Performing collective operations in a distributed processing system

• US 9,262,201 B2
• Filed: 07/13/2011
• Issued: 02/16/2016
• Est. Priority Date: 07/13/2011
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Archer, Charles J., Carey, James E., Markland, Matthew W., Sanders, Philip J.
• Primary Examiner(s): MIRZA, ADNAN M
• Application Number:
  US13/181,669
• Publication Number:
  US 20130018935A1
• Time in Patent Office: 1,679 Days
• Field of Search: 709/201, 709/202, 709/203, 709/204
• US Class Current: 1/1
• CPC Class Codes: G06F 9/46 Multiprogramming arrangements
• 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: H04L 45/02 Topology update or discovery
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

Methods, apparatuses, and computer program products for performing collective operations on a hybrid distributed processing system are provided. Embodiments include determining by at least one task that a parent of the task has failed to send the task data through the tree topology; and determining whether to request the data from a grandparent of the task or a peer of the task in the same tier in the tree topology; and if the task requests the data from the grandparent, requesting the data and receiving the data from the grandparent of the task through the second networking topology; and if the task requests the data from a peer of the task in the same tier in the tree, requesting the data and receiving the data from a peer of the task through the second networking topology.

Claims

1. Apparatus for performing collective operations on a hybrid distributed processing system, the hybrid distributed processing system including a plurality of compute nodes, each compute node having a plurality of tasks, each task assigned a unique rank, each compute node coupled for data communications by at least one data communications network implementing at least two different networking topologies;

wherein the at least two networking topologies further comprise two independent data communications networks, and wherein a first networking topology comprises a tiered tree topology having a root task, and at least two child tasks, where the two child tasks are peers of one another in the same tier, the apparatus comprising a computer processor, a computer memory operatively coupled to the computer processor, the computer memory having disposed within it computer program instructions that, when executed by the computer processor, cause the apparatus to carry out the steps of;

determining by at least one task that a parent of the task has failed to send the task data through the tree topology; and

determining whether to request the data from a grandparent of the task or a peer of the task in the same tier in the tree topology;

if the task requests the data from the grandparent, requesting the data and receiving the data from the grandparent of the task through the second networking topology; and

if the task requests the data from a peer of the task in the same tier in the tree, requesting the data and receiving the data from a peer of the task through the second networking topology.

2. The apparatus of claim 1 wherein determining whether to request the data from the grandparent of the task or a peer of the task in the same tier in the tree further comprises first requesting the data from a peer.

3. The apparatus of claim 1 wherein determining whether to request the data from the grandparent of the task or a peer of the task in the same tier in the tree further comprises determining whether a link in between the grandparent and the task failed and if the link failed, requesting the data from a peer.

4. The apparatus of claim 1 wherein the second networking topologies further comprises a torus topology.

5. The apparatus of claim 1 wherein the second networking topologies further comprises a mesh topology.

6. A computer program product for performing collective operations on a hybrid distributed processing system, the hybrid distributed processing system including a plurality of compute nodes, each compute node having a plurality of tasks, each task assigned a unique rank, each compute node coupled for data communications by at least one data communications network implementing at least two different networking topologies;

wherein the at least two networking topologies further comprise two independent data communications networks, and wherein a first networking topology comprises a tiered tree topology having a root task, and at least two child tasks, where the two child tasks are peers of one another in the same tier, the computer program product disposed upon a non-transitory computer readable storage medium, the computer program product comprising computer program instructions that, when executed, cause a computer to carry out the steps of;

determining by at least one task that a parent of the task has failed to send the task data through the tree topology; and

determining whether to request the data from a grandparent of the task or a peer of the task in the same tier in the tree topology;

if the task requests the data from the grandparent, requesting the data and receiving the data from the grandparent of the task through the second networking topology; and

if the task requests the data from a peer of the task in the same tier in the tree, requesting the data and receiving the data from a peer of the task through the second networking topology.

7. The computer program product of claim 6 wherein determining whether to request the data from the grandparent of the task or a peer of the task in the same tier in the tree further comprises first requesting the data from a peer.

8. The computer program product of claim 6 wherein determining whether to request the data from the grandparent of the task or a peer of the task in the same tier in the tree further comprises determining whether a link in between the grandparent and the task failed and if the link failed, requesting the data from a peer.

9. The computer program product of claim 6 wherein the second networking topologies further comprises a torus topology.

10. The computer program product of claim 6 wherein the second networking topologies further comprises a mesh topology.