Endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface of a parallel computer

• US 8,892,850 B2
• Filed: 01/17/2011
• Issued: 11/18/2014
• Est. Priority Date: 01/17/2011
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Archer, Charles J., Blocksome, Michael A., Cernohous, Bob R., Ratterman, Joseph D., Smith, Brian E.
• Primary Examiner(s): Caldwell, Andrew
• Assistant Examiner(s): Xiao, Yuqing
• Application Number:
  US13/007,848
• Publication Number:
  US 20120185679A1
• Time in Patent Office: 1,401 Days
• Field of Search: 709/201, 712/16
• US Class Current: 712/16
• CPC Class Codes: G06F 9/54 Interprogram communication

Abstract

Methods, apparatuses, and computer program products for endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface (‘PAMI’) of a parallel computer are provided. Embodiments include establishing by a parallel application a data communications geometry, the geometry specifying a set of endpoints that are used in collective operations of the PAMI, including associating with the geometry a list of collective algorithms valid for use with the endpoints of the geometry. Embodiments also include registering in each endpoint in the geometry a dispatch callback function for a collective operation and executing without blocking, through a single one of the endpoints in the geometry, an instruction for the collective operation.

Claims

1. A parallel computer that implements endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface (‘

PAMI’

) of the parallel computer, the parallel computer comprising a plurality of compute nodes that execute a parallel application, the PAMI comprising data communications endpoints, each endpoint comprising a specification of data communications parameters for a thread of execution on a compute node, the endpoints coupled for data communications through the PAMI, the compute nodes comprising computer processors operatively coupled to computer memory having disposed within it computer program instructions that, when executed by the computer processors, cause the parallel computer to function by;

establishing by the parallel application a data communications geometry, by;

calling, by an application-level entity, a PAMI initialization function configured to establish the geometry by reading the geometry from a PAMI configuration, the geometry specifying, for tasks representing processes of execution of the parallel application, a set of endpoints that are used in collective operations of the PAMI, and specifications of a task, client, and context for each endpoint, and

associating with the geometry a list of collective algorithms for collective operations valid for use with the endpoints of the geometry read from the PAMI configuration,

wherein the list of collective algorithms is dependent upon a nature of underlying data communications resources available to carry out any particular collective operation;

registering, by the parallel application in each endpoint in the geometry, a dispatch callback function for each of the collective operations; and

executing, by the parallel application without blocking, through a single one of the endpoints in the geometry, an instruction for one of the collective operations, the instruction specifying communications of transfer data among the endpoints of the geometry, an identifier of the dispatch callback function associated with the collective operation, and the collective algorithm.

2. The parallel computer of claim 1 wherein executing an instruction for one of the collective operations comprises executing the instruction by only a single instance of the parallel application.

3. The parallel computer of claim 1 further comprising computer program instructions that, when executed by the computer processors, cause the parallel computer to function by determining by an instance of the parallel application executing in a process of execution on the parallel computer that the instance is a root of the collective operation;

and

wherein executing an instruction for one of the collective operations includes posting by the instance the instruction in a work queue of a context in the single endpoint, the single endpoint being an endpoint comprising a task that represents the process of execution in which the instance is executing.

4. The parallel computer of claim 1 wherein:

the parallel computer further comprises computer program instructions that, when executed by the computer processors, cause the parallel computer to function by executing the identified dispatch callback function by all the endpoints in the geometry.

5. The parallel computer of claim 1 wherein:

each client comprises a collection of data communications resources dedicated to the exclusive use of an application-level data processing entity;

each context comprises a subset of the collection of data processing resources of a client, context functions, and a work queue of data transfer instructions to be performed by use of the subset through the context functions operated by an assigned thread of execution; and

each task represents a process of execution of the parallel application.

6. The parallel computer of claim 1 wherein each context carries out, through post and advance operations, data communications for the parallel application on data communications resources in the exclusive possession of that context.

7. The parallel computer of claim 1 wherein each context carries out data communications operations independently and in parallel with other contexts.

8. A computer program product for endpoint-based parallel data processing with non-blocking collective instructions in a parallel active messaging interface (‘

PAMI’

) of a parallel computer, the parallel computer comprising a plurality of compute nodes that execute a parallel application, the PAMI comprising data communications endpoints, each endpoint comprising a specification of data communications parameters for a thread of execution on a compute node, the endpoints coupled for data communications through the PAMI, the computer program product disposed upon a computer readable storage medium, wherein the computer readable storage medium is not a signal, and the computer program product is not a signal, the computer program product comprising computer program instructions that, when installed and executed, cause the parallel computer to function by;

establishing by the parallel application a data communications geometry, by;

calling, by an application-level entity, a PAMI initialization function configured to establish the geometry by reading the geometry from a PAMI configuration, the geometry specifying, for tasks representing processes of execution of the parallel application, a set of endpoints that are used in collective operations of the PAMI, and specifications of a task, client, and context for each endpoint, and

associating with the geometry a list of collective algorithms for collective operations valid for use with the endpoints of the geometry read from the PAMI configuration,

wherein the list of collective algorithms is dependent upon a nature of underlying data communications resources available to carry out any particular collective operation;

registering, by the parallel application in each endpoint in the geometry, a dispatch callback function for each of the collective operations; and

executing, by the parallel application without blocking, through a single one of the endpoints in the geometry, an instruction for one of the collective operations, the instruction specifying communications of transfer data among the endpoints of the geometry, an identifier of the dispatch callback function associated with the collective operation, and the collective algorithm.

9. The computer program product of claim 8 wherein executing an instruction for one of the collective operations comprises executing the instruction by only a single instance of the parallel application.

10. The computer program product of claim 8 further comprising computer program instructions that, when installed and executed, cause the parallel computer to function by determining by an instance of the parallel application executing in a process of execution on the parallel computer that the instance is a root of the collective operation;

wherein executing an instruction for one of the collective operations includes posting by the instance the instruction in a work queue of a context in the single endpoint, the single endpoint being an endpoint comprising a task that represents the process of execution in which the instance is executing.

11. The computer program product of claim 8 wherein:

the computer program product further comprises computer program instructions that, when installed and executed, cause the parallel computer to function by executing the identified dispatch callback function by all the endpoints in the geometry.

12. The computer program product of claim 8 wherein:

each client comprises a collection of data communications resources dedicated to the exclusive use of an application-level data processing entity;

each context comprises a subset of the collection of data processing resources of a client, context functions, and a work queue of data transfer instructions to be performed by use of the subset through the context functions operated by an assigned thread of execution; and

each task represents a process of execution of the parallel application.

13. The computer program product of claim 8 wherein each context carries out, through post and advance operations, data communications for the parallel application on data communications resources in the exclusive possession of that context.