JPH11510011A - Priority arbitration for point-to-point and multipoint transmission - Google Patents

Abstract

SUMMARY An asynchronous transfer mode switch and method for facilitating priority arbitration of point-to-point and point-to-multipoint transmissions is disclosed. To perform a point-to-point operation, the bandwidth arbiter (12) maintains a first connection list and a bit vector indicating a designated destination port. The list maintained by the bandwidth arbiter is compared to the unallocated output port bit vector and a match between the two is made for a point-to-multipoint transmission utilizing the immediate unused bandwidth in the switch (18). Is determined. To execute the point-to-point operation, each input port holds a connection list associated with each output port. This list is used in the bandwidth arbiter along with the output request information for each input port to match requests to unassigned output bit ports. The bandwidth arbiter may assign a priority to the connections in the list.

Description

Detailed Description of the Invention Priority arbitration for point-to-point and multipoint transmission Field of the invention The present invention relates generally to telecommunications networks, and more particularly to point-to-point and point-to-multipoint arbitration, bandwidth allocation, and delay management in asynchronous transfer mode switches. Related matter information Claim priority to provisional application 60 / 001,498 (Title of Invention "Communication Method and Apparatus", filed July 19, 1995). Background of the Invention Telecommunications networks, such as Asynchronous Transfer Mode (ATM), are used to transfer voice, video, and other data. The ATM network sends data from a source to a destination through a switch by routing data units such as ATM cells. The switch includes an input / output (I / O) port through which ATM cells are transmitted and received. The appropriate output port for transmitting the cell is determined based on the cell header. One of the problems associated with ATM networks is cell loss. Cells are buffered in each switch before being routed and transmitted from the switch. More specifically, a switch generally has a buffer at its input or output that temporarily stores cells before transmission. As network traffic increases, the likelihood of data loss due to lack of buffer space increases. If the buffer size is insufficient, cells will be lost. Cell loss can cause undesired interruptions in voice and video data transmission, and can cause even more severe damage to other types of data transmission. In point-to-point transmission, cells are transmitted from a single input port to a single output port through the switch body. In point-to-multipoint transmission, cells are transmitted from a single input to multiple outputs through the switch body. To perform such a transmission, each of the designated outputs must be able to receive cells from the transmitting input port. That is, it must have an appropriate buffer space. However, the more traffic in the switch, the less likely it is that each of the designated outputs will be ready to receive the cell at the same time as the cell is enqueued. In some situations, this will result in delayed transmission. In the worst case, cells are delayed indefinitely and incoming cells on that connection are discarded. Therefore, it is desired to realize transmission with reduced or eliminated cell loss. Summary of the Invention Asynchronous transfer mode (ATM) switches and methods for implementing point-to-multipoint and point-to-point transmissions are disclosed. The ATM switch includes a bandwidth arbiter, a plurality of input ports each including one switch To Switch Port Processor (TSPP), and a plurality of output ports. Each input port of the switch contains a switch assignment table (SAT) that allows bandwidth for the connection. Each SAT includes a number of consecutive ordered cell timeslots and a point pointing to one of the slots. The SAT pointer for each input port is synchronized so that at any given time, each of the pointers points to the same slot location of each SAT corresponding to the pointer. Each TSPP maintains a list of point-to-point connections, and more specifically, one list for each output port of the switch. The bandwidth arbiter holds a bit vector for each port indicating an output port required for transmission of a point-to-point cell. Each connection is assigned to a bandwidth type based on the traffic type associated with the connection. There are two types of bandwidth allowed in a switch. Allocated bandwidth and dynamic bandwidth. Dynamic bandwidth is the bandwidth "reserved" for use of the connection for which bandwidth is to be allocated. In general, a connection with an allocatable bandwidth is permitted to access all amounts of the bandwidth allocated to the connection. Thus, traffic types that require deterministic control of delay are assigned allocated bandwidth. Dynamic bandwidth is the bandwidth "shared" by any of the various competing connections. Since dynamic bandwidth is a shared resource, it is generally not guaranteed that any connection can access a particular amount of bandwidth. For this reason, dynamic bandwidth is typically allocated to connections that have relatively large delay bounds. Other connections may be assigned to a combination of dynamic and allocated bandwidth. Thus, any cell time for which the SAT entry is not valid or whose scheduling list does not accommodate the cell will represent an opportunity for unallocated bandwidth. When performing a point-to-point operation, the switch grants dynamic bandwidth to the point-to-point connection using a point-to-point request bit vector and a round robin operation. At the beginning of the cell time, a match is determined for each selected request bit vector in parallel and authorization is performed according to a prioritization scheme starting from the first position. Then, until all the requested bit vectors have been given a permission opportunity, the other request bit vectors are given a permission opportunity. The second position indicates the individual bits that receive the priority for the grant opportunity. If bandwidth is not granted, the opportunity for grant is given to other bits in the request bit vector. If the output port specified by the second location is enabled, then at the next cell time, the first location will be located at the next successive request bit vector relative to the previous cell time. Otherwise, the first position is not changed. Thus, each TSPP receives the same treatment over a period of time. When performing a point-to-multipoint operation, the bandwidth arbiter maintains a list of connections and a bit vector indicating the designated destination port for the point-to-multipoint cell. The bandwidth arbiter list is compared to an unassigned output port bit vector generated from the SAT, and a point-to-multipoint transmission is performed by utilizing the immediately unused bandwidth in the switch. Is determined. The bandwidth arbiter may assign a priority to the connections in the list. Bandwidth arbiters also include a combined arbiter mechanism that allocates dynamic bandwidth to both point-to-multipoint and point-to-point connections. In the preferred embodiment, each type of connection, point-to-multipoint and point-to-point, is prioritized at least two levels, high and low. Next, dynamic bandwidth is granted in four main steps. In the first step, a high priority point-to-multipoint connection is granted to the dynamic bandwidth in the manner described above. In a second step, a high-priority point-to-point connection is granted to the remaining dynamic bandwidth from the first step in the manner described above. In a third step, a low priority point-to-multipoint connection is granted to the remaining bandwidth from the second step. In a fourth step, a low priority point-to-point connection is granted to the remaining bandwidth from the third step. Switch efficiency is improved by using immediate unused bandwidth. As switch traffic increases, the available bandwidth decreases. However, there is always unused bandwidth and such bandwidth will be wasted if not used. Thus, by using unused bandwidth, point-to-point and point-to-multipoint transmissions that would otherwise degrade would be realized, and switch efficiency would be improved. Such use is made possible by arbitration techniques that reduce delay. BRIEF DESCRIPTION OF THE FIGURES These and other features and advantages of the present invention will become apparent from the following detailed description of the invention. FIG. 1 is a block diagram of an exchange that facilitates point-to-multipoint operation. FIG. 2 is a block diagram showing the operation of the exchange assignment table of FIG. FIG. 3 is a block diagram illustrating the operation of the bandwidth arbiter list. FIG. 4 is a flow diagram illustrating the matching between the requested bit vector and the unassigned output port bit vector. FIG. 5 is a block diagram illustrating round-robin assignment of bandwidth to TSPP requests. FIG. 6 is a flowchart illustrating a method of point-to-multipoint band arbitration. 7 and 8 are block diagrams illustrating point-to-point bandwidth arbitration. FIG. 9 is a block diagram illustrating point-to-point / point-to-multipoint combined band arbitration. 10A and 10B are flowcharts illustrating a method of point-to-point / point-to-multipoint combined band arbitration. Detailed description of the invention Referring to FIG. 1, the exchange comprises an N × N exchange main body 10, a bandwidth arbiter 10, a plurality of exchange terminating port processor subsystems (TSPP) 14, a plurality of exchange terminating port processors ASIC 15, a plurality of exchange originating sides. It includes a port processor subsystem (FSPP) 16, a plurality of switch originating processor ASICs 17, a plurality of multipoint topology controllers (MTCs) 18, and a switch assignment table (SAT) 20. The N × N switch body, which may be an ECL crosspoint switch body, is used for cell data transmission and achieves a throughput of N × 670 Mbps. The bandwidth arbiter dynamically controls switch body interconnects and schedules temporarily unused bandwidth to resolve multipoint-to-point bandwidth contention. Each TSPP 14 schedules the transmission of cells 22 from multiple connections to the switch itself. The physical line interface between the input link and TSPP 14 is not shown. The FSPP receives cells from the switch body and structures these cells into outgoing links. The physical line interface between the output link and the FSP P16 is not shown. The switch allocation table controls the crossbar input / output mapping, connection bandwidth, and maximum delay through the switch itself. When traversing the switch, cell 22 first enters the switch through input port 24 and is buffered in queue 26 of the input buffer. The cells are then transmitted from the input buffer to the output buffer queue 28 of the output port. The cells are sent from the output port 30 to the outside of the switch, such as another switch. Each input port 24 includes a TSPP 14 and each output port 30 includes a FSPP 16 to facilitate traversing the switch. The TSPP and FSPP each include a cell buffer RAM 32 structured into queues 26,28. All cells in the connection path pass through one queue of each port for the duration of the connection, one TSPS queue and one FSPP queue. Thus, the queue preserves cell order by handling only one connection per queue. This method also enables quality of service (QoS) guarantee for each connection. Request and feedback messages are transmitted between the TSPP and the FSPP, and flow control is performed. Flow control prevents cell loss in the switch and is performed after arbitration and before transmission of data cells. Flow control is realized for each connection. Referring to FIGS. 1 and 2, each TSPP in the switch includes a SAT 20 that manages bandwidth allocation. SAT is the basic mechanism behind cell scheduling. Each SAT 20 includes a plurality of consecutively ordered cell timeslots 50 and a pointer 52 pointing to one of the slots. All pointers in the switch are synchronized such that at any given time, each of the SAT pointers at each input port points to the same slot location of each SAT to which the pointer is associated, e.g., the first slot. You. In operation, the pointer is advanced by one and each slot is active for 32 clocks of 50 MHz. If the pointer points to a slot, the TSPP uses the corresponding entry 51 in the SAT to obtain a cell to be sent to the switch body 10 and starts flow control. Each of the counters is incremented once at each cell time. Then, when the pointer reaches the last slot, it returns to the first slot. Thus, assuming that the depth of the SAT defining the frame is 8k, the pointer scans the SAT about every 6 mec, which gives a maximum delay of about 6 msec for transmission opportunities. By multiplexing a given entry of multiple slots in the SAT, delay can be reduced. The maximum delay experienced by the terminating cell corresponds to the number of slots between the pointer and the slot containing the entry specifying the cell destination. Thus, when creating multiple entries to reduce the maximum number between slots, multiple entries are preferably placed at equal intervals in the SAT. Thus, the maximum transmission opportunity delay corresponds to the frequency and interval of multiple entries in the SAT. The amount of bandwidth allowed for a particular connection corresponds to the frequency with which a given entry appears on the SAT. Each slot 50 provides 64 Kbps of bandwidth. Since pointers cycle through the SAT at a constant rate, the total bandwidth guaranteed for a particular connection corresponds to the product of 64 Kbps and the number of occurrences of that entry. For example, a bandwidth of 320 Kbps is permitted for the connection identifier “g (4, 6)” appearing in five slots. Importantly, during operation, the immediate unused bandwidth 60 is made available to the switch. Such immediate unused bandwidth occurs when the bandwidth, ie, the SAT entry, has not been assigned to any connection. This bandwidth is referred to as “unallocated bandwidth”. Immediate unused bandwidth also occurs when a SAT entry is assigned to a connection, but the connection does not have any cells enqueued for transmission across the switch. This bandwidth is referred to as “unused allocated bandwidth”. Both types of bandwidth are collectively referred to as "dynamic bandwidth." Some connections, such as those assigned to available bit rate (ABR) QoS levels, use such dynamic bandwidth. The bandwidth arbiter operates to increase efficiency within the switch by allowing dynamic bandwidth for such connections. Referring to FIGS. 1-3, dynamic bandwidth is used when the connection has no allocated bandwidth, or when the incoming cell rate is greater than the allocated rate indicated by the input queue threshold. Can be In either situation, the point-to-multipoint transmission described in the SAT entry 51 is a list maintained by the band arbiter as a "request" so that the point-to-multipoint transmission can take place at the next available opportunity. 53. The list 53 maintained by the band arbiter includes two fields for storing point-to-point transmissions utilizing dynamic bandwidth. The connection identifier field 56 is used to store a connection identifier (eg, “a”), and thus also indicates the original port. Bit vector field 58 is used to indicate the output port designated for transmission. The bit vector field is a bit mask containing 8 bits in the case of an 8 × 8 switch, each bit corresponding to a particular output port. Thus, for example, if the SAT entry is “a (2,3)”, the list 53 will contain “00000110” in the bit vector field (the port number starts with “1” instead of “0”). A logical value “1” in this bit vector field indicates that the destination output ports are “2” and “3”, and a logical value “0” indicates an output port that is not a destination. The connection and the bit vectors of the list 53 are entered sequentially in the same order as received. In another implementation, a point-to-multipoint connection may be split into two subclasses. Cells are transferred to each of these subsets. A point-to-multipoint bit vector lookup will have an additional identifier that indicates which subset will forward the cell. In this case, the list held in the band arbiter and the TSPP contains both the connection identifier and the subset identifier. In this embodiment, the subset identifier is called a sub-queue. When performing a point-to-multipoint operation of the cells described in the list maintained by the bandwidth arbiter, the bandwidth arbiter checks for a match between the list and the dynamic bandwidth. Specifically, the connection identifier 56 and bit vector 58 corresponding to "a (2,3)" are enabled for dynamic bandwidth opportunities to be simultaneously transmitted to each output port specified by the request. The cell is put into the list 53 so that the cell is transmitted when the cell is transmitted. Referring to FIGS. 1-4, in order to determine a match between the requests in the list held in the bandwidth arbiter and the available bandwidth, the bandwidth arbiter first determines all the bit vectors assigned to the SAT. And compute the unassigned output port vector by inverting the resulting bits to obtain a single unassigned output port bit vector. For a particular input port, incoming requests are checked in parallel for matching. For simplicity, matching may only be performed on the first four requests in the list. A match is established if all bits in the request match the unassigned bit vector. If the match is successful, the request is stripped from the unassigned bit vector, and the stripped bit vector serves as a new unassigned bit vector. The remaining available output ports that are matched against the port request bit vector are shown. After matching all requests, the matched request is transmitted and the transmitted request is dequeued from the list. Prioritization techniques may be used in conjunction with bandwidth arbiter matching operations to support switch traffic with different priority levels, such as QoS levels. To achieve such prioritization, each TSPP determines a priority for each request issued. Such priority levels may be high and low levels, or may include more than two levels. When prioritization is performed, the band arbiter attempts to match higher priority requests before attempting to match lower priority requests. When matching is successively established, the number of unassigned bits contained in the unassigned bit vector decreases, so that a request with a high priority is more easily obtained and transmitted as compared with a request with a lower priority. Such easy matching achieves faster response and higher bandwidth for high-priority connections. Referring to FIG. 5, the bandwidth arbiter may grant bandwidth to the requesting TSPP by attempting to match available bandwidth in a round-robin fashion. Pointer 67 is used to select the TSPP for which matching is attempted first, eg, TSPPi + 1. After matching is attempted for TSPPi + 1, then matching is attempted for TSPPi + 2. Then, the process is continued until TSPPi so that matching is attempted for all TSPPs. If the first TSPP (here, TSPPi + 1) can transmit the cell of the oldest entry (here, indicated by connection "a"), at the next cell time, the pointer 67 moves to the next TSPP (here, TSPPi + 2). ) To start with. On the other hand, if the first TSPP cannot transmit the cell of the oldest entry, at the next cell time, the pointer 67 starts from the same TSPP (here, TSPPi + 1). If a plurality of matches are determined for one TSPP, the oldest match is selected and transmitted. This ensures that the point-to-multipoint connection receives the bandwidth. If high / low priority is used, independent high and low round robin operations are performed to grant bandwidth. Each round robin operation operates similarly, but does not attempt to match low priority requests until all high priority requests have been matched. That is, an independent round robin operation is performed for each priority level. To further ensure that transmission opportunities are given to point-to-multipoint connections, a portion of unallocated bandwidth, ie, unallocated SAT entries, is reserved for point-to-multipoint transmission. This approach increases the chances given to point-to-multipoint connections that specify a large number of output ports to be matched and transmitted, thus eliminating connections that are stuck due to bandwidth exhaustion. FIG. 6 shows a method of point-to-multipoint arbitration. In a first step 68, the bit vector representation of the SAT entry is listed as a connection identifier and output bit vector. Then, at the next cell time, the allocated bit vectors are ORed in step 70 and used to generate the unallocated bit vectors. Next, in step 72, an attempt is made to match the unassigned bit vector with the request N in the list. Where N is the oldest request in the list. If no match is found, N is incremented in step 74 and an attempt is made to match the unassigned bit vector with the request N + 1, the next oldest request in the list. If the match is successful, at step 76, the matched request bit vector is removed from the unassigned bit vector to obtain an updated unassigned bit vector. Next, in step 78, the cell corresponding to the matched request is transmitted, and in step 80, it is determined whether the end of the list held by the bandwidth arbiter has been reached. If the end of the list is reached, that is, if an attempt is made to match the unassigned bit vector with all the requests in the list, the flow is terminated. If the end of the list has not been reached, N is incremented and an attempt is made to match the next oldest request in the list with the unassigned bit vector. Referring to FIG. 7, a bandwidth arbiter 12 may be used to grant dynamic bandwidth for point-to-point transmission. Each point-to-point transmission is from one input port to one output port. To perform point-to-point transmission, each TSPP 14 includes a connection list 82 corresponding to each output port of the switch, ie, one connection list for each output port, and the bandwidth arbiter It contains a point-to-point request bit vector 84 corresponding to the TSPP, ie, one request bit vector for each TSPP. The connection list having a depth of, for example, 16,384 includes a list of connections having cells enqueued for point-to-point transmission to the output port associated with the connection list. Each request bit vector is a bit mask for each TSPP indicating to which output port each TSPP is requesting transmission by a logical value “1”. Both the connection list and the request bit vector are used to track the output ports at which cells are enqueued to each TSPP and to grant bandwidth based on that information. The point-to-point request bit vector is set according to a signal from the TSPP. More specifically, when a cell is enqueued for point-to-point transmission, the connection corresponding to that cell is loaded into the TSPP connection list, and the TSPP transmits the transmission to the bandwidth arbiter to the output port specified by the connection. Send a request message 86 containing the request. For example, when connection "a" is enqueued in connection list 1, TSPP0 transmits a request message to the bandwidth arbiter, and in response, the bandwidth arbiter sets bit 1 of request bit vector 0 to a logical value. Set to “1”. When the cell is transmitted to the output port, the connection is dequeued from the connection list, and when the connection list becomes empty, a withdrawal request message 88 is transmitted to the bandwidth arbiter. In response, the bandwidth arbiter sets the bit corresponding to the request to a logical "0". On the other hand, if the connection list is not empty when the connection is dequeued, the withdrawal request message is not sent to the bandwidth arbiter and the request remains valid for the next enqueued connection. 7 and 8, the bandwidth arbiter grants dynamic bandwidth to the point-to-point connection using a point-to-point request bit vector and a nested round-robin operation. At the beginning of the cell time, a matching is determined bit by bit on each selected request bit vector, and then authorization is performed according to a prioritization scheme starting from a first location, for example location 90. Until the opportunity for permission is given for all the requested bit vectors, the opportunity for permission is given to other request bit vectors. The second position 92 indicates each bit in the selection request bit that receives the priority for the opportunity of grant. If bandwidth is not granted, the opportunity for grant is given to other bits in the request bit vector. If the output port specified by the second location 92 is enabled, then at the next cell time, the first location will be located at the next successive request bit vector relative to the previous cell time. Otherwise, the first position is not changed. The second position start point is determined similarly. In this way, each TSPP receives the same treatment over a period of time. Referring to FIG. 9, the bandwidth arbiter may include a combined arbiter mechanism that allows dynamic bandwidth for both point-to-multipoint and point-to-point connections. In the preferred embodiment, both point-to-multipoint and point-to-point are prioritized at least two levels, such as high and low. Dynamic bandwidth is granted in four main steps. In a first step 94, a high priority point-to-multipoint connection is granted for dynamic bandwidth in the manner described with respect to FIGS. In a second step 96, the remaining dynamic bandwidth from the first step is granted to a high priority point-to-point connection in the manner described with respect to FIGS. 7 and 8 above. In a third step 98, the remaining bandwidth from the second step is granted to a low priority point-to-multipoint connection. In a fourth step 100, the remaining bandwidth from the third step is granted to a low priority point-to-point connection. 10A and 10B illustrate a method for allocating dynamic bandwidth to both point-to-multipoint and point-to-point connections. In a first matching step 102, an attempt is made to match an initial high priority point-to-multipoint request with an unassigned output port bit vector representing an unassigned output port. If no match is found, then in step 104 it is determined whether the end of the point-to-multipoint high priority list has been reached. If a match is found in step 102, then in step 106 the high priority point-to-multipoint cell bit vector is removed from the unassigned output port bit vector and after the cell is transmitted in step 106, Proceed to step 104. If the end of the list has not been reached, then the next request is loaded at step 110 and then the method proceeds to step 102. If the end of the list has been reached, the process proceeds to the second matching step 112. In a second matching step, an attempt is made to match the first high priority point-to-point cell indicated by the first and second pointers. If no match is found, then at step 114, it is determined whether the TSPP pointed to by the first pointer has been tried for all bits of the point-to-point request bit vector. If not all bits have been examined, the second pointer is incremented at step 116 and the method proceeds to step 112. If a match is found in step 112, the selected bits are removed from the unassigned output port bit vector in step 118, and the cell is transmitted in step 120. Next, in step 122, the first pointer is incremented. Next, in step 124, it is determined whether the matching has been checked for all TSPPs. If a negative determination is made, the process returns to step 112. If all TSPPs have been examined, then, in step 126, the first and second pointers are reset according to the no exhaustion policy described above. Following step 126, the match is checked for a low priority point-to-multipoint request. In a third matching step 128, an attempt is made to match the initial low priority point-to-multipoint request with an unassigned output port bit vector representing an unassigned output port, ie, dynamic bandwidth. If no match is found, then in step 130 it is determined whether the end of the point-to-multipoint low priority list has been reached. If a match is found in step 128, in step 132 the high priority point-to-multipoint cell bit vector is removed from the unassigned output port bit vector, the cell is transmitted in step 134, and then the step 130 Proceed to. If the end of the list has not been reached, then the next request is loaded at step 136 and the method proceeds to step 128. When the end of the list has been reached, the process proceeds to the fourth matching step 138. A fourth matching step 138 attempts to match the low priority point-to-point cells indicated by the first and second pointers. If no match is found, then in step 140 it is determined whether all bits of the point-to-point request bit vector for the TSPP pointed to by the first pointer have been tried. If not all bits have been examined, the second pointer is incremented at step 142 and the method proceeds to step 138. If the match is successful at step 138, the selected bit is removed from the unassigned output port bit vector at step 144 and the cell is transmitted at step 146. Next, at step 148, the first pointer is incremented. Next, in step 150, it is determined whether the matching has been checked for all TSPPs. If a negative determination is made, the process returns to step 138. If all TSPPs have been checked, then in step 152 the first and second pointers are reset according to the no depletion policy and the flow for the current cell time ends. Having described the preferred embodiment of the invention, it will be apparent to one skilled in the art that other embodiments using the same concept are possible. Therefore, it is considered that the invention should not be limited to the disclosed embodiments, but only by the spirit and scope of the appended claims.

[Procedure of Amendment] Article 184-8, Paragraph 1 of the Patent Act [Submission date] February 18, 1997 [Correction contents] And a structured cell buffer RAM 32. All in the connection path All cells have one queue for each port for the duration of the connection: It passes through one queue of TSPP and one queue of FSPP. Therefore, the queue Preserves the cell order. In this way, the quality of service for each connection ( QoS) can be guaranteed.   Request and feedback messages are transmitted between the TSPP and the FSPP, Flow control is performed. Flow control prevents cell loss in the switch. Yes, after arbitration and before transmission of data cells. Flow system Control is realized for each connection.   Referring to FIGS. 1 and 2, each TSPP in the switch manages bandwidth allocation. SAT20. SAT is the basic mechanism behind cell scheduling is there. Each SAT 20 has a plurality of consecutively ordered cell timeslots 50 and slots. A pointer 52 pointing to one of the All pointers in the switch are At any given time, each of the SAT pointers at each input port will The same slot location of each SAT with which the Synchronized to point to In operation, the pointer is advanced one at a time, Become active for 32 clocks of 50 MHz. When the pointer points to a slot In this case, the TSPP uses the corresponding entry 51 in the SAT to Acquire the cell sent to 0 and start the flow control.   Each of the counters is incremented once at each cell time. And the pointer Returns to the first slot when it reaches the last slot. Therefore, define the frame If the SAT depth is 8k, the pointer scans the SAT about every 6 mec, This provides a maximum delay of about 6 msec for transmission opportunities. In SAT More than one                                The scope of the claims 1. Point-to-point and data units associated with the connection And a network switch for facilitating point-to-multipoint transmission,   Multiple output ports,   Receives a data unit from outside the exchange and outputs the received data unit A plurality of input ports each operable to transmit to at least one of the ports. And   An allocation map operable to store a representation of the dynamic bandwidth in the switch;   Data units enqueued for point-to-multipoint transmission A point-to-multipoint request map operable to store the representation;   Representation of data units enqueued for point-to-point transmission A point-to-point request map operable to store;   The dynamic bandwidth to the point-to-multipoint request map and the point-to-point -A matching operator that works to match the point request map With   When matching dynamic bandwidth becomes available, point-to-point and And the data units enqueued for point-to-multipoint transmission Network switch to be transmitted. 2. The point-to-multipoint request map includes a point-to-multipoint Connection associated with each data unit enqueued for 2. The connection field of claim 1 including a connection field operable to store an indication of the action. Network switch. 3. The point-to-multipoint request map contains each point-to-multipoint Operate to store a representation of the output port to which the int data unit is to be transmitted 3. The network switch of claim 2, further comprising a possible bit vector field. 4. The allocation map comprises a switch allocation operable to store an index identifier. Operative to store a table and a bit mask representing dynamic bandwidth within the switch A possible allocation table, the allocation table being indexed by the index identifier. The network switch according to claim 3, wherein 5. The matching operator is point-to-point via dynamic bandwidth For each data unit enqueued for transmission, a dynamic bandwidth is first enqueued. Continuously starting from queued point-to-multipoint data units 2. The network switch according to claim 1, which functions to perform matching. 6. The enqueued point-to-multipoint data unit has fewer At least two groups are prioritized, and the matching operator dynamically assigns low priority groups. Before matching bandwidth, make sure to match dynamic bandwidth to high priority groups. The network exchange according to claim 5. 7. The matching operator is compared with the bit vector field. Generate an unassigned output port bit vector 4. Match dynamic bandwidth to a to-multipoint data unit. Network switch as described. 8. The request map contains the enqueued point-to-multipoint Order in which data units are matched to dynamic bandwidth A first pointer indicating the data unit matching. 8. The network switch according to claim 7, wherein said network switch is incremented so as to be arranged in a rondrobin manner. 9. Each input port has a point-to-point core associated with each output port. Exchange port processor (TS) having a connection list of connection PP), and the list of point-to-point connections includes A command having a data unit enqueued for each assigned output port. 2. The network exchange according to claim 1, wherein a representation of the connection is stored. 10. The point-to-point request map includes, for each of the TSPPs, A point-to-point request bit vector, the point-to-point request The bit vector is associated with the point-to-point request bit vector. Each output to which a point-to-point data unit is to be transmitted from each TSPP 10. The network switch according to claim 9, wherein the network switch indicates a port. 11. Operable to select a point-to-point request bit vector. A first operation performed by the matching operator in a round-robin selection. 11. The network exchange according to claim 10, further comprising a pointer. 12. Output port bits in the point-to-point request bit vector Operable to select and round robin by the matching operator. 11. The network switch according to claim 10, including a second pointer operated by selecting an expression. 13. In the network exchange, point-to-point and And a point-to-multipoint transmission,   In a first storing step, storing the representation of the data unit in the request list;   In a second storing step, storing a representation of the dynamic bandwidth in the allocation list;   The request list is compared with the allocation list, and a match is established between the two. Judge whether or not   Determining at least one data unit for which a match has been determined, by the dynamic bandwidth Transmitting the data through the method. 14． The first storing step is for point-to-multipoint transmission. Stores the representation of the connection associated with each enqueued data unit Further storing a request map containing a connection field operable to 14. The method of claim 13, comprising steps. 15. The first storing step comprises the steps of: 15. The method of claim 14, further comprising the step of storing the requested bit vector representation of the packet. the method of. 16. The second storing step includes a bitmap representing a dynamic bandwidth in the switch. The method of claim 15 including the further step of storing a disk. 17． The comparing step includes the step of comparing the dynamic bandwidth bit mask with the request bit. 17. The method according to claim 16, comprising the further step of comparing with a vector. 18. Store multiple request bit vectors,   The step of comparing includes changing the request bit vector from high priority to low priority. Comprising the further step of prioritizing the at least two independent groups configured,   The step of comparing comprises comparing the low priority request bit vector with the low priority request bit vector. 18. The method of claim 17, wherein the method is performed before the priority request bit vector. 19. The request bit mask field contains the enqueued data unit Contains a pointer to the order in which the dynamic bandwidth was first matched,   The comparing may include incrementing a pointer to a round robin order. 18. The method of claim 17, further comprising the step of implementing data unit matching of Method. 20. The first storing step includes a step of connecting a point to each input port of the exchange. Storing a request-to-point bit vector,   The requested bit vector is used for each output requested by each input port of the switch. 14. The method of claim 13, containing an identifier of the force port. 21. The first storing step includes, for each output port associated with each list, Point-to-point connector with enqueued data unit 21. The method of claim 20, further comprising the step of storing a plurality of lists of options. 22. Transmission of point-to-point cells and point-to-multipoint cells An asynchronous transfer mode (ATM) switch for arbitrating for   Point-to-point and point-to-multipoint cells A plurality of input ports operable to receive a cell comprising:   A plurality of outputs operable to transmit the received data cells from the switch. Power port and   The cell is selected from the plurality of output ports from the plurality of input ports. A switch body operable to selectively forward to a port,   Operate the point-to-point cell and the point-to-multipoint cell. Arbitration operator operable to match specific bandwidth Prepared,   The arbitration operator is operated by the arbitration operator. Point-to-point and point-to-multipoint matched to dynamic bandwidth Before the int cell is forwarded to a specific port among the plurality of output ports, Which cells received at the plurality of input ports are output to the plurality of outputs through the switch. An ATM switch operable to determine whether to be forwarded to a port. 23. Point-to-multipoint cells matched to dynamic bandwidth The point-to-point cell matched to the specific bandwidth is Before being routed to the plurality of output ports by the Request to a specific port among the plurality of output ports by an operator Item 23. The ATM switch according to Item 22. 24. The arbitration operator removes point-to-point cells At least prioritize the first and second groups of high and low priority respectively. The ATM switch according to claim 22. 25. The arbitration operator is a point-to-multipoint cell At least the high priority and the low priority, respectively. 23. The ATM switch according to claim 22, wherein the first and second groups are prioritized. 26. The high priority group is matched to dynamic bandwidth before the low priority group The ATM switch according to claim 25. 27. The high-priority point-to-multipoint cell is the high-priority point. 27. The ATM of claim 26, which is matched to the dynamic bandwidth before the two-point cell. switch. 28. The low priority point-to-multipoint cell is the low priority point 28. The ATM of claim 27, wherein the ATM is matched to the dynamic bandwidth before the two-point cell. switch. 29. The arbitration operator is responsible for each point-to-point cell. A record is kept at least until the cell enters the switch body, and the record is 23. The ATM switch of claim 22, including an indication of an output port to which the cell is to be transmitted. 30. The arbitration operator is responsible for each point-to-multipoint Holding a record of the cell at least until the cell enters the switch body; 30. The ATM switch of claim 29, including an indication of an output port to which said cell is to be transmitted. Exchange. 31. When a point-to-point cell is received on an input port, the cell is Indicates that the queue has been queued and the output to which the point-to-point cell should be transmitted. A corresponding request message identifying the power port is provided by the arbitration operator. 31. The ATM switch of claim 30, which is sent to a server. 32. When the point-to-point cell is dequeued, a withdrawal request message A message is sent from the input port to the arbitration operator Item 34. The ATM switch according to Item 31. 33. The data unit associated with the connection at each input port is A plurality of input ports for receiving and a data unit associated with the connection. A plurality of output ports for transmitting data to a communication link coupled to each output port. Network switch,   During a specific time interval, data from an input port that competes for an output port Operable to store a representation of an output port that can be used to receive data units Bandwidth allocation data structure,   One of the plurality of input ports to at least one of the plurality of output ports Also act to store indications of data units enqueued for transmission to two A first set of possible request data structures;   At least one of the plurality of input ports is connected to the plurality of output ports. Each of said input ports having data units enqueued for transmission Data units enqueued for transmission to each output port selected for A second set of request data structures operable to store the indication;   Data enqueued for transmission in the first and second sets of the request data structure. The display of the control unit is competed for an output port during the specified time interval. Map to an available output port that can be used to receive the matching data unit. Matching control logic to make   Data enqueued for transmission in the first and second sets of the request data structure. Said output port wherein a display of a data unit is available for receiving a data unit Is reflected in the bandwidth allocation data structure, The data unit selected from the data units is selected from among the input ports. Selected An port operable to transfer from a port to a selected one of the output ports. -A network switch provided with a bitization operator. 34. The matching control logic may include: in the second set of request data structures, Competing display of data units enqueued for transmission for output port Match an available output port that can be used to receive the data unit Prior to the first time interval of the request data structure during the particular time interval. An indication of the data units enqueued for transmission in the set is shown in said data unit. 34. Match an available output port that can be used to receive the Network switch as described. 35. The arbitration logic is represented in a second set of the request data structures. The represented data units are at least as high priority and low priority first, respectively. 34. The network switch of claim 33, operable to prioritize and a second group. 36. The arbitration logic is represented in a first set of the request data structure. The represented data units are at least as high priority and low priority first, respectively. 36. The network switch of claim 35, operable to prioritize and a second group. 37. The arbitration logic is configured to store the data represented in the low priority group. Before matching the power unit to an available output port, Operate to match each represented data unit to an available output port 37. The network switch according to claim 36, which is operable. 38. The arbitration logic comprises the request data structure To a usable output port the data units represented in the first group of the second set of Prior to matching, the first set of the request data structure is represented in the first set. Operable to match the selected data unit to an available output port. 38. The network switch according to claim 37. 39. The arbitration logic includes a second set of request data structures. The data units represented in the second group are matched to available output ports. Before the requesting data structure, the data unit represented in the second set of the first set of request data structures. 39. The system of claim 38, operable to match the knit to an available output port. Network switch. 40. The arbitration logic mechanism includes a second Each output port where each data unit represented in the set is to be enqueued and transmitted. 34. The network switch according to claim 33, wherein the network switch holds the display of the network switch. 41. The arbitration logic mechanism includes a first data structure of the request data structure. Each output port where each data unit represented in the set is to be enqueued and transmitted. 41. The network exchange according to claim 40, wherein the network switch holds the display of the network switch. 42. A corresponding to each data unit represented in the second set of the request data structure Request message from the associated input port. And the request message is transmitted when the data unit is enqueued. That the data unit should be enqueued and transmitted 42. The network switch of claim 41, wherein said network switch indicates an output port. 43. Withdrawal request when the data unit is dequeued A message is transmitted from the corresponding input port to the arbitration logic. 43. The network switch of claim 42, wherein

────────────────────────────────────────────────── ─── Continuation of front page    (81) Designated countries EP (AT, BE, CH, DE, DK, ES, FI, FR, GB, GR, IE, IT, L U, MC, NL, PT, SE), OA (BF, BJ, CF) , CG, CI, CM, GA, GN, ML, MR, NE, SN, TD, TG), AP (KE, LS, MW, SD, S Z, UG), UA (AM, AZ, BY, KG, KZ, MD , RU, TJ, TM), AL, AM, AT, AU, AZ , BB, BG, BR, BY, CA, CH, CN, CZ, DE, DK, EE, ES, FI, GB, GE, HU, I L, IS, JP, KE, KG, KP, KR, KZ, LK , LR, LS, LT, LU, LV, MD, MG, MK, MN, MW, MX, NO, NZ, PL, PT, RO, R U, SD, SE, SG, SI, SK, TJ, TM, TR , TT, UA, UG, US, UZ, VN (72) Inventor Caldara, Stephen A             Massachusetts, United States             01776, Sudbury, Horse Pond Low             C 220 (72) Inventor Hauser, Stephen A             Massachusetts, United States             01803, Burlington, Farms Dora             Eve 106 (72) Inventors Corsman, Matthias L             Germany, 50858 Kologne, Bu             Rugenlandweg No. 1

Claims (1)

[Claims] 1. Data unit associated with a connection using an unassigned output port Facilitate point-to-point and point-to-multipoint transmission of packets A network switch,   Receives a data unit from outside the exchange and outputs the received data unit A plurality of input ports each operable to transmit to a port;   An allocation map operable to store a representation of the dynamic bandwidth in the switch;   Data units enqueued for point-to-multipoint transmission A point-to-multipoint request map operable to store the representation;   Representation of data units enqueued for point-to-point transmission A point-to-point request map operable to store;   The dynamic bandwidth to the point-to-multipoint request map and the point-to-point -A matching operator that works to match the point request map With   When matching dynamic bandwidth becomes available, point-to-point and And the data units enqueued for point-to-multipoint transmission Network switch to be transmitted. 2. The point-to-multipoint request map includes a point-to-multipoint Connection associated with each data unit enqueued for 2. The connection field of claim 1 including a connection field operable to store an indication of the action. Network switch. 3. The point-to-multipoint request map is used for each point. Stores a representation of the output port to which the two-multipoint data unit is to be transmitted 3. The network switch of claim 2, further comprising a bit vector field operable to perform Machine. 4. The allocation map comprises a switch allocation operable to store an index identifier. Operative to store a table and a bit mask representing dynamic bandwidth within the switch A possible allocation table, the allocation table being indexed by the index identifier. The network switch according to claim 3, wherein 5. The matching operator is point-to-point via dynamic bandwidth For each data unit enqueued for transmission, a dynamic bandwidth is first enqueued. Continuously starting from queued point-to-multipoint data units 2. The network switch according to claim 1, which functions to perform matching. 6. The enqueued point-to-multipoint data unit has fewer At least two groups are prioritized, and the matching operator dynamically assigns low priority groups. Before matching bandwidth, make sure to match dynamic bandwidth to high priority groups. The network exchange according to claim 5. 7. The matching operator is compared with the bit vector field. Generate an unassigned output port bit vector 4. Match dynamic bandwidth to a to-multipoint data unit. Network switch as described. 8. The request map contains the enqueued point-to-multipoint Contains a first pointer indicating the order in which the data units are matched to the dynamic bandwidth. The pointer is the data unit map. 8. The method of claim 7, wherein the incrementing is performed in a round robin order. Network switch. 9. Each input port has a point-to-point core associated with each output port. Exchange port processor (TS) having a connection list of connection PP), and the list of point-to-point connections includes A command having a data unit enqueued for each assigned output port. 2. The network exchange according to claim 1, wherein a representation of the connection is stored. 10. The point-to-point request map includes, for each of the TSPPs, A point-to-point request bit vector, the point-to-point request The bit vector is associated with the point-to-point request bit vector. Each output to which a point-to-point data unit is to be transmitted from each TSPP 10. The network switch according to claim 9, wherein the network switch indicates a port. 11. Operable to select a point-to-point request bit vector. A first operation performed by the matching operator in a round-robin selection. 11. The network exchange according to claim 10, further comprising a pointer. 12. Output port bits in the point-to-point request bit vector Operable to select and round robin by the matching operator. 11. The network switch according to claim 10, including a second pointer operated by selecting an expression. 13. Within the network exchange, point-to-point and point-to-point -A method of performing multipoint transmission,   In a first storing step, storing the representation of the data unit in the request list;   In a second storage step, storing the representation of available bandwidth in an allocation list;   The request list is compared with the allocation list, and a match is established between the two. Judge whether or not   Determining at least one data unit for which a match has been determined, using the available bandwidth Transmitting the data through the method. 14． The first storing step is for point-to-multipoint transmission. Stores the representation of the connection associated with each enqueued data unit Further storing a request map containing a connection field operable to 14. The method of claim 13, comprising steps. 15. Said first storing step comprises the step of: 15. The method of claim 14, further comprising the step of storing a requested bit vector representation of the Method. 16. The second storing step includes a bitmap representing a dynamic bandwidth in the switch. The method of claim 15 including the further step of storing a disk. 17． The comparing step includes the step of comparing the dynamic bandwidth bit mask with the request bit. 17. The method according to claim 16, comprising the further step of comparing with a vector. 18. Store multiple request bit vectors,   The comparing step includes determining whether the requested bit vector has a high priority. Further steps to prioritize at least two independent groups configured to low priority With a floor,   The step of comparing comprises comparing the low priority request bit vector with the low priority request bit vector. 18. The method of claim 17, wherein the method is performed before the priority request bit vector. 19. The request bit mask field contains the enqueued data unit Contains a pointer to the order in which the dynamic bandwidth was first matched,   The comparing may include incrementing a pointer to a round robin order. 18. The method of claim 17, further comprising the step of implementing data unit matching of Method. 20. The first storing step includes a step of connecting a point to each input port of the exchange. Storing a request-to-point bit vector,   The requested bit vector is used for each output requested by each input port of the switch. 14. The method of claim 13, containing an identifier of the force port. 21. The first storing step includes, for each output port associated with each list, Point-to-point connector with enqueued data unit 21. The method of claim 20, further comprising the step of storing a plurality of lists of options.