METHOD AND APPARATUS FOR DISTRIBUTING COMPUTATION CLOSURES

• US 20120072917A1
• Filed: 05/16/2011
• Published: 03/22/2012
• Est. Priority Date: 07/16/2010
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Boldyrev, Sergey, Pyhälammi, Seppo Juhani, Mannermaa, Mika Juhani, Oliver, Ian Justin, Lassila, Ora, Dive-Reclus, Corinne
• Granted Patent: US 9,201,701 B2
• Time in Patent Office: Days
• US Class Current: 718/104
• CPC Class Codes: G06F 9/5066 Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs mappping at compile time, see G06F8/451
• CPC Class Codes: G06F 9/5072 Grid computing
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

An approach is provided for backend based computation closure oriented distributed computing. A computational processing support infrastructure receives a request for specifying one or more processes executing on a device for distribution over a computation space. The computational processing support infrastructure also causes, at least in part, serialization of the one or more processes as one or more closure primitives, the one or more closure primitives representing computation closures of the one or more processes. The computational processing support infrastructure further causes, at least in part, distribution of the one or more closure primitives over the computation space based, at least in part, on a cost function.

Claims

1. A method comprising:

receiving a request for specifying one or more processes executing on a device for distribution over a computation space;

causing, at least in part, serialization of the one or more processes as one or more closure primitives, the one or more closure primitives representing computation closures of the one or more processes; and

causing, at least in part, distribution of the one or more closure primitives over the computation space based, at least in part, on a cost function.

2. A method of claim 1, wherein the cost function is based, at least in part, on one or more resources of the device, the computation space, one or more other devices with access to the computation space, or a combination thereof.

3. A method of claim 2, wherein the one or more resources include power reserves, processing power, memory size, bandwidth, or a combination thereof.

4. A method of claim 2, further comprising:

causing, at least in part, optimization of the cost function with respect to scalability, load-balancing, or a combination thereof.

5. A method of claim 1, further comprising:

determining whether the device is a legacy device; and

causing, at least in part, wrapping of at least one of the one or more closure primitives with one or more legacy libraries based, at least in part, on the determination.

6. A method of claim 1, further comprising:

determining a time of execution of the one or more processes; and

causing, at least in part, tracing of the one or more processes, taking a snapshot of a current state of the one or more processes,

wherein the serialization of the one or more closure primitives is further based, at least in part, on the tracing, the snapshot, or a combination thereof.

7. A method of claim 1, further comprising:

determining a user context, an execution context, or a combination thereof associated with the one or more processes;

generating metadata based, at least in part, on the user context, the execution context, or a combination thereof; and

causing, at least in part, annotation of the one or more closure primitives with the metadata.

8. A method of claim 1, wherein the computation space comprises the device, one or more other devices, one or more servers, or a combination thereof, and wherein all or a portion of the one or more closures primitives are distributed to the device, the one or more other devices, the one or more servers, of a combination thereof for reconstruction.

9. A method of claim 1, further comprising:

retrieving one or more lambda expressions corresponding to the one or more processes, the one or more lambda expressions defining one or more anonymous functions corresponding to the one or more processes,

wherein the one or more closure primitives are based, at least in part, on the one or more lambda expressions.

10. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

receive a request for specifying one or more processes executing on a device for distribution over a computation space;

cause, at least in part, serialization of the one or more processes as one or more closure primitives, the one or more closure primitives representing computation closures of the one or more processes; and

cause, at least in part, distribution of the one or more closure primitives over the computation space based, at least in part, on a cost function.

11. An apparatus of claim 10, wherein the cost function is based, at least in part, on one or more resources of the device, the computation space, one or more other devices with access to the computation space, or a combination thereof.

12. An apparatus of claim 11, wherein the one or more resources include power reserves, processing power, memory size, bandwidth, or a combination thereof.

13. An apparatus of claim 11, wherein the apparatus is further caused to:

cause, at least in part, optimization of the cost function with respect to scalability, load-balancing, or a combination thereof.

14. An apparatus of claim 10, wherein the apparatus is further caused to:

determine whether the device is a legacy device; and

cause, at least in part, wrapping of at least one of the one or more closure primitives with one or more legacy libraries based, at least in part, on the determination.

15. An apparatus of claim 10, wherein the apparatus is further caused to:

determine a time of execution of the one or more processes; and

cause, at least in part, tracing of the one or more processes, taking a snapshot of a current state of the one or more processes,

wherein the serialization of the one or more closure primitives is further based, at least in part, on the tracing, the snapshot, or a combination thereof.

16. An apparatus of claim 10, wherein the apparatus is further caused to:

determine a user context, an execution context, or a combination thereof associated with the one or more processes;

generate metadata based, at least in part, on the user context, the execution context, or a combination thereof; and

cause, at least in part, annotation of the one or more closure primitives with the metadata.

17. An apparatus of claim 10, wherein the computation space comprises the device, one or more other devices, one or more servers, or a combination thereof, and wherein all or a portion of the one or more closures primitives are distributed to the device, the one or more other devices, the one or more servers, of a combination thereof for reconstruction.

18. An apparatus of claim 10, wherein the apparatus is further caused to:

retrieve one or more lambda expressions corresponding to the one or more processes, the one or more lambda expressions defining one or more anonymous functions corresponding to the one or more processes,

wherein the one or more closure primitives are based, at least in part, on the one or more lambda expressions.

19. A computer-readable storage medium carrying one or more sequences of one or more instructions which, when executed by one or more processors, cause an apparatus to at least perform the following steps:

receiving a request for specifying one or more processes executing on a device for distribution over a computation space;

causing, at least in part, serialization of the one or more processes as one or more closure primitives, the one or more closure primitives representing computation closures of the one or more processes; and

causing, at least in part, distribution of the one or more closure primitives over the computation space based, at least in part, on a cost function.

20. A computer-readable storage medium of claim 19, wherein the cost function is based, at least in part, on one or more resources of the device, the computation space, one or more other devices with access to the computation space, or a combination thereof.