Administering group identifiers of processes in a parallel computer

1. A method of administering group identifiers of processes in a parallel computer, the parallel computer comprising a plurality of compute nodes, the compute nodes coupled for data communications by one or more data communications networks, one or more of the compute nodes executing a set of processes, the set of processes organized in an operational group for collective parallel operations, the method comprising:

receiving from a compute node of the plurality of compute nodes, by each process in the set of processes, a request to establish the set of processes as an operational group including receiving a list of process identifiers for each process of the set of processes; and

generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers.

2. The method of claim 1 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers includes:

generating based on the list of process identifiers, by each process, a stride triplet comprising the following elements: a lowest process identifier, a value representing a stride size between the set of processes, and a number of processes in the set of processes; and

generating, by each process without communication amongst the processes and in dependence upon the stride triplet, the unique group identifier.

3. The method of claim 2 wherein generating, by each process in dependence upon the stride triplet, a unique group identifier further comprises:

concatenating the elements of the stride triplet.

4. The method of claim 2 , further comprising:

responsive to receiving a second request to establish the set of processes as a second group, without previously destroying the operational group, generating a second unique group identifier for the second group in dependence upon the stride triplet and an instance identifier.

5. The method of claim 4 wherein generating a second unique group identifier for the second group in dependence upon the stride triplet and an instance identifier includes appending the instance identifier to the stride triplet.

6. The method of claim 1 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

concatenating the sorted process identifiers, wherein the concatenated process identifiers comprises the unique group identifier.

7. The method of claim 1 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

hashing the sorted process identifiers to generate a hash value, wherein the hash value comprises the unique group identifier.

8. The method of claim 7 wherein

at least one process is a member of a second operational group and the group identifier of the second operational group matches the hash value; and

wherein the method further includes:

determining, by the at least one process, that the group identifier of the second operational group matches the hash value; and

in response to determining that the group identifier of the second operational group matches the hash value, informing, by the at least one process, the other processes of the operational group, that the group identifier of the second operational group matches the hash value; and

in response to the group identifier of the second operational group matching the hash value, changing, by each process, the hash value to a same new hash value.

9. The method of claim 1 , further comprising destroying, by each process, the unique group identifier in response to destruction of the operational group.

10. An apparatus for executing administering group identifiers of processes in a parallel computer, the parallel computer comprising a plurality of compute nodes, the compute nodes coupled for data communications by one or more data communications networks, one or more of the compute nodes executing a set of processes, the set of processes organized in an operational group for collective parallel operations, the apparatus comprising a computer processor and 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:

receiving from a compute node of the plurality of compute nodes, by each process in the set of processes, a request to establish the set of processes as an operational group including receiving a list of process identifiers for each process of the set of processes; and

generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers.

11. The apparatus of claim 10 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers includes:

generating based on the list of process identifiers, by each process, a stride triplet comprising the following elements: a lowest process identifier, a value representing a stride size between the set of processes, and a number of processes in the set of processes; and

generating, by each process without communication amongst the processes and in dependence upon the stride triplet, the unique group identifier.

12. The apparatus of claim 10 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

concatenating the sorted process identifiers, wherein the concatenated process identifiers comprises the unique group identifier.

13. The apparatus of claim 10 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

hashing the sorted process identifiers to generate a hash value, wherein the hash value comprises the unique group identifier.

14. A computer program product for administering group identifiers of processes in a parallel computer, the parallel computer comprising a plurality of compute nodes, the compute nodes coupled for data communications by one or more data communications networks, one or more of the compute nodes executing a set of processes, the set of processes organized in an operational group for collective parallel operations, the computer program product disposed upon a computer readable medium, the computer program product comprising computer program instructions that, when executed, cause a computer to carry out the steps of:

receiving from a compute node of the plurality of compute nodes, by each process in the set of processes, a request to establish the set of processes as an operational group including receiving a list of process identifiers for each process of the set of processes; and

generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers.

15. The computer program product of claim 14 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers includes:

generating based on the list of process identifiers, by each process, a stride triplet comprising the following elements: a lowest process identifier, a value representing a stride size between the set of processes, and a number of processes in the set of processes; and

generating, by each process without communication amongst the processes and in dependence upon the stride triplet, the unique group identifier.

16. The computer program product of claim 14 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

concatenating the sorted process identifiers, wherein the concatenated process identifiers comprises the unique group identifier.

17. The computer program product of claim 14 wherein generating, by each process without communication amongst the processes, a unique group identifier in dependence upon the list of process identifiers further comprises:

sorting the process identifiers of the list of process identifiers according to a predefined sort criteria; and

hashing the sorted process identifiers to generate a hash value, wherein the hash value comprises the unique group identifier.

18. The computer program product of claim 14 , further comprising:

destroying, by each process, the unique group identifier in response to destruction of the operational group.

19. The computer program product of claim 14 wherein the computer readable medium comprises a signal medium.

20. The computer program product of claim 14 wherein the computer readable medium comprises a storage medium.