Executing Multiple Instructions Multiple Data ('MIMD') Programs on a Single Instruction Multiple Data ('SIMD') Machine

• US 20080288747A1
• Filed: 05/18/2007
• Published: 11/20/2008
• Est. Priority Date: 05/18/2007
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Inglett, Todd A., Peters, Amanda, McCarthy, Patrick J.
• Granted Patent: US 7,814,295 B2
• Time in Patent Office: Days
• US Class Current: 712/20
• CPC Class Codes: G06F 9/5061 Partitioning or combining of resources

Abstract

Executing MIMD programs on a SIMD machine, including establishing SIMD partitions on the SIMD machine; booting SIMD partitions in MIMD mode; executing MIMD programs on the compute nodes of a first SIMD partition booted in MIMD mode; re-executing a launcher program by an operating system on a compute node in the first SIMD partition booted in MIMD mode upon termination of the MIMD program executed by the launcher program; determining by a scheduler that the first SIMD partition booted in MIMD mode is required to establish a new SIMD partition large enough to run a SIMD program that is scheduled for execution; moving by the scheduler data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode; and establishing by the scheduler the new SIMD partition.

Claims

1. A method of executing Multiple Instructions Multiple Data (‘

MIMD’

) programs on a Single Instruction Multiple Data (‘

SIMD’

) machine, the SIMD machine comprising a plurality of compute nodes, each compute node capable of executing only a single thread of execution, the compute nodes initially configured exclusively for SIMD operations, the SIMD machine further comprising a data communications network, the network comprising synchronous data communications links among the compute nodes, the network characterized by a network topology, the method comprising;

establishing on the SIMD machine a plurality of SIMD partitions, each SIMD partition comprising a plurality of the compute nodes, the compute nodes in each SIMD partition electronically isolated from compute nodes in other partitions of the SIMD machine and coupled to one another through links of the network for synchronous data communications for parallel SIMD operations among the compute nodes in each SIMD partition;

booting in MIMD mode a first SIMD partition and a second SIMD partition;

executing, by launcher programs on the compute nodes of the first SIMD partition booted in MIMD mode, a plurality of MIMD programs on two or more of the compute nodes of the first SIMD partition booted in MIMD mode, including replacing the launcher programs with the MIMD programs in process address space in computer memory of the two or more compute nodes, each MIMD program autonomously executing different instructions on different data;

re-executing a launcher program by an operating system on a compute node in the first SIMD partition booted in MIMD mode upon termination of the MIMD program executed by the launcher program;

determining by a scheduler that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a new SIMD partition large enough to run a SIMD program that is scheduled for execution;

moving by the scheduler data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode; and

establishing by the scheduler the new SIMD partition large enough to run the SIMD program that is scheduled for execution, the new SIMD partition including compute nodes from the first SIMD partition booted in MIMD mode.

2. The method of claim 1 wherein booting a SIMD partition in MIMD mode further comprises:

setting, in operating systems on the compute nodes of a SIMD partition booted in MIMD mode, flags indicating MIMD operation;

loading onto the compute nodes of the SIMD partition booted in MIMD mode a launcher program;

initializing with link training synchronous data communications among links of the network among compute nodes in the SIMD partition booted in MIMD mode;

initializing, with a parallel processing barrier, parallel operations among the compute nodes of the SIMD partition booted in MIMD mode, and

executing a launcher program on each compute node in the SIMD partition booted in MIMD mode.

3. The method of claim 1 wherein determining that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a SIMD partition large enough to run a SIMD program that is scheduled for execution further comprises determining that the SIMD partition running in MIMD mode is required to form a new SIMD partition comprising compute nodes connected through the network to each of the compute nodes in the new SIMD partition.

4. The method of claim 1 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises sending from the scheduler to an operating system on each compute node in the first SIMD partition booted in MIMD mode an instruction that immediately stops application program execution on the compute nodes of the first SIMD partition booted in MIMD mode.

5. The method of claim 1 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises draining the MIMD operations on the SIMD partition running in MIMD mode, including sending from the scheduler to an operating system on each compute node in the first SIMD partition running in MIMD mode an instruction to refrain from re-executing the launcher if a program other than the launcher is presently executing on the node and, if the launcher is presently executing on the node, to kill the launcher.

6. The method of claim 1 wherein the second SIMD partition booted in MIMD mode comprises at least as many compute nodes as the first SIMD partition booted in MIMD mode;

and moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises;

receiving in each compute node in the first SIMD partition booted in MIMD mode an instruction to migrate application program execution from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode;

suspending, by operating systems on each compute node in the first SIMD partition booted in MIMD mode, application program execution on each compute node in the SIMD partition booted in MIMD mode;

transferring the suspended application programs and current states of program execution for the suspended application programs to compute nodes in the second SIMD partition booted in MIMD mode; and

resuming, from the point where application program execution was suspended, application program execution on compute nodes in the second SIMD partition booted in MIMD mode.

7. Apparatus for executing Multiple Instructions Multiple Data (‘

MIMD’

) programs on a Single Instruction Multiple Data (‘

SIMD’

) machine, the SIMD machine comprising a plurality of compute nodes, each compute node capable of executing only a single thread of execution, the compute nodes initially configured exclusively for SIMD operations, the SIMD machine further comprising a data communications network, the network comprising synchronous data communications links among the compute nodes, the apparatus comprising a computer processor, a computer memory operatively coupled to the computer processor, the network characterized by a network topology, the computer memory having disposed within it computer program instructions capable of;

establishing on the SIMD machine a plurality of SIMD partitions, each SIMD partition comprising a plurality of the compute nodes, the compute nodes in each SIMD partition electronically isolated from compute nodes in other partitions of the SIMD machine and coupled to one another through links of the network for synchronous data communications for parallel SIMD operations among the compute nodes in each SIMD partition;

booting in MIMD mode a first SIMD partition and a second SIMD partition;

executing, by launcher programs on the compute nodes of the first SIMD partition booted in MIMD mode, a plurality of MIMD programs on two or more of the compute nodes of the first SIMD partition booted in MIMD mode, including replacing the launcher programs with the MIMD programs in process address space in computer memory of the two or more compute nodes, each MIMD program autonomously executing different instructions on different data;

re-executing a launcher program by an operating system on a compute node in the first SIMD partition booted in MIMD mode upon termination of the MIMD program executed by the launcher program;

determining by a scheduler that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a new SIMD partition large enough to run a SIMD program that is scheduled for execution;

moving by the scheduler data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode; and

establishing by the scheduler the new SIMD partition large enough to run the SIMD program that is scheduled for execution, the new SIMD partition including compute nodes from the first SIMD partition booted in MIMD mode.

8. The apparatus of claim 7 wherein booting a SIMD partition in MIMD mode further comprises:

setting, in operating systems on the compute nodes of a SIMD partition booted in MIMD mode, flags indicating MIMD operation;

loading onto the compute nodes of the SIMD partition booted in MIMD mode a launcher program;

initializing with link training synchronous data communications among links of the network among compute nodes in the SIMD partition booted in MIMD mode;

initializing, with a parallel processing barrier, parallel operations among the compute nodes of the SIMD partition booted in MIMD mode, and

executing a launcher program on each compute node in the SIMD partition booted in MIMD mode.

9. The apparatus of claim 7 wherein determining that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a SIMD partition large enough to run a SIMD program that is scheduled for execution further comprises determining that the SIMD partition running in MIMD mode is required to form a new SIMD partition comprising compute nodes connected through the network to each of the compute nodes in the new SIMD partition.

10. The apparatus of claim 7 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises sending from the scheduler to an operating system on each compute node in the first SIMD partition booted in MIMD mode an instruction that immediately stops application program execution on the compute nodes of the first SIMD partition booted in MIMD mode.

11. The apparatus of claim 7 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises draining the MIMD operations on the SIMD partition running in MIMD mode, including sending from the scheduler to an operating system on each compute node in the first SIMD partition running in MIMD mode an instruction to refrain from re-executing the launcher if a program other than the launcher is presently executing on the node and, if the launcher is presently executing on the node, to kill the launcher.

12. The apparatus of claim 7 wherein the second SIMD partition booted in MIMD mode comprises at least as many compute nodes as the first SIMD partition booted in MIMD mode, and moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises:

receiving in each compute node in the first SIMD partition booted in MIMD mode an instruction to migrate application program execution from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode;

suspending, by operating systems on each compute node in the first SIMD partition booted in MIMD mode, application program execution on each compute node in the SIMD partition booted in MIMD mode;

transferring the suspended application programs and current states of program execution for the suspended application programs to compute nodes in the second SIMD partition booted in MIMD mode; and

resuming, from the point where application program execution was suspended, application program execution on compute nodes in the second SIMD partition booted in MIMD mode.

13. A computer program product for executing Multiple Instructions Multiple Data (‘

MIMD’

) programs on a Single Instruction Multiple Data (‘

SIMD’

) machine, the SIMD machine including a plurality of compute nodes, each compute node capable of executing only a single thread of execution, the compute nodes initially configured exclusively for SIMD operations, the SIMD machine also including a data communications network, the network comprising synchronous data communications links among the compute nodes, the network characterized by a network topology, the computer program product disposed in a computer readable, signal bearing medium, the computer program product comprising computer program instructions capable of;

establishing on the SIMD machine a plurality of SIMD partitions, each SIMD partition comprising a plurality of the compute nodes, the compute nodes in each SIMD partition electronically isolated from compute nodes in other partitions of the SIMD machine and coupled to one another through links of the network for synchronous data communications for parallel SIMD operations among the compute nodes in each SIMD partition;

booting in MIMD mode a first SIMD partition and a second SIMD partition;

executing, by launcher programs on the compute nodes of the first SIMD partition booted in MIMD mode, a plurality of MIMD programs on two or more of the compute nodes of the first SIMD partition booted in MIMD mode, including replacing the launcher programs with the MIMD programs in process address space in computer memory of the two or more compute nodes, each MIMD program autonomously executing different instructions on different data;

re-executing a launcher program by an operating system on a compute node in the first SIMD partition booted in MIMD mode upon termination of the MIMD program executed by the launcher program;

determining by a scheduler that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a new SIMD partition large enough to run a SIMD program that is scheduled for execution;

moving by the scheduler data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode; and

establishing by the scheduler the new SIMD partition large enough to run the SIMD program that is scheduled for execution, the new SIMD partition including compute nodes from the first SIMD partition booted in MIMD mode.

14. The computer program product of claim 13 wherein the signal bearing medium comprises a recordable medium.

15. The computer program product of claim 13 wherein the signal bearing medium comprises a transmission medium.

16. The computer program product of claim 13 wherein booting a SIMD partition in MIMD mode further comprises:

setting, in operating systems on the compute nodes of a SIMD partition booted in MIMD mode, flags indicating MIMD operation;

loading onto the compute nodes of the SIMD partition booted in MIMD mode a launcher program;

initializing with link training synchronous data communications among links of the network among compute nodes in the SIMD partition booted in MIMD mode;

initializing, with a parallel processing barrier, parallel operations among the compute nodes of the SIMD partition booted in MIMD mode, and

executing a launcher program on each compute node in the SIMD partition booted in MIMD mode.

17. The computer program product of claim 13 wherein determining that the first SIMD partition booted in MIMD mode is required, according to the network topology, to establish a SIMD partition large enough to run a SIMD program that is scheduled for execution further comprises determining that the SIMD partition running in MIMD mode is required to form a new SIMD partition comprising compute nodes connected through the network to each of the compute nodes in the new SIMD partition.

18. The computer program product of claim 13 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises sending from the scheduler to an operating system on each compute node in the first SIMD partition booted in MIMD mode an instruction that immediately stops application program execution on the compute nodes of the first SIMD partition booted in MIMD mode.

19. The computer program product of claim 13 wherein moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises draining the MIMD operations on the SIMD partition running in MIMD mode, including sending from the scheduler to an operating system on each compute node in the first SIMD partition running in MIMD mode an instruction to refrain from re-executing the launcher if a program other than the launcher is presently executing on the node and, if the launcher is presently executing on the node, to kill the launcher.

20. The computer program product of claim 13 wherein the second SIMD partition booted in MIMD mode comprises at least as many compute nodes as the first SIMD partition booted in MIMD mode;

and moving data processing operations from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode further comprises;

receiving in each compute node in the first SIMD partition booted in MIMD mode an instruction to migrate application program execution from the first SIMD partition booted in MIMD mode to the second SIMD partition booted in MIMD mode;

suspending, by operating systems on each compute node in the first SIMD partition booted in MIMD mode, application program execution on each compute node in the SIMD partition booted in MIMD mode;

transferring the suspended application programs and current states of program execution for the suspended application programs to compute nodes in the second SIMD partition booted in MIMD mode; and

resuming, from the point where application program execution was suspended, application program execution on compute nodes in the second SIMD partition booted in MIMD mode.