PERFORMING COLLECTIVE OPERATIONS IN A DISTRIBUTED PROCESSING SYSTEM

• US 20130081037A1
• Filed: 11/16/2012
• Published: 03/28/2013
• 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.
• Granted Patent: US 9,459,909 B2
• Time in Patent Office: Days
• US Class Current: 718/102
• 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 including: 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. A method of 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 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 method comprising:

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 method 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 method 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 method of claim 1 wherein the at least two networking topologies further comprise two independent data communications networks.

5. The method of claim 1 wherein the second networking topologies further comprises a torus topology.

6. The method of claim 1 wherein the second networking topologies further comprises a mesh topology.

7-18. -18. (canceled)