Claims:We Claim:
1. An inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising:
receiving a data frame by the processor in the network and identify a connection name and the flag of the received data frame;
traversing the read list and master list records by the processor to determine whether the identified connection name of the data frame is distinct;
creating a connection descriptor for the connection upon detection that the identified connection name is unique;
creating a new record and the fields of the record are updated with the connection name, the flag (READ) and the connection descriptor;
inserting the new created record into the READ list and the inserted index position is updated in the appropriate field of the connection descriptor; and
broadcasting the read list to all the processor in the network.

2. The method as claimed in claim 1, further comprising:
receiving the broadcasted read list by all the processor and store the same as a sub-list in the master list.

3. The method as claimed in claim 1, wherein the updated read list supersedes the previously sent read list.

4. The method as claimed in claim 1, wherein, if the identified connection name is already present in the read list and the master list, indicate duplicate connection name error to the network.

5. The method as claimed in claim 1, further comprising:
assigning a customised identifier including connection name and flag to each processor in the network.

6. The method as claimed in claim, wherein read list is packetized and transmitted, wherein the number of packets depends on the size of the list and each packet has a unique ID, and wherein each unique ID includes start of message, continuation of message and end of message.

7. An inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising:
transmitting a data frame by the processor in the network by identifying a resolved connection name. traversing the write list records by the processor to determine whether the identified connection name of the data frame is distinct;
creating a connection descriptor for the connection upon detection that the identified connection name is unique;
creating a new record and the fields of the record are updated with the connection name, the flag (WRITE) and the connection descriptor;
inserting the new created record into the WRITE list and the inserted index position is updated in the appropriate field of the connection descriptor;
traversing the master list records by the processor to determine whether the identified connection name of the data frame is matching with the input name; and
retrieving from the master list records and update the connection descriptor of the WRITE record, if an entry is found.

8. The method as claimed in claim 6, wherein, if the identified connection name is not found in the master list, indicate matching connection name not found.

9 The method as claimed in claim 6 ensures that during WRITE operation, the destination details are readily available and repeated list traversal can be avoided.

10. The method as claimed in claim 6, further comprising:
resetting the write list records to un-resolved if the time tag field is not updated for n seconds after broadcast data reception. , Description:FORM 2
THE PATENTS ACT, 1970
(39 of 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(See section 10, rule 13)
“A method for resolving and routing name based connections to physical address to transfer messages reliably across multiple compute engines”
By
BHARAT ELECTRONICS LIMITED
Nationality: Indian
M/s. Bharat Electronics Limited, Corporate Office, Outer Ring Road, Nagavara, Bangalore-560045, Karnataka, India

The following specification particularly describes the invention and the manner in which it is to be performed.

Field of the invention
The present invention mainly relates to communication method between compute engines connected via a network and more particularly to a method for resolving and routing name based connections to physical address to transfer messages reliably across multiple compute engines rather than IP address/port/hardware address.
Background of the invention
Generally, most electronics devices and systems include a number of networked elements (components) such as hardware and software that forms the system. The electronic system executing on any data network requires transmitting/receiving (communication) data across the various compute engines on the network.
A communication system and methods are well known in the art which provides various types of communication mode, such as asynchronous transfer mode (ATM), synchronous digital hierarchy (SDH), and Internet protocol (IP), etc. In most of the systems there is a layer responsible for communication between the different components that form a networked element as well as between the different networked elements themselves.
In an example communication system, each system uses an interprocess communication (IPC) method which is different from the other system. The IPC is tightly coupled to and depends on the respective hardware device of each system. For example, an asynchronous transfer mode system uses an IPC method which is different than the IPC method made by a synchronous digital hierarchy system.
The communication methods of such communication systems are different from each other, depending on the respective network or of the systems. Depending on the physical media of the data network, the method of transmitting and receiving data will be different which means that an application needs to be modified when the underlying media of the data network is changed.
Current RADAR and SONAR applications use multi-processor/core high performance embedded boards for signal processing and control purposes. The communication media across the nodes/cores may be backplane, SRIO (Serial Rapid Input Output), Ethernet, serial etc. The application should have a common API based communication method which abstracts the physical media component so that it can work seamlessly regardless of the physical connectivity.
For example, document US 20030115358A1 describes a unified interprocess communication system, and a unified interprocess communication method, which are compatible with different hardware and software. The unified interprocess communication system can be used with any equipment, regardless of the communication method. This method introduces and operating system independent layer (OIA) and device independent access layer (DIA). This method uses channel ID, near end address to establish link and connection based messages.
Further in document, US5867656A describes a system in which nodes are connected to each other via a network, transmission and reception buffers of sender and receiver processes are prepared as resident areas in a main storage. A node of a receiver side notifies, prior to initiation of a communication, a physical address of a data reception area of the node to a node on a sender side. In the node on the sender side, the reported physical address is added to transmission data to transfer a resultant item. On the receiver side, reception data is written in a location of the main storage at the physical address. In the receiver node, the double buffering is employed to prevent an overwriting operation of another node onto the data reception area. This system uses a virtual memory space allocated by combuf_alloc () and uses the combuf number, receiver node number to establish connections.
Another document, US8326918B2 describes a radio communication device has a baseband processor acting as an InterProcessor Communication (IPC) server and an application processor acting as an IPC client. The baseband processor and the application processor communicate with each other via an IPC network. The IPC server and the IPC client can switch functions via negotiation to allow the IPC client to become the new IPC server. The IPC network includes multiple IPC clients, and remaining IPC clients are instructed to change the IPC address of the IPC server if the IPC client becomes the new IPC server. The IPC network allows any processor that adopts the IPC as its interprocessor communication stack to co-exist together and operate as if the two were actually running on the same processor core sharing a common operating system and memory. But, the device uses component ID, the destination ID, a channel ID for facilitating multi-processor communications. All the above patents do not have name based unique connection identifier and the above patent designs do not have Read, Write and Master List to resolve the logical address to the physical address.
Therefore there is a need in the art with the method and system for resolving and routing name based connections to physical address to transfer messages across multiple compute engines and to solve the above mentioned limitations.
Summary of the Invention
An aspect of the present invention is to address at least the above-mentioned problems and/or disadvantages and to provide at least the advantages described below.
Accordingly, in one aspect of the present invention relates to an inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising: opening a connection name with a unique connection descriptor, traversing the read list and master list records by the processor to determine whether the identified connection name of the data frame is distinct, creating a connection descriptor for the connection upon detection that the identified connection name is unique, creating a new record and the fields of the record are updated with the connection name, the flag (READ) and the connection descriptor, inserting the new created record into the READ list and the inserted index position is updated in the appropriate field of the connection descriptor and broadcasting the read list to all the processor in the network.
On receiving a data frame by the processor in the network, the method identifies the destination application and sends the data to the destination application., In another aspect, the present invention relates to an inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising: opening a connection name with a unique connection descriptor upon detection that the identified connection name is unique, creating a new record and the fields of the record are updated with the connection name, the flag (WRITE) and the connection descriptor, inserting the new created record into the WRITE list and the inserted index position is updated in the appropriate field of the connection descriptor. The connection is resolved by traversing the master list records by the processor to determine whether the identified connection name is matching with the input name and retrieving from the master list records and update the connection descriptor of the WRITE record, if an entry is found.
For transmitting a data frame by the processor in the network, the fields of the connection descriptor is examined to retrieve the physical address of the destination processor and the data is transmitted to the destination processor. Other aspects, advantages, and salient features of the invention will become apparent to those skilled in the art from the following detailed description, which, taken in conjunction with the annexed drawings, discloses exemplary embodiments of the invention.
Brief description of the drawings
The above and other aspects, features, and advantages of certain exemplary embodiments of the present invention will be more apparent from the following description taken in conjunction with the accompanying drawings in which:
Figure 1 shows compute engines/processors connected on a data network according to one embodiment of the present invention.
Figure 2 explains the various components present in the processor node according to one embodiment of the present invention.
Figure 3 is the generic frame which is transmitted across the network according to one embodiment of the present invention.
Figure 4 is the flow chart explaining the open connection process for the read/receive end of a connection according to one embodiment of the present invention.
Figure 5 is the flow chart explaining the open connection process for the write/transmit end of a connection according to one embodiment of the present invention.
Figure 6 is the flow chart explaining the processing of the broadcast data according to one embodiment of the present invention.
Persons skilled in the art will appreciate that elements in the figures are illustrated for simplicity and clarity and may have not been drawn to scale. For example, the dimensions of some of the elements in the figure may be exaggerated relative to other elements to help to improve understanding of various exemplary embodiments of the present disclosure. Throughout the drawings, it should be noted that like reference numbers are used to depict the same or similar elements, features, and structures.
Detailed description of the invention
The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of exemplary embodiments of the invention as defined by the claims and their equivalents. It includes various specific details to assist in that understanding but these are to be regarded as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.
The terms and words used in the following description and claims are not limited to the bibliographical meanings, but, are merely used by the inventor to enable a clear and consistent understanding of the invention. Accordingly, it should be apparent to those skilled in the art that the following description of exemplary embodiments of the present invention are provided for illustration purpose only and not for the purpose of limiting the invention as defined by the appended claims and their equivalents.
It is to be understood that the singular forms “a,” “an,” and “the” include plural referents unless the context clearly dictates otherwise. Thus, for example, reference to “a component surface” includes reference to one or more of such surfaces.
By the term “substantially” it is meant that the recited characteristic, parameter, or value need not be achieved exactly, but that deviations or variations, including for example, tolerances, measurement error, measurement accuracy limitations and other factors known to those of skill in the art, may occur in amounts that do not preclude the effect the characteristic is intended to provide.
Figs. 1 through 6, discussed below, and the various embodiments used to describe the principles of the present disclosure in this patent document are by way of illustration only and should not be construed in any way that would limit the scope of the disclosure. Those skilled in the art will understand that the principles of the present disclosure may be implemented in any suitably arranged communications system. The terms used to describe various embodiments are exemplary. It should be understood that these are provided to merely aid the understanding of the description, and that their use and definitions, in no way limit the scope of the invention. Terms first, second, and the like are used to differentiate between objects having the same terminology and are in no way intended to represent a chronological order, unless where explicitly stated otherwise. A set is defined as a non-empty set including at least one element.
The present invention introduces a name based communication methodology which is device independent. In this method, the application communicates on name based channel which is resolved at execution time to the physical device address of the media. The method for resolving name based connections to physical address to transfer messages reliably across multiple compute engines is proposed. The user can open a connection on a processor on the network.
The unique identifier is the name of the connection. The data can be written to this connection by using the name, by any other processor on the network, and the owner of the connection can read the data. The name of the connection is in the form of a character string, this name has to be resolved into a physical address so that data can be transferred across the network. The method ensures duplicate checking/handling of the name based connection across the processors. It also keeps track of unresolved connections, current connection status etc.
The present invention is a method for resolving and routing name based connections to physical address to transfer messages reliably across applications executing on multiple compute engines. This method identifies and assigns a unique identifier to all the processor. The enumeration or discovery of the processor on the networks is not done by this method. It is assumed that the enumerated information is already available. The method reads this information and assigns a customised identifier to each processor on the network.
An application running on any of the processor can open a name based connection. The connection details are stored in the local processor as well as broadcasted across all the processors on the network. The storage is in the form of lists. This ensures that at all time the connection details are updated at all the processors. When the data has to be transmitted across these connections, the method identifies the read end (owner) of the connection by traversing the broadcasted details list. It then frames a packet with the physical communication details derived from the list and transmits the packet on the communication media. Similarly when data is received on the physical media, the method decodes the received frame and routes the data to the relevant application connection.
Figure 1 shows compute engines/processors connected on a data network according to one embodiment of the present invention.
The figure shows the compute engines/processors connected on a data network. The processors are already enumerated and have their own physical identifiers. The data processing system network 102 consists of processors 101 connected via communication links. It is assumed that all the processors in the network are enumerated and have a unique physical identifier.
Figure 2 explains the various components present in the processor node according to one embodiment of the present invention.
The figure explains the various components present in the processor node 200. The processor node 200 is abstracted into physical (204), Interface (203) and application (201) component. The application opens n number of connections (202) each with unique name. The present invention is embedded in the interface component.
The physical layer consists of the networking hardware transmission technologies of a network. It is a fundamental layer underlying the logical data structures of the higher level functions in a network. The physical layer defines the means of transmitting raw bits rather than logical data packets over a physical link connecting network nodes. The physical layer provides an electrical, mechanical, and procedural interface to the transmission medium.
The Interface component is the interface between the application and the physical layer. The actual logic of sending and receiving the data is encapsulated in the interface component and the features are made available to the application through defined Application programming interfaces (APIs).
Figure 3 is the generic frame which is transmitted across the network according to one embodiment of the present invention.
The figure shows the generic frame which is transmitted across the network. It comprises of the header portion and the payload portion. The Interface layer accepts the payload data 302 from the application layer appends a header 301 and transmits the completed frame on the network. The header portion contains details that are required for routing the packet to the right connection. On receipt of the frame from the physical layer, the interface layers strips the frame into header portion and payload portion. The header portion is examined for routing details and the payload is delivered to right connection at the application layer.
Figure 4 is the flow chart explaining the open connection process for the read/receive end of a connection according to one embodiment of the present invention.
The figure shows the flow chart explaining the open connection process for the read/receive end of a connection. The successful result of the process is a valid connection descriptor. In the figure, the flow chart for opening a connection in Read Mode is explained. The open call requires an input of connection name and the flag (Step 400).The Read List and Master List records are traversed to check if the name is unique. If the name is already present in the Read List or the Master List, then open call fails with duplicate name error.
If the name is unique, a connection descriptor is created for the said connection. A new record is created and the fields of the record are updated with the connection name, the flag (in this case READ) and connection descriptor. The record is inserted into the Read List and the inserted index position is updated into the appropriate field of the connection descriptor (Step 401).The Read List is broadcasted (Step 402).All the processors on the network will receive this Read List and it is stored as a sub-list in the Master List. The latest Read List supersedes the previously sent Read List from any node. The master List comprises of the all the Read List of all the nodes.
In another aspect of the present invention relates to an inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising: receiving a data frame by the processor in the network and identify a connection name and the flag of the received data frame, traversing the read list and master list records by the processor to determine whether the identified connection name of the data frame is distinct, creating a connection descriptor for the connection upon detection that the identified connection name is unique, creating a new record and the fields of the record are updated with the connection name, the flag (READ) and the connection descriptor, inserting the new created record into the READ list and the inserted index position is updated in the appropriate field of the connection descriptor and broadcasting the read list to all the processor in the network.
The broadcasted read lists are received by all the processor and store the same as a sub-list in the master list. The updated read list supersedes the previously sent read list. If the identified connection name is already present in the read list and the master list, indicate duplicate connection name error to the network.
Further, the method assigns a customised identifier including connection name and flag to each processor in the network. The read list is packetized and transmitted, wherein the number of packets depends on the size of the list and each packet has a unique ID, and wherein each unique ID includes start of message, continuation of message and end of message.
Figure 5 is the flow chart explaining the open connection process for the write/transmit end of a connection according to one embodiment of the present invention.
The figure shows the flow chart explaining the open connection process for the write/transmit end of a connection. The successful result of the process is a valid connection descriptor. In the figure, the flow chart for opening a connection in Write Mode is explained. The open call requires an input of connection name and the flag (Step 500).The Write List is traversed to check if the name is unique. If the name is already present in the Write List, then open call fails with duplicate name error.
If the name is unique, a connection descriptor is created for the said connection. A new record is created and the fields of the record are updated with the connection name, the flag (in this case WRITE ONLY) and connection descriptor. The record is inserted into the Write List and the inserted index position is updated into the appropriate field of the connection descriptor (Step 501).The write connection has to be resolved with the read end details. For this the Master List is traversed and checked for an entry which is matching with the input name (502).
If an entry is found, the details of user id and index position is retrieved from the master record and updated into the Connection descriptor of the write record. This ensures that during a write operation, the destination details are readily available and repeated list traversal can be avoided (Step 503). If a matching entry is not found in the Master list, the connection remains unresolved and fill be resolved during a subsequent write or a subsequent broadcast data processing.
If a connection is unresolved a query is initiated. Query initiation involves broadcasting a query command across the network. On reception of a query command, all the processors on the network will broadcast their respective read list. On reception of the broadcast data, broad cast data processing is initiated at all the processors which also results in Master List update as well as resolving unresolved write connections.
In another aspect of the present invention relates to an inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising: transmitting a data frame by the processor in the network and identify a connection name and the flag of the transmitted data frame, traversing the write list records by the processor to determine whether the identified connection name of the data frame is distinct, creating a connection descriptor for the connection upon detection that the identified connection name is unique, creating a new record and the fields of the record are updated with the connection name, the flag (WRITE) and the connection descriptor, inserting the new created record into the WRITE list and the inserted index position is updated in the appropriate field of the connection descriptor, traversing the master list records by the processor to determine whether the identified connection name of the data frame is matching with the input name and retrieving from the master list records and update the connection descriptor of the WRITE record, if an entry is found. If the identified connection name is not found in the master list, indicate matching connection name not found.
During WRITE operation, the destination details are readily available and repeated list traversal can be avoided. Moreover, the present invention updates the time tag field of the write list record with current time to ensure that any unresolved connection at the write list will get resolved.
Figure 6 is the flow chart explaining the processing of the broadcast data according to one embodiment of the present invention.
The figure shows the flow chart explaining the processing of the broadcast data. The broadcast processing entitles updating the Master List and the Write List. The figure further explains the flow chart for broadcast processing of Read List. The Read List of a processor is broadcasted. The read List is packetized and transmitted. The number of packets depends on the size of the list and each packet has a unique id (Start of message, Continuation of message, and End of message). This id helps the receiver to decipher if all the packets have been received and the entire read list can be recreated at the receiver end. The input here is a broadcast packet frame (Step 600).The frame is interpreted and the User ID, data and Message type is retrieved. The layer will discard the existing data available at the master list for this particular user id (Step 601). The data contains the read list records which are updated in the Master List for this particular user id. As and when the record is updated in the master list, the name field of the record is compared with all the entries of the Write list till the first matching name is encountered. If a matching record is found, then that Write List record entry is updated with the master record details. The time tag field of the write list record is also updated with current time. This step ensures that any unresolved connection at the write list will get resolved (Step 602).
Once all the records are updated, The Write List is traversed for all the entries which has user id as the current received user id. The time tag field of all these records are inspected. If the time tag field and the current time are different by more than n seconds, then that particular write entry is considered as stale, the connection name is reset to unresolved state (Step 603). The Read List is broadcasted on opening of a read connection, on closing of a read connection and on reception of a query command. When a connection is resolved, the owner details are available. The physical layer can then transmit the data on the communication media.
Those skilled in this technology can make various alterations and modifications without departing from the scope and spirit of the invention. Therefore, the scope of the invention shall be defined and protected by the following claims and their equivalents.
FIGS. 1-6 are merely representational and are not drawn to scale. Certain portions thereof may be exaggerated, while others may be minimized. FIGS. 1-6 illustrate various embodiments of the invention that can be understood and appropriately carried out by those of ordinary skill in the art.
In the foregoing detailed description of embodiments of the invention, various features are grouped together in a single embodiment for the purpose of streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments of the invention require more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive subject matter lies in less than all features of a single disclosed embodiment. Thus, the following claims are hereby incorporated into the detailed description of embodiments of the invention, with each claim standing on its own as a separate embodiment.
It is understood that the above description is intended to be illustrative, and not restrictive. It is intended to cover all alternatives, modifications and equivalents as may be included within the spirit and scope of the invention as defined in the appended claims. Many other embodiments will be apparent to those of skill in the art upon reviewing the above description. The scope of the invention should, therefore, be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled. In the appended claims, the terms “including” and “in which” are used as the plain-English equivalents of the respective terms “comprising” and “wherein,” respectively.

We Claim:
1. An inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising:
receiving a data frame by the processor in the network and identify a connection name and the flag of the received data frame;
traversing the read list and master list records by the processor to determine whether the identified connection name of the data frame is distinct;
creating a connection descriptor for the connection upon detection that the identified connection name is unique;
creating a new record and the fields of the record are updated with the connection name, the flag (READ) and the connection descriptor;
inserting the new created record into the READ list and the inserted index position is updated in the appropriate field of the connection descriptor; and
broadcasting the read list to all the processor in the network.

2. The method as claimed in claim 1, further comprising:
receiving the broadcasted read list by all the processor and store the same as a sub-list in the master list.

3. The method as claimed in claim 1, wherein the updated read list supersedes the previously sent read list.

4. The method as claimed in claim 1, wherein, if the identified connection name is already present in the read list and the master list, indicate duplicate connection name error to the network.

5. The method as claimed in claim 1, further comprising:
assigning a customised identifier including connection name and flag to each processor in the network.

6. The method as claimed in claim, wherein read list is packetized and transmitted, wherein the number of packets depends on the size of the list and each packet has a unique ID, and wherein each unique ID includes start of message, continuation of message and end of message.

7. An inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network, the method comprising:
transmitting a data frame by the processor in the network by identifying a resolved connection name. traversing the write list records by the processor to determine whether the identified connection name of the data frame is distinct;
creating a connection descriptor for the connection upon detection that the identified connection name is unique;
creating a new record and the fields of the record are updated with the connection name, the flag (WRITE) and the connection descriptor;
inserting the new created record into the WRITE list and the inserted index position is updated in the appropriate field of the connection descriptor;
traversing the master list records by the processor to determine whether the identified connection name of the data frame is matching with the input name; and
retrieving from the master list records and update the connection descriptor of the WRITE record, if an entry is found.

8. The method as claimed in claim 6, wherein, if the identified connection name is not found in the master list, indicate matching connection name not found.

9 The method as claimed in claim 6 ensures that during WRITE operation, the destination details are readily available and repeated list traversal can be avoided.

10. The method as claimed in claim 6, further comprising:
resetting the write list records to un-resolved if the time tag field is not updated for n seconds after broadcast data reception.

Abstract
A method for resolving and routing name based connections to physical address to transfer messages reliably across multiple compute engines
The present invention mainly relates to communication method between compute engines connected via a network. In one embodiment, the present invention relates to an inter-processor data handling method including a plurality of processor and a data transfer network connecting the processors, each processor includes a memory having a logic which is executed by the processor for resolving and routing of data across the network. The method includes receiving a data frame by the processor in the network and identify a connection name and the flag of the received data frame, traversing the read list and master list records by the processor to determine whether the identified connection name of the data frame is distinct, creating a connection descriptor for the connection upon detection that the identified connection name is unique, creating a new record and the fields of the record are updated with the connection name, the flag (READ) and the connection descriptor, inserting the new created record into the READ list and the inserted index position is updated in the appropriate field of the connection descriptor and broadcasting the read list to all the processor in the network.

Figure 1 for publication