Manageability redundancy for micro server and clustered system-on-a-chip deployments

Patent metadata

Field	Value
Publication number	US-9367406-B2
Application number	US-201314125516-A
Country	US
Kind code	B2
Filing date	Aug 14, 2013
Priority date	Aug 14, 2013
Publication date	Jun 14, 2016
Grant date	Jun 14, 2016

Abstract

Technologies for providing manageability redundancy for micro server and clustered System-on-a-Chip (SoC) deployments are presented. A configurable multi-processor apparatus may include multiple integrated circuit (IC) blocks where each IC block includes a task block to perform one or more assignable task functions and a management block to perform management functions with respect to the corresponding IC block. Each task block and each management block may include one or more instruction processors and corresponding memory. Each IC block may be controllable to perform a function of one or more other IC blocks. The IC blocks may communicate with each other via a management communication infrastructure that may include a communication path from each of the management blocks to each of the other management blocks. Via the management communication infrastructure, the management blocks may bridge communication paths between pairs of management blocks.

First claim

What is claimed is:

1. An apparatus, comprising:
a first integrated circuit (IC) block that includes a first task block configured to perform a first task, and a first management block configured to perform a first management function related to the first task block;
a second IC block that includes a second task block configured to perform a second task, and a second management block configured to perform a second management function related to the second task block; and
a management controller configured to dynamically control the second management block to perform the first management function if the first management block fails to perform the first management function, and to dynamically control the second task block to perform a third task based on one or more factors related to the first IC block.

2. The system of claim 1 , wherein the management controller is further configured to dynamically control the second management block to access the first task block over a communication infrastructure to perform the first management function, if the first management block fails to perform the first management function.

3. The system of claim 2 , wherein:
the first management block is further configured to receive information from the first task block and report the information over the communication infrastructure; and
the management controller is further configured to dynamically control the second management block to retrieve the information from the first task block over the communication infrastructure and to report the information over the communication infrastructure, if the first management block fails to report the information over the communication infrastructure.

4. The system of claim 3 , wherein the information includes a sensed parameter recorded by the first task block.

5. The system of claim 1 , further including one or more additional IC blocks, each including a respective task block and a respective management block, wherein the management controller is further configured to:
manage workloads of the first, second, and one or more additional task blocks based at least in part on temperatures reported by the respective management block; and
dynamically control the second management block to estimate a temperature of the first IC block based on temperatures reported by the one or more additional IC blocks, if the first management block fails to report a temperature of the first IC block and/or if the temperature of the first IC block is not accessible from the first task block by the second management block.

6. The system of claim 1 , further including a third IC block that includes a third task block and a third management block, wherein:
the first, second, and third IC blocks are functionally identical to one another;
each of the first, second, and third IC blocks is configurable as the management controller; and
the third IC block is configured as the management controller based on one or more factors.

7. The system of claim 6 , wherein each of the first, second, and third task blocks include a processor and memory configurable to perform the first and second tasks.

8. The system of claim 6 , further including an IC die that includes the first, second, and third IC blocks.

9. The system of claim 6 , further including an integrated circuit board that includes the first, second, and third IC devices, configured as a blade of a server system.

10. A method of managing integrated circuit (IC) blocks, comprising:
dynamically re-assigning, by a managing IC block of the IC blocks, a management function from a first IC block of the IC blocks to one or more other IC blocks under a first circumstance, over a management communication infrastructure; and
dynamically re-assigning, by the managing IC block, a task function from the first IC block to one or more other IC blocks under a second circumstance, over the management communication infrastructure;
wherein each IC block includes a task block to perform one or more assignable task functions and a management block to perform management functions with respect to the corresponding IC block; and
wherein the IC blocks are configured to communicate with one another over the management communication infrastructure.

11. The method of claim 10 , wherein the dynamically re-assigning the management function comprises:
dynamically re-assigning the management function within a subset of IC blocks.

12. The method of claim 10 , wherein the dynamically re-assigning the management function comprises:
dynamically re-assigning the management function between a pair of IC blocks.

13. The method of claim 10 , wherein the dynamically re-assigning the management function comprises:
dynamically re-assigning the management function from the first IC block if status is not received from the first IC block.

14. The method of claim 10 , wherein the dynamically re-assigning the management function comprises:
dynamically re-assigning the management function from the first IC block if status from the first IC block indicates a fault in the corresponding management block.

15. The method of claim 10 , wherein the dynamically re-assigning the task function comprises:
dynamically re-assigning the task function if status from the first IC block indicates a fault in the corresponding task block.

16. The method of claim 10 , wherein the dynamically re-assigning the task function comprises:
dynamically re-assigning the task function from the first IC block to balance power consumption amongst multiple IC blocks.

17. The method of claim 10 , wherein the dynamically re-assigning the task function comprises:
dynamically re-assigning the task function to balance processing load amongst multiple IC blocks.

18. The method of claim 10 , wherein the dynamically re-assigning the task function comprises:
dynamically dividing the task function amongst multiple IC blocks.

19. The method of claim 10 , wherein the dynamically re-assigning the task function comprises:
dynamically re-assigning the task function from a first set of multiple IC blocks to a second set of one or more IC blocks, and placing the first set of IC blocks in a reduced power consumption state.

20. An apparatus, comprising:
means for dynamically re-assigning, by a managing integrated circuit (IC) block of a plurality of IC blocks, a management function from a first IC block of the plurality of IC blocks to one or more other IC blocks of the plurality of IC blocks under a first circumstance, over a management communication infrastructure; and
means for dynamically re-assigning, by the managing IC block, a task function from the first IC block to one or more other IC blocks under a second circumstance, over the management communication infrastructure;
wherein each IC block includes a task block to perform one or more assignable task functions and a management block to perform management functions with respect to the corresponding IC block; and
wherein the IC blocks are configured to communicate with another over the management communication infrastructure.

21. A non-transitory computer-readable medium encoded with a computer program that includes instructions to cause a managing IC block of a plurality of IC blocks of a computing device to:
dynamically re-assign a management function from a first IC block of the plurality of IC blocks to one or more other IC blocks of the plurality of IC blocks under a first circumstance, over a management communication infrastructure; and
dynamically

Assignees

• Intel Corp

Inventors

• Swanson Robert C
• Oriol Mariusz
• Jurski Janusz
• Sawicki Piotr
• Cone Robert W
• O'Sullivan William J
• Stepka Mariusz
• Nikjou Babak
• Rangarajan Madhusudhan
• Szymanski Pawel
• Kwidzinski Piotr
• Bahnsen Robert
• Bulusu Mallik

Classifications

• G06F11/2033

  switching over of hardware resources · CPC title

• G06F11/203

  using migration · CPC title

• G06F11/14

  Error detection or correction of the data by redundancy in operations (error detection or correction of the data by redundancy in hardware G06F11/16) · CPC title

• G06F11/2035

  without idle spare hardware · CPC title

• G06F11/2028

  eliminating a faulty processor or activating a spare · CPC title