Fencing data transfers in a parallel active messaging interface of a parallel computer

• US 9,047,150 B2
• Filed: 11/15/2012
• Issued: 06/02/2015
• Est. Priority Date: 11/05/2010
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Blocksome, Michael A., Mamidala, Amith R.
• Primary Examiner(s): Vu, Viet
• Assistant Examiner(s): BELCHER, HERMAN A
• Application Number:
  US13/677,507
• Publication Number:
  US 20130097614A1
• Time in Patent Office: 929 Days
• Field of Search: 709/201, 712/225
• US Class Current: 1/1
• CPC Class Codes: G06F 15/16 Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs coordinating program control therefor G06F9/52; in regulating and control system G05B
• CPC Class Codes: G06F 15/17331 Distributed shared memory [DSM], e.g. remote direct memory access [RDMA]
• CPC Class Codes: G06F 9/544 Buffers; Shared memory; Pipes
• CPC Class Codes: G06F 9/546 Message passing systems or structures, e.g. queues
• CPC Class Codes: H04L 67/133 Protocols for remote procedure calls [RPC]

Abstract

Fencing data transfers in a parallel active messaging interface (‘PAMI’) of a parallel computer, the PAMI including data communications endpoints, each endpoint including a specification of data communications parameters for a thread of execution on a compute node, including specifications of a client, a context, and a task; the compute nodes coupled for data communications through the PAMI and through data communications resources including at least one segment of shared random access memory; including initiating execution through the PAMI of an ordered sequence of active SEND instructions for SEND data transfers between two endpoints, effecting deterministic SEND data transfers through a segment of shared memory; and executing through the PAMI, with no FENCE accounting for SEND data transfers, an active FENCE instruction, the FENCE instruction completing execution only after completion of all SEND instructions initiated prior to execution of the FENCE instruction for SEND data transfers between the two endpoints.

Claims

1. A method for fencing data transfers in a parallel active messaging interface (‘

PAMI’

) of a parallel computer, the method comprising;

receiving, at an origin endpoint in the PAMI, a plurality of non-blocking SEND instructions from an application, wherein each of the plurality of SEND instruction specifies a data transfer from the origin endpoint to a target endpoint in the PAMI;

receiving, at an origin endpoint, a FENCE instruction corresponding to transfers between the origin endpoint and the target endpoint,

wherein the FENCE instruction advises the application when the transfers between the origin endpoint and the target endpoint are complete,

wherein the origin endpoint are on a same compute node, and

wherein the transfers between the origin endpoint and the target endpoint occur across a segment of memory shared between the origin endpoint and the target endpoint;

posting the plurality of SEND instruction in an ordered sequence in a work queue of the origin endpoint;

posting the FENCE instruction in the work queue of the origin endpoint at a location in the ordered sequence such that the FENCE instruction is processed after each of the plurality of SEND instructions is processed; and

executing, by the origin endpoint, an advance function comprising initiating execution through the PAMI of instructions in the work queue, such that the FENCE instruction executing only after completion of all SEND instructions initiated prior to the FENCE instruction in the work queue, wherein execution of the FENCE instruction, wherein execution of the FENCE instruction indicates to the application that execution of the SEND instructions is complete.

2. The method of claim 1 wherein:

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

the context comprises a subset of the collection of data processing resources, 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

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

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

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

5. The method of claim 1 wherein executing a FENCE instruction further comprises:

receiving in the origin endpoint the FENCE instruction, the FENCE instruction specifying a FENCE done callback function;

transmitting the FENCE instruction through the segment of shared memory from the origin endpoint to the target endpoint, the FENCE instruction specifying a dispatch callback function;

executing, after completion of all SEND data transfers previously initiated between the two endpoint, by the target endpoint the dispatch callback function for the FENCE instruction, including registering in PAMI a FENCE acknowledgment callback function;

executing by the target endpoint the FENCE acknowledgment callback function, including transmitting through the segment of shared memory from the target endpoint to the origin endpoint a FENCE acknowledgment message; and

executing by the origin endpoint the FENCE done callback function.

6. The method of claim 1 wherein executing a FENCE instruction further comprises:

receiving in the origin endpoint the FENCE instruction, the FENCE instruction specifying a FENCE done callback function;

transmitting, after completion of all SEND data transfers previously initiated between the two endpoints, the FENCE instruction through the segment of shared memory from the origin endpoint to the target endpoint, the FENCE instruction specifying a FENCE dispatch callback function;

executing by the PAMI in the target compute node the dispatch callback function for the FENCE instruction, including sending to the origin a FENCE synchronization message;

executing by the target endpoint the FENCE acknowledgment callback function, including transmitting through the segment of shared memory from the target endpoint to the origin endpoint a FENCE acknowledgment message; and

executing by the origin endpoint the FENCE done callback function.