TECHNIQUES FOR DYNAMICALLY ASSIGNING JOBS TO PROCESSORS IN A CLUSTER BASED ON INTER-THREAD COMMUNICATIONS

• US 20100153965A1
• Filed: 12/16/2008
• Published: 06/17/2010
• Est. Priority Date: 12/16/2008
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Calvignac, Jean L., Arimilli, Lakshminarayana Baba, Basso, Claude, Arimilli, Ravi Kumar
• Granted Patent: US 9,384,042 B2
• Time in Patent Office: Days
• US Class Current: 718/105
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/5066 Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs mappping at compile time, see G06F8/451
• CPC Class Codes: G06F 9/5088 involving task migration

Abstract

A technique for operating a high performance computing (HPC) cluster includes monitoring communication between threads assigned to multiple processors included in the HPC cluster. The HPC cluster includes multiple nodes that each include two or more of the multiple processors. One or more of the threads are moved to a different one of the multiple processors based on the communication between the threads.

Claims

1. A method of operating a high performance computing cluster, comprising:

monitoring communication between threads assigned to multiple processors, wherein the high performance computing cluster includes multiple nodes that each include two or more of the multiple processors; and

moving one or more of the threads to a different one of the multiple processors based on the communication between the threads.

2. The method of claim 1, further comprising:

moving one or more of the threads to a different one of the multiple processors based on workloads of the multiple processors.

3. The method of claim 2, wherein the workloads of the multiple processors are based on utilization of one or more floating-point units included within each of the multiple processors.

4. The method of claim 1, further comprising:

cracking one of the threads that is executing on a first processor, included in the multiple processors, into at least two secondary threads based on a first workload of the first processor; and

moving one of the at least two secondary threads to a second processor, included in the multiple processors, based on a second workload of the second processor.

5. The method of claim 1, wherein the moving further comprises:

moving identified threads, included in the threads, that communicate above a threshold level to identified processors, included in the multiple processors, that are located physically closer to each other.

6. The method of claim 1, wherein the multiple nodes are arranged in a three-dimensional Taurus topology.

7. The method of claim 1, further comprising:

periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes;

updating respective local job tables maintained in each of the multiple nodes based on the broadcast information; and

moving, based on the broadcast information in the respective local job tables, at least one of the one or more threads to a different one of the multiple processors.

8. The method of claim 7, wherein the information is broadcast using a message passing interface.

9. The method of claim 1, wherein the multiple processors are included within multiple chip-level multiprocessors.

10. The method of claim 1, wherein at least some of the multiple processors included within different ones of the multiple chip-level multiprocessors are coupled together via host channel adapters and switch fabrics including one or more switches.

11. A high performance computing cluster, comprising:

multiple nodes that each include multiple processors; and

monitoring hardware included in each of the multiple nodes, wherein the monitoring hardware is configured to monitor communication between threads assigned to the multiple processors and the high performance computer cluster is configured to move one or more of the threads to a different one of the multiple processors based on the communication between the threads.

12. The high performance computing cluster of claim 11, wherein the high performance computer cluster is further configured to move one or more of the threads to a different one of the multiple processors based on workloads of the multiple processors.

13. The high performance computing cluster of claim 12, wherein the workloads of the multiple processors are based on utilization of one or more floating-point units included within each of the multiple processors.

14. The high performance computing cluster of claim 11, wherein the high performance computer cluster is further configured to crack one of the threads that is executing on a first processor, included in the multiple processors, into at least two secondary threads based on a first workload of the first processor and move one of the at least two secondary threads to a second processor, included in the multiple processors, based on a second workload of the second processor.

15. The high performance computing cluster of claim 11, wherein the high performance computer cluster is further configured to move identified threads, included in the threads, that communicate above a threshold level to identified processors, included in the multiple processors, that are located physically closer to each other.

16. The high performance computing cluster of claim 11, wherein the multiple nodes are arranged in a three-dimensional Taurus topology.

17. The high performance computing cluster of claim 11, further comprising:

periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes;

updating respective local job tables maintained in each of the multiple nodes based on the broadcast information; and

moving, based on the broadcast information in the respective local job tables, at least one of the one or more threads to a different one of the multiple processors.

18. The high performance computing cluster of claim 17, where the information is broadcast using a message passing interface.

19. The high performance computing cluster of claim 11, wherein the multiple processors are included within multiple chip-level multiprocessors and at least some of the multiple processors included within different ones of the multiple chip-level multiprocessors are coupled together via host channel adapters and switch fabrics including one or more switches.

20. A method of operating a high performance computing cluster, comprising:

monitoring communication between threads assigned to multiple processors, wherein the high performance computing cluster includes multiple nodes that each include two or more of the multiple processors;

moving one or more of the threads to a different one of the multiple processors based on the communication between the threads;

periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes;

updating respective local job tables maintained in each of the multiple nodes based on the broadcast information; and

moving, based on the broadcast information in the respective local job tables, at least one of the one or more threads to a different one of the multiple processors, wherein the information is broadcast using a message passing interface and the multiple nodes are arranged in a three-dimensional Taurus topology.