JP3152813B2 - Nodes in a lattice network system - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

This invention relates to a packet switching system .
About nodes constituting the rated child network system.

[0002]

2. Description of the Related Art In recent years, in a packet switching type network system, a system capable of high speed switching has been developed in order to increase the speed of a terminal and to improve the throughput.

In such a network system, even if the data amount increases, it is necessary to prevent the exchange efficiency from lowering due to data collision. In addition, it is necessary that the arrival time of the packet does not vary depending on the position of the destination node.

In order to meet this demand, the present applicant proposed a high-speed grid network system in Japanese Patent Application No. 244626 filed on Sep. 14, 1992.

In this network system, a plurality of nodes are arranged in a grid, and a plurality of nodes belonging to each column and each row are connected so that packets can be directly transmitted between any two nodes. It is like that.

According to such a configuration, a packet can be transmitted by one hop between any two nodes belonging to the same column or the same row. Further, by providing a relay function in each node, a packet can be transmitted in two hops between any two nodes belonging to different columns and different rows. As a result, it is possible to reduce the variation in the arrival time of the packet due to the position of the destination node.

[0007] When a packet is relayed, only one relay node is required, so that even if the data amount increases, data collision can be suppressed. As a result, a decrease in transfer efficiency can be prevented.

[0008]

THE INVENTION Problems to be Solved] However, the conventional
Since in the rated subtype network system, which can only specify one node in one packet, 1
When performing communication (broadcasting) with respect to N, a packet in which the destination is written for each node must be transmitted. As a result, in the conventional system, when one-to-N communication is performed, it takes time and when relaying is required,
There is a problem that the probability of dropping the packet increases and the throughput decreases.

[0009] Therefore, the present invention is, intended to provide the rated subtype network system, without sending the packet wrote the destination for each node, a node that can communicate one-to-N I do.

[0010]

Means for Solving the Problems] The present invention in order to achieve the above objects, in the node of case child network system of the destination indicating section of the packet, at least one of the column-side indicating section and line-side shower unit By writing a predetermined value, a packet destined for a certain row in a given column is generated, the packet is transmitted to another node in the column or row to which the own node belongs, and the predetermined value is written in a destination notation section. And means for appropriately executing capture and relay of the packet based on the destination of the received packet.

[0011]

The operation of the above-described configuration will be described with reference to a case where a packet is transmitted to all nodes in a row different from the row to which the own node belongs. In this case, a predetermined value is written in the column-side notation section of the packet, and the coordinates of the destination row are written in the row-side notation section. This packet is transmitted to each node in the column to which the own node belongs. In this case, the transmission packet is captured only at the node belonging to the destination line, and is relayed by this node to all other nodes belonging to the destination line. This means that one packet output from a certain node has been transmitted to all nodes belonging to the destination line.

[0012]

Embodiments of the present invention will be described below in detail with reference to the drawings.

FIG. 1 is a block diagram showing a configuration of an embodiment of a node according to the present invention. Here, before describing the configuration of the node, illustrating the connection structure of nodes in rated child network systems that are used this node.

FIG. 2 is a diagram showing a logical arrangement of nodes in the network system.

As shown in the figure, in this system, a plurality of nodes 10 are arranged in an M × N (M, N is an integer of 2 or more) lattice, and each column (row) and each row (column) are arranged. Are grouped in In the figure, the group G in the m-th (m = 1,..., K,..., M) column is shown as GRm, and the group G in the n-th (n = 1,..., L,.

Each node 10 is assigned an address. Each address is composed of a column direction address and a row direction address. The address in the column direction is represented by the coordinate m in the column direction, and the address in the row direction is represented by the coordinate n in the row direction. Therefore, the address of the node 10 located at the m-th column and the n-th row is represented as (m, n).

Each node 10 is connected so that packets can be directly transmitted between any two nodes for each group G. In this case, a physical connection form may be any form such as a bus type, a ring type, and a star type.

According to such a configuration, the same group G
Can be transmitted by one hop between the two nodes 10 belonging to. For example, a packet can be transmitted at one hop between the (1,1) node 10 and the (1, L) node 10 belonging to the column group GR1.

Further, between two nodes 10 belonging to different groups G, by providing a relay function in each node 10, a packet can be transmitted in two hops.
For example, (1,1) node 1 belonging to column group GR1
Between 0 and the (K, L) node 10 belonging to the row group GCL, a packet can be transmitted in two hops via the (1, L) node 10 or the (K, 1) node 10.

The above is the connection of the nodes in the rated child network system. Next, an internal configuration of the node 10 will be described with reference to FIG.

In FIG. 1, a transmission packet output circuit 11 outputs a transmission packet. FIG. 3 is a diagram showing a configuration of a packet output from the transmission packet output circuit 11. As shown, the packet includes a destination address portion DA in which a destination address is written, a source address portion SA in which a source address is written,
And a data section DATA in which user data is written.

The destination address section DA includes a column address section DAR and a row address section DAC. The column address of the destination node 10 or a predetermined value (for example, 0) is written in the column address section DAR. Similarly,
The row address of the destination node 10 or a predetermined value (for example, 0) is written in the column address section DAR.

The source address section SA also has a column address section S
AR and row address section SAC. Column address section SA
In R, the column address of the source node 10 is written,
The row address of the source node 10 is written in the row address section SAC.

The packet output from the transmission packet output circuit 11 is supplied to a row output line 14 or a column output line 15 via a concentrator 12 or 13. The row- side output line 14 is connected to the row-side input lines of all the other nodes 10 in the row group GCn to which the own node 10 belongs. Similarly, the column side output line 15 is connected to the own node 10.
Are connected to the column-side input lines of all the other nodes 10 in the column group GRm to which.

Reference numeral 16 denotes a column-side input line. Since the column-side input lines 16 are connected to all the other nodes 10 in the column group GRm to which the own node 10 belongs, (N − 1) columns are provided. 17 is a row-side input line. Since the row-side input lines 22 are connected to all the other nodes 10 in the row group GCn to which the own node 10 belongs, (M − 1) lines are provided.

Reference numeral 18 denotes a DAC filter provided for each column-side input line 16. This DAC filter 18
The content of the DAC is read from the received packet, and it is determined whether or not the content of the DAC matches the column address of the own node 10 or whether or not the value is a predetermined value 0. Column selector corresponding to the received packet
20 and discarded otherwise.

Reference numeral 19 denotes a DAR filter provided for each row-side input line 17. The DA R filter 19,
The content of the DAR is read from the received packet, and it is determined whether or not the DAR matches the row address of the own node 10 or whether or not the value is a predetermined value 0. It supplies the received packet to the corresponding rowset selector 21, in the case of other discarded.

[0028] 20 is a Retsuse reflectors provided for each DAC filter 18. DAC The column filter 20 reads the contents of the DAR from the received packet, whether it matches the column address of the node 10, or to determine whether or not a predetermined value 0, corresponding to the judgment result Based on the determination result of the filter 18, the following five processes
,, And are selectively executed.

When the content of the DAC matches the row address n of the own node 10 and the content of the DAR matches the column address m of the own node 10 In this case, in the one-to-one communication, the own node 10 Is equivalent to Therefore, in this case, only the process of capturing the received packet is performed. That is, in this case, the received packet is supplied from the column selector 20 to the reception buffer 22. As a result, the received packet is stored in the reception buffer 2
2 is stored.

When the content of the DAC matches the row address n of the own node 10 and the content of the DAR does not match either the column address m of the own node 10 or a predetermined value 0, in this case, in the one-to-one communication, This corresponds to the case where the own node 10 is the relay node 10. Therefore, in this case, only the relay processing of the received packet is performed.

That is, in this case, the received packet is supplied from the column selector 20 to the concentrator 12.
As a result, this packet is transmitted via the row output line 14 to each node 1 in the row group GCn to which the own node 10 belongs.
Sent to 0.

In this case, the ACK circuit 23 is activated by the column selector 20. As a result, this ACK
The circuit 23 outputs an ACK (acknowledge) signal. This ACK signal is supplied to the column side output line 15 via the concentrator 13. As a result, the source node 10 is notified that the packet has been successfully relayed.

When the content of the DAC matches the row address n of the own node 10 and the content of the DAR is a predetermined value 0, in this case, in one-to-N communication, another node in the column group GRm to which the own node 10 belongs 10 to own node 10
Corresponds to the case where a packet addressed to the row group GCn to which the packet belongs belongs. In this case, the own node 10 operates as a destination node and a relay node. Therefore, in this case, the above-described acquisition processing and relay processing are performed.

The content of the DAC is a predetermined value 0,
When the content of R matches the column address m of the own node 10 In this case, in the point-to-N communication, a packet addressed to this column group GCm is sent from another node 10 in the column group GRm to which the own node 10 belongs. Corresponds to the case of being sent. In this case, the own node 10 operates as a destination node. Therefore, in this case, only the above-described fetching process is performed.

When both the contents of the DAC and the contents of the DAR coincide with the predetermined value 0, in this case, in one-to-N communication, the other node 10 in the column group GRm to which the own node 10 belongs, Corresponds to a case in which a packet addressed to all the row groups GCn other than the row group GCn to which the packet belongs belongs. In this case, the own node 10 operates as a destination node and a relay node. Therefore, in this case, the own node 10 performs the above-described acquisition processing and relay processing. However, in this case, in the relay process, a process of rewriting the destination of the packet to the row group GCn to which the own node 10 belongs is performed. This is to prevent the packet from being relayed forever.

[0036] 21 is a rowset reflectors provided on each DAR filter 19. The Gyofu filter 21, although a detailed description is omitted, reads the contents of the DAR from the received packet, whether it matches the row address n of the node 11, or determining whether or not a predetermined value 0 Then, based on the determination result and the determination result of the DAR filter 19 corresponding to the determination result, the above-described five processes,. Note that the five processes described above
,,, And are the five processes described above,
Replace "column" with "row" in ",", "row"
Is replaced by "column". 24 is its own node 1
0 to other nodes 10 in the row group GCn to which AC 0 belongs.
An ACK circuit for returning the K signal.

When a packet conflict occurs,
For example, one-to-N communication packets have priority over one-to-one communication packets. Also in the one-to-N communication, packets for a plurality of groups G have priority over packets for one group G. That is, (DAR, D
AC) is given priority over a packet represented by (0, 0) over a packet represented by (0, n) or (m, 0).

The contention arbitration process is performed by, for example, a contention arbitration circuit (not shown) provided at the input stage of the concentrators 12 and 13.

The operation of the above configuration will be described. First, the operation when performing one-to-one communication will be described with reference to FIG.

FIG. 4 shows that (1,1) node 10 to (1,1)
(L) shows a case where a packet is transmitted to the (K, L) node 10 via the node 10.

In this case, from the transmission packet output circuit 11 of the (1, 1) node 10, a packet in which the column address K of the (K, L) node 10 is written in the DAR and the row address L is written in the DAC is written. Is output. This packet is transmitted through the concentrator 13 and the column side output line 15,
Each node 1 in the column group GR1 to which the own node 10 belongs
0 is supplied.

The packet supplied to each node 10 in the column group GR1 has the DAC content of (1, L) node 1
Since it matches the row address L of 0, it passes through the DAC filter 18 of this (1, L) node 10 and is discarded at the other nodes 10.

(1, L) DAC filter 1 of node 10
The packet passing through the node 8 has the DAR content of this node 10
Is not coincident with the row address L, and is supplied from the column selector 20 to the concentrator 12 (processing). Thereby, this packet is transmitted to each node 10 in the row group GCL to which the (1, L) node 10 belongs.

At the same time, the column selector 20
The CK circuit 23 is activated (process). As a result, an ACK signal is output from the ACK circuit 23. This A
The CK signal is returned to the transmission source node 10 via the concentrator 13 and the column output line 15. This allows
The node 10 can confirm that the packet has been relayed normally.

The packet supplied to each node 10 in the row group GCL has a DAR content of (K, L) node 1
Since it matches the column address K of 0, only the DAR filter 19 of this (K, L) node 10 passes, and the other nodes 10 discard it.

(K, L) DAR filter 1 of node 10
9, the content of the DAC is the node 10
, Is supplied from the row selector 21 to the reception buffer 22 and stored in the buffer 22 (processing). As a result, the packet has been transmitted from the (1, 1) node 10 to the (K, L) node 10.

In the above description, the case where the (1, L) node 10 is a relay node has been described.
A similar operation is performed when the node 10 is used as a relay node.

In the above description, the source node 10
Although the case has been described where the destination node 10 and the destination node 10 belong to different groups G in both columns and rows , packets can be transmitted even when one of the columns or rows belongs to the same group G.
In this case, the packet relay process is not performed, and only the capturing process is performed. For example, when transmitting a packet from the (1,1) node 10 to the (1, L) node 10 in the same column group GR1, the (1, L) node 10 performs a capturing process.

Next, a case where one-to-N communication is performed will be described.
First, a case of performing one-to-N communication with one group G as a destination will be described with reference to FIGS.

FIG. 5 shows a case in which one-to-N communication from the (1, 1) node 10 to the row group GCL is performed.

In this case, the transmission packet output circuit 11 of the transmission source node 10 outputs a packet in which the predetermined value 0 is written in the DAR and the row address L is written in the DAC. This packet is supplied to each node 10 in the column group GR1 to which the own node 10 belongs via the concentrator 13 and the column side output line 15.

The packet supplied to each node 10 in the column group GR1 is such that the contents of the DAC are (1, L) nodes 1
Since it matches the row address L of 0, it passes through the DAC filter 18 of this (1, L) node 10 and is discarded at the other nodes 10.

(1, L) DAC filter 1 of node 10
Since the content of the DAR is the predetermined value 0, the packet passing through 8 is supplied from the column selector 20 to the reception buffer 22 and stored in the reception buffer 22 (processing).

This packet is supplied from the column selector 20 to the concentrator 12 (processing). Thereby, this packet is transmitted to each node 10 in the row group GCL to which the (1, L) node 10 belongs. At the same time, the ACK circuit 23 is activated by the column selector 20 (process). As a result, the source node 10 is notified that the packet has been relayed normally.

The packet supplied to each node 10 in the row group GCL is taken in by the DAR filters 19 of all the nodes 10 because the content of the DAR is a predetermined value 0. Thereafter, since the content of the DAC matches the row address L of the corresponding node 10, the packet is supplied from the row selector 21 to the reception buffer 22 and stored in the buffer 22 (processing). As a result, in one packet, the (1,1) node 10
1: N communication has been made to all the nodes 10 within the group.

FIG. 6 shows a case in which one-to-N communication is performed from the (1, 1) node 10 to the column group GRK.

In this case also, a detailed description is omitted,
The packet output from the (1,1) node 10 is
The (K, 1) node 10 captures the
The data is transmitted to all the other nodes 10 in the column group GRK via the (K, 1) node 10, and is taken in by each node 10.

In the above description, the case where the destination is a group G different from the group G to which the own node 10 belongs is described. However, in this embodiment, the same group G can be the destination.

For example, one-to-N from the (1, 1) node 10 to the column group GR1 to which the node 10 belongs
When communication is performed, a packet in which the column address 1 is written in the DAR and the predetermined value 0 is written in the DAC may be output to the column side output line 15. In this case, the column group GR
At all other nodes 10 in 1, packet capture is performed according to:

Next, referring to FIG. 7, all row groups GC1 to GCN (in other words, all column groups
The case where one-to-N communication is performed with destinations GR1 to GRM) will be described.

FIG. 7 shows a case where one-to-N communication is performed from the (1, 1) node 10 to all the row groups GC1 to GCN.

In this case, the transmission packet output circuit 11 of the (1, 1) node 10 outputs a predetermined value 0
Is written, and a second packet in which, for example, a predetermined value 0 is written in DAR and the row address 1 of the own node 10 is written in DAC is output.

The first packet is sent to the concentrator 13
Via the column side output line 15 to each node 10 in the column group GR1 to which the own node 10 belongs. On the other hand, the second packet is transmitted via the concentrator 12 and the row side output line 14 to the row group G to which the own node 10 belongs.
It is supplied to each node 10 in C1.

The first packet supplied to each node 10 in the column group GR 1 is taken in by the DAC filters 18 of all the nodes 10 because the content of the DAC is a predetermined value 0. Thereafter, since the content of the DAR of the first packet is the predetermined value 0, the column selector 20 sends the first packet to the reception buffer 2.
2 and stored in the buffer 22 (processing).

In the first packet, the contents of the DAC are rewritten from the predetermined value 0 to the row address of the own node by the column selector 20 (processing). For example,
In the (1, N) node 10, the contents of the DAC are rewritten from the predetermined value 0 to the row address N of the own node 10.

The first packet whose rewriting has been completed is
It is supplied to the concentrator 12 (processing). Thereby, the first packet is supplied to each node 10 in the row group GCn to which the own node 10 belongs. At the same time, the ACK circuit 23 is activated by the column selector 20 (process). Thus, the (1, 1) node 10 is notified that the relay of the packet has been normally completed.

The first packet supplied to each node 10 in the row group GCn (excluding GC1)
0 is stored in the receiving buffer 22 (process).

On the other hand, each node 10 in row group GC1
Are stored in the reception buffer 22 of each node 10 according to the processing.

As described above, by transmitting two packets, one-to-N communication has been performed from the (1, 1) node 10 to all the other nodes 10.

In the above description, the first packet is transmitted to each node 1 in the column group GRm to which the own node 10 belongs.
0, and the second packet is transmitted to each node 10 in the row group GCn to which the own node belongs. However, the reverse transmission may be performed.

In the above description, the case where packets are transmitted to all the row groups GC1 to GCN has been described. However, if the second packet is not transmitted, the destination of the packet is changed to the row to which the own node 10 belongs. Row groups GC2 to GCN other than group GC1 can be limited.

According to this embodiment described in detail above, the following effects can be obtained.

(1) First, the destination of a packet can be specified in units of one or a plurality of groups G, so that a packet having the destination written for each node 10 is not transmitted and a 1: N Communication can be performed. This can reduce the time and effort when performing one-to-N communication, and can suppress a decrease in throughput when relaying is required.

(2) DA (DAR and / or DA
By writing the predetermined value 0 to C) , one-to-N communication can be performed.
Packets of the same structure can be used. Thereby, the configuration for generating the transmission packet can be simplified.

In the above description, the case where the node has the one-to-one communication function and the one-to-N communication function has been described.
In the present invention, only the one-to-N communication function may be provided. In addition, it goes without saying that the present invention can be variously modified without departing from the gist thereof.

[0076]

As described in detail above, according to the present invention ,
In Case subtype network system, without sending the packet wrote the destination for each node, one-to-N
Can be provided.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of the present invention.

2 is a diagram illustrating a logical arrangement of the nodes in the rated child network system.

FIG. 3 is a diagram showing a configuration of a packet.

FIG. 4 is a diagram illustrating an example of one-to-one communication.

FIG. 5 is a diagram for explaining an example of one-to-N communication for one group.

FIG. 6 is a diagram for explaining another example of one-to-N communication for one group.

FIG. 7 is a diagram for explaining an example of one-to-N communication for all groups.

[Explanation of symbols]

10 node, 11 transmission packet output circuit, 12, 1
3 ... concentrator, 14 ... row side output line, 15 ... column side output line, 16 ... column side input line, 17 ... row side input line, 18 ...
DAC filter, 19: DAR filter, 20: column selector, 21: row selector, 22: reception buffer, 23,
24 ... ACK output circuit.

──────────────────────────────────────────────────続 き Continued on the front page (72) Inventor Masanori Nozaki 1-7-12 Toranomon, Minato-ku, Tokyo Inside Oki Electric Industry Co., Ltd. (56) References Oie, Y. Sasaki, Y .; Miyahara, H .; , "LookNet: A switching net work for high speed communication", IEEE ICC '93. vol2, (1993.5.23), pp. 1225-1230 (58) Field surveyed (Int. Cl. ⁷ , DB name) H04L 12/28 H04L 12/56

Claims (3)

(57) [Claims] And 1. A plurality arranged in a grid nodes, each column and each row, a plurality of nodes belonging to them their
And a node connection means for directly connecting a packet to all nodes belonging to the same row or column so that the packet can be transmitted, and the destination of the packet is the coordinate of the destination node in the column direction. in nodes in rated child network system configured to be represented as by the row direction of the coordinates, of the destination indicating section of the packet, the column coordinate is written
By writing a predetermined value to the column
Generate packets destined for any column to which the node does not belong
This packet is sent to all other
To the node, and in the destination notation part of the packet,
A predetermined value is set in the line-side notation portion where the coordinates in the line direction are written.
By writing, any line to which the own node does not belong
Generates a packet to be the destination, and the own node
Packet transmission to send to all other nodes in the column to which it belongs
Means and own node belongs from other nodes in the row to which own node belongs
When a packet destined for a column is received, this packet is
Take in the own node and in the column to which the own node belongs
To all other nodes, and the own node belongs to
From the other node in the column, the destination
When a packet is received, this packet is
And all other nodes in the row to which the own node belongs.
Packet capture / relay means to be transmitted to the node , and the own node belongs from another node in the row to which the own node belongs
When a packet addressed to a row is received, this packet is
Incorporated in own node, and in the column to which own node belongs
A packet from another node destined to the column to which the node belongs
When receiving the packet, the
Case subtype network system node characterized by comprising a packet capturing means. 2. A plurality of nodes arranged in a grid,
For each column and each row, the nodes belonging to them are
Respectively, directly to all of the nodes belonging to the same row or column
Node connection means for connecting so that packets can be transmitted;
And the destination of the packet is
It is represented by the coordinates in the column direction and the coordinates in the row direction of the destination node.
In a grid-type network system configured to
In that node, if giving the packet to all nodes except the own node
In the column, the coordinates of the destination notation section in the column direction are written.
Column side notation part and row side table in which the coordinates in the row direction are written
A first packet in which a predetermined value is written to both the
Write a predetermined value in the column-side notation section (or the row-side notation section)
In the row side notation part (or the column side notation part),
The first column in which the column coordinates (or row coordinates) of the
The packet and the data part generate the same second packet,
1 packet in the column (or row) to which the own node belongs
Sends the second packet to the node to which the node belongs.
Packet transmitting means for transmitting to another node within (or within a column)
And from another node in the column (or row) to which the own node belongs
The predetermined value is written in both the column side notation section and the row side notation section.
When the first packet is received, the first packet is received.
Packet into the own node, and the first packet
The row side notation part (or the column side notation part)
Rewrite to the row (or column) to which the node belongs, and own node belongs
Packet to be sent to all other nodes in a row (or column)
From the other node in the row (or in the column) to which the own node belongs.
First packet addressed to the row (or column) to which the code belongs
Or, when the second packet is received, this packet is
It has and a packet capture means for capturing within over de
A node of the grid type network system characterized by the above. 3. A plurality of nodes arranged in a grid,
For each column and each row, the nodes belonging to them are
Directly to all nodes belonging to the same row or column
Node connection means for connecting so that packets can be transmitted;
And the destination of the packet is
It is represented by the coordinates in the column direction and the coordinates in the row direction of the destination node.
In a grid-type network system configured to
In that node, all lines except the own node belongs (or other sequence)
(Or column) in the case of providing the packets to a node,
Column-side notation in which the coordinates in the column direction of the destination notation section are written
Part and the line-side notation part in which the coordinates in the line direction are written.
A packet in which a predetermined value is written is generated in the
To the other node in the column (or row) to which the node belongs.
Packet transmitting means for transmitting a packet from another node in a column (or a row) to which the own node belongs.
The predetermined value is written in both the column side notation section and the row side notation section.
When a packet is received, it
And the line-side notation of this packet
Section (or the column-side notation section) to the row (or
In the row (or in the column) to which the own node belongs
Capture and middle joint to send to all other nodes
A row and another node in the row (or column) to which the own node belongs
Receives a packet addressed to the row (or column) to which the code belongs
Then, a packet that takes this packet into its own node
A grid-type net provided with an intake means
Work system node.