Providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer

• US 9,882,801 B2
• Filed: 02/27/2013
• Issued: 01/30/2018
• Est. Priority Date: 08/06/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Archer, Charles J., Faraj, Daniel A., Inglett, Todd A., Ratterman, Joseph D.
• Primary Examiner(s): Kassim, Khaled
• Application Number:
  US13/778,581
• Publication Number:
  US 20130176904A1
• Time in Patent Office: 1,798 Days
• Field of Search: None
• CPC Class Codes: G06F 15/173 using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
• CPC Class Codes: H04L 45/02 Topology update or discovery

Abstract

Methods, apparatus, and products are disclosed for providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer, each compute node connected to each adjacent compute node in the global combining network through a link, that include: receiving a network packet in a compute node, the network packet specifying a destination compute node; selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node; and forwarding the network packet along the selected link to the adjacent compute node connected to the compute node through the selected link.

Claims

1. A method for providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer, the method comprising:

receiving a network packet in a compute node of a parallel computer, wherein the parallel computer comprises a plurality of compute nodes coupled for point-to-point data communications in a global combining network, the global combining network comprises a binary tree, each compute node is coupled to each adjacent compute node in the global combining network through a link, and the network packet specifies a destination compute node;

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node, each link comprising an exclusive, dedicated data communications connection between a single compute node and one adjacent compute node, including;

identifying a receipt link on which the network packet was received by the compute node;

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting all of the links for the compute node except the receipt link if the destination compute node is not one of the adjacent compute nodes for the compute node; and

forwarding the network packet along the selected link to the adjacent compute node connected to the compute node through the selected link.

2. The method of claim 1 wherein:

the method further comprises;

determining a network topology for the compute nodes of the operational group in the global combining network, and creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table that associates one of the links for the compute node along which to forward network packets to each of the other compute nodes in the operational group; and

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises identifying, from the forwarding table, the link associated with the destination compute node.

3. The method of claim 2 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in the compute node.

4. The method of claim 2 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in an input/output node supporting the compute node.

5. The method of claim 1 wherein selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises:

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting the link to the destination compute node if the destination compute node is one of the adjacent compute nodes for the compute node.

6. A parallel computer for providing full point-to-point communications among compute nodes of an operational group in a global combining network, each compute node connected to each adjacent compute node in the global combining network through a link, the parallel computer comprising a plurality of computer processors and computer memory operatively coupled to the computer processors, the computer memory having disposed within it computer program instructions capable of:

receiving a network packet in a compute node of a parallel computer, wherein the parallel computer comprises a plurality of compute nodes coupled for point-to-point data communications in a global combining network, the global combining network comprises a binary tree, each compute node is coupled to each adjacent compute node in the global combining network through a link, and the network packet specifies a destination compute node;

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node, each link comprising an exclusive, dedicated data communications connection between a single compute node and one adjacent compute node, including;

identifying a receipt link on which the network packet was received by the compute node;

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting all of the links for the compute node except the receipt link if the destination compute node is not one of the adjacent compute nodes for the compute node; and

forwarding the network packet along the selected link to the adjacent compute node connected to the compute node through the selected link.

7. The parallel computer of claim 6 wherein:

the computer memory also has disposed within it computer program instructions capable of;

determining a network topology for the compute nodes of the operational group in the global combining network, and creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table that associates one of the links for the compute node along which to forward network packets to each of the other compute nodes in the operational group; and

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises identifying, from the forwarding table, the link associated with the destination compute node.

8. The parallel computer of claim 7 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in the compute node.

9. The parallel computer of claim 7 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in an input/output node supporting the compute node.

10. The parallel computer of claim 6 wherein selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises:

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting the link to the destination compute node if the destination compute node is one of the adjacent compute nodes for the compute node.

11. A computer program product for providing full point-to-point communications among compute nodes of an operational group in a global combining network of a parallel computer, each compute node connected to each adjacent compute node in the global combining network through a link, the computer program product disposed upon a non-transitory computer readable recordable medium, the computer program product comprising computer program instructions capable of:

receiving a network packet in a compute node of a parallel computer, wherein the parallel computer comprises a plurality of compute nodes coupled for point-to-point data communications in a global combining network, the global combining network comprises a binary tree, each compute node is coupled to each adjacent compute node in the global combining network through a link, and the network packet specifies a destination compute node;

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node, each link comprising an exclusive, dedicated data communications connection between a single compute node and one adjacent compute node, including;

identifying a receipt link on which the network packet was received by the compute node;

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting all of the links for the compute node except the receipt link if the destination compute node is not one of the adjacent compute nodes for the compute node; and

forwarding the network packet along the selected link to the adjacent compute node connected to the compute node through the selected link.

12. The computer program product of claim 11 wherein:

the computer program product further comprises computer program instructions capable of;

determining a network topology for the compute nodes of the operational group in the global combining network, and creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table that associates one of the links for the compute node along which to forward network packets to each of the other compute nodes in the operational group; and

selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises identifying, from the forwarding table, the link associated with the destination compute node.

13. The computer program product of claim 12 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in the compute node.

14. The computer program product of claim 12 wherein creating, for each compute node of the operational group in dependence upon the network topology, a forwarding table further comprises storing each compute node'"'"'s forwarding table in an input/output node supporting the compute node.

15. The computer program product of claim 11 wherein selecting, in dependence upon the destination compute node, at least one of the links for the compute node along which to forward the network packet toward the destination compute node further comprises:

determining whether the destination compute node is one of the adjacent compute nodes for the compute node; and

selecting the link to the destination compute node if the destination compute node is one of the adjacent compute nodes for the compute node.