Bus bandwidth sharing physically remote distributed processing functional nodes coupled to passive cooling interface assembly with minimal thermal path

• US 8,261,044 B2
• Filed: 12/19/2007
• Issued: 09/04/2012
• Est. Priority Date: 06/12/2002
• Status: Active Grant

• Current Assignee: The Boeing Co.
• Original Assignee: The Boeing Co.
• Inventors: Kinstler, Gary A.
• Primary Examiner(s): KIM, KENNETH S
• Application Number:
  US11/960,465
• Publication Number:
  US 20080098059A1
• Time in Patent Office: 1,721 Days
• Field of Search: None
• US Class Current: 712/28
• CPC Class Codes: G06F 9/5016 the resource being the memory
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

The distributed data handling and processing resources system of the present invention includes a) a number of data handling and processing resource nodes that collectively perform a desired data handling and processing function, each data handling and processing resource node for providing a data handling/processing subfunction; and, b) a low latency, shared bandwidth databus for interconnecting the data handling and processing resource nodes. In the least, among the data handling and processing resource nodes, is a processing unit (PU) node for providing a control and data handling/processing subfunction; and, an input/output (I/O) node for providing a data handling/processing subfunction for data collection/distribution to an external environment. The present invention preferably uses the IEEE-1394b databus due to its unique and specialized low latency, shared bandwidth characteristics.

Claims

1. A distributed data handling and processing system comprising:

a passive cooling interface assembly within a defined area;

a plurality of resource nodes collectively configured to perform a desired data handling and processing function, each of said resource nodes configured to perform one desired data handling and processing sub-function of the desired data handling and processing function, each of said resource nodes located physically remote from one another within the defined area and operably connected to said passive cooling interface assembly, as dispersed within the defined area, such that a length of a thermal path between a respective said resource node and the passive cooling interface assembly is minimized within the defined area, said plurality of nodes including at least one processing unit node configured for control, data handling, and data processing sub-functions and at least one input/output node configured for data collection and distribution with respect to an external environment; and

a low latency, shared bandwidth databus for interconnecting said plurality of resource nodes.

2. A distributed data handling and processing system according to claim 1 wherein said plurality of resource nodes comprises at least one memory node configured to provide a memory subfunction.

3. A distributed data handling and processing system according to claim 1 wherein said low latency, shared bandwidth databus comprises a IEEE-1394b databus.

4. A distributed data handling and processing system according to claim 1 further comprising an application programming interface (API) configured to segment messages from said databus into multiple, smaller messages for communication with an environment external to said distributed data handling and processing system.

5. A distributed data handling and processing system according to claim 4 wherein said API is configured to create gaps within the messages so that other messages can have timely access to said databus.

6. A distributed data handling and processing system according to claim 1 wherein said low latency, shared bandwidth databus comprises a directly addressable, non-overlapping address space serving all of said resource nodes.

7. A method for reducing a total weight of a system configured to perform a given data handling and processing function, said method comprising:

dividing the system into a plurality of resource nodes collectively configured to perform the given data handling and processing function, each of the resource nodes configured to perform one sub-function of the given data handling and processing function, each of the resource nodes located physically remote from one another within a defined area, wherein the dividing includes configuring at least one of the resource nodes as a processing node and configuring at least one of the resource nodes as an input/output node configured for data collection and distribution with respect to an external environment;

providing a passive cooling interface assembly within the defined area;

attaching each of the resource nodes to the passive cooling interface assembly such that a thermal path to the passive cooling interface assembly is minimized for each resource node within the defined area; and

interconnecting the plurality of resource nodes with a low latency, shared bandwidth databus.

8. A method according to claim 7 wherein dividing the system into a plurality of resource nodes comprises configuring at least one of the resource nodes as a memory node configured to provide a memory subfunction.

9. A method according to claim 7 wherein interconnecting the plurality of resource nodes comprises interconnecting the plurality of resource nodes utilizing a IEEE-1394b databus.

10. A method according to claim 7 further comprising configuring the databus to include a directly addressable, non-overlapping address space serving all of the resource nodes.

11. A method according to claim 7 further comprising segmenting messages from the databus into multiple, smaller messages for communication with an environment external to the system.

12. A method according to claim 11 wherein segmenting messages comprises creating gaps within the messages to provide timely access to the databus for other messages.

13. A distributed data handling and processing system comprising:

a passive cooling interface assembly within a defined area;

at least one processing unit resource node configured for control, data handling, and data processing sub-function;

at least one input/output resource node configured for providing a data handling and data processing sub-function for data collection and data distribution with respect to an area external to the defined area;

at least one special purpose resource node configured to perform a subsystem control function, each of said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node located physically remote and separately packaged from one another within the defined area, and each of said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node connected to said passive cooling interface assembly, as dispersed within the defined area, such that a length of a thermal path between a respective one of said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node and said passive cooling interface assembly is minimized; and

a databus for interconnecting said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node, said databus incorporating message packet sizes to control a latency of messages between said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node.

14. A distributed data handling and processing system according to claim 13 wherein said databus is configured such that messages between said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node have a latency between about 0.5 and 10 microseconds.

15. A distributed data handling and processing system according to claim 13 wherein said databus comprises a IEEE-1394b databus.

16. A distributed data handling and processing system according to claim 13 wherein each said at least one processing unit resource node, said at least one input/output resource node, and said at least one special purpose resource node comprises a separate enclosure, said separate enclosures independently connectable to said passive cooling interface assembly.