Data processing system, method and interconnect fabric having an address-based launch governor

• US 7,415,030 B2
• Filed: 02/10/2005
• Issued: 08/19/2008
• Est. Priority Date: 02/10/2005
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Stuecheli, Jeffrey A., Goodman, Benjiman L., Reddy, Praveen S.
• Primary Examiner(s): Sam; Phirin
• Application Number:
  US11/054,910
• Publication Number:
  US 20060176885A1
• Time in Patent Office: 1,286 Days
• Field of Search: None
• US Class Current: 370/401
• CPC Class Codes: G06F 12/0811 with multilevel cache hierarchies
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/0831 using a bus scheme, e.g. with bus monitoring or watching means

Abstract

A data processing system includes an interconnect fabric, a protected resource having a plurality of banks each associated with a respective one of a plurality of address sets, a snooper that controls access to the resource, one or more masters that initiate requests, and interconnect logic coupled to the one or more masters and to the interconnect fabric. The interconnect logic regulates a rate of delivery to the snooper via the interconnect fabric of requests that target any one the plurality of banks of the protected resource.

Claims

1. A method of data processing, comprising:

detecting one or more requests that target a protected resource having a plurality of banks each associated with a respective one of a plurality of address sets; and

regulating a rate of delivery of requests that target any one said plurality of banks of said protected resource to a snooper controlling access to said protected resource, wherein said regulating comprises decreasing said rate below a maximum request arrival rate supported by an interconnect fabric to which said snooper is coupled.

2. The method of claim 1, wherein said regulating comprises regulating a launch of said requests at a processing unit containing said one or more masters.

3. The method of claim 1, wherein said data processing system includes a first processing unit containing said one or more masters and a second processing unit coupled to said first processing unit by an interconnect fabric, wherein said regulating comprises regulating said rate at said second processing unit.

4. The method of claim 1, wherein:

said method further comprises buffering, in a previous request buffer, information regarding one or more previous requests; and

said regulating comprises determining which of said plurality of banks said one or more previous requests targeted.

5. The method of claim 4, wherein said buffering comprises buffering one or more entries each indicating which if any of said plurality of banks was targeted in a previous address tenure on an interconnect fabric.