory request in a serial fashion (i.e., completing one memory request before beginning to process a subsequent memory request). Never the less, memory controllers were still able to fill most of the bandwidth of the memory bus, despite processing the requests in a serial fashion.
Advancements in the technology of the memory bus, however, have increased the bandwidth of transmitting data/controls on the memory bus. As a result, there is a need to increase the speed of the memory controller to process memory requests in order to take advantage of the increased bandwidth.
SUMMARY OF THE INVENTION
The present invention provides a pipelined memory controller that includes a decode stage, and a scheduling stage, wherein the scheduling stage includes a command queue to store multiple commands. In one embodiment, the scheduling stage further includes look ahead logic which can modify an order memory commands are stored in the command queue.
REFERENCES:
patent: 5058051 (1991-10-01), Brooks
patent: 5060145 (1991-10-01), Scheuneman et al.
patent: 5222223 (1993-06-01), Webb, Jr. et al.
patent: 5280597 (1994-01-01), Takata et al.
patent: 5323489 (1994-06-01), Bird
patent: 5379379 (1995-01-01), Becker et al.
patent: 5546546 (1996-08-01), Bell et al.
patent: 5586282 (1996-12-01), Iino et al.
patent: 5617559 (1997-04-01), Le et al.
patent: 5619730 (1997-04-01), Ando
patent: 5680577 (1997-10-01), Aden et al.
patent: 5696910 (1997-12-01), Pawlowski
patent: 5732236 (1998-03-01), Nguyen et al.
patent: 5822772 (1998-10-01), Chan et al.
patent: 5835962 (1998-11-01), Chang et al.
patent: 5873119 (1999-02-01), Khandekar et al.
patent: 5893136 (1999-04-01), Stolt et al.
patent: 5903916 (1999-05-01), Pawlowski et al.
patent: 5920898 (1999-07-01), Bolyn et al.
patent: 5940848 (1999-08-01), Bains
patent: 5983325 (1999-11-01), Lewchuk
patent: 6052756 (2000-04-01), Barnaby et al.
IBM Technical Disclosure Bulletin, “Central Processing Unit Lookahead Logic for Video Memory”, vol. 36, Issue 6B, pp. 45-46, Jun. 1, 1999.
Nizar Puthiya K.
Williams Michael W.
Blakely , Sokoloff, Taylor & Zafman LLP
Intel Corporation
Robertson David L.
LandOfFree
Method and apparatus for providing a pipelined memory... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for providing a pipelined memory..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for providing a pipelined memory... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2510364