JP2006092432A - Information processing device, method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To enable distributed processing considering a change in each equipment state or network environment. <P>SOLUTION: A distribution validity determination part 64-1 recognizes substantially current hardware conditions of own equipment 1 and peripheral equipment 2 and a substantially current software condition of an execution object from function information for a function of the execution object stored in a function storage part 61-1 and equipment information for the own equipment 1 and the peripheral equipment 2 stored in an equipment information storage part 62-1. The distribution validity determination part 64-1 determines the validity of distributed processing of the execution object by the own equipment 1 and the peripheral equipment 2 based on each of the recognized conditions, the substantially current zone of a communication infrastructure calculated by a distributed equipment retrieval part 63-1 and the like, and assigns each function element constituting the function to either the own equipment 1 or the peripheral equipment 2. The present invention is applicable to an information processing system for performing distributed processing by a plurality of information processors. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to an information processing apparatus, method, and program, and more particularly, to an information processing apparatus, method, and program capable of distributed processing in consideration of a change in the state of a distributed device and a change in a network environment.

  In recent years, grid computing has attracted attention. Grid computing is a technology that realizes high computing performance by cooperating a plurality of information processing devices connected to a network. This technique is disclosed in Patent Documents 1 to 5, for example.

By using this technique, distributed processing by a plurality of information processing apparatuses can be easily realized.
JP 2002-342165 A JP 2002-351850 A JP 2002-358289 A JP 2002-366533 A JP 2002-366534 A

  However, when distributed processing is executed by using conventional techniques such as Patent Documents 1 to 5 alone or in combination, the distance from the network of the execution environment without grasping the current state of the distributed device Regardless of the current state, the distributed device assumed to be operable is fixed and used as the execution target device.

  For this reason, depending on the current state of fixed distributed devices and the current network environment, the real-time performance of distributed processing may not be maintained, and in the worst case, it may become impossible to execute distributed processing. was there. In other words, there has conventionally been a problem that distributed processing that does not take into account state changes of distributed devices and changes in the network environment has been performed.

  The present invention has been made in view of such a situation, and makes it possible to perform distributed processing in consideration of a state change of a distributed device and a network environment change.

  The information processing apparatus of the present invention is an information processing apparatus that performs distributed processing of a predetermined function in cooperation with the peripheral device by performing communication with the peripheral device using a predetermined communication infrastructure. Specifically, the information processing apparatus according to the present invention is configured to execute a function composed of a plurality of functional elements as software, and the hardware conditions currently requested by the information processing apparatus itself and each peripheral device are substantially Based on the software conditions that the execution target is requesting at the present time and the current bandwidth of the communication infrastructure, the validity of the execution of the distributed processing of the execution target by the information processing device itself and the peripheral device is determined. If it is determined that the process is valid, the process of each of the plurality of functional elements constituting the execution target is allocated to either the information processing apparatus itself or the peripheral device, and the validity determination unit When it is determined that the execution target is not legitimate, the execution target is executed by itself. Among the functional elements, the first functional element assigned to the information processing apparatus itself by the validity judging means is executed by itself, and the second functional element assigned to the peripheral equipment by the validity judging means is used as the peripheral equipment. And a function execution means for executing the distributed processing to be executed by combining the execution results of the first function element and the second function element.

  Other information processing apparatuses that can communicate using a communication infrastructure, and that have at least one of a plurality of functional elements that constitute an execution target, and that can currently execute it The information processing apparatus is further provided with a search means for searching as a peripheral device, and the validity determination means determines the validity of the execution of the distributed processing to be executed by the information processing apparatus itself and the peripheral device searched by the search means. If it is determined that the function is legitimate, a function element that can be executed by the peripheral device substantially among the plurality of function elements constituting the execution target is assigned to the peripheral device as the second function element, and other functions The element can be assigned to the information processing apparatus itself as the first functional element.

  The information processing method of the present invention is an information processing method for an information processing apparatus that performs distributed processing of a predetermined function in cooperation with a peripheral device by communicating with the peripheral device using a predetermined communication infrastructure. Specifically, the information processing method according to the present invention has a hardware condition that each of the information processing apparatus itself and the peripheral device requests substantially at the present time, with a function composed of a plurality of functional elements as software being executed. Based on the software conditions that the execution target is currently requesting and the current bandwidth of the communication infrastructure, the validity of the distributed processing executed by the information processing device itself and peripheral devices is judged. If it is determined that there is a legitimacy, the processing of each of the plurality of functional elements constituting the execution target is assigned to either the information processing apparatus itself or the peripheral device, and the legitimacy judgment step When it is determined that the processing is not legitimate, the information processing apparatus itself is controlled to execute the execution target, and the legitimacy judging unit judges that the legitimacy is not legitimate. In this case, control is performed to cause the information processing apparatus itself to execute the first functional element allocated to the information processing apparatus itself by the process of the validity determination step among the plurality of functional elements constituting the execution target. Execute by controlling the peripheral device to execute the second functional element allocated to the peripheral device by the processing of the determination step, and by combining the execution results of the first functional element and the second functional element And a function execution control step for controlling the execution of the target distributed processing.

  The program of the present invention is a computer that controls a peripheral device and a main device that performs a distributed operation of a predetermined function in cooperation with the peripheral device by communicating with the peripheral device using a predetermined communication infrastructure. It is a program to be executed. Specifically, the program according to the present invention has a function composed of a plurality of functional elements as software as execution targets, and the hardware conditions and execution targets requested by the main device and peripheral devices are almost the same at present. Based on the software conditions requested at the present time and the current bandwidth of the communication infrastructure, the validity of the execution of the distributed processing of the execution target by the main device and the peripheral device is judged and valid. If it is determined that there is no legitimacy due to the legitimacy determination step of allocating the processing of each of the plurality of functional elements constituting the execution target to either the main device or the peripheral device and the legitimacy determination step If it is determined, control is performed to cause the execution target to be executed by the main device, and if the validity determination means determines that the execution target is not valid, a plurality of functional elements constituting the execution target are required. The second functional element assigned to the peripheral device by the process of the legitimacy determination step is performed to control the main apparatus to execute the first functional element allocated to the main apparatus by the legitimacy judgment step process. A function execution control step for controlling the execution of the distributed processing to be executed by combining the execution results of the first functional element and the second functional element. It is characterized by that.

  In the information processing apparatus, method, and program according to the present invention, communication with a peripheral device is performed using a predetermined communication infrastructure, whereby distributed processing of a predetermined function is executed in cooperation with the peripheral device. Specifically, a function composed of a plurality of functional elements as software is targeted for execution, and the information processing device itself or the main device itself (hereinafter, only the information processing device is described, each of the peripheral devices is substantially Based on the requested hardware conditions, the software conditions that the execution target is requesting at the present time, and the approximate current bandwidth of the communication infrastructure, the distributed processing of the execution targets by the information processing device itself and peripheral devices When it is determined that there is no validity, the execution target is executed by the information processing apparatus itself. Based on the current hardware and software conditions and the current bandwidth of the communication infrastructure, the processing of each of the plurality of functional elements constituting the execution target is The first functional element allocated to one of the information processing apparatus itself and the peripheral device, the first functional element allocated to the information processing apparatus itself is executed by the information processing apparatus itself, and the second functional element allocated to the peripheral apparatus is The execution processing is executed by the peripheral device, and the execution results of the first functional element and the second functional element are combined to execute the distributed processing to be executed.

  As described above, according to the present invention, it is possible to perform distributed processing of a predetermined function. In particular, distributed processing can be performed in consideration of changes in the state of distributed devices and changes in the network environment.

  Embodiments of the present invention will be described below. Correspondences between constituent elements described in the claims and specific examples in the embodiments of the present invention are exemplified as follows. This description is to confirm that specific examples supporting the invention described in the claims are described in the embodiments of the invention. Therefore, even though there are specific examples that are described in the embodiment of the invention but are not described here as corresponding to the configuration requirements, the specific examples are not included in the configuration. It does not mean that it does not correspond to a requirement. On the contrary, even if a specific example is described here as corresponding to a configuration requirement, this means that the specific example does not correspond to a configuration requirement other than the configuration requirement. not.

  Further, this description does not mean that all the inventions corresponding to the specific examples described in the embodiments of the invention are described in the claims. In other words, this description is an invention corresponding to the specific example described in the embodiment of the invention, and the existence of an invention not described in the claims of this application, that is, in the future, a divisional application will be made. Nor does it deny the existence of an invention added by amendment.

  According to the present invention, an information processing apparatus is provided. This information processing apparatus (for example, the information processing apparatuses 1 and 2 in FIG. 1) uses a predetermined communication infrastructure (for example, a communication infrastructure including the network 3 in FIG. 1) and a peripheral device (for example, the information processing apparatus in FIG. 1). 1 is the information processing device 2, and the information processing device 2 is the information processing device 1 when paying attention to the information processing device 2. An information processing apparatus that performs distributed processing of a predetermined function. Specifically, this information processing apparatus has a function composed of a plurality of functional elements as software (for example, a function P composed of functional elements A, B, C, and D in FIG. , E, F function Q), the hardware conditions that the information processing device itself and the peripheral device are requesting at the present time, and the execution target is requested at the present time. Software conditions (for example, these hardware conditions and software conditions include the device information of the information processing device 1 in FIG. 11, the device information of the information processing device 2 in FIG. 12, and the function information of the function Q in FIG. And at least one descriptive value of each item is available), and the current bandwidth of the communication infrastructure (for example, the calculated value in step S4 of FIG. 4, for a specific example of the calculation method) To be described later Based on the information processing apparatus itself and the peripheral device to determine the validity of the execution of the distributed processing of the execution target, and if it is determined that there is a validity, a plurality of the functions constituting the execution target Validity determination means for allocating each process of the element to either the information processing apparatus itself or the peripheral device (for example, the distribution of FIG. 2 provided in the information processing controller 11-1 or 11-2 in FIG. 1) When the validity judgment unit 64-1 or 64-2) and the legitimacy judging means judge that the legitimacy is not legitimate, the execution target is executed by itself, and the legitimacy judging means has legitimacy. If it is determined that the first functional element allocated to the information processing apparatus itself by the legitimacy determining means among the plurality of functional elements constituting the execution target is executed by itself. And executing control of causing the peripheral device to execute the second functional element allocated to the peripheral device by the validity determining unit, and executing each of the first functional element and the second functional element. By combining the results, function execution means for executing the distributed processing to be executed (for example, the distributed function execution unit 65-1 or 65 in FIG. 2 provided in the information processing controller 11-1 or 11-2 in FIG. 1). -2).

  The information processing apparatus (for example, the information processing apparatus 2 in FIGS. 1 and 2) includes a plurality of information processing apparatuses that can communicate with each other using the communication infrastructure. Other information processing apparatuses that have at least one of the functional elements and are capable of executing it at present (for example, among the functional elements A, D, E, and F included in the function Q in FIG. 3) Retrieval means (for example, the distributed device of FIG. 2 provided in the information processing controller 11-1 or 11-2 of FIG. 1) for retrieving the information processing apparatus 1 having the function P including the functional elements A and D as the peripheral device The search unit 63-1 or 63-2) is further provided, and the validity determination unit is configured to verify whether the information processing apparatus itself and the peripheral device searched by the search unit execute the distributed processing to be executed. Judging sex and being legitimate If it is determined, among the plurality of functional elements constituting the execution target, a functional element that is substantially executable by the peripheral device is assigned to the peripheral device as the second functional element, and other functional elements are assigned. Assigned to the information processing apparatus itself as the first functional element (for example, as shown in FIG. 14, functional elements A, D of functional elements A, D, E, and F included in function Q are information It can be assigned to the processing device (peripheral device) 1 and the functional elements E and F are assigned to the information processing device 2 itself).

  According to the present invention, an information processing method is provided. This information processing method uses a predetermined communication infrastructure (for example, a communication infrastructure including the network 3 of FIG. 1) and peripheral devices (for example, the information processing device 2 when paying attention to the information processing device 1 of FIG. 1). The information processing apparatus (which is the information processing apparatus 1 when paying attention to the information processing apparatus 2) performs cooperative processing with the peripheral device and executes distributed processing of a predetermined function by communicating with the information processing apparatus 2 For example, the information processing method of the information processing apparatus 1 or 2) of FIG. More specifically, this information processing method has a hardware condition that each of the information processing apparatus itself and the peripheral device requests substantially at the present time, with a function composed of a plurality of functional elements as software being executed. , Execution of the distributed processing of the execution target by the information processing apparatus itself and the peripheral device based on the software condition that the execution target is requesting at the present time and the current current bandwidth of the communication infrastructure. If it is determined that there is a legitimacy, the processing of each of the plurality of functional elements constituting the execution target is legitimately assigned to either the information processing apparatus itself or the peripheral device. There is no legitimacy due to the sex judging step (for example, the processing after step S7 in the “distributed preparation processing” of FIG. 4) and the legitimacy judging step. If it is determined that the information processing apparatus itself executes the execution target, and if the validity determination unit determines that the execution target is valid, the plurality of functional elements constituting the execution target Among them, the information processing apparatus itself is controlled to execute the first functional element allocated to the information processing apparatus itself by the process of the legitimacy determination step, and the peripheral device is controlled by the process of the legitimacy determination step. The distributed processing of the execution target is performed by controlling the peripheral device to execute the allocated second functional element, and combining the execution results of the first functional element and the second functional element. And a function execution control step (for example, “function execution processing by the execution source” in FIGS. 6 and 7).

  According to the present invention, a program is provided. This program is a program corresponding to the information processing method of the present invention described above, and is executed by a computer such as the information processing controllers 11-1 and 11-2 in FIG. The main device referred to in the program of the present invention corresponds to the information processing device referred to in the information processing method of the present invention described above.

  Furthermore, according to the present invention, of course, a recording medium on which the above-described program of the present invention is recorded is also provided.

  Next, embodiments of the present invention will be described with reference to the drawings.

  FIG. 1 shows a configuration example of an information processing system to which the present invention is applied. In other words, FIG. 1 shows an information processing system composed of N information processing devices to which the present invention is applied (N is an arbitrary integer value of 1 or more, but 2 in the example of FIG. 1). The example of a structure is shown.

  As shown in FIG. 1, this information processing system is configured by connecting information processing apparatuses 1 and 2 to each other via a predetermined network 3.

  Hereinafter, a hardware configuration example of the information processing apparatuses 1 and 2 will be described. First, a hardware configuration example of the information processing apparatus 1 will be described.

  The information processing device 1 is configured to include an information processing controller 11-1, a network interface 12-1, a main memory 13-1, a storage device 14-1, and a drive 15-1.

  The information processing controller 11-1 executes various programs stored in the main memory 13-1 and the storage device 14-1, and controls the entire information processing device 1.

  The information processing controller 11-1 includes a main process unit (MPU) 21-1 and sub-process units (SPUs) 31-1 to 33-1 via a bus 51-1. Are connected to each other.

  A dedicated memory 22-1 is connected to the MPU 21-1. Therefore, the MPU 21-1 can temporarily store data and programs loaded from the main memory 13-1 and the like in the memory 22-1. The MPU 21-1 can read out data and programs from the memory 22-1, and can execute various processes based on the data and programs.

  For example, the MPU 21-1 can execute various processes for performing schedule management of program execution by the SPUs 31-1 to 33-1 and managing the entire information processing controller 11-1 (information processing apparatus 1). .

  Further, for example, the MPU 21-1 can execute various processes for managing other information processing apparatuses that execute distributed processes. The other information processing apparatus mentioned here corresponds to the information processing apparatus 2 in the example of FIG.

  Thus, it can be said that the MPU 21-1 is configured to execute a management program. However, the MPU 21-1 can be configured to execute a program other than the management program. In this case, the MPU 21-1 functions as an SPU.

  Each of the SPUs 31-1 to 33-1 processes data by executing programs in parallel and independently based on the control of the MPU 21-1. Furthermore, if necessary, the program executed by the MPU 21-1 can be configured to operate in cooperation with each of the programs executed by the SPUs 31-1 to 33-1.

  Dedicated memories 41-1 to 43-1 are connected to the SPUs 31-1 to 33-1 respectively. Accordingly, each of the SPUs 31-1 to 33-1 can temporarily store data and programs in the memories 41-1 to 43-1 dedicated to the SPU 31-1 to 33-1 as necessary. Each of the SPUs 31-1 to 33-1 can read data and programs from the memories 41-1 to 43-1 dedicated to the SPUs 31-1 to 33-1 and execute various processes based on the data and programs. it can.

  As described above, in the example of FIG. 1, the information processing apparatus 1 is provided with three SPUs 31-1 to 33-1. However, as a matter of course, the number of SPUs is not limited to the example of FIG. 1 and may be any number.

  The information processing controller 11-1 having such a configuration is connected to the network interface 12-1, the main memory 13-1, the storage device 14-1, and the drive 15-1. More precisely, in the example of FIG. 1, the network interface 12-1 and the main memory 13-1 are connected to the MPU 21-1 of the information processing controller 11-1, and a storage device is connected to the bus 51-1. 14-1 and the drive 15-1 are connected.

  The network interface 12-1 is configured by, for example, a modem, a terminal adapter, a wireless communication device, and the like. The network interface 12-1 having such a configuration controls communication with other information processing apparatuses via the network 3. The other information processing apparatus mentioned here corresponds to the information processing apparatus 2 in the example of FIG.

  The main memory 13-1 is composed of, for example, a RAM (Random Access Memory). The main memory 13-1 stores various programs executed by at least one of the MPU 21-1 and the SPUs 31-1 to 33-1 and various data used or generated when executing these various programs. Stored as appropriate.

  The storage device 14-1 is configured by one or more external storage devices such as a flash memory and a hard disk drive, for example. That is, the storage device 14-1 is often composed of a plurality of external storage devices. The storage device 14-1 stores various programs executed by at least one of the MPU 21-1 and the SPUs 31-1 to 33-1, and various data used or generated when executing these various programs. Stored as appropriate. Further, the storage device 14-1 appropriately stores other data such as data supplied from the information processing controller 11-1.

  The drive 15-1 is connected to the bus 51-1 as necessary. A removable recording medium 16-1 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately attached to the drive 15-1, and a computer program read therefrom is stored in the storage device 14 as necessary. -1 and the main memory 13-1.

  The configuration example of the information processing apparatus 1 has been described above.

  The information processing apparatus 2 has basically the same configuration as the information processing apparatus 1 described above. That is, each block of the information processing apparatus 2 shown in FIG. 1 corresponds to a block of the information processing apparatus 1 having the same code before the hyphen “−”. For example, the information processing controller 11-2 of the information processing device 2 corresponds to the information processing controller 11-1 of the information processing device 1. Thus, since the information processing apparatus 2 has basically the same configuration as the information processing apparatus 1, it is naturally possible to perform basically the same operation (processing) as the information processing apparatus 1.

  Further, each of the information processing apparatuses 1 and 2 is not limited to the above-described configuration, and various functions can be added or deleted as necessary, and configurations corresponding to the various functions ( Each block).

  Furthermore, in the example of FIG. 1, two information processing apparatuses 1 and 2 are connected to the network 3, but the number of information processing apparatuses connected to the network 3 is not limited to the example of FIG. Any number can be used. In this case, other information processing apparatuses (not shown) connected to the network 3 preferably have basically the same configuration as the information processing apparatuses 1 and 2, but have other configurations. Of course.

  The information processing system including the information processing apparatuses 1 and 2 having the configuration shown in FIG. 1 can realize the grid computing described above. That is, for example, the information processing apparatuses 1 and 2 can perform distributed processing that realizes a predetermined function by performing a cooperative operation by performing communication with each other using a communication infrastructure including the network 3. In this case, each of the information processing apparatuses 1 and 2 can have a functional configuration as shown in FIG. That is, FIG. 2 shows a functional configuration example of an information processing system including the information processing apparatuses 1 and 2.

  Hereinafter, functional configuration examples of the information processing apparatuses 1 and 2 will be described. First, a functional configuration example of the information processing apparatus 1 will be described.

  The main memory 13-1 is provided with a function storage unit 61-1 and a device information storage unit 62-1.

  The function storage unit 61-1 stores one or more function programs.

  The function program refers to a program for realizing a function provided to the user. For example, as the function program, there are a program for realizing a video / audio recording / playback function and a program for realizing a search function for searching predetermined video data from recorded video data. This function program is mainly executed by at least one of the SPUs 31-1 to 33-1.

  The function storage unit 61-1 further stores information (hereinafter referred to as function information) including the identification ID and version of each function program, software conditions required by each function program, and the like.

  Hereinafter, the function program is simply referred to as a function. A specific example of the function stored in the function storage unit 61-1 will be described later with reference to FIG. 3, and a specific example of the function information will be described later with reference to FIG.

  The device information storage unit 62-1 stores information (hereinafter referred to as device information) indicating the characteristics, performance, current state, etc. of the information processing apparatus 1 itself. The substantially current state includes functions that can be executed substantially now. That is, a specific example will be described later with reference to FIG. 11, but the device information of the information processing apparatus 1 mainly includes hardware conditions requested by the information processing apparatus 1, and may be omitted if necessary. Other information such as software conditions required by the currently executable function is also included.

  Furthermore, the device information storage unit 62-1 may store device information of other information processing apparatuses as necessary. That is, although details will be described later, in the example of FIG. 2, the device information of the information processing apparatus 2 may also be stored in the device information storage unit 62-1.

  Each of the function storage unit 61-1 and the device information storage unit 62-1 is provided in the main memory 13-1 in the example of FIG. 1, but may be stored in the storage device 14-1 or the like as necessary. It may be provided. In this case, the function storage unit 61-1 and the device information storage unit 62-1 do not need to be paired. That is, for example, one of the function storage unit 61-1 and the device information storage unit 62-1 may be provided in the main memory 13-1, and the other may be provided in the storage device 14-1.

  The information processing controller 11-1 is provided with a distributed device searching unit 63-1 to a device information providing unit 66-1.

  More precisely, for example, each of the distributed device searching unit 63-1 to the device information providing unit 66-1 is configured as software and stored in the main memory 13-1 or the storage device 14-1. Therefore, the information processing controller 11-1 loads and executes each of the distributed device searching unit 63-1 to the device information providing unit 66-1 from the main memory 13-1 or the storage device 14-1 as necessary. .

  The processors that execute the distributed device search unit 63-1 to the device information providing unit 66-1 except the distributed function execution unit 65-1 are mainly the MPU 21-1, but are the SPUs 31-1 to 33-1. Alternatively, any number of arbitrary combinations of the MPU 21-1 and the SPUs 31-1 to 33-1 may be used.

  Similarly, the processor that executes the distributed function execution unit 65-1 is mainly one or more of the SPUs 31-1 to 33-1, but may be the MPU 21-1 or the MPU 21-1. And any number of arbitrary combinations of SPUs 31-1 to 33-1 may be used. For example, when a predetermined function is distributedly processed by the information processing apparatuses 1 and 2, one or more of the SPUs 31-1 to 33-1 is a part (described later) assigned to the information processing apparatus 1. And the MPU 21-1 performs control for causing the information processing apparatus 2 to execute the portion assigned to the information processing apparatus 2 and manages the entire distributed processing. Alternatively, the distributed function execution unit 65-1 may be executed.

  When a predetermined function stored in the function storage unit 61-1 is executed, the distributed device search unit 63-1 searches for peripheral devices that are candidates for the distributed device of the function. Note that the distributed device here refers to a device that bears distributed processing of the function. Further, the peripheral device referred to here refers to an information processing apparatus other than the information processing apparatus 1 itself among the information processing apparatuses connected to the network 3. Therefore, for example, in the example of FIGS. 1 and 2, the information processing apparatus 2 is searched as a peripheral device by the distributed device search unit 63-1.

  Therefore, in the following description, the information processing device 1 will be referred to as the own device 1 and the information processing device 2 will be referred to as the peripheral device 2 when the description is made with focus on the information processing device 1. On the other hand, when the description is given focusing on the information processing device 2, the information processing device 2 is referred to as the own device 2, and the information processing device 1 is referred to as the peripheral device 1.

  At this time, the distributed device search unit 63-1 acquires the device information of the peripheral device 2 and stores it in the device information storage unit 62-1.

  In addition, the distributed device search unit 63-1 calculates a substantially current band (substantially current communication speed) of the communication infrastructure between the own device 1 and the peripheral device 2.

  Furthermore, if necessary, the distributed device search unit 63-1 has at least a part of the execution target function (a functional element described later) in the searched peripheral device and can execute it almost now. It is determined whether or not the current state is correct. The executable state refers to a state in which at least a part of a function to be executed is loaded in a memory-mapped program executable area. For example, in the example of FIG. 1, the memory-executable program executable area refers to at least a part of the memory 22-1, the memories 41-1 to 43-1 and the like.

  Then, the distributed device search unit 63-1 provides the above-described various processing results to the distributed validity determination unit 64-1.

  Note that the distributed device search unit 63-1 does not particularly perform the above-described processes when no peripheral device connected to the network 3 can be searched, that is, when no peripheral device is connected to the network 3. At that time, the processing result that “the peripheral device does not exist” is provided to the distributed validity judgment unit 64-1.

  When the processing result of the distributed device search unit 63-1 is provided, the distributed validity judgment unit 64-1 is valid for executing the distributed processing of the function to be executed by the own device 1 and the peripheral device 2. Judging. In other words, the distributed validity determining unit 64-1 determines whether or not it is appropriate to execute the distributed processing of the function to be executed between the own device 1 and the peripheral device 2. At this time, the distributed legitimacy determination unit 64-1 uses the processing result of the distributed device search unit 63-1, for example, the approximately current bandwidth of the communication infrastructure calculated by the distributed device search unit 63-1, as the determination material. Can be used. Further, the distributed validity judgment unit 64-1 can also use the device information of the own device 1 itself and the peripheral device 2 stored in the device information storage unit 62-1, as the judgment material. .

  When the distributed validity determining unit 64-1 determines that there is no validity in performing the distributed processing of the function to be executed between the own device 1 and the peripheral device 2, that is, the function to be executed only by the own device 1. Is determined to be executed, or when the execution itself is determined not to be performed, the determination result is notified to the distributed function execution unit 65-1.

  On the other hand, when the distributed validity determining unit 64-1 determines that the distributed processing of the function to be executed between the own device 1 and the peripheral device 2 is valid, the distributed device 1 and the peripheral device Allocate functions for each of the two. In other words, the distributed validity judgment unit 64-1 determines which part of the function is to be handled by the own device 1 and which part is to be handled by the peripheral device 2. At this time, the distributed legitimacy determining unit 64-1 stores the device information of the own device 1 itself and the peripheral device 2 stored in the device information storage unit 62-1, and the distributed device search unit 63-1. The substantially current bandwidth of the provided communication infrastructure can be used as necessary for determining the allocation.

  Specifically, for example, although details will be described later with reference to FIG. 3, the function stored in the function storage unit 61-1 may be modularized. That is, the function may be configured by a plurality of modules. In such a case, the distributed legitimacy determination unit 64-1 determines which module of the functions is to be handled by the own device 1 and which module is to be handled by the peripheral device 2. To do. Hereinafter, each of the modules constituting the function is referred to as a functional element.

  In this case, “the peripheral device 2 has at least one of the functional elements constituting the function to be executed and can execute it substantially now” means that the distributed device search unit 63-1. Is recognized and notified to the distributed legitimacy determination unit 64-1, the distributed legitimacy determination unit 64-1 uses the peripheral device 2 when allocating each functional element constituting the function to be executed. Functional elements that can be executed substantially now can be assigned to the peripheral device 2, and other functional elements can be assigned to the own device 1.

  In summary, the distributed validity judgment unit 64-1 is stored in the function information on the function to be executed stored in the function storage unit 61-1, and in the device information storage unit 62-1. From the respective device information of the own device 1 and the peripheral device 2, the hardware conditions requested by the own device 1 and the peripheral device 2 and the software requested by the function to be executed are substantially requested. Recognize wear conditions. In addition to these substantially current hardware conditions and software conditions, the distributed legitimacy determination unit 64-1 automatically determines based on the substantially current bandwidth of the communication infrastructure notified from the distributed device search unit 63-1. It is determined whether or not the device 1 and the peripheral device 2 cooperate to perform the distributed processing to be executed.

  If the division validity determining unit 64-1 determines that there is a validity, the division validity determining unit 64-1 appropriately uses these substantially current hardware conditions and software conditions, the bandwidth of the communication infrastructure, and the like. Each functional element to be configured is allocated to one of the own device 1 and the peripheral device 2. At this time, if necessary, the distributed validity judgment unit 64-1 can allocate functional elements that can be substantially executed by the peripheral device 2 to the peripheral device 2, and can allocate other functional elements to the own device 1.

  Thereafter, the division validity determining unit 64-1 notifies the distributed function execution unit 65-1 of the processing result.

  Upon receiving this notification, the distributed function execution unit 65-1 executes a function to be executed among the functions stored in the function storage unit 61-1.

  Specifically, for example, when the information indicating that “the function to be executed is executed only by the own device 1” is notified as the processing result from the distributed validity determining unit 64-1, the distributed function executing unit 65-1 All the functions to be executed are loaded from the function storage unit 61-1 and executed.

  On the other hand, for example, each of the first information with the content “perform distributed processing of the function to be executed between the own device 1 and the peripheral device 2” and “each functional element constituting the function to be executed” When the second information indicating the “allocation result” is notified from the distributed validity determining unit 64-1 as the processing result, the distributed function executing unit 65-1 performs the function to be executed based on the second information. Among the functional elements constituting the device, the first functional element allocated to the own device 1 is loaded from the function storage unit 61, and the execution request of the second functional element allocated to the peripheral device 2 is peripheral. Issue to device 2. Upon receiving this execution request, the peripheral device 2 executes the second functional element and transmits the execution result to the own device 1. The distributed function execution unit 65-1 executes the first functional element, acquires the execution result of the second functional element from the peripheral device 2, and executes the execution result of the first functional element and the second functional element. Is combined with the execution result of. In this way, distributed processing of the function to be executed is performed between the own device 1 and the peripheral device 2.

  In summary, when the distributed validity determining unit 64-1 of the own device 1 determines that the execution of the distributed processing of the function to be executed is not valid, the distributed device searching unit 63-1 performs the execution. Run the target yourself. On the other hand, the distributed device search unit 63-1, when the distributed validity determination unit 64-1 determines that the execution of the distributed processing of the function to be executed is valid, a plurality of items constituting the execution target Among the functional elements, the first functional element allocated to the own device 1 itself by the distributed validity determining unit 64-1 is executed by itself, and allocated to the peripheral device 2 by the distributed validity determining unit 64-1. The second functional element is controlled to be executed by the peripheral device 2, and the execution target is executed by synthesizing the execution results of the first functional element and the second functional element.

  By the way, the distributed function execution unit 65-2 on the peripheral device 2 side corresponding to the distributed function execution unit 65-1 sends an execution request to the own device 1 from among functional elements constituting a predetermined function. Of course, it may be issued. In such a case, the distributed function execution unit 65-1 of the own device 1 loads and executes the functional element that has received the execution request from the function storage unit 61-1, and transmits the execution result to the peripheral device 2. At this time, the distributed function execution unit 65-1 also transmits other information to the peripheral device 2 as necessary. As will be described in detail later, when the execution request is received, the function element requested for execution is often loaded. In such a case, the distributed function execution unit 65-1 performs the function. It is possible to execute the element immediately.

  When the device information providing unit 66-1 receives a device information acquisition request from the distributed device search unit 63-2 on the peripheral device 2 side corresponding to the above-described distributed device search unit 63-1, the device information storage unit 62- 1 acquires the device information of its own device 1 from 1 and transmits (provides) it to the peripheral device 2.

In other words, when the distributed device search unit 63-1 of the own device 1 acquires the device information of the peripheral device 2 as described above, it issues a request for acquiring the device information of the peripheral device 2 to the peripheral device 2. .
Then, the device information providing unit 66-2 of the peripheral device 2 acquires the device information of the peripheral device 2 from the device information storage unit 62-2 and transmits it to the own device 1. Therefore, the distributed device search unit 63-1 of the own device 1 receives the device information of the peripheral device 2 and stores it in the device information storage unit 62-1.

  The device information acquisition request may be transmitted to the peripheral device 2, or may be transmitted as a broadcast signal. Although details will be described later, in the latter case, the distributed device search unit 63-1 can recognize (search) the peripheral device specified by the device information by receiving the device information. That is, in the latter case, it is possible to search for peripheral devices and acquire the device information at once.

  As described above, the information processing controller 11-1 in the example of FIG. 2 is provided with functional blocks such as the four distributed device search units 63-1 to the device information providing unit 66-1. That is, in the example of FIG. 2, it can be said that the processing units of the information processing controller 11-1 are the four distributed device search units 63-1 to the device information providing unit 66-1. However, as a matter of course, the processing unit of the information processing controller 11-1 is not limited to the example of FIG. 2 and may be an arbitrary unit. That is, it is sufficient for the information processing controller 11-1 to be able to comprehensively execute all the processes corresponding to each of the above-described distributed device search unit 63-1 to device information providing unit 66-1, and the processing unit. Is not particularly limited. Therefore, for example, it is possible to divide or integrate the distributed device search unit 63-1 to the device information providing unit 66-1 into functional blocks that perform an arbitrary number of arbitrary processes.

  Heretofore, the functional configuration example of the information processing apparatus 1 has been described.

  The information processing apparatus 2 also has basically the same functional configuration as the information processing apparatus 1 described above. That is, each of the functional blocks of the information processing apparatus 2 illustrated in FIG. 2 corresponds to the functional block of the information processing apparatus 1 having the same reference sign before the hyphen “-”. For example, the distributed legitimacy determining unit 64-2 and the distributed function executing unit 65-2 of the information processing apparatus 2 are respectively connected to the distributed legitimacy determining unit 64-1 and the distributed function executing unit 65-1 of the information processing apparatus 1. Corresponding to each of the. As described above, the information processing apparatus 2 has basically the same functional configuration as the information processing apparatus 1, and therefore can perform basically the same operation (processing) as the information processing apparatus 1.

  Furthermore, as described above, the number of information processing apparatuses connected to the network 3 is not limited to the example of FIG. 1 and may be an arbitrary number. In this case, the other information processing apparatus (not shown) connected to the network 3 preferably has basically the same functional configuration as the information processing apparatuses 1 and 2, but the other functional configuration Of course, you may have. However, when the information processing apparatus 1 or 2 uses another information processing apparatus (not shown) as a distributed device, that is, when the other information processing apparatus (not shown) bears distributed processing, it is not shown. The other information processing apparatus needs to have software or hardware corresponding to each of the device information providing units 66-1 and 66-2 and the distributed function executing units 65-1 and 65-2.

  Next, with reference to FIG. 3 and subsequent drawings, details of the distributed processing of a predetermined function executed by the information processing apparatuses 1 and 2 having such a functional configuration will be described.

  In the following description, when at least a part of a predetermined function is executed based on the determination of the own device, rather than an execution request from a peripheral device, the own device is referred to as an execution source own device (information processing apparatus). In this case, as described later, the execution source device may issue an execution request of at least a part of the function to the peripheral device. In such a case, the peripheral device is referred to as a requested peripheral device (information processing apparatus).

  As described above, the information processing apparatuses 1 and 2 exist in an environment where mutual dispersion is possible. Further, each of the information processing apparatuses 1 and 2 can exchange information on functions (programs) or data being executed or held. Examples of the functions exchanged with each other include a program group such as an image processing codec. Moreover, as information exchanged, user preference information etc. correspond to the information necessary for the function, for example. The degree of abstraction (granularity and hierarchy) of these functions and data varies depending on the load / execution architecture in the information processing system and the substantially current bandwidth (approximately the current communication speed) of the communication infrastructure in the information processing system. The load / execution architecture refers to hardware conditions required by the information processing apparatuses 1 and 2, software conditions required by functions, and the like.

  Further, as described above, the information processing apparatuses 1 and 2 can load and execute a program in a memory-mapped program executable area. For example, in the example of FIG. 1, the information processing devices 1 and 2 are storage devices 14-1 and 14-2 made up of NAND Flash memory or the like used as a large capacity program storage area, or main memories 13-1 and 13. -2 can be loaded into an executable memory area of one or more predetermined processors and executed. In the example of FIG. 1, the processor here refers to at least one of the MPU 21-1 and the SPUs 31-1 to 33-1 and the MPU 21-2 and the SPUs 31-2 to 33-2. Therefore, the executable memory area referred to here is the memory 22-1 and the memories 41-1 to 43-1 and the memory 22-2 and the memories 41-2 to 43-2 in the example of FIG. Refers to at least one region. The main memories 13-1 and 13-2 are handled as program storage areas in the present embodiment, but can be handled as executable memory areas as necessary.

  The information processing apparatuses 1 and 2 as described above are assumed to have functions P and Q as shown in FIG. That is, as shown in FIG. 3, the function P is stored in the function storage unit 61-1 of the information processing apparatus 1, and when there is an instruction to execute the function P, the information processing controller 11-1 Suppose that function P can be loaded and executed. Similarly, the function storage unit 61-2 of the information processing apparatus 2 stores the function Q. When there is an instruction to execute the function Q, the function Q is loaded and executed by the information processing controller 11-2. Suppose that it can be done.

  Furthermore, it is assumed that function information including an identification ID and version of the function P, various software conditions required by the function P, and the like is stored in the function storage unit 61-1 in association with the function P. Similarly, it is assumed that function information including the identification ID and version of the function Q, various software conditions required by the function Q, and the like is stored in the function storage unit 61-2 in association with the function Q. A specific example of the function information will be described later with reference to FIG.

  The function P is composed of four functional elements A, B, C, D and data x, y.

  It is assumed that each of the functional elements A, B, C, and D is a unit that has few common data to be changed at the same time, maintains high independence, and can be distributed. Furthermore, it is simplified here, and each of the functional elements A, B, C, and D has no common data and is a completely independent component group.

  It is assumed that data x indicates data necessary for executing the function P. Data y represents the result obtained by executing function P.

  The function Q is assumed to be composed of functional elements A, D, E, and F and data x and w.

  It is assumed that each of the functional elements A, D, E, and F is a unit that has few common data to be changed at the same time, maintains high independence, and can be distributed. Furthermore, it is simplified here, and each of the functional elements A, D, E, and F has no common data and is a completely independent component group.

  It is assumed that data x indicates data necessary for executing the function Q. The data w represents the result obtained by executing the function Q.

  What should be noted here is that the functional elements A and D and the data x are common components that exist in both the functions P and Q. These common components are assumed to have the same program performance in the information processing apparatuses 1 and 2. Program performance refers to execution speed, real-time performance, quality, and the like.

  Hereinafter, in a state in which the functions P and Q shown in FIG. 3 are not loaded, the information processing apparatus 1 first executes the function P, and then the information processing apparatuses 1 and 2 operate cooperatively to function Q. Suppose that distributed processing is executed.

  In this case, the information processing system including the information processing apparatuses 1 and 2 executes processing according to the flowcharts illustrated in FIGS. 4 to 8, for example.

  That is, the flowchart of FIG. 4 shows an example of pre-processing, that is, preparation processing when the execution source device executes a function to be executed. That is, the flowchart of FIG. 4 determines the processing mode of the function to be executed, such as whether the function is executed only by the own device, or whether the function is executed by distributed processing between the own device and the peripheral device, An example of processing executed by the execution source device such as allocating each functional element constituting the function when it is determined that the function is executed in the distributed processing is shown. Hereinafter, such processing in FIG. 4 is referred to as “distributed preparation processing”.

  The flowchart of FIG. 5 is a process executed on the peripheral device side when the execution source device executes the “distribution preparation process” of FIG. That is, the flowchart of FIG. 5 is a process executed by the peripheral device in order to provide the peripheral device information of the information necessary for the “distributed preparation process” of FIG. 4 from the peripheral device to the execution source device. An example is shown. Hereinafter, such processing in FIG. 5 is referred to as “device information transmission processing”.

  The flowcharts of FIGS. 6 and 7 are processes executed after the execution of the “distributed preparation process” in FIG. That is, the flowcharts of FIGS. 6 and 7 show an example of processing in which the own device itself executes a predetermined function, or the own device cooperates with the peripheral device to execute distributed processing of the predetermined function. ing. Hereinafter, such processing in FIGS. 6 and 7 is referred to as “function execution processing by the execution source”.

  The flowchart in FIG. 8 is a process executed by the peripheral device when the execution source device executes the “function execution process by the execution source” in FIGS. 6 and 7 (particularly FIG. 7). That is, the flowchart of FIG. 8 illustrates an example of processing executed by the peripheral device such as executing a functional element requested by the execution source among the functional elements constituting the function to be executed. Hereinafter, such processing in FIG. 8 is referred to as “function execution processing by the request destination”.

  In this case, as described above, the information processing apparatus 1 first executes the function P in a state where the functions P and Q shown in FIG. 3 are not loaded. Therefore, first, the information processing apparatus 1 executes the “distributed preparation process” of FIG. 4 as the execution source device. Accordingly, the information processing apparatus 2 executes the “device information transmission process” in FIG. 5 as a peripheral device. Thereafter, the information processing apparatus 1 executes “function execution processing by the execution source” of FIGS. 6 and 7 (particularly FIG. 6).

  The mutual relationship between the processes of the information processing apparatuses 1 and 2 when the information processing apparatus 1 first executes the function P is shown in the arrow chart of FIG. Therefore, the processing of the information processing apparatuses 1 and 2 when the information processing apparatus 1 first executes the function P with reference mainly to the flowcharts of FIGS. 4, 5 and 6 and the arrow chart of FIG. 9. explain.

  First, in step S <b> 1, the distributed device search unit 63-1 in FIG. 2 of the information processing apparatus 1 searches for peripheral devices connected to the network 3.

  Specifically, for example, in step S1, the distributed device search unit 63-1 transmits a broadcast signal to the network 3 using a communication infrastructure defined by Ethernet (registered trademark), IEEE802.11, Bluetooth, or the like. . That is, the distributed device search unit 63-1 tries to connect at the physical layer. Then, after the connection, the distributed device search unit 63-1 connects the link layer and the application layer, and finally issues a command (corresponding to the above-described device information acquisition request) for receiving device information. And wait for a reply.

  During this time, the device information providing unit 66-2 of the information processing device 2 determines whether or not a search has been received from the peripheral device in step S21.

  In the “apparatus information transmission process” in FIG. 5, the information processing apparatus 2 that executes it is naturally the own apparatus, and the information processing apparatus 1 that executes the “distributed preparation process” in FIG. 4 is the other apparatus. However, the description has been given focusing on the information processing apparatus 1 that is the execution source, and here, the description will be made as described in the drawing, that is, the peripheral device and the own device will be reversed. Yes, it will be confusing. Therefore, within the scope of explaining the “apparatus information transmission process” in FIG. 5, explanations will be made without using names such as the own apparatus and peripheral equipment.

  Unless a broadcast signal is received, it is determined in step S21 that the search has not been received, the process returns to step S21, and it is determined again whether the search has been received. That is, in this case, since only two information processing apparatuses 1 and 2 are connected to the network 3, the determination process in step S21 is repeated until a broadcast signal is received from the information processing apparatus 1.

  Therefore, when the broadcast signal transmitted from the information processing apparatus 1 in step S1 is received by the network interface 12-2 of the information processing apparatus 2, the device information providing unit 66-2 of the information processing apparatus 2 is received in step S21. Acquires it, determines that a search has been received from the information processing apparatus 1, and advances the process to step S22.

  In step S22, the device information providing unit 66-2 of the information processing device 2 acquires the device information of the information processing device 2 itself from the device information storage unit 62-2, and the network interface 12- 2 and network 3.

  During this time, in step S2, the distributed device search unit 63-1 of the information processing apparatus 1 determines whether there is a peripheral device.

  If the reply to the broadcast signal, that is, the device information of the peripheral device is not transmitted at all even if the predetermined time has elapsed, it is determined in step S2 that the peripheral device does not exist, and “distributed preparation process” is performed. Ends. In this case, if the function to be executed can be executed by the own device 1 alone, the function is executed only by the own device 1. That is, although details will be described later, when the process of step S11 is completed and the “distributed preparation process” is completed, the function to be executed is executed by the distributed process of the own device and the peripheral device. On the other hand, when the “distributed preparation process” is terminated for other reasons such as NO in the process of step S2, the function is executed only by the own device, or The function is not performed.

  On the other hand, in this case, since the device information of the peripheral device 2 is transmitted in the process of step S22 as described above, the network interface 12-1 of the information processing apparatus 1 stores the device information of the peripheral device 2. Will receive.

  Then, the distributed device search unit 63-1 of the information processing device 1 determines in step S2 that the peripheral device 2 exists, acquires device information of the peripheral device 2 in step S3, and acquires a device information storage unit 61-. 1 is stored.

  A specific example of the device information will be described later with reference to FIGS.

  In step S <b> 4, the distributed device search unit 63-1 of the information processing device 1 calculates a substantially current band (substantially current communication speed) of the communication infrastructure between the own device 1 and the peripheral device 2.

  Note that the substantially current bandwidth of this communication infrastructure is used in the process of step S9 described later. However, in this case, that is, when the information processing apparatus 1 executes the function P for the first time, the process of step S9 is not executed. Therefore, a calculation method of the substantially current bandwidth of the communication infrastructure will be described later.

  In step S5, the distributed device search unit 63-1 of the information processing device 1 determines whether or not the function having the same identification ID as the identification ID of the function P owned by the own device 1 is already loaded in the peripheral device 2. To do.

  That is, in the process of step S5 (including step S6 to be described later precisely), the peripheral device 2 has at least one of the functional elements A, B, C, and D that constitute the function P to be executed. In addition, it is determined whether or not it is in a state where it can be executed at present.

  In this case, since the function Q is not yet loaded in the peripheral device 2, the function having the same identification ID as the identification ID of the function P possessed by the own device 1 is not already loaded in the peripheral device 2 in step S5. Is determined, and the “distribution preparation process” ends. Also in this case, as described above, the function to be executed is executed only by the own device or not. That is, in this case, as will be described later, the function P is executed only by the information processing apparatus 1.

  Of the matters related to the determination process of step S5 when the information processing apparatus 1 executes the function P for the first time, the description of matters other than the determination of NO in the determination process of step S5 This is omitted here and will be described later. The matters other than being determined as NO in the determination process in step S5 include, for example, the function identification ID, further details of the determination process in step S5, and YES in the determination process in step S5. It refers to matters such as the subsequent processing when it is done.

  The distributed device search unit 63-1 of the information processing device 1 determines that the determination in step S5 is NO, that is, the distribution validity determination that the function P should be executed only by the own device 1. When the distributed function execution unit 65-1 is notified via the unit 64-1, the “distributed preparation process” is terminated.

  More precisely, when receiving the notification from the distributed device search unit 63-1, the distributed validity determining unit 64-1 determines whether or not the function P can be executed by the own device 1 alone, and executes it. Only when it is determined that it is possible, the distributed function execution unit 65-1 is notified that the function P should be executed only by the own device 1. That is, when the distributed validity determining unit 64-1 determines that execution is impossible, the function P is not executed, and a predetermined error process is executed.

  However, here, the distributed legitimacy determination unit 64-1 determines that it can be executed, and notifies the distributed function execution unit 65-1 that the function P should be executed only by its own device 1. Then. In this case, upon receiving this notification, the distributed function execution unit 65-1 of the information processing apparatus 1 starts the “function execution process by the execution source” in FIG.

  That is, in step S <b> 41, the distributed function execution unit 65-1 of the information processing apparatus 1 determines whether or not to perform distributed execution with the peripheral device 2.

  In this case, since it has been determined that the determination in step S5 is NO, that is, the function P should be executed only by the own device 1 from the distributed validity judgment unit 64-1, If the result of S41 is NO, the process proceeds to step S42.

  As described above, when the information processing apparatus 1 executes the function P for the first time, it is determined as NO in the determination process of step S41. Therefore, it is determined as YES in the determination process of step S41. The subsequent processing at that time is omitted here and will be described later.

  In step S42, the distributed function execution unit 65-1 of the information processing apparatus 1 loads all the components A, B, C, and D included in the function P from the function storage unit 61-1.

  In step S43, the distributed function execution unit 65-1 of the information processing apparatus 1 loads all the data x and y included in the function P from the function storage unit 61-1.

  In step S44, the distributed function execution unit 65-1 of the information processing apparatus 1 executes the function P. That is, the distributed function execution unit 65-1 executes the function P by executing each of the constituent elements A, B, C, and D using the data x and y as appropriate.

  When the execution of the function P is completed, the “function execution process by the execution source” of FIG. 6 for the function P by the information processing apparatus 1 is also ended. Here, the information processing apparatus 1 is executing the function P. Now, it is assumed that the information processing apparatus 2 starts processing for executing the function Q.

  Hereinafter, processing of the information processing apparatuses 1 and 2 when the information processing apparatus 2 executes the function Q while the information processing apparatus 1 is executing the function P (more accurately, in a state where the function P can be executed) ( Hereinafter, the processing for function Q) will be described.

  In order to realize the function Q processing, the information processing apparatus 2 executes the “distributed preparation processing” in FIG. 4 as the execution source device. Accordingly, the information processing apparatus 1 executes the “device information transmission process” in FIG. 5 as a peripheral device. Next, the information processing apparatus 2 executes “function execution processing by the execution source” of FIGS. 6 and 7 (particularly FIG. 7). Accordingly, the information processing apparatus 1 executes “function execution processing by the request destination” in FIG.

  The mutual relationship of such processing for function Q is shown in the arrow chart of FIG. The function Q process will be described below mainly with reference to the flowcharts of FIGS. 4 to 8 and the arrow chart of FIG.

  First, in step S <b> 1, the distributed device search unit 63-2 in FIG. 2 of the information processing apparatus 2 searches for peripheral devices connected to the network 3. That is, as described above, the distributed device search unit 63-2 transmits a broadcast signal to the network 3.

  During this time, the device information providing unit 66-1 of the information processing apparatus 1 determines whether or not a search has been received from the peripheral device in step S21.

  As described above, in the “apparatus information transmission process” in FIG. 5, naturally, the information processing apparatus 1 that executes the information processing apparatus becomes its own apparatus, and the information processing apparatus 2 that executes the “distributed preparation process” in FIG. It becomes other equipment. However, as described above, within the scope of explaining the “apparatus information transmission process” in FIG.

  When the broadcast signal transmitted from the information processing device 2 in step S1 is received by the network interface 12-1 of the information processing device 1, the device information providing unit 66-1 acquires it in step S21. Thus, it is determined that a search has been received from the information processing apparatus 2, and the process proceeds to step S22.

  In step S22, the device information providing unit 66-1 of the information processing device 1 acquires the device information of the information processing device 1 itself from the device information storage unit 62-1, and the network interface 12- 1 and the network 3.

  During this time, in step S2, the distributed device search unit 63-2 of the information processing device 2 determines whether there is a peripheral device.

  If the reply to the broadcast signal, that is, the device information of the peripheral device is not transmitted at all even if the predetermined time has elapsed, it is determined in step S2 that the peripheral device does not exist, and “distributed preparation process” is performed. Ends. In this case, as described above, the function Q is executed only by the own device 2 or not.

  On the other hand, in this case, since the device information of the peripheral device 1 is transmitted in the process of step S22 as described above, the network interface 12-2 of the information processing device 2 stores the device information of the peripheral device 1. Will receive.

  Then, the distributed device search unit 63-2 of the information processing device 2 determines in step S2 that the peripheral device 1 exists, acquires device information of the peripheral device 1 in step S3, and acquires a device information storage unit 62- 2 is memorized.

  Specifically, for example, assume that the device information shown in FIG. 11 is acquired as device information of the peripheral device 1 and stored in the device information storage unit 62-2.

  At this time, for example, it is assumed that the device information shown in FIG. 12 is also stored in the device information storage unit 62-2 as the device information of the device 2 itself.

  That is, FIG. 11 and FIG. 12 show examples of device information of the information processing apparatuses 1 and 2, respectively.

  As shown in FIGS. 11 and 12, the device information includes “CPU”, “memory”, “operating frequency”, “processor usage rate”, “processor usage rate predicted value”, “free memory”, “OFF” Items such as “Schedule” and “Holding program identification ID: version” are provided.

  In “CPU”, information on the MPU and the SPU is described. For example, as shown in “Content”, “CPU” describes a number, a version, a vendor, and a MIPS (Million Instructions Per Second) value in that order.

  Specifically, for example, “2”, “0.53 / 0.53”, and “sany” .500 are described in the “CPU” of the device information of the information processing apparatus 1 in the example of FIG. Thereby, the information processing apparatus 1 is provided with “2” processors, each version is “0.53 / 0.53”, the vendor is “sany”, and the MIPS value is 500. Recognize. On the other hand, “1”, “0.53 / 0.53”, and “sany” .300 are described in the “CPU” of the device information of the information processing apparatus 2 in the example of FIG. As a result, the information processing apparatus 2 is provided with “1” processors, the version is “0.53 / 0.53”, the vendor is “sany”, and the MIPS value is 300. .

  In the example of FIG. 1, the information processing apparatus 1 is provided with a total of four processors of one MPU 21-1 and three SPUs 31-1 to 33-1. As the number of “CPU” in the device information of the information processing apparatus 1, “4” is described. However, as described above, the number of SPUs is not particularly limited to the example of FIG. Therefore, within the scope of the description of the function Q process, the information processing apparatus 1 includes two processors, that is, one MPU 21-1 and one SCPU 31-1, in addition to the description of the device information in FIG. Suppose that it is provided.

  Similarly, in the example of FIG. 1, the information processing apparatus 2 is provided with a total of four processors of one MPU 21-2 and three SPUs 31-2 to 33-2, and is combined with the example of FIG. 1. Then, “4” is described as the number of “CPUs” in the device information of the information processing apparatus 2. However, as described above, the number of SPUs is not particularly limited to the example of FIG. Therefore, within the scope of the description of the function Q processing, it is assumed that only one processor, that is, one MPU 21-2 is provided in the information processing apparatus 2 in addition to the description of the device information in FIG. .

  In the “memory”, as shown in “content”, the total size of the memory having the program executable area is described. Specifically, for example, “1024 Mbit” is described in the “memory” of the device information of the information processing apparatus 1 in the example of FIG. As a result, it is understood that the total size of the dedicated memory 22-1 for the MPU 21-1 and the dedicated memory 41-1 for the SPU 31-1 of the information processing apparatus 1 is “1024 Mbit”. On the other hand, “256 Mbit” is described in the “memory” of the device information of the information processing apparatus 2 in the example of FIG. Thereby, it can be seen that the size of the dedicated memory 22-2 for the MPU 21-2 of the information processing apparatus 2 is “256 Mbit”.

  The “operation frequency” describes the operation clock of the processor by the number of processors. Note that the value in the normal state is described for the dynamically changing clock. Specifically, for example, “2G / 2 GHz” is described in the “operating frequency” of the device information of the information processing apparatus 1 in the example of FIG. Thereby, in the information processing apparatus 1, it can be seen that the operation clock of the MPU 21-1 is “2 GHz” and the operation clock of the SPU 31-1 is “2 GHz”. On the other hand, “500 MHz” is described in the “operating frequency” of the device information of the information processing apparatus 2 in the example of FIG. Thereby, it can be seen that the operation clock of the MPU 21-2 of the information processing apparatus 2 is “500 MHz”.

  In the “processor usage rate”, approximately the current usage rate [%] of the processor is described by the number of processors. Specifically, for example, “30% / 30%” is described in the “processor usage rate” of the device information of the information processing apparatus 1 in the example of FIG. As a result, in the information processing apparatus 1, it can be seen that the substantially current usage rate of the MPU 21-1 is "30%" and the substantially current usage rate of the SPU 31-1 is "30%". On the other hand, “90%” is described in the “processor utilization” of the device information of the information processing apparatus 2 in the example of FIG. Thereby, it can be seen that the substantially current usage rate of the MPU 21-2 of the information processing apparatus 2 is "90%".

  The “processor usage rate prediction value” describes the processor usage rate [%] expected in advance after a predetermined time [min] has elapsed when a processor schedule is set. Specifically, for example, “5 min: 20% / 10%; 10 min: 10% / 5%” is described in the “processor utilization rate prediction value” of the device information of the information processing apparatus 1 in the example of FIG. Yes. As a result, the utilization rate of the MPU 21-1 of the information processing apparatus 1 is approximately “30%” at present, but decreases to “20%” after “5 min” and further decreases to “10%” after “10 min”. It can be seen that is predicted. In addition, the utilization rate of the SPU 31-1 of the information processing apparatus 1 is currently “30%”, but after “5 min” it may drop to “10%”, and after “10 min” it may drop to “5%”. You can see that it is predicted. On the other hand, “5 min: 90%; 10 min: 90%” is described in the “processor utilization rate prediction value” of the device information of the information processing apparatus 2 in the example of FIG. Accordingly, it can be seen that the utilization rate of the MPU 21-2 of the information processing apparatus 2 is predicted to be maintained at “90%” both after “5 min” and further after “10 min”.

  “Free memory” describes the total available free size among the sizes described in the “memory” described above. Specifically, for example, “800 Mbit” is described in “free memory” of the device information of the information processing apparatus 1 in the example of FIG. Thereby, the total free size of the dedicated memory 22-1 for the MPU 21-1 and the dedicated memory 41-1 for the SPU 31-1 of the information processing apparatus 1, that is, the usable size is “800 Mbit”. Recognize. On the other hand, “100 Mbit” is described in “free memory” of the device information of the information processing apparatus 2 in the example of FIG. Thereby, it can be seen that the free size of the dedicated memory 22-2 for the MPU 21-2 of the information processing apparatus 2, that is, the usable size is “100 Mbit”.

  In “OFF schedule”, as shown in “contents”, information indicating that a power supply OFF is scheduled is described. Note that nothing is described in the “OFF schedule” of the device information of the information processing apparatus 1 in the example of FIG. 11 and the “OFF schedule” of the device information of the information processing apparatus 2 of the example of FIG. Since it is None), it can be seen that neither the information processing apparatus 1 or 2 is particularly scheduled to be turned off.

  “Holding program identification ID: version” describes the identification ID and version (version) of the function (program) held by the device itself.

  The function held by the device itself may refer to the function loaded in the program executable area, or the function stored in the program storage area regardless of whether the program is loaded into the program executable area. Sometimes it points. In the present embodiment, for example, it is assumed that the former is adopted.

  The identification ID refers to a unique value uniquely assigned to each function. A predetermined function can be identified by this identification ID. However, when only a predetermined part of functional elements and data constituting a function having a predetermined identification ID is updated, the identification ID remains unchanged and only the version may be changed. For example, in the example of FIG. 3, it is assumed that “uniqidxx” is assigned to each of the functions P and Q as an identification ID. However, among the functional elements A, B, C, and D of the function P, each of the functional elements B and C is updated to, for example, each of the functional elements D and E (accordingly, the data y is updated to the data w). Suppose that the result is function Q. In this case, different versions are assigned to identify each of the functions P and Q. For example, if “1.1a” is attached to the function P as a version, “1.1b” is attached to the function Q as a version.

  The identification ID and version are obtained from function information associated with each function. Details of the function information will be described later with reference to FIG.

  Specifically, for example, “uniqidxx: 1.1a / uniqidyy: 1.4” is described in “holding program identification ID: version” of the device information of the information processing apparatus 1 in the example of FIG. As a result, either the dedicated memory 22-1 for the MPU 21-1 or the dedicated memory 41-1 for the SPU 31-1 of the information processing apparatus 1 has the identification ID “uniqidxx” and the version is It can be seen that the function P which is “1.1a” is loaded. Also, in either one of the dedicated memory 22-1 for the MPU 21-1 and the dedicated memory 41-1 for the SPU 31-1 of the information processing apparatus 1, the identification ID is “uniqidyy” and the version is “ It can be seen that the functions not shown in FIG.

  Further, for example, “uniqidxx: 1.1b / uniqidyy: 1.6” is described in “holding program identification ID: version” of the device information of the information processing apparatus 2 in the example of FIG. Thereby, it can be seen that the function Q having the identification ID “uniqidxx” and the version “1.1b” is loaded in the dedicated memory 22-2 for the MPU 21-2 of the information processing apparatus 1. Further, the dedicated memory 22-2 for the MPU 21-2 of the information processing apparatus 2 is loaded with a function not shown in FIG. 3 whose identification ID is “uniqidyy” and whose version is “1.6”. I understand.

  In this case, that is, when the function Q process is executed, the information processing apparatus 2 has not yet loaded the function Q at the time of the process of step S3 in FIG. 4 and FIG. “Uniqidxx: 1.1b” is not described in “Holding program identification ID: version” of the device information 2.

  When the device information of the information processing apparatus 1 among the device information is acquired in the process of step S3 in FIGS. 4 and 10, the process proceeds to step S4.

  In step S <b> 4, the distributed device search unit 63-2 in FIG. 2 of the information processing device 2 calculates a substantially current band (substantially current communication speed) of the communication infrastructure between the own device 2 and the peripheral device 1.

  For example, in step S 4, the distributed device search unit 63-2 determines the current communication based on the communication time until a predetermined amount of data (device information of the peripheral device 1) is returned from the peripheral device 1. Calculate the speed. Specifically, for example, when the communication time (excluding the time until connection) of data having a data amount of 1024 kbit is 500 msec, 2048 (= 1024/500) kbps is calculated as the substantially current communication speed.

  In step S <b> 5, the distributed device search unit 63-2 of the information processing apparatus 2 determines whether or not the function having the same identification ID as the identification ID of the function owned by the own device 2 is already loaded in the peripheral device 1. .

  For example, in this case, the possessed function of the device 2 is the function Q stored in the function storage unit 61-2. The identification ID of the function Q is “uniqidxx” as described above, and can be obtained from “function Q function information” stored in the function storage unit 61-2. Specifically, for example, “function Q function information” as shown in FIG. 13 is stored in the function storage unit 61-2, and the function Q identification ID can be acquired from this “function Q function information”. It is. That is, FIG. 13 shows an example of “function Q function information”. This “function Q function information” includes an item “identification ID”, and “uniqidxx” is described as the function Q identification ID in this “identification ID”. The other items of “function Q function information” will be described later.

  Further, as described above, the identification ID of the function P loaded in the peripheral device 1 at this time is “uniqidxx”, and the identification ID of the function P is obtained by the process of FIG. Device information of peripheral device 1 ”.

  Therefore, the distributed device search unit 63-1 compares the “function Q function information” stored in the own device 2 with the “device information of the peripheral device 1”, and both “uniqidxx” are described. If this is recognized, it is determined as YES in the process of step S5, and the process proceeds to step S6.

  If there is no identification ID common to the “function Q function information” and the “device information of the peripheral device 1” held in the own device 2, it is determined as NO in the process of step S5. Thus, the “distributed preparation process” is completed. In this case, as described above, the function Q is executed only by the information processing apparatus 2 or not.

  In step S <b> 6, the distributed device search unit 63-2 of the information processing device 2 determines whether the functions of the self device 2 and the peripheral device 1 have compatibility (compatibility).

  Here, for example, in the two functions, if at least one common functional element exists, it is assumed that the two functions have compatibility. In addition, a method for determining whether or not a common functional element exists is not particularly limited. For example, it is possible to adopt a determination method in which an identification ID is assigned in units of functional elements, and it is determined whether or not there is a functional element with a matching identification ID. However, here, for simplification of description, for example, it is assumed that a determination method is adopted in which it is determined whether or not a common functional element exists by comparing versions of two functions.

  In this case, the version of the function Q is “1.1b” as described above. For example, as shown in FIGS. 3 and 14, “function Q function information” stored in the function storage unit 61-2. Can be obtained from That is, as shown in FIG. 13, “function Q function information” includes an item “version”, and “version” includes “1.1b” as the version of function Q. Yes. The other items of “function Q function information” will be described later.

  Further, as described above, the version of the function P is “1.1a”, and the version of the function P is described in “apparatus information of the peripheral device 1” of FIG. 11 acquired in the process of step S3. .

  It is assumed that the function P of the version “1.1a” and the function Q of the version “1.1b” are compatible, and this is known to the information processing apparatus 2 itself.

  In this case, the distributed device search unit 63-2 of the information processing apparatus 2 compares the “function Q function information” stored in the own device 2 with the acquired “device information of the peripheral device 1”. As a result, it is determined in step S6 that the function “P” of version “1.1a” and the function “Q” of version “1.1b” have compatibility.

  Note that if the function P of the version “1.1a” and the function Q of the version “1.1b” are not compatible (not compatible), it is determined as NO in the process of step S6, The “distributed preparation process” ends. In this case, as described above, the function Q is executed only by the information processing apparatus 2 or not.

  As described above, the distributed device search unit 63-2 of the information processing device 2 executes the processes in steps S1 to S6, and thus, among the peripheral devices that can perform communication using the communication infrastructure including the network 3. To search for the peripheral device 1 as “a peripheral device that has at least one of the functional elements A, D, E, and F constituting the function Q to be executed and can execute it at present”. The approximate current bandwidth of the communication infrastructure is calculated.

  If it is determined as YES in the process of step S6, the process result of steps S1 to S6, that is, “having at least one of functional elements A, D, E, and F constituting the function Q to be executed” is held. In addition, the peripheral device that can currently execute it is the information processing apparatus 1, and “substantially current bandwidth of the communication infrastructure between the own device 2 and the peripheral device 1 ( "Substantially current communication speed)" is supplied from the distributed device search unit 63-2 to the distributed validity judgment unit 64-2. Thereby, a process progresses to step S7.

  In step S7, the distribution validity determining unit 64-2 of the information processing apparatus 2 determines whether or not the memory space of the self device 2 is sufficient.

  That the memory free capacity is sufficient means that the description size of “free memory” in “device information of own device 2” in FIG. 12 is a size necessary for executing the function Q.

  The size required to execute the function Q is the sum of the program size when the function Q is expanded in the memory and the memory size of the heap and stack required for program execution. It can be obtained from “Function Q Function Information”. That is, in the item “program size” of “function Q function information” in FIG. 13, the program size when the function Q is expanded in the memory is described. For example, in the example of FIG. 13, “100 Mbit” is described in “program size”. In the “memory size” item, the memory size of the heap and stack necessary for program execution is described. For example, in the example of FIG. 13, “500 Mbit / 100 Mbit” is described. The other items of “function Q function information” will be described later.

  Therefore, in step S7, the distribution validity judgment unit 64-2 of the information processing apparatus 2 performs the description value “100Mbit” of “program size” of “function Q function information” and the description value “500Mbit / 100Mbit” of “memory size”. Based on ", the size required to realize the function Q is calculated to be 700 (= 100 + 500 + 100) Mbit. Then, the distributed validity judgment unit 64-2 obtains 700 Mbit which is a size necessary for realizing the function Q and “100 Mbit” which is a description value of “free memory” of “device information of the own device 2”. As a result of the comparison, it is determined that there is not enough memory capacity of the device 2 and the process proceeds to step S8.

  In other words, if the memory capacity of the own device 2 does not exist sufficiently, distributed processing with the peripheral device 1 is required to execute the function Q. That is, if it is determined as NO in the process of step S7, the process for determining the validity of the distributed process needs to be further continued. Therefore, if it is determined NO in step S7, the process proceeds to step S8.

  In other words, if the description value of “free memory” of “device information of own device 2” exceeds “700 Mbit”, distributed processing is not particularly essential for executing function Q. It is determined as YES in the process of step S7, and the “distribution preparation process” ends. In this case, as described above, the function Q is executed only by the information processing apparatus 2.

  Note that the distributed processing of the function Q cannot be performed unless there is sufficient memory space on the peripheral device 1 side. Therefore, although not shown in FIG. 4, in reality, the distributed validity judgment unit 64-2 has sufficient memory free space for the peripheral device 1 just like the own device 2. It is preferable to determine whether or not.

  Then, when it is determined that there is not enough free memory on the peripheral device 1 side, the distributed validity determination unit 64-2 presents a message such as “function Q cannot be executed” to the user. After executing the error process, it is preferable to end the “distributed preparation process”.

  However, in this case, the description value of “free memory” of “device information of peripheral device 1” of FIG. 11 acquired in the process of step S3 is “800 Mbit”, and the memory space of peripheral device 1 is free. It will be determined that there is sufficient capacity. That is, it is determined that the function Q can be executed by the distributed processing of the own device 2 and the peripheral device 1.

  Accordingly, even if the “free memory” on the peripheral device 1 side is checked, in this case, the process eventually proceeds to step S8.

  In step S <b> 8, the distribution legitimacy determination unit 64-2 of the information processing apparatus 2 calculates respective predicted execution times of the own device 2 and the peripheral device 1.

  Here, for example, it is assumed that the “predicted execution time of function Q” expressed by a normalized value that does not depend on the performance of the device is calculated in the process of step S8. Specifically, for example, the “predicted execution time of function Q” is calculated by “standard execution time of function Q” ÷ “performance ratio of device (vs. 100 MIPS)”. “Standard execution time of function Q” is described in “execution time” of “function Q function information”. For example, in the example of FIG. 13, “15 sec” is described in the “execution time”. Further, the “performance ratio of device (vs. 100 MIPS)” is described as the MIPS value of “CPU” in the device information of each device. For example, in “device information of peripheral device 1” in the example of FIG. 11, 500 is described as the MIPS value of “CPU”. Therefore, when the function Q is executed on the peripheral device 1 side, the “predicted execution time of the function Q” is 3 sec (= 15 / (500/100) sec). Similarly, in “device information of own device 2” in the example of FIG. 12, 300 is described as the MIPS value of “CPU”. Accordingly, when the function Q is executed by the own device 2, the “predicted execution time of the function Q” is 5 sec (15 / (300/100) sec).

  In step S9, the distribution validity judgment unit 64-2 of the information processing device 2 calculates a value for comparison with the required real-time performance.

  The required real-time performance indicates, for example, allowable communication indicating the degree of coupling with other divided function elements if the function to be executed is a divided function. In addition, for example, interrupt delay time, program memory transfer time, stack memory transfer time, heap memory transfer time, and the like are one of the required real-time performances. Further, for example, the data coupling degree indicating the relationship between the division source and other division functional elements and the data is one of the required real-time performances.

  These required real-time performances are described (defined) in “Required real-time performance” of “Function Q function information”. For example, in the example of FIG. 13, “required real-time performance” describes “allowable stack memory transfer time: 50 sec”. That is, in the example of FIG. 13, only the allowable stack memory transfer time is defined as the required real-time performance.

  Therefore, in this case, the distribution validity judgment unit 64-2 of the information processing device 2 calculates “substantially current stack memory transfer time” as a value for comparison with the required real-time performance in step S9. The “substantially current stack memory transfer time” can be calculated, for example, by “transfer stack memory amount (bit)” ÷ “substantially current bandwidth of communication infrastructure (substantially current communication speed) (bps)”. “Transfer stack memory amount (bit)” is described in the stack memory size of “memory size” of “function Q function information”. For example, in the example of FIG. 13, “100 Mbit” is described in the “memory size”. In addition, the “substantially current bandwidth of communication infrastructure (substantially current communication speed) (bps)” has been calculated in the process of step S4 described above. In this case, 2048 (kbps) is calculated as described above. ing. Therefore, 48.82 sec (= 100M / 2048k) is calculated as the “substantially current stack memory transfer time”.

  In step S10, the distributed validity judgment unit 64-2 of the information processing device 2 is capable of distributed processing of the function Q between the own device 2 and the peripheral device 1 from the viewpoint of the predicted execution time, the required real-time performance, and the like. Determine whether or not.

  Specifically, for example, 48.82 sec (= 100M / 2048k) is calculated as the “substantially current stack memory transfer time” in the process of step S9, and the “function Q function information” in FIG. Since the stack memory transfer time is defined as “50 sec”, the distributed validity judgment unit 64-2 can perform distributed processing of the function Q between the own device 2 and the peripheral device 1 from the viewpoint of the required real-time performance. It can be determined that

  Note that “from the viewpoint of predicted execution time, required real-time performance, etc.” and “etc.” are described in terms of the function Q between the own device 2 and the peripheral device 1 from the viewpoint other than the predicted execution time and required real-time performance This is because it is naturally possible to determine whether or not distributed processing is possible. Specifically, for example, although not defined in the example of FIG. 13, an item “option” is provided in “function Q function information”. Therefore, it is possible to determine whether or not the distributed processing of the function Q between the own device 2 and the peripheral device 1 is possible based on the description value of the “option”. In the “option” item, as shown in “content”, information on a special load method such as byte alignment is described.

  If it is determined in step S10 that the distributed processing of the function Q between the own device 2 and the peripheral device 1 is impossible, the “distributed preparation processing” ends. In this case, since it has already been determined in step S7 that there is not enough free memory in the own device 2, the function Q cannot be executed not only in the distributed processing but also in the own device 2 alone. I know that there is. Therefore, in such a case, although not shown in FIG. 4, the own device 2 executes a predetermined error process such as presenting a message such as “function Q cannot be executed” to the user, It is preferable to end the “dispersion preparation process”.

  On the other hand, if it is determined in step S10 that the function Q can be distributed between the own device 2 and the peripheral device 1, the process proceeds to step S11.

  In step S <b> 11, the distributed legitimacy determination unit 64-2 of the information processing device 2 determines functional elements to be distributed and executed by the peripheral device 1.

  Hereinafter, functional elements that are to be distributed and executed by peripheral devices are referred to as peripheral device functional elements. On the other hand, functional elements that should be distributed and executed by the own device are referred to as own device function elements.

  Specifically, for example, in the processing of steps S5 and S6 described above, “the peripheral device 1 has at least one of the functional elements A, D, E, and F that constitute the function Q to be executed, and The distributed device search unit 63-2 recognizes that it can be executed at present and has already been notified to the distributed validity judgment unit 64-2.

  In addition, here, it is assumed that the same or different function elements of the function P and the function Q can be determined by version. That is, among the function Q of the version “1.1b”, the functional elements A and D are also included in the function P of the version “1.1a”, and the functions E and F are not included in the function P. Is known to the distribution validity judgment unit 64-2.

  That is, at the start of the processing in step S11, the distributed validity judgment unit 64-2 determines that the functional elements A, D out of the functional elements A, D, E, and F constituting the function Q are substantially present in the peripheral device 1. Suppose you know it is feasible.

  In this case, in step S11, the distribution validity judgment unit 64-2 determines the function elements A and D of the function Q as the peripheral device 1 function elements as shown in FIG. , F can be determined as two functional elements of the own device.

  In addition, when the same functional element of function P and function Q or different functional elements cannot be determined depending on the version, for example, as described above, an identification ID is given in units of functional elements, and the identification ID of this functional element unit It becomes possible to determine by comparing.

  As described above, the distributed validity judgment unit 64-2 eventually executes the processing of steps S7 to S11, so that the hardware conditions that each of the own device 2 and the peripheral device 1 are currently requesting are substantially present. The distribution of the function Q between the own device 2 and the peripheral device 1 based on the software condition that the function Q to be executed is currently requesting and the current bandwidth (substantially the current communication speed) of the communication infrastructure. The validity of the process is determined, and if it is determined that the process is valid, each functional element constituting the function Q is assigned to either the own device 1 or the peripheral device 2.

  It should be noted that the hardware conditions that each of the own device 2 and the peripheral device 1 substantially request and the software conditions that the execution target function Q currently requests are described as information. As described above, among the description values of “device information of peripheral device 1 (see FIG. 11)”, “device information of own device 2 (see FIG. 12)”, and “function Q function information (see FIG. 13)”. At least one of the above.

  In this way, when it is determined in the process of step S10 that the function Q can be distributed between the own device 2 and the peripheral device 1, and the peripheral device 1 functional element is determined in the process of step S11, The processing results of steps S10 and S11 are notified from the distributed validity determining unit 64-2 of the information processing apparatus 2 to the distributed function executing unit 65-2.

  Then, as illustrated in FIG. 10, the information processing apparatus 2 ends the “distributed preparation process” in FIG. 4 and starts the “function execution process by the execution source” in FIG. 6.

  That is, the distributed function execution unit 65-2 of the information processing apparatus 2 determines that the distributed function is executed with the peripheral device 1 in step S41, and the process proceeds to step S45 in FIG.

  In step S45, the distributed function execution unit 65-2 of the information processing device 2 peripherally requests execution of the peripheral device 1 functional elements A and D among the functional elements A, D, E, and F included in the function Q. Issued to device 1.

  During this time, in step S <b> 71 of “function execution process by request destination” in FIG. 8, the device information providing unit 65-1 of the information processing apparatus 1 determines whether an execution request has been issued from the information processing apparatus 2. .

  Naturally, when viewed from the information processing apparatus 1 that executes the “function execution process by the request destination” in FIG. 8, the information processing apparatus 2 is a peripheral device and the information processing apparatus 1 is its own device. However, the description has been given focusing on the information processing apparatus 2 that is the execution source, and here, the description will be made as described in the drawings, that is, the peripheral device and the own device will be reversed. Yes, it will be confusing. Therefore, within the scope of the description of “function execution processing by the request destination” in FIG. 8, descriptions will be made without using names such as the own device and peripheral devices. Accordingly, the peripheral device 1 functional elements A and D are referred to as requested functional elements A and D within the scope of the description of “function execution processing by the request destination” in FIG.

  Unless an execution request is issued, it is determined in step S71 that the execution request has not been issued from the information processing apparatus 2, and the process returns to step S71 to determine whether or not the execution request has been issued from the information processing apparatus 2. It is determined again. That is, the determination process in step S71 is repeated until an execution request is issued from the information processing apparatus 2.

  Then, when an execution request for the requested functional elements A and D is issued from the information processing apparatus 2, it is determined as YES in Step S71, and the process proceeds to Step S72.

  In step S72, the distributed function execution unit 65-1 of the information processing apparatus 1 uses the data x (hereinafter referred to as function execution necessary data x) as shown in FIG. At least. The reason why “at least” is described is that the distributed function execution unit 65-1 may also execute the functional elements B and C at this time.

  In step S73, the distributed function execution unit 65-1 of the information processing apparatus 1 receives the function execution necessary data x and the execution results of the requested function elements A and D via the network interface 12-1 and the network 3. Transmit to the processing device 2.

  During this time, the distributed function execution unit 65-2 of the information processing apparatus 2 performs the function of its own device 2 among the functional elements A, D, E, and F included in the function Q as shown in FIG. Elements E and F are loaded, and data w (hereinafter referred to as function execution result data w) of data x and w included in function Q is loaded in step S47.

  In step S48, the distributed function execution unit 65-2 of the information processing device 2 sends the function execution necessary data x and the execution results of the peripheral device 1 functional elements A and D from the peripheral device 1 via the network interface 12-12. Get.

  In step S49 of FIG. 7, the distributed function execution unit 65-2 of the information processing device 2 determines whether the function execution necessary data x acquired from the peripheral device 1 can be used as it is.

  The distributed function execution unit 65-2 of the information processing device 2 cannot use the function execution necessary data x acquired from the peripheral device 1 as it is in step S49 of FIG. 7 (not usable). In step S50 of FIG. 7, the function execution necessity data x acquired from the peripheral device 1 and the function execution necessity data x held by the own device 2 are combined. Thereafter, the process proceeds to step S51.

  That is, when there is a possibility that the function execution necessary data x may be changed between the information processing apparatuses 1 and 2, one of the information processing apparatuses 1 and 2 becomes the master, and each function execution necessary data It is necessary to perform a process of merging each function execution necessary data x at the end by managing each x or adding time information to each function execution necessary data x. This process corresponds to the process of step S50 in the example of FIG.

  On the other hand, when it is determined in step S49 of FIG. 7 that the function execution necessary data x acquired from the peripheral device 1 can be used as it is, the process of step S50 of FIG. 7 is executed. Instead, the process proceeds directly to step S51.

  In step S51, the distributed function execution unit 65-2 of the information processing apparatus 2 uses the function execution necessary data x to execute the own device 2 function elements E and F as shown in FIG.

  Here, for simplification of explanation, the processing of step S51 is performed after the processing of step S48, but the order of the processing of steps S48 and S51 is not particularly limited as long as it is before step S52 described later. . That is, the process of step S51 may be executed before the process of step S48, or the processes of steps S48 and S51 may be executed almost simultaneously.

  In step S52, the distributed function execution unit 65-2 of the information processing device 2 executes the execution result of the peripheral device 1 functional elements A and D acquired in the process of step S48 and the own device 2 executed by the process of step S51. The function Q is executed by combining the execution results of the functional elements E and F.

  In step S <b> 53, the distributed function execution unit 65-2 of the information processing apparatus 2 determines whether or not the end of the execution of the function Q has been instructed.

  The determination condition in step S53 is not particularly limited. For example, the determination condition may be that there is an end instruction from the user, or the function Q is executed for each predetermined unit amount of data. The determination condition may be that the execution of the function Q for the last data of one unit amount is completed.

  If it is determined in step S53 that the end of execution of the function Q has not been instructed yet, the process returns to step S48, and the subsequent processes are repeated.

  That is, during this time, the distributed function execution unit 65-1 of the information processing apparatus 1 transmits the function execution necessary data x and the execution results of the requested function elements A and D to the information processing apparatus 2 in the process of step S73. In step S74, it is determined whether or not a function execution stop request has been issued from the information processing apparatus 2. If the distributed function execution unit 65-1 determines that it has not been issued, it returns the process to step S72 and repeats the subsequent processes. That is, until the function execution stop request is issued from the information processing apparatus 2, the loop processing of steps S72 to S74 is repeated, and the function execution necessary data x and the execution results of the requested function elements A and D are 1 to the information processing apparatus 2 sequentially (for example, for each predetermined unit amount of data).

  Therefore, the distributed function execution unit 65-2 of the information processing device 2 also repeats the loop processing of steps S48 to S53, thereby executing the execution results of the peripheral device 1 functional elements A and D sequentially transferred from the peripheral device 1. The function Q is sequentially executed (for example, for each predetermined unit amount of data) by sequentially synthesizing the execution results of the own device 2 functional elements E and F sequentially executed by itself.

  Thereafter, when an instruction to end the execution of the function Q is given, it is determined as YES in the process of the next step S53, and the process proceeds to step S54.

  In step S54, the distributed function execution unit 65-2 of the information processing device 2 issues a function execution stop request to the peripheral device 1 via the network interface 12-2 and the network 3. As a result, the “function execution process by the execution source” in FIGS. 6 and 7 ends.

  On the other hand, when the distributed function execution unit 65-1 of the information processing apparatus 1 acquires the function execution stop request via the network interface 12-1, the distributed function execution unit 65-1 determines YES in the process of the next step S74. Thereby, the “function execution process by the request destination” in FIG. 8 is also ended.

  The details of the distributed processing of the function Q executed by the information processing apparatuses 1 and 2 have been described above with reference to FIGS. That is, the distributed processing and the preprocessing described with reference to FIGS. 3 to 14 are examples of the distributed processing and the preprocessing according to the present invention.

  By executing the distributed processing and the preprocessing thereof according to the present invention, it is possible to achieve an effect that can solve the conventional problems described above. That is, as described above, the information processing apparatus 1 or 2 has the hardware conditions that each of the own device and the peripheral device substantially request, the software conditions that the function to be executed substantially requests, and Based on the current bandwidth of the communication infrastructure (substantially the current communication speed), the validity of the distributed processing of the function between the own device and the peripheral device is judged, and if it is judged to be valid, the function It is possible to execute a preprocessing of distributed processing such as allocating each of the functional elements constituting each to one of the own device and the peripheral device. As a result, it is possible to achieve an effect that distributed processing can be performed in consideration of the state of the distributed device and the change in the network environment.

  Furthermore, as described above, the information processing apparatus 1 or 2 searches for a peripheral device that has at least one of the functional elements constituting the function to be executed and can execute it substantially at present. When allocating elements, it is possible to execute preprocessing of distributed processing, such as allocating functional elements that can be executed almost at the peripheral device to the peripheral device. As a result, for example, the following first and second effects can be achieved.

  The first effect is that it is not necessary to doublely execute execution resources in a memory (a memory having a program execution area). For example, in the above-described example, the function elements A and D of the function Q are assigned to the information processing apparatus. Since there is no need to expand to both memories 1 and 2, it is possible to effectively use memory resources such as being able to execute other programs.

  The second effect is that the state of the peripheral device to which the peripheral device functional element is requested is, for example, the state of the information processing apparatus 1 in the above-described example of FIG. 10 is a state in which the peripheral device functional element can already be executed. Therefore, there is no need to load it again, and as a result, the time for loading can be reduced.

  For the purpose of easy understanding of distributed processing according to the present invention, in the above-described example, an information processing system including two information processing apparatuses 1 and 2 is used, and functions P and Q are used. However, as a matter of course, even in an information processing system including three or more information processing devices, the above-described distributed processing of a predetermined function can be easily performed by executing the above-described series of processing basically. Become. In addition to the functions P and Q, any of the functions can be performed by an information processing system including two or more information processing apparatuses basically executing the above-described series of processes, thereby distributing the functions described above. Execution of processing becomes easy.

  In the above-described example, the device information is basically stored in the own device. When the “distributed preparation process” in FIG. 4 is performed, more precisely, at the end of step S3, the peripheral information of the peripheral device is stored. Device information is acquired by the device itself. That is, the sharing timing of the device information between the own device and the peripheral device is the end point of step S3 in the above-described example. However, as a matter of course, the device information sharing timing is not limited to the above-described example, and may be any timing. For example, information can be shared by performing broadcast communication at an arbitrary timing to a device capable of distributed processing of a list of programs and data loaded by the device itself.

  Furthermore, in the above-described example, the function identification ID included in the device information is the function identification ID downloaded to the program executable area. However, the function identification ID may be a shared executable function identification ID.

  Furthermore, in the above-described example, a series of processing for performing distributed processing of the function when the function is modularized is described. However, even if the function is hierarchized, this series of processing is performed. By executing basically the same processing as the processing, it is possible to distribute the functions.

  By the way, the series of processes described above can be executed by software as described above, but can also be executed by hardware.

  In addition, when the above-described series of processing is executed by software, a program constituting the software is installed in a dedicated hardware or a computer, or various programs are installed to install various programs. For example, a general-purpose personal computer that can execute the function is installed from a network or a recording medium.

  As shown in FIG. 1, the recording medium including such a program is distributed to provide a program to the user separately from the apparatus main body, and a magnetic disk (including a floppy disk) on which the program is recorded. , Removable recording media (package media) consisting of optical disks (including compact disk-read only memory (CD-ROM), DVD (digital versatile disk)), magneto-optical disks (including MD (mini disk)), or semiconductor memory ) Main memory 13-1 or 13-2 in which a program is recorded, which is not only configured by 16-1 and 16-2 but also provided to the user in a state of being incorporated in the apparatus main body in advance, and a storage device It is composed of hard disks included in 14-1 and 14-2.

  In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series along the order, but is not necessarily performed in time series, either in parallel or individually. The process to be executed is also included.

  Further, in the present specification, the system represents the entire apparatus including a plurality of apparatuses and processing units.

It is a block diagram which shows the hardware structural example of the information processing system to which this invention is applied, ie, the information processing system which consists of information processing apparatuses to which this invention is applied. It is a block diagram which shows the functional structural example of the information processing system of FIG. It is a figure which shows the example of the function program currently hold | maintained at the two information processing apparatuses of FIG. 1 and FIG. 3 is a flowchart illustrating an example of “distributed preparation processing” executed by an information processing apparatus that is a function execution source of the information processing apparatuses illustrated in FIGS. 1 and 2. 3 is a flowchart for explaining an example of “apparatus information transmission processing” executed by an information processing device other than the information processing device that executes “distributed preparation processing” of the information processing devices of FIG. 1 and FIG. 3 is a flowchart for explaining an example of “function execution processing by an execution source” executed by an information processing device that is a function execution source of the information processing devices of FIGS. 1 and 2; 3 is a flowchart for explaining an example of “function execution processing by an execution source” executed by an information processing device that is a function execution source of the information processing devices of FIGS. 1 and 2; 2 is a flowchart for explaining an example of “function execution processing by a request destination” executed by an information processing device requested by an information processing device that executes “function execution processing by execution source” of the information processing devices of FIG. . 3 is an arrow chart for explaining an example of the relationship between the two information processing apparatuses in FIG. 1 and FIG. 2 when the functions of FIG. 3 are distributed. 3 is an arrow chart for explaining an example of the relationship between the two information processing apparatuses in FIG. 1 and FIG. 2 when the functions of FIG. 3 are distributed. It is a figure which shows the example of one apparatus information of the two information processing apparatuses of FIG. 1 and FIG. It is a figure which shows the example of the other apparatus information among the two information processing apparatuses of FIG. 1 and FIG. It is a figure which shows the example of the function information of one of the two functions of FIG. It is a figure which illustrates the process of FIG. 11 typically.

Explanation of symbols

  1, 2 Information processing device 3 Network, 11-1, 11-2 Information processing controller, 12-1, 12-2 Network interface, 13-1, 13-2 Main memory, 14-1, 14-2 Storage device, 15-1, 15-2 drive, 16-1, 16-2 removable recording medium, 21-1, 21-2 MPU, 22-1, 22-2 memory, 31-1 to 33-1, 31-2 to 33-2 SPU, 41-1 to 43-1, 41-2 to 43-2 memory, 51-1, 51-2 bus, 61-1, 61-2 function storage unit, 62-1, 62-2 equipment Information storage unit, 63-1, 63-2 Distributed device search unit, 64-1, 64-2 Distributed validity judgment unit, 65-1, 65-2 Distributed function execution unit, 66-1, 66-2 Device information Provision department

Claims (4)

In an information processing apparatus that performs distributed processing of a predetermined function in cooperation with the peripheral device by performing communication with the peripheral device using a predetermined communication infrastructure,
A hardware condition that each of the information processing device itself and the peripheral device requests at the present time, and the execution target is requested at a substantially current time. On the basis of the current software conditions and the current bandwidth of the communication infrastructure, the validity of the execution of the distributed processing of the execution target by the information processing apparatus itself and the peripheral device is determined, and the validity is When it is determined that there is a legitimacy determining unit that allocates each of the plurality of functional elements constituting the execution target to either the information processing apparatus itself or the peripheral device;
When the validity determining unit determines that there is no validity, the execution target is executed by itself, and when the validity determining unit determines that there is validity, a plurality of items constituting the execution target Of the functional elements, the first functional element allocated to the information processing apparatus itself by the validity determining means is executed by itself, and the second functional element allocated to the peripheral device by the validity determining means. Function execution means for executing distributed processing of the execution target by performing control of causing the peripheral device to execute the function element and combining the execution results of the first function element and the second function element An information processing apparatus comprising: Holds at least one of the plurality of functional elements constituting the execution target from among other information processing apparatuses capable of performing communication using the communication infrastructure, and is currently executing it. Further comprising a search means for searching other possible information processing devices as the peripheral device,
The validity determination means determines the validity of the execution of the distributed processing of the execution target by the information processing apparatus itself and the peripheral device searched by the search means, and determines that there is validity, Of the plurality of functional elements constituting the execution target, a functional element that is substantially executable by the peripheral device is assigned to the peripheral device as the second functional element, and other functional elements are assigned to the first functional element. The information processing apparatus according to claim 1, wherein the information processing apparatus is assigned as a functional element to the information processing apparatus itself. In an information processing method of an information processing apparatus that performs distributed processing of a predetermined function in cooperation with the peripheral device by communicating with the peripheral device using a predetermined communication infrastructure,
A hardware condition that each of the information processing device itself and the peripheral device requests at the present time, and the execution target is requested at a substantially current time. On the basis of the current software conditions and the current bandwidth of the communication infrastructure, the validity of the execution of the distributed processing of the execution target by the information processing apparatus itself and the peripheral device is determined, and the validity is When it is determined that there is a legitimacy determining step of allocating the processing of each of the plurality of functional elements constituting the execution target to either the information processing apparatus itself or the peripheral device;
When it is determined that there is no legitimacy by the processing of the legitimacy judgment step, the information processing apparatus itself is controlled to execute the execution target, and when the legitimacy judgment unit determines that the legitimacy is legitimate, Among the plurality of functional elements constituting the execution target, performing control to cause the information processing apparatus itself to execute the first functional element allocated to the information processing apparatus itself by the process of the validity determination step, Control is performed to cause the peripheral device to execute the second functional element allocated to the peripheral device by the process of the legitimacy determining step, and the respective execution results of the first functional element and the second functional element And a function execution control step for controlling the execution of the distributed processing to be executed by synthesizing the information. A program executed by a computer that controls a peripheral device and a main apparatus that performs a distributed operation of a predetermined function in cooperation with the peripheral device by communicating with the peripheral device using a predetermined communication infrastructure. There,
Hardware functions requested by each of the main device and the peripheral device at substantially the current time, and the execution objects are requested at the substantially current time, with a function composed of a plurality of functional elements as software being executed. Based on the software conditions and the approximate current bandwidth of the communication infrastructure, the validity of the execution of the distributed processing of the execution target by the main device and the peripheral device is determined, and the validity is determined In this case, a legitimacy determination step of allocating the processing of each of the plurality of functional elements constituting the execution target to either the main device or the peripheral device;
When it is determined by the process of the legitimacy determination step that the legitimacy is not legitimate, the main device is controlled to execute the execution target. Of the plurality of functional elements constituting the object, control is performed to cause the main apparatus to execute the first functional element allocated to the main apparatus by the process of the validity determining step. By performing control to cause the peripheral device to execute the second functional element allocated to the peripheral device by processing, and combining the execution results of the first functional element and the second functional element, A function execution control step for controlling execution of the distributed processing to be executed.

Images