MECHANISM TO SUPPORT GENERIC COLLECTIVE COMMUNICATION ACROSS A VARIETY OF PROGRAMMING MODELS

• US 20090006810A1
• Filed: 06/26/2007
• Published: 01/01/2009
• Est. Priority Date: 06/26/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kumar, Sameer, Dozsa, Gabor, Almasi, Gheorghe
• Granted Patent: US 7,984,448 B2
• Time in Patent Office: Days
• US Class Current: 712/35
• CPC Class Codes: G06F 9/54 Interprogram communication

Abstract

A system and method for supporting collective communications on a plurality of processors that use different parallel programming paradigms, in one aspect, may comprise a schedule defining one or more tasks in a collective operation an executor that executes the task, a multisend module to perform one or more data transfer functions associated with the tasks, and a connection manager that controls one or more connections and identifies an available connection. The multisend module uses the available connection in performing the one or more data transfer functions. A plurality of processors that use different parallel programming paradigms can use a common implementation of the schedule module, the executor module, the connection manager and the multisend module via a language adaptor specific to a parallel programming paradigm implemented on a processor.

Claims

1. A system for supporting collective communications on a plurality of processors that use different parallel programming paradigms, comprising:

a schedule module operable to define one or more tasks in a collective operation;

an executor module operable to execute said one or more tasks;

a multisend module operable to perform one or more data transfer functions in said one or more tasks;

a connection manager operable to control one or more connections and identify an available connection,

the multisend module further operable to use the available connection in performing the one or more data transfer functions; and

a language adaptor operable to interface at least to the multisend module,

wherein a plurality of processors that use different parallel programming paradigms can use a common implementation of the schedule module, the executor module, the connection manager and the multisend module via the language adaptor specific to a parallel programming paradigm.

2. The system of claim 1, wherein the schedule module, the executor module, the connection manager and the multisend module are created on each processor of a multiple processor system, the multiple processor system being connected by a tree network.

3. The system of claim 1, wherein the schedule module, the executor module, the connection manager and the multisend module are created on each processor of a multiple processor system, the multiple processor system being connected by a torous network with deposit bit sends.

4. The system of claim 1, wherein the schedule module is operable to define one or more tasks in a collective operation per each phase of the collective operation.

5. The system of claim 1, wherein the executor module performs the one or more tasks using one or more optimizations.

6. The system of claim 5, wherein said one or more optimizations include pipelining, phase independence, or multi-color routes or combinations thereof.

7. The system of claim 1, wherein the multisend module performs data transfer using point-to-point communication.

8. The system of claim 1, wherein the multisend module is invoked for each phase of a collective operation.

9. The system of claim 1, wherein the executor module is created for each collective operation being performed.

10. A method of supporting collective communications on a plurality of processors that use different parallel programming paradigms, comprising:

receiving an application call invoking a collective operation from a processor via a language adaptor;

creating a schedule defining one or more tasks in a collective operation;

creating a executor for executing said one or more tasks; and

invoking a multisend operation to perform a communication tasks associated with said one or more tasks.

11. The method of claim 10, further including:

managing one or more connections among a plurality of processors; and

identifying an available connection to use in the multisend operation.

12. The method of claim 10, further including:

invoking a multisend operation for each phase of the collective operation.

13. The method of claim 10, further including:

performing one or more optimizations during executing said one or more tasks.

14. The method of claim 13, wherein said one or more optimizations include pipelining, phase independence, or multi-color routing, or combinations thereof.

15. The method of claim 10, wherein the plurality of processors is connected by a tree network.

16. The method of claim 10, wherein the plurality of processors is connected by a torus network with deposit bit sends.

17. A method of supporting collective communications on a plurality of processors that use different parallel programming paradigms, comprising:

receiving a plurality of application calls invoking a collective operation from a plurality of processors using different parallel programming language, each of the plurality of application calls being received via a language adaptor specific to a parallel programming language implemented in a processor;

for each of the plurality of application calls,

creating a schedule defining one or more tasks in a collective operation associated with an application call;

creating a executor for executing said one or more tasks; and

invoking a multisend operation to perform a communication tasks associated with said one or more tasks.

18. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a method of supporting collective communications on a plurality of processors that use different parallel programming paradigms, comprising:

receiving an application call invoking a collective operation from a processor via a language adaptor;

creating a schedule defining one or more tasks in a collective operation;

creating a executor for executing said one or more tasks; and

invoking a multisend operation to perform a communication tasks associated with said one or more tasks.

19. The program storage device of claim 18, further including:

managing one or more connections among a plurality of processors; and

identifying an available connection to use in the multisend operation.

20. The program storage device of claim 18, further including:

invoking a multisend operation for each phase of the collective operation.