WO2002069601A2 - Linking frame data by inserting qualifiers in control blocks - Google Patents
Linking frame data by inserting qualifiers in control blocks Download PDFInfo
- Publication number
- WO2002069601A2 WO2002069601A2 PCT/GB2002/000751 GB0200751W WO02069601A2 WO 2002069601 A2 WO2002069601 A2 WO 2002069601A2 GB 0200751 W GB0200751 W GB 0200751W WO 02069601 A2 WO02069601 A2 WO 02069601A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- frame
- control block
- buffer
- fcb
- data
- Prior art date
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/90—Buffering arrangements
- H04L49/9047—Buffering arrangements including multiple buffers, e.g. buffer pools
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L49/00—Packet switching elements
- H04L49/30—Peripheral units, e.g. input or output ports
- H04L49/3081—ATM peripheral units, e.g. policing, insertion or extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
- G06F13/38—Information transfer, e.g. on bus
- G06F13/42—Bus transfer protocol, e.g. handshake; Synchronisation
- G06F13/4204—Bus transfer protocol, e.g. handshake; Synchronisation on a parallel bus
- G06F13/4234—Bus transfer protocol, e.g. handshake; Synchronisation on a parallel bus being a memory bus
- G06F13/4243—Bus transfer protocol, e.g. handshake; Synchronisation on a parallel bus being a memory bus with synchronous protocol
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L45/00—Routing or path finding of packets in data switching networks
- H04L45/54—Organization of routing tables
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/54—Store-and-forward switching systems
- H04L12/56—Packet switching systems
- H04L12/5601—Transfer mode dependent, e.g. ATM
- H04L2012/5678—Traffic aspects, e.g. arbitration, load balancing, smoothing, buffer management
- H04L2012/5681—Buffer or queue management
Definitions
- the present invention relates to the field of a networking communication system, and more particularly to reducing memory accesses.
- a packet switching network has switching points or nodes for transmission of data among senders and receivers connected to the network.
- the switching performed by these switching points is m fact the action of passing on packets or "frames" of data received by a switching point or node to a further node in the network.
- Such switching actions are the means by which communication data is moved through the packet switching network.
- Each node may comprise a packet processor configured to process packets or frames of data.
- the packet processor may comprise a data storage unit, e.g., Double Data Rate Static Random Access Memory (DDR SRAM), configured with a plurality of buffers to store frame data.
- DDR SRAM Double Data Rate Static Random Access Memory
- Each frame of data may be associated with a Frame Control Block (FCB) configured to describe the corresponding frame of data.
- FCB Frame Control Block
- Each FCB may be associated with one or more Buffer Control Blocks (BCBs) where each BCB associated with an FCB may be associated with a buffer in the data storage unit.
- BCBs Buffer Control Blocks
- FCBs and BCBs may be configured to describe the associated buffer
- FCBs and BCBs comprise various fields of information where the fields of information in FCBs and BCBs are each supplied by a separate memory, e.g., Quadruple Data Rate Static Random Access Memory (QDR SRAM), n the packet processor. That is, the fields of information m FCBs and BCBs may be obtained by accessing a separate memory, e.g., QDR SRAM, in the packet processor.
- QDR SRAM Quadruple Data Rate Static Random Access Memory
- the present invention allows qualifiers to be inserted in control blocks, e.g., frame control blocks, buffer control blocks, that comprise information unrelated to the current control block.
- qualifiers in control blocks e.g., frame control blocks, buffer control blocks
- the last frame control block in a queue in the packet processor as well as the last buffer control block associated with a frame control block may comprise fields with no information thereby reducing memory accesses to a memory, e.g., QDR SRAM, to access information to be inserted n those fields. Subsequently, the bandwidth of the memory, e.g., QDR SRAM supplying information to those fields is improved.
- the present invention provides a system comprising: a processor configured to process frames of data, wherein said processor comprises: a plurality of buffers configured to store said frames of data, wherein each frame of data is associated with a frame control block; and a plurality of queues configured to temporarily store one or more frame control blocks, wherein each of said one or more frame control blocks comprises one or more qualifier fields, wherein said one or more qualifier fields in said one or more frame control blocks comprise information related to one or more buffers in said plurality of buffers.
- each of said one or more frame control blocks is associated with one or more buffer control blocks, wherein each of said one or more buffer control blocks is associated w th a particular buffer of said plurality of buffers.
- one or more qualifier fields m all but a last frame control block in a particular queue of said plurality of queues comprise information as to a byte count length of said one or more buffer control blocks associated with a next frame control block.
- the one or more qualifier fields in each of said one or more frame control blocks comprise information as to an address of a buffer control block associated with said current frame control block.
- the one or more qualifier fields m each of said one or more frame control blocks comprise information as to a starting byte position and to an ending byte position of frame data stored in a buffer associated with said buffer control block associated with said current frame control block.
- each of said one or more buffer control blocks associated with a particular frame control block comprises one or more qualifier fields, wherein said one or more qualifier fields m all but the last buffer control block of said one or more buffer control blocks associated with said particular frame control block comprise information as to a starting byte position and to an ending byte position of frame data stored in a buffer associated with a next buffer control block.
- each of said plurality of queues comprises a control block, wherein said control block in each of said plurality of queues comprises a head field, wherein said head field comprises an address of a first frame control block in a queue of said plurality of queues.
- the head field further comprises a qualifier, wherein said qualifier comprises information as to a byte count length of said plurality of buffer control blocks associated with said first frame control block and the control block further comprises a tail field, wherein said tail field comprises an address of a last frame control block n said queue.
- the control block further comprises a count field, wherein said count field comprises a number of frame control blocks in said queue.
- the present invention provides a method for reducing memory accesses by inserting qualifiers in control blocks comprising the steps of: receiving a frame of data; leasing one or more buffer control blocks; storing said frame of data in one or more buffers associated with said one or more buffer control blocks in a data storage unit; and leasing a frame control block associated with said one or more buffer control blocks; wherein said frame control block comprise one or more qualifier fields, wherein said one or more qualifier fields in said frame control block comprise information related to one of said one or more buffers in said data storage unit.
- the method further comprises the step of: enqueuing said frame control block in a queue.
- the one or more qualifier fields in said frame control block comprise information as to an address of one of said one or more buffer control blocks associated with current frame control block.
- the one or more qualifier fields in said frame control block comprise information as to a starting byte position and to an ending byte position of data stored in said one of said one or more buffers storing said frame of data.
- each of said one or more buffer control blocks comprise one or more qualifier fields, wherein said one or more qualifier fields in all but a last buffer control block of said one or more buffer control blocks associated with said frame control block comprise information as to a starting byte position and to an ending byte position of data stored in one of said one or more buffers associated with a next buffer control block.
- the queue comprises a control block, wherein said control block in said queue comprises a head field, wherein said head field in said queue comprises an address of a first frame control block in sa d queue.
- the head field in said queue further comprises a qualifier, wherein said qualifier comprises information as to a byte count length of one or more buffer control blocks associated with said first frame control block.
- the control block of said queue further comprises a tail field, wherein said tail field comprises an address of a last frame control block n said queue and the said control block of said queue further comprises a count field, wherein said count field comprises a number of frame control blocks in said queue.
- the present invention provides a computer program product stored on a computer readable storage medium for, when run on a computer system, instructing the computer system to implement the system as described above.
- Figure 1 illustrates a packet processor configured in accordance with the present invention
- Figure 2 illustrates a data flow unit configured in accordance with the present invention
- Figure 3 is a diagram illustrating the reduction of memory accesses by linking frame data with qualifiers n control blocks;
- Figure 4 is a flowchart of a method for reducing memory accesses by linking frame data with qualifiers in control blocks.
- a system comprises a packet processor configured to process packets, i.e., frames, of data.
- the processor may comprise a plurality of buffers configured to store frames of data where each frame of data may be associated with a frame control block.
- Each frame control block associated with a frame of data may be associated with one or more buffer control blocks.
- Each buffer control block associated with a frame control block may be associated with a particular buffer of the plurality of buffers.
- Each control block e.g., frame control blocks, buffer control Diocks, may comprise one or more qualifier fields.
- the one or more qualifier fields may comprise information unrelated to the current control block.
- qualifiers in control blocks may comprise information related to another control block.
- the last frame control block in a queue in the packet processor as well as the last buffer control block associated with a frame control block may comprise fields with no information thereby reducing memory accesses to a memory, e.g., QDR SRAM, to access information to be inserted in those fields. Subsequently, the bandwidth of the memory, e.g., QDR SRAM, supplying information to those fields is improved.
- Packet processor 100 may comprise a data flow unit 110 configured to receive digital packets, i.e., frames, of data, from a particular switch (not shown) or port (not shown) of a packet switching network and transmit the digital packets, e , frames, of data to another switch or port, e.g., switch/port 120, in the packet switching network.
- Each frame of data may be associated with a Frame Control Block (FCB) where the FCB describes the associated frame of data.
- FCB Frame Control Block
- FCBs Buffer Control Blocks
- a BCB may be configured to describe the buffer associated with the next chained BCB as described in Figures 3 and 4.
- data flow unit 110 may reside on an integrated circuit, i.e., integrated chip.
- Data flow unit 110 may be coupled to data storage unit 140 configured to temporarily store frames of data received by data flow unit 110 from a switch (not shown) or port (not shown) in the packet switching network.
- Data flow unit 110 may further be coupled to a scheduler 130 configured to schedule frames of data to be transmitted from data flow unit 110 to switch/port 120.
- scheduler 130 may reside on an integrated circuit, i.e., integrated chip.
- data flow unit 110 may further be coupled to an embedded processor 150 configured to process frames of data received by data flow unit 110.
- Data flow unit 110 may comprise a receiver controller 203 configured to receive and temporarily store packets, i.e., frames, of data received from a switch
- Data flow unit 110 may further comprise a transmitter controller 201 configured to modify the frame data as well as transmit the modified frame data to a switch (not shown) or port (not shown) in a packet switching network.
- Data flow unit 110 may further comprise an embedded processor interface controller 202 configured to exchange frames to be processed by embedded processor 150.
- Packets i.e., frames
- Port/switch interface unit 221 may receive data from a switch (not shown) in the packet switching network when data flow unit
- port/switch interface unit 221 may receive data from a port (not shown) that operates as an interface to the packet switching network when data flow unit 110 operates in an ingress mode.
- Data received by data flow unit 110 may be temporarily stored in a receiving preparation area memory 220 prior to being stored in data storage unit 140 which may be represented by a plurality of slices 205AF.
- Slices 205AF may collectively or individually be referred to as slices 205 or slice 205, respectively.
- the number of slices 205 in Figure 2 is illustrative, and an embodiment of data flow unit 110 in accordance with the present invention may have other predetermined number of slices 205.
- Each slice may comprise a plurality of buffers.
- Each slice may represent a slice of memory, e.g., Dynamic Random Access Memory (DRAM), so that frame data may be written into different buffers in different slices in order to maximize memory bandwidth.
- a memory arbiter 204 may be configured to collect requests, e.g., read, write, from receiver controller 203, transmitter controller 201 and embedded processor interface controller 202 and subsequently schedule access to particular data store memory slices, i.e., particular buffers in particular slices 205.
- receiver controller 203 may be configured to issue write requests to memory arbiter 204 in order to write received data into individual buffers in a particular slice 205.
- frame data may be stored in data storage unit 140, i.e., a plurality of slices 205.
- frame data may be stored in one or more buffers in one or more slices 205 in a manner such that the data in each particular frame may be reco posed by having the buffers chained together. That is, data in a particular frame may be stored in one or more buffers that are chained together in the order that data is written into the one or more buffers.
- the chaining of the one or more buffers may be controlled by a Buffer Control Block Unit (BCBU) 208 in a memory 229, e.g., Quadruple Data Rate Static Random Access Memory (QDR SRAM), coupled to data flow unit 110.
- BCBU 208 may be configured to comprise the addresses of each of the one or more buffers chained together in the order data was written into buffers.
- the different buffers comprising data of the same frames may be linked together by means of pointers stored in BCBU 208.
- each frame of data may be associated with a Frame Control Block (FCB) where the FCB describes the associated frame of data.
- FCB Frame Control Block Unit 1
- a memory 210 e.g., QDR SRAM
- FCBU1 209 in a memory 210 may be configured to store the information, e.g., frame control information, to be filled in the fields of the FCBs. That is, the fields of information in FCBs may be obtained by accessing memory 210, i.e., FCBU1 209 of memory 210. Additional details regarding FCBU1 209 of memory 210 storing fields of information are discussed m the description of Figure 3.
- Frame data stored in buffers may be processed by embedded processor 150 by transmitting the header of each frame to be processed to embedded processor 150.
- each frame of data may be represented by an FCB.
- FCBs may be temporarily stored m G Queues (GQs) 218.
- Dispatcher logic 217 may be configured to dequeue the next FCB from GQs 218. Once dispatcher logic 217 dequeues the next FCB, dispatcher logic 217 issues a read request to memory arbiter 204 to read the data at the beginning of the frame, i.e., header of the frame, stored m data storage unit 140 associated with the dequeued FCB. The data read by dispatcher logic 217 is then processed by embedded processor 150.
- the processed frame data may be temporarily stored in data storage unit 140, i.e., slices 205, by embedded processor logic 216 issuing a write request to memory arbiter 204 to write the processed frame data into individual buffers in one or more slices 205.
- Scheduler 130 may be configured to comprise flow queues 223 configured to store FCBs.
- Scheduler 130 may further comprise a Frame Control Block Unit 2 (FCBU2) 225 within a memory 224, e.g., QDR SRAM, configured to operate similarly as FCBUl 209.
- FCBU2 225 may be configured to store the information to be filled in the fields of the FCBs when the FCBs are temporarily residing in flow queues 223.
- Scheduler 130 may be configured to transmit the FCBs stored in flow queues 223 to Target Blade Queues (TBQs) 215 enqueue logic 227 configured to enqueue the received FCBs m TBQs 215.
- TBQs Target Blade Queues
- FCBs queued in TBQs 215 may be scheduled to be dequeued from TBQs 215 by TBQ scheduler 228 and loaded into Port Control Block (PCB) 224.
- TBQ scheduler 228 may be configured to dequeue the next FCB from TBQs 215 and enqueue that FCB into PCB 224.
- PCB 224 may issue a read request to memory arbiter 204 to read the data at the beginning of the frame, i.e., header of the frame, stored in data storage unit 140 associated with the dequeued FCB.
- the data read by PCB 224 may be temporarily stored in data preparation area memory 214 prior to transmitting the processed frame data to a switch (not shown) or port (not shown) in a packet switching network. It is noted for clarity that PCB 224 may be configured to read a portion of the data stored in the processed frame m each particular read request. That is, the entire data stored in the processed frame may be read in multiple read requests provided by PCB 224. Once the entire data stored n the processed frame is read, the data storage unit 140 may store additional frame data.
- Transmitter controller 201 may further comprise a frame alteration preparation area memory 213 configured to receive commands to modify the processed frames temporarily stored in data preparation area memory 21 . These commands are commonly referred to as frame modification commands which are issued by embedded processor 150 and stored m a particular bank in a particular buffer by embedded processor logic 216. Additional details regarding the storing of frame modification commands in a particular bank m a particular buffer are disclosed m U.S. Patent Application Serial No. 09/792,557.
- PCB 224 may be configured to retrieve the frame modification commands stored in a particular bank in a particular buffer and store them in frame alteration preparation area memory 213.
- a Frame Alteration (FA) logic unit 212 may be configured to execute the commands stored in frame alteration preparation area memory 213 to modify the contents of the processed frames temporarily stored in data preparation area memory 214. Once FA logic 212 has modified the contents of the processed frames, then modified processed frames may be transmitted through a switch/port interface unit 211. Switch/port interface unit 211 may transmit data to a port (not shown) that operates as an interface to the packet switching network when data flow unit 110 operates in an egress mode. Otherwise, switch/port interface unit 211 may transmit data to a switch (not shown) n the packet swi t ching network when data flow unit 110 operates in an ingress mode.
- a port not shown
- switch/port interface unit 211 may transmit data to a switch (not shown) n the packet swi t ching network when data flow unit 110 operates in an ingress mode.
- Data flow unit 110 may further comprise a Buffer Control Block (BCB) Arbiter 207 configured to arbitrate among different BCB requests from transmitter controller 201, embedded processor interface controller 202 and receiver controller 203 to read from or write to BCBU 208.
- BCB Arbiter 207 may be configured to schedule different accesses m order to utilize memory bandwidth as efficiently as possible.
- Data flow unit 110 may further comprise a Frame Control Block (FCB) Arbiter 206 configured to arbitrate among different FCB requests from embedded processor interface controller 202, receiver controller 203 and transmitter controller 201 to read from or write to FCBU1 209.
- FCB Frame Control Block
- each frame of data may be associated with an FCB.
- the FCB associated with such processed frame ceases to represent that particular frame of data.
- the FCB may be stored in a FCB free queue 222 within FCB Arbiter 206.
- FCB free queue 222 may be configured to comprise a plurality of FCBs that are no longer associated with particular frame data. It is noted that FCB free queue 222 may comprise any number of FCBs that are no longer associated with particular frame data.
- a Reassembly Control Block (RCB) 219 of receiver controller 203 may associate a particular FCB from FCB free queue 222 with the received frame of data where the newly associated FCB may then be queued in GQs 218 by RCB 219.
- RRCB Reassembly Control Block
- each frame of data may be associated with an FCB.
- Each FCB associated with a frame of data may be associated with one or more BCBs where each BCB associated with an FCB may be associated with a particular buffer of data storage unit 140.
- a BCB may be configured to describe the buffer associated with the next chained BCB as described in the discussion of Figures 3 and 4.
- the BCB associated with the particular buffer that no longer includes any frame data includes data that is no useful since the particular buffer associated with the BCB no longer includes any frame data.
- the BCB may be stored n a BCB free queue 226 within BCB Arbiter 206.
- BCB free queue 226 may be configured to comprise a plurality of BCBs that do not comprise any valid information. It is noted that BCB free queue 226 may comprise any number of BCBs that do not comprise any valid information.
- RCB 219 of receiver controller 203 may retrieve a BCB in BCB free queue 226 so that RCB 219 may write the received frame data in the particular buffer associated with the BCB retrieved from BCB free queue 226.
- FCBs and BCBs may comprise various fields of information where the fields of information are supplied by a separate memory 210, i.e., FCBU1 209 of memory 210, and memory 229, i.e., BCBU 208 of memory 229, respectively. That is, the fields of information in FCBs may be obtained by accessing memory 210, i.e., FCBU1 209 of memory 210. The fields of information m BCBs may be obtained by accessing memory 229, i.e., BCBU 208 of memory 229.
- FIG. 3 schematically illustrates an exemplary set 300 of control blocks depicting the inclusion of qualifiers in control blocks, e.g., FCB, BCB, in order to reduce accesses to memories 210 and 229 in accordance with the principles of the present invention.
- FCBs may temporarily reside in a queue 305 which may be one of the following queues: FCB free queue 222, GQs 218, flow queues 223, and TBQs 215.
- the queue has a control block commonly referred to as a Queue Control Block (QCB) 301 comprising information as to the number of FCBs that currently reside in that particular queue.
- QB Queue Control Block
- BCB free queue 226 may also comprise QCB 301.
- QCB 301 may comprise other information than the number of FCBs that currently reside that particular queue.
- QCB 301 may comprise a head field 302, a tail fiel d 303 and a count field 304.
- Head field 302 may comprise an FCB Address (FCBA) of a first FCB, e.g., FCB 310A, located in the queue, e.g., FCB free queue 222, GQs 218, flow queues 223, TBQs 215, comprising QCB 301.
- FCBA FCB Address
- FCBA FCB Address
- FCB 310A located in the queue, e.g., FCB free queue 222, GQs 218, flow queues 223, TBQs 215, comprising QCB 301.
- Head field 302 may further comprise the Byte Count (BCNT) of the one or more BCBs, e.g., BCBs 320AC, associated with the first FCB, e.g., FCB 310A, located in the queue, e.g., FCB free queue 222, GQs 218, flow queues 223, TBQs 215.
- the BCNT n head field 302 may be referred to as an qualifier as it identifies the byte count length of the one or more BCBs, e g., BCBs 320AC, associated with the first FCB, e.g., FCB 310A, in the queue 305 comprising QCB 301.
- Tail field 303 may comprise the FCB Address (FCBA) of last FCB, e g., FCB 310B, in queue 305, e.g., FCB free queue 222, GQs 218, flow queues 223, TBQs 215, comprising QCB 301.
- Count field 304 may comprise the number of FCBs in queue 305 comprising QCB 301. Because in the exemplary set 300 of Figure there are two FCBs, e.g., FCB 310AB, in queue 305 comprising QCB 301, count field 304 comprises the number two.
- FCB free queue 222 may comprise any number of FCBs and that Figure 3 is illustrative.
- FCBs 310AB may collectively or individually be referred to as FCBs 310 or FCB 310, respectively.
- Each FCB 310 may comprise two entries or rows of fields.
- the first entry may comprise a field comprising a pointer to the Next FCB Address (NFA) .
- the first entry may further comprise a field comprising the Byte Count (BCNT) length of the one or more BCBs associated with the next FCB 310. That is, instead of FCBs 310 storing the Byte Count length (BCNT) of the one or more BCBs associated with the current FCB 310, the BCNT field stores the byte count length of the one or more BCBs associated with the next FCB 310.
- BCNT Byte Count
- FCB 310A comprises the FCB address of the following FCB 310, e.g., FCB 310B, in the NFA field as well as the byte count length of the one or more BCBs, e.g., BCBs 320 DF, associated with the following FCB 310, e.g., FCB 310B, in the BCNT field.
- the BCNT field may be referred to as an qualifier as it identifies the byte count length of the one or more BCBs, e.g., BCBs 320DF, associated with FCB 310B identified in the NFA field, i.e., the next FCB 310 in the chain of FCBs 310.
- FCB 310B does not comprise any information in the NFA field or in the BCNT field as there are no more FCBs 310 following FCB 310B. (Th s is denoted in the exemplary set 300 of Figure 3 by "empty" parentheses “( )"). By not storing information in the NFA field and n the BCNT field of FCB 310B, memory accesses to memory 210 are reduced thereby improving the efficiency of the bandwidth of memory 210.
- the second entry may comprise the fields of the First BCB Address (FBA) of the first BCB associated with that particular
- FCB the Starting Byte Position (SBP) of the frame data stored m a buffer associated with the first BCB, and the Ending Byte Position (EBP) of the frame data stored in the buffer associated w th the first BCB.
- SBP Start Byte Position
- EBP Ending Byte Position
- Each FCB may be associated with one or more BCBs.
- FCB 310A is associated with BCBs 320AC.
- FCB 310B is associated w th BCBs 320DF.
- FCBs may be associated with any number of BCBs and that Figure 3 is illustrative, as would be recognized by an artisan of ordinary skill.
- BCBs 320AF may collectively or individually be referred to as BCBs 320 or BCB 320, respectively.
- Each BCB 320 may be associated with a particular buffer n data storage unit 140.
- BCB 320A is associated with buffer 330A.
- BCB 320B is associated with buffer 330B.
- BCB 320C is associated with buffer 330C.
- BCB 320D is associated with buffer 330D.
- BCB 320E is associated with buffer 330E.
- BCB 320F is associated with buffer 330F.
- Buffers 330A-F may collectively or individually be referred to as buffers 330 or buffer 330, respectively.
- data storage unit 140 of packet processor 100 may comprise any number of slices 205 comprising any number of buffers 330.
- each BCB 320 may be associated with a particular buffer 330 in data storage unit 140.
- the FBA field in the second entry may comprise the address of the first BCB 320, e.g., BCB 320A, associated with FCB 310A.
- FCB 310A may further comprise an SBP field storing the starting address of the frame data stored in the buffer 330, e.g., buffer 330A, associated with the first BCB 320, e.g., BCB 320A.
- FCB 310A may further comprise an EBP field storing the ending address of the frame data stored m the buffer 330, e.g., buffer 330A, associated with the first BCB 320, e.g., BCB 320A.
- FCB 310B may comprise an FBA field in the second entry which comprises the address of the first BCB 320, e.g., BCB 320D, associated with FCB 310B.
- FCB 310B may further comprise an SBP field storing the starting address of the frame data stored in the buffer 330, e.g., buffer 330D, associated with the first BCB 320, e.g., BCB 320D.
- FCB 310B may further comprise an EBP field storing the ending address of the frame data stored m the buffer 330, e.g., buffer 330D, associated with the first BCB 320, e.g., BCB 320D.
- the SBP and EBP fields may be referred to as qualifiers as they comprise information about the starting byte position and ending byte position of the frame data associated with the first BCB 320, e.g., BCB 320D, and not information about the current FCB 310, e.g., FCB 310B.
- each FCB 310 may be associated with one or more
- BCBs 320 are associated with BCBs 320AC and FCB 310B is associated with BCBs 320DF.
- Each BCB 320 may comprise three fields that are similar to the three fields in the second entry of FCBs 310.
- Each BCB 320 may comprise a pointer to the Next BCB Address iNBAj as well as the fields of SBP and EBP which are the starting and ending byte positions of the buffer 330 associated with the next BCB.
- the SBP and EBP fields may be referred to as qualifiers as they store the starting byte position and ending byte position of the buffer 330, e.g., buffer 330B, associated with the next BCB 320, e.g., BCB 320C.
- the starting and ending byte positions of the buffer 330 e.g., buffer 330B, associated with the current BCB 320, e.g., BCB 320B, thereby resulting an extra write access to memory 229
- the starting and ending byte positions of the buffer 330, e.g., buffer 330B, associated with tne next BCB 320, e.g., BCB 320B is stored in the SBP and EBP fields, respectively, in the previous BCB 320, e.g., BCB 320A.
- BCB 320A comprises the BCB address of the next BCB 320, e.g., BCB 320B, in the NBA field as well as the starting byte position of the frame data stored in the buffer 330, e.g., buffer 330B, associated with the next BCB 320, e.g., BCB 320B, in the SBP field and the ending byte position of the frame data stored in the buffer 330, e.g., buffer
- BCB 320B comprises the BCB address of the next BCB 320, e.g., BCB 320C, m the NBA field as well as the starting byte position of the frame data stored m the buffer 330, e.g., buffer 330C, associated with the next BCB, e.g., BCB 320C, m the SBP field and the ending byte position of the frame data stored in the buffer 330, e.g., buffer 330C, associated with the next BCB 320, e.g., BCB 320C, n the EBP field.
- BCB 320 e.g., BCB 320C
- FCB 310 e.g., FCB 310A
- Figure 4 illustrates a flowchart of a method 400 for reducing memory accesses to memories 210 and 229 by linking frame data with qualifiers in control blocks, e.g., FCBs 310, BCBs 320.
- a frame of data may be received from a switch (not shown) or a port (not shown) in a packet switching network and temporarily stored in receiving preparation area memory 220 by receiver controller 203.
- RCB 219 of receiver controller 203 may be then be configured to lease one or more BCBs 320 from BCB free queue 226 ( Figure 2) .
- a BCB may be said to be "leased” from BCB free queue 226 as the BCB may be temporarily removed from BCB free queue 226 during the "life cycle" of the FCB. Additional details regarding the "l fe cycle" of the FCB are disclosed m U.S. Patent Application Serial No. 09/792,494.
- RCB 219 may then write the received data in one or more particular buffers 330 associated with the one or more BCBs 320 leased from BCB free queue 226.
- RCB 219 may issue one or more write requests to memory arbiter 204 in order to write the received frame data into one or more buffers 330 associated with the one or more BCBs leased from BCB free queue 226.
- each particular buffer 330 may be associated with a particular BCB 320.
- BCB 320 may be configured as illustrated m Figure 3 where BCB 320 may comprise the field of a Next BCB Address (NBA) which comprises a pointer to the next BCB 320 address as well as the fields of SBP and EBP which are the starting and ending byte positions of the buffer 330 associated with the next BCB 320.
- NBA Next BCB Address
- SBP and EBP fields may be referred to as qualifiers as they store the starting byte position and ending byte position of the buffer 330 associated with the next BCB 320.
- the starting and ending byte positions of the buffer 330 e.g., buffer 330A ( Figure 3)
- the current BCB 320 e.g., BCB 320A ( Figure 3)
- the next BCB 320 e.g., BCB 320B ( Figure 3)
- RCB 219 may read the head field 302 m QCB 301 ( Figure 3) of BCB free queue 226. RCB 219 may then read the NBA field of the first BCB 320, e.g., BCB 320A, which may comprise the address of the next BCB 320 in the BCB free queue 226 to retrieve. Head field 302 of QCB 301 may subsequently be updated by RCB 219 so that the address in the head fj.eld 302 is the address of the next BCB 320 that may be retrieved during the next lease operation.
- the count field 304 of QCB 301 of BCB free queue 226 may then be decremented to indicate that a BCB 320 has been retrieved from BCB free queue 226.
- Head field 302 of QCB 301 may further comprise the Byte Count (BCNT) of the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), associated with the one or more buffers 330, e.g., buffers 330AC ( Figure 3), storing the frame of data.
- BCNT Byte Count
- the BCNT in head field 302 may be referred to as an qualifier as it identifies the byte count length of the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), associated with the one or more buffers 330, buffers 330AC ( Figure 3) , storing the frame of data and not information about the BCB free queue 226 comprising QCB 301.
- QCB 301 may further comprise a tail field 303 comprising the address of the last FCB, e.g., FCB 310B ( Figure 2), located in the queue, e.g., FCB free queue 222.
- RCB 219 of receiver controller 203 may associate the one or more BCBs 320, e.g. BCBs 320AC ( Figure 3), with an FCB 310 in step 403.
- RCB 219 may lease an FCB 310 from FCB free queue 222 ( Figure 2) thereby associating the leased FCB 310 with the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), that are associated with the one or more buffers 205, e.g., buffers 205AC ( Figure 3), storing the frame of data.
- An FCB may be said to be "leased" from FCB free queue 222 as the FCB may be temporarily removed from FCB free queue 222 during the "life cycle" of the FCB.
- FCB 310 may be configured as illustrated in Figure 3 with two entries or rows of fields
- the first entry may comprise a field comprising a pointer to the Next FCB Address (NFA) .
- the first entry may further comprise a field comprising the Byte Count (BCNT) length of the one or more BCBs 320, e.g., BCBs 320DF ( Figure 3), associated with the next FCB 310. That is, instead of FCB 310 storing the Byte Count length (BCNT) of the one or more BCBs 320 associated with the current FCB 310, the BCNT field stores the byte count length of the one or more BCBs 320 associated with the next FCB 310.
- BCNT Byte Count
- the last FCB 310 in the queue, e.g., FCB free queue 222 ( Figure 2), does not comprise any 5 information in the NFA field or m the BCNT field as there are no more FCBs 310 following the last FCB 310, e.g., FCB 310B ( Figure 3), n the queue, e.g., FCB free queue 222 ( Figure 2).
- memory accesses to memory 210 are reduced thereby improving C the bandwidth of memory 210.
- the last FCB 310 located in the queue, e.g., FCB free queue 222 ( Figure 2), may be identified in tail field 303 of QCB 301 ( Figure 3) of FCB free queue 222.
- tail field 303 may comprise the address of the last FCB 310, e.g., FCB 310B ( Figure 2), located in the 5 queue, e.g., FCB free queue 222.
- the second entry of FCB 310 may comprise the fields of the First BCB Address (FBA) of the first BCB 320, e.g., BCB 320A ( Figure 3), associated with tnat particular FCB 310, the Starting Byte Position (SBP) of the frame data stored m buffer 330, e.g., buffer 330A ( Figure 3), associated 0 with the first BCB 320, e.g., BCB 320A ( Figure 3), and the Ending Byte
- FBA First BCB Address
- SBP Starting Byte Position
- the SBP and EBP fields may be referred to as qualifiers as they comprise information about the starting byte position and ending byte position of the frame data associated with the first BCB 320, e.g., BCB 320A ( Figure 3), and not information about the current FCB 310, e.g., FCB 310A ( Figure
- RCB 219 may read the head field 302 in QCB 301 of FCB free queue 222.
- Head field 302 may include the address of the first FCB 310, e.g., FCB 310A ( Figure 3), to retrieve from FCB free queue 222.
- RCB 219 may then read the NFA field of the first FCB 310, e.g., FCB 310A, which may comprise the address of the next FCB 310 n the FCB free queue 222 to retrieve.
- Head field 302 of QCB 301 may subsequently be updated so that the address in head field 302 is the address of the next FCB 310 that may be retrieved during the next lease operation.
- FCB 310 may be enqueued in GQs 218 by RCB 219.
- FCB 310 may comprise the fields of FBA as well as the qualifiers SBP and EBP m the second entry.
- RCB 219 may store the starting and ending byte position of the frame data it stored m the first buffer 330, e.g., buffer 330A, associated with the first BCB 320, e.g., BCB 320A, associated with the FCB 310, e.g., FCB 310A, enqueued m GQs 218 by RCB 219 when RCB 219 writes the received frame data into the first buffer 330, e.g., buffer 330A, associated with the first BCB 320, e.g., BCB 320A, associated with the FCB 310, e.g., FCB 310A, enqueued n GQs 218 by RCB 219.
- the BCNT field in the first entry of FCB 310 may be copied from RCB 219.
- FCB 310 enqueued m GQs 218 may then be chained together with the other FCBs 310 in GQs 218 in step 405.
- RCB 219 may read the tail field 303 in QCB 301 of GQs 218 to retrieve the address of the current last FCB 310 m GQs 218.
- the tail field 303 in QCB 301 of GQs 218 may subsequently be updated by RCB 219 so that the pointer m tail field 303 points to the FCB 310 just enqueued in GQs 218.
- the count field 304 of QCB 301 of GQs 218 may then be incremented by RCB 219 to indicate that an FCB 310 has been retrieved from FCB free queue 222 and enqueued n GQs 218.
- FCB 310 may be dequeued from GQs 218.
- Dispatcher logic 217 of embedded processor interface controller 202 may read the head field 302 of QCB 301 of GQs 218 to retrieve the address of the FCB 310 to dequeue.
- Dispatcher logic 217 may further read the NFA field in the FCB 310 to determine the address of the next FCB 310 in GQs 218 to dequeue.
- Dispatcher logic 217 may be configured to update the head field 302 of QCB 301 in GQs 218 so that the address m the head field 302 is the address of the next FCB 310 that may be dequeued at the next dequeue operation.
- the court field 304 of QCB 301 in GQs 218 may be decremented to indicate that an FCB 301 has been dequeued from GQs 218.
- the contents of the dequeued FCB 310 may then be read by dispatcher logic 217 and transferred to embedded processor 150.
- the dequeued FCB 310 may be enqueued m TBQs 215.
- FCB 310 may first be enqueued in flow queues 223 of scheduler 130 and then dequeued and enqueued n TBQs 215. Additional details regarding enqueuing and dequeuing the FCB 310 in flow queues 223 of scheduler 130 are disclosed in U.S. Patent Application Serial No. 09/792,494.
- the enqueued FCB 310 n TBQs 215 may then be dequeued by TBQ scheduler 228 to be loaded into PCB 224 to be read by PCB 224 as discussed in the description of Figure 2.
- the address in the FBA field of the FCB 310 may be loaded nto PCB 224.
- the frame of data to be transmitted through switch/port interface unit 211 to a switch (not shown) or a port (not shown) in the packet switching network may be read from the one or more buffers 330 associated with the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), by PCB 224.
- PCB retrieves the address of the first BCB 320, i.e., the address included in the FBA field of the FCB 310 dequeued in step 408, that was loaded into PCB 224.
- the address of the next BCB 320, e.g., BCB 320B ( Figure 3) may be located in the NBA field of the first BCB 320, e.g., BCB 320A ( Figure 3).
- step 410 when all the data of a frame is read by PCB from the one or more buffers 330 of data storage unit 140 that stored the frame of data, the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), associated with the one or more buffers 330, e.g., buffers 330AC ( Figure 3), are enqueued in BCB free queue 226.
- each BCB 320 may be enqueued one at a time in BCB free queue 226 as frame data m each associated buffer 330 is read by PCB 224.
- step 411 when the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3), associated with the one or more buffers 330, e.g., buffers 330AC ( Figure 3), have been enqueued in BCB free queue 226, the FCB 310 associated with the one or more BCBs 320, e.g., BCBs 320AC ( Figure 3) is enqueued m FCB free queue 222.
- the FCB 310 associated with the one or more BCBs 320 e.g., BCBs 320AC ( Figure 3) is enqueued m FCB free queue 222.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020037010706A KR100554825B1 (en) | 2001-02-23 | 2002-02-20 | Linking frame data by inserting qualifiers in control blocks |
EP02712096A EP1362465B1 (en) | 2001-02-23 | 2002-02-20 | System and method for linking frame data by inserting qualifiers in control blocks |
DE60210748T DE60210748T2 (en) | 2001-02-23 | 2002-02-20 | System and method for merging frame data by inserting destination fields into control blocks |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US09/791,336 US7130916B2 (en) | 2001-02-23 | 2001-02-23 | Linking frame data by inserting qualifiers in control blocks |
US09/791,336 | 2001-02-23 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2002069601A2 true WO2002069601A2 (en) | 2002-09-06 |
WO2002069601A3 WO2002069601A3 (en) | 2003-03-13 |
Family
ID=25153396
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/GB2002/000751 WO2002069601A2 (en) | 2001-02-23 | 2002-02-20 | Linking frame data by inserting qualifiers in control blocks |
Country Status (7)
Country | Link |
---|---|
US (2) | US7130916B2 (en) |
EP (1) | EP1362465B1 (en) |
KR (1) | KR100554825B1 (en) |
CN (1) | CN100429906C (en) |
AT (1) | ATE323999T1 (en) |
DE (1) | DE60210748T2 (en) |
WO (1) | WO2002069601A2 (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110113197A1 (en) * | 2002-01-04 | 2011-05-12 | Intel Corporation | Queue arrays in network devices |
Families Citing this family (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7130916B2 (en) * | 2001-02-23 | 2006-10-31 | International Business Machines Corporation | Linking frame data by inserting qualifiers in control blocks |
US7200696B2 (en) * | 2001-04-06 | 2007-04-03 | International Business Machines Corporation | System method structure in network processor that indicates last data buffer of frame packet by last flag bit that is either in first or second position |
US6937606B2 (en) * | 2001-04-20 | 2005-08-30 | International Business Machines Corporation | Data structures for efficient processing of IP fragmentation and reassembly |
US7522621B2 (en) * | 2005-01-06 | 2009-04-21 | International Business Machines Corporation | Apparatus and method for efficiently modifying network data frames |
US7466715B2 (en) * | 2005-03-28 | 2008-12-16 | International Business Machines Corporation | Flexible control block format for frame description and management |
US8795926B2 (en) | 2005-08-11 | 2014-08-05 | Intelligent Energy Limited | Pump assembly for a fuel cell system |
US7980582B2 (en) * | 2006-08-09 | 2011-07-19 | Atc Leasing Company Llc | Front tow extended saddle |
US9034531B2 (en) * | 2008-01-29 | 2015-05-19 | Ardica Technologies, Inc. | Controller for fuel cell operation |
US8741004B2 (en) | 2009-07-23 | 2014-06-03 | Intelligent Energy Limited | Cartridge for controlled production of hydrogen |
US8808410B2 (en) * | 2009-07-23 | 2014-08-19 | Intelligent Energy Limited | Hydrogen generator and product conditioning method |
US8940458B2 (en) | 2010-10-20 | 2015-01-27 | Intelligent Energy Limited | Fuel supply for a fuel cell |
US9169976B2 (en) | 2011-11-21 | 2015-10-27 | Ardica Technologies, Inc. | Method of manufacture of a metal hydride fuel supply |
US20230236756A1 (en) * | 2022-01-25 | 2023-07-27 | Infineon Technologies Ag | Buffer management in an ethernet switch |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5333269A (en) * | 1988-10-28 | 1994-07-26 | International Business Machines Corporation | Mechanism for transferring messages between source and destination users through a shared memory |
US5561807A (en) * | 1993-04-29 | 1996-10-01 | International Business Machines Corporation | Method and device of multicasting data in a communications system |
Family Cites Families (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4168469A (en) | 1977-10-04 | 1979-09-18 | Ncr Corporation | Digital data communication adapter |
US4703475A (en) | 1985-12-04 | 1987-10-27 | American Telephone And Telegraph Company At&T Bell Laboratories | Data communication method and apparatus using multiple physical data links |
US5136582A (en) | 1990-05-29 | 1992-08-04 | Advanced Micro Devices, Inc. | Memory management system and method for network controller |
US5247516A (en) * | 1991-03-28 | 1993-09-21 | Sprint International Communications Corp. | Configurable composite data frame |
US5410677A (en) | 1991-12-30 | 1995-04-25 | Apple Computer, Inc. | Apparatus for translating data formats starting at an arbitrary byte position |
US5267240A (en) * | 1992-02-20 | 1993-11-30 | International Business Machines Corporation | Frame-group transmission and reception for parallel/serial buses |
US5440545A (en) * | 1993-08-02 | 1995-08-08 | Motorola, Inc. | Packet delivery system |
US5617537A (en) * | 1993-10-05 | 1997-04-01 | Nippon Telegraph And Telephone Corporation | Message passing system for distributed shared memory multiprocessor system and message passing method using the same |
US5574934A (en) * | 1993-11-24 | 1996-11-12 | Intel Corporation | Preemptive priority-based transmission of signals using virtual channels |
US5832310A (en) * | 1993-12-30 | 1998-11-03 | Unisys Corporation | Serial I/O channel having dependent and synchronous sources of control data and user defined data |
US5553302A (en) * | 1993-12-30 | 1996-09-03 | Unisys Corporation | Serial I/O channel having independent and asynchronous facilities with sequence recognition, frame recognition, and frame receiving mechanism for receiving control and user defined data |
US5551020A (en) | 1994-03-28 | 1996-08-27 | Flextech Systems, Inc. | System for the compacting and logical linking of data blocks in files to optimize available physical storage |
US5574905A (en) | 1994-05-26 | 1996-11-12 | International Business Machines Corporation | Method and apparatus for multimedia editing and data recovery |
US5812775A (en) * | 1995-07-12 | 1998-09-22 | 3Com Corporation | Method and apparatus for internetworking buffer management |
US5651002A (en) * | 1995-07-12 | 1997-07-22 | 3Com Corporation | Internetworking device with enhanced packet header translation and memory |
US6400715B1 (en) * | 1996-09-18 | 2002-06-04 | Texas Instruments Incorporated | Network address matching circuit and method |
US6477584B1 (en) * | 1997-03-21 | 2002-11-05 | Lsi Logic Corporation | Message FIFO empty early warning method |
AUPO932297A0 (en) * | 1997-09-19 | 1997-10-09 | Commonwealth Scientific And Industrial Research Organisation | Medium access control protocol for data communications |
US6519686B2 (en) * | 1998-01-05 | 2003-02-11 | Intel Corporation | Information streaming in a multi-process system using shared memory |
US7055151B1 (en) * | 1998-04-03 | 2006-05-30 | Applied Micro Circuits Corporation | Systems and methods for multi-tasking, resource sharing and execution of computer instructions |
US6330584B1 (en) * | 1998-04-03 | 2001-12-11 | Mmc Networks, Inc. | Systems and methods for multi-tasking, resource sharing and execution of computer instructions |
US6434145B1 (en) * | 1998-06-22 | 2002-08-13 | Applied Micro Circuits Corporation | Processing of network data by parallel processing channels |
US6735679B1 (en) * | 1998-07-08 | 2004-05-11 | Broadcom Corporation | Apparatus and method for optimizing access to memory |
US6661774B1 (en) * | 1999-02-16 | 2003-12-09 | Efficient Networks, Inc. | System and method for traffic shaping packet-based signals |
JP3561870B2 (en) * | 1999-02-19 | 2004-09-02 | 富士通株式会社 | Packet buffer device |
US7116679B1 (en) * | 1999-02-23 | 2006-10-03 | Alcatel | Multi-service network switch with a generic forwarding interface |
AU3529500A (en) * | 1999-03-17 | 2000-10-04 | Broadcom Corporation | Network switch |
US7145869B1 (en) * | 1999-03-17 | 2006-12-05 | Broadcom Corporation | Method for avoiding out-of-ordering of frames in a network switch |
US6643716B2 (en) * | 1999-03-29 | 2003-11-04 | Intel Corporation | Method and apparatus for processing serial data using a single receive fifo |
JP2000332817A (en) * | 1999-05-18 | 2000-11-30 | Fujitsu Ltd | Packet processing unit |
US6747978B1 (en) * | 1999-05-27 | 2004-06-08 | Nortel Networks Limited | Direct memory access packet router method and apparatus |
US7046686B1 (en) * | 1999-08-17 | 2006-05-16 | Mindspeed Technologies, Inc. | Integrated circuit that processes communication packets with a buffer management engine having a pointer cache |
JP2001127766A (en) * | 1999-10-25 | 2001-05-11 | Toshiba Corp | Line interface and packet exchange |
US6687247B1 (en) * | 1999-10-27 | 2004-02-03 | Cisco Technology, Inc. | Architecture for high speed class of service enabled linecard |
US6788697B1 (en) * | 1999-12-06 | 2004-09-07 | Nortel Networks Limited | Buffer management scheme employing dynamic thresholds |
US6876659B2 (en) * | 2000-01-06 | 2005-04-05 | International Business Machines Corporation | Enqueuing apparatus for asynchronous transfer mode (ATM) virtual circuit merging |
US6922408B2 (en) * | 2000-01-10 | 2005-07-26 | Mellanox Technologies Ltd. | Packet communication buffering with dynamic flow control |
JP3732989B2 (en) * | 2000-01-12 | 2006-01-11 | 富士通株式会社 | Packet switch device and scheduling control method |
US6731644B1 (en) * | 2000-02-14 | 2004-05-04 | Cisco Technology, Inc. | Flexible DMA engine for packet header modification |
US6977930B1 (en) * | 2000-02-14 | 2005-12-20 | Cisco Technology, Inc. | Pipelined packet switching and queuing architecture |
US6963921B1 (en) * | 2001-02-16 | 2005-11-08 | 3Com Corporation | Method and apparatus for hardware assisted TCP packet re-assembly |
US7230917B1 (en) * | 2001-02-22 | 2007-06-12 | Cisco Technology, Inc. | Apparatus and technique for conveying per-channel flow control information to a forwarding engine of an intermediate network node |
US7130916B2 (en) * | 2001-02-23 | 2006-10-31 | International Business Machines Corporation | Linking frame data by inserting qualifiers in control blocks |
US6658546B2 (en) * | 2001-02-23 | 2003-12-02 | International Business Machines Corporation | Storing frame modification information in a bank in memory |
US6681340B2 (en) * | 2001-02-23 | 2004-01-20 | International Business Machines Corporation | Efficient implementation of error correction code scheme |
US6532185B2 (en) * | 2001-02-23 | 2003-03-11 | International Business Machines Corporation | Distribution of bank accesses in a multiple bank DRAM used as a data buffer |
-
2001
- 2001-02-23 US US09/791,336 patent/US7130916B2/en not_active Expired - Fee Related
-
2002
- 2002-02-20 CN CNB028048490A patent/CN100429906C/en not_active Expired - Fee Related
- 2002-02-20 AT AT02712096T patent/ATE323999T1/en not_active IP Right Cessation
- 2002-02-20 WO PCT/GB2002/000751 patent/WO2002069601A2/en active IP Right Grant
- 2002-02-20 DE DE60210748T patent/DE60210748T2/en not_active Expired - Lifetime
- 2002-02-20 EP EP02712096A patent/EP1362465B1/en not_active Expired - Lifetime
- 2002-02-20 KR KR1020037010706A patent/KR100554825B1/en not_active IP Right Cessation
-
2006
- 2006-08-31 US US11/469,390 patent/US20070002172A1/en not_active Abandoned
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5333269A (en) * | 1988-10-28 | 1994-07-26 | International Business Machines Corporation | Mechanism for transferring messages between source and destination users through a shared memory |
US5561807A (en) * | 1993-04-29 | 1996-10-01 | International Business Machines Corporation | Method and device of multicasting data in a communications system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110113197A1 (en) * | 2002-01-04 | 2011-05-12 | Intel Corporation | Queue arrays in network devices |
US8380923B2 (en) * | 2002-01-04 | 2013-02-19 | Intel Corporation | Queue arrays in network devices |
Also Published As
Publication number | Publication date |
---|---|
DE60210748T2 (en) | 2007-01-04 |
CN1502198A (en) | 2004-06-02 |
US20020118694A1 (en) | 2002-08-29 |
KR20030076680A (en) | 2003-09-26 |
US7130916B2 (en) | 2006-10-31 |
EP1362465A2 (en) | 2003-11-19 |
WO2002069601A3 (en) | 2003-03-13 |
CN100429906C (en) | 2008-10-29 |
EP1362465B1 (en) | 2006-04-19 |
US20070002172A1 (en) | 2007-01-04 |
KR100554825B1 (en) | 2006-02-22 |
DE60210748D1 (en) | 2006-05-24 |
ATE323999T1 (en) | 2006-05-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20070002172A1 (en) | Linking frame data by inserting qualifiers in control blocks | |
US6967951B2 (en) | System for reordering sequenced based packets in a switching network | |
US5875189A (en) | Method and apparatus for multicast of ATM cells | |
US6757791B1 (en) | Method and apparatus for reordering packet data units in storage queues for reading and writing memory | |
US6711170B1 (en) | Method and apparatus for an interleaved non-blocking packet buffer | |
US6598132B2 (en) | Buffer manager for network switch port | |
US20030016689A1 (en) | Switch fabric with dual port memory emulation scheme | |
US7085266B2 (en) | Apparatus, method and limited set of messages to transmit data between components of a network processor | |
US6310879B2 (en) | Method and apparatus for multicast of ATM cells where connections can be dynamically added or dropped | |
US7072347B2 (en) | Assignment of packet descriptor field positions in a network processor | |
US6681340B2 (en) | Efficient implementation of error correction code scheme | |
US6658546B2 (en) | Storing frame modification information in a bank in memory | |
US6678277B1 (en) | Efficient means to provide back pressure without head of line blocking in a virtual output queued forwarding system | |
US10021035B1 (en) | Queuing methods and apparatus in a network device | |
CN117015764A (en) | Message communication between integrated computing devices | |
EP0710047B1 (en) | Method and apparatus for multicast of ATM cells | |
KR100378372B1 (en) | Apparatus and method for packet switching in data network | |
EP1499076A2 (en) | Method and apparatus for multicast of ATM cells |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG UZ VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
DFPE | Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101) | ||
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
AK | Designated states |
Kind code of ref document: A3 Designated state(s): AE AG AL AM AT AU AZ BA BB BG BR BY BZ CA CH CN CO CR CU CZ DE DK DM DZ EC EE ES FI GB GD GE GH GM HR HU ID IL IN IS JP KE KG KP KR KZ LC LK LR LS LT LU LV MA MD MG MK MN MW MX MZ NO NZ OM PH PL PT RO RU SD SE SG SI SK SL TJ TM TN TR TT TZ UA UG UZ VN YU ZA ZM ZW |
|
AL | Designated countries for regional patents |
Kind code of ref document: A3 Designated state(s): GH GM KE LS MW MZ SD SL SZ TZ UG ZM ZW AM AZ BY KG KZ MD RU TJ TM AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE TR BF BJ CF CG CI CM GA GN GQ GW ML MR NE SN TD TG |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2002712096 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 028048490 Country of ref document: CN |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1020037010706 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 1020037010706 Country of ref document: KR |
|
WWP | Wipo information: published in national office |
Ref document number: 2002712096 Country of ref document: EP |
|
REG | Reference to national code |
Ref country code: DE Ref legal event code: 8642 |
|
WWG | Wipo information: grant in national office |
Ref document number: 1020037010706 Country of ref document: KR |
|
NENP | Non-entry into the national phase |
Ref country code: JP |
|
WWW | Wipo information: withdrawn in national office |
Country of ref document: JP |
|
WWG | Wipo information: grant in national office |
Ref document number: 2002712096 Country of ref document: EP |