WO1999039479A1 - Distributed arbitration on a full duplex bus - Google Patents

Distributed arbitration on a full duplex bus Download PDF

Info

Publication number
WO1999039479A1
WO1999039479A1 PCT/US1999/002043 US9902043W WO9939479A1 WO 1999039479 A1 WO1999039479 A1 WO 1999039479A1 US 9902043 W US9902043 W US 9902043W WO 9939479 A1 WO9939479 A1 WO 9939479A1
Authority
WO
WIPO (PCT)
Prior art keywords
node
arbitration
packet
token
root node
Prior art date
Application number
PCT/US1999/002043
Other languages
French (fr)
Inventor
Jerrold V. Hauck
David W. Lafollette
Original Assignee
Intel Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Intel Corporation filed Critical Intel Corporation
Priority to AU24871/99A priority Critical patent/AU2487199A/en
Priority to EP99904479A priority patent/EP1053617A4/en
Publication of WO1999039479A1 publication Critical patent/WO1999039479A1/en

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • H04L12/40Bus networks
    • H04L12/40052High-speed IEEE 1394 serial bus
    • H04L12/40084Bus arbitration
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/14Handling requests for interconnection or transfer
    • G06F13/36Handling requests for interconnection or transfer for access to common bus or bus system
    • G06F13/368Handling requests for interconnection or transfer for access to common bus or bus system with decentralised access control

Definitions

  • the invention relates to data transfer systems. More specifically the invention relates to arbitration on a full duplex bus.
  • 1394 systems a plurality of nodes are organized into a tree topology. Additionally, all nodes are initially deemed peer to peer but on bus reset, one node assumes root status while the remaining nodes become branches and leaves of the topology.
  • 1394-1995 and 1394a are half-duplex protocols. Thus, data may only flow in one direction at any given time. Both of these protocols employ a discrete arbitration phase during which all nodes seeking access to the bus send arbitration requests to the root node. The root node then resolves the arbitration and grants the bus to one of the arbitrating nodes. During this discrete arbitration phase no other useful work can be done on the bus. Desire to eliminate the discrete arbitration phase has spawned various embedded token approaches in which arbitration requests are embedded as tokens within the data packet itself.
  • the 1394b provides a full-duplex serial bus protocol. This has permitted a combination of embedded token and propagation of requests on the unused signal line to eliminate the discrete arbitration phase. Specifically, when the packet is being sent by a parent node, requests from the children nodes are free to propagate on the unused signal line going back to the parent node. If however, the packet is directed to a parent node the request must be embedded within the data stream. All requests are still handled by the sole root node which remains fixed after system initialization. Accordingly, token embedding will occur on nearly all transactions on at least some bus segments.
  • Embedding tokens requires that the elasticity buffer of each PHY have extra capacity so as to allow insertion of the extra symbol into the data stream.
  • the larger elasticity buffer increases the latency of repetition through each PHY and therefore increases latency of the overall bus system.
  • arbitration tokens must frequently be embedded in the packet, there is a practical limit to the size and number of tokens that can be used for arbitration.
  • the embedded token approach presumes that only a single arbitration request can be made during a packet time. Since current protocols favor the first received arbitration request, a tension exists between sending an arbitration request as soon as a desire to arbitrate is known and waiting to see if a higher priority requests arrives from a child node before making the arbitration request. Additionally, once a request has been issued it cannot be withdrawn or modified in any manner until the beginning of another transmitted packet is detected on the bus, at which time any denied node must reissue its arbitration request.
  • a method and apparatus for improving bus efficiency is disclosed.
  • a full-duplex serial bus couples together a plurality of nodes in a tree topology.
  • node transmitting a current packet is a nominal root node toward which the other node transmits current arbitration information.
  • Figure 1 is a block diagram of a physical layer of one embodiment of the invention.
  • Figure 2 is a block diagram of a tree topology of one embodiment of the invention during a first unit of time.
  • Figure 3 is a block diagram of the tree topology of Figure 2 during a second unit of time.
  • Figure 4 is a block diagram of the tree topology of Figure 2 during a third unit of time.
  • Figure 5 is a block diagram of the tree topology of Figure 2 during an alternative third unit of time.
  • Figure 6 is a block diagram of the tree topology of Figure 2 during a alternative second time unit in which the packet sent in the first unit did not end a subaction.
  • Figure 7 is a block diagram of the tree topology of Figure 6 during an alternative third unit of time.
  • Figure 8 is a block diagram of the tree topology of Figure 6 during a fourth unit of time.
  • Figure 9 is a flow chart of arbitration flow in a nominal root node of one embodiment of the invention.
  • Figure 10 is a flow chart of error recovery in a physical root node of one embodiment of the invention. DETAILED DESCRIPTION OF THE INVENTION
  • a physical layer (PHY) 10 has one or more ports which can be connected to a serial bus not shown.
  • per port logic 12 is provided as part of the PHY 10.
  • the PHY 10 receives a receive signal 32 and transmits a transmit signal 34 through each active port.
  • Per port logic 12 includes a decoder 22 to decode and descramble the incoming receive signal 32.
  • the decoder 22 is an 8B10B decoder and descrambler, which performs 8-bit 10-bit decoding. This means each 10-bit value coming in as the receive signal 32 is decoded into an 8-bit value.
  • the decoder 22 is coupled to a port state machine 26 which receives a control value decoded by the decoder.
  • an encoder 24 is used to encode and scramble the outgoing transmit signal 34.
  • the encoder performs 8B10B encoding. This is analogous to the decode case, each byte of data to be transmitted is encoded as a 10-bit value. Thus, a number of codings exist that are not used for normal data encoding.
  • the decoder 22 is coupled to an elasticity buffer 18.
  • the elasticity buffer 18 buffers data decoded from the received signal 32 while that data is awaiting transfer to the link and /or repetition out on one or more ports of the PHY 10 as the transmit signal 34.
  • the PHY state machine 14 and the arbitration state machine 16 may be combined as a single state machine or may be implemented as two separate state machines.
  • the PHY state machine 14 provides the intelligence for the PHY including generation of any PHY generated packets.
  • the arbitration state machine 16 assesses incoming arbitration information and provides outgoing arbitration requests. If the node is originating a packet on the bus it is the nominal root node. The nominal root node has complete arbitration state information for the topology. Based on this -5-
  • the arbitration state machine 16 of the nominal root node grants the arbitration request of a highest priority branch. Since nominal root status passes with the grant of the bus, each node should be able to act as arbitrator for the topology.
  • the PHY state machine identifies if a packet to be transmitted is a last packet of a subaction. In the case of a link generated packet it is preferred that the link or some higher layer notify the PHY 10 either through the PHY state machine 14 or possibly the encoder 24 directly, that the packet being sent is the last packet of the subaction. In this way the PHY state machine 14 can cause the encoder 24 to (or the encoder can on its own initiative) insert an end of subaction (EOS) token at the end of a packet to be transmitted.
  • EOS end of subaction
  • EOS token acts as an explicit grant token and is only sent down a highest priority branch.
  • the remaining branches receive the usual data delimiting token, end of data token (EOD).
  • EOD end of data token
  • GNT grant
  • DEN deny
  • Figure 2 shows a system that includes a plurality of nodes 50-58.
  • the nodes 50-58 are organized in a tree topology.
  • node 50 is the physical root node.
  • employing the invented distributed arbitration technique which node is the nominal root, nominal branches and nominal leaves depends on which node is permitted to originate a packet on the bus.
  • the nodes are all interconnected by a full duplex serial bus 100.
  • serial bus 100 follows the 1394b protocol.
  • Each node has one or more ports 30 through which communication between serial bus 100 and PHY 10 is conducted.
  • the PHY 10 communicates with a link layer 36, which in turn communicates with a transaction layer 40.
  • a link layer 36 includes a subaction end identifier (SEID) 38 to identify which link generated packets are last packets of subactions.
  • SEID 38 may communicate with the PHY state machine or directly with the encoder. As a result, the transmitter knows if the transmitted packet is a last packet of a subaction. This knowledge permits the transmitter to appropriately issue a GNT token.
  • node 54 is transmitting a last packet of a subaction (PACKET A) out all of its ports.
  • Node 54 is therefore the nominal root node and receives arbitration information from each child node such that node 54 has the complete arbitration state of the topology available to it.
  • node 54 is a nominal root node and is the only node entitled to transmit a packet on the bus, the opposite directional path towards node 54 from nodes 50, 56 & 58 is available for arbitration state information.
  • the path from node 52 to node 50 is also available for arbitration state information thus, node 52 continually forwards the arbitration state information for node 52 to node 50.
  • Node 50 then sends arbitration state information for node 50 and any children nodes in this case its sole child node 52 to node 54.
  • Nodes 56 and 58 send corresponding arbitration state information directly to node 54. It is within the scope and contemplation of the invention that a node not wishing to arbitrate could send no state information or it could send state information reflecting no request at the time. Because node 54 receives the arbitration state information concurrently with packet transmission and node 54 being the nominal root is deemed the arbitrator for the topology, it is able to resolve the arbitration without a discrete arbitration phase.
  • FIG. 3 shows the tree topology of Figure 2 at a later instant in time.
  • Node 54 has completed transmission of PACKETA which ends in or is followed by a GNT token granting the bus to a particular branch or the DEN token which is sent down all lower priority branches.
  • the branch containing node 50 received the GNT token.
  • node 54 is no longer the nominal root and begins sending arbitration information out each of its ports.
  • the GNT token is followed immediately by arbitration state information for nodes 54, 56 and 58.
  • the deny token to node 56 is followed by arbitration state information for nodes 50, 52, 54 -7-
  • the arbitration state information might be regarded as a logic level on a virtual wire.
  • the node transmitting the arbitration information can change the arbitration state at any time.
  • nodes 56 and 58 continue to transmit their state information to node 54 permitting node 54 to constantly update the arbitration state information provided to node 50 along the virtual wire.
  • PACKETA having been repeated by node 50 propagates to node 52.
  • Node 52 continues to send arbitration state information to node 50.
  • node 50 may either take the token for itself thereby becoming the nominal root node or it may forward it on to a child having a higher priority arbitration request (here the only possibility is node 52).
  • node 50 may take the token for itself thereby becoming the nominal root node or it may forward it on to a child having a higher priority arbitration request (here the only possibility is node 52).
  • bus efficiency is enhanced by node 50 taking the bus first. This is because bus efficiency is negatively impacted by the duration of idle time between two sequential transmitted packets. In turn, idle time is a function of the network distance between the originators of the packets. Consequently, it is desirable to show preference to requesting nodes that are physically closer to the previous packet initiator.
  • the decision point begins with the last packet originator and follows the last packet of the subaction along the highest priority arbitration path.
  • nodes closer to the originator have the first opportunity to win the bus.
  • the root in the prior art embedded token approach usually grants the bus before knowing where the initiator for the last packet in the subaction is located.
  • large idle times may exist when sequential packet initiators are significant distances apart.
  • Figure 6 which presumes that PACKETA (of Figure 2) requires an acknowledgment (ACK)
  • Figure 6 is the same as Figure 3 except that since the PACKETA must be acknowledged, no GNT token is sent. Therefore, node 54 transmits a DEN token along with arbitration state information to node 50.
  • node 56 was the target for PACKETA, which we have presumed required an ACK. Even though it did not receive an explicit grant token, node 56 implicitly becomes the nominal root with the right to transmit an ACK packet.
  • the ACK packet is transmitted from node 56 to node 54.
  • Node 50 propogates the DEN token and arbitration state information to node 52. The remaining paths carry arbitration state information between the respective nodes.
  • node 56 sends a GNT token followed immediately by arbitration state information to node 54.
  • Node 54 repeats the previously received ACK to nodes 50 and 58. Once node 54 receives the grant token it may decide to keep it or pass it along in the manner described above. In a subsequent unit of time the ACK will be propagated to node 52, such that -9-
  • the distributed arbitration system eliminates the need to embed tokens in the data stream. Because the nominal root shifts from node to node it is guaranteed that the flow path from all other nodes towards the nominal root will be available for arbitration state information. Therefore, unlike the prior art proposed embedded token approach, no increase of the size of elasticity buffers within each node is required. Thus, latency of the system is not increased as would be the case if larger elasticity buffers were used. Moreover, because the arbitration data need not be embedded within packets or added to the elasticity buffer, the size and number of tokens used for arbitration is not as constrained as the prior art case.
  • the availability of the virtual wire permits the arbitration state to contain encoded priority information. As time passes, the priority of the underlying arbitration request may increase (such as when it becomes time to send a cycle start packet) or may decrease (in the case the request is withdrawn). The change is propagated to all other nodes by the virtual wire.
  • the embedded token approach does not provide an efficient way to achieve this function since a token cannot be modified once it has been submitted. Similarly, once a grant is given in an embedded token system, it cannot be withdrawn based on a later arriving higher priority request. Moreover, because the embedded token approach uses only a single token it requires heavy error handling support to address lost tokens and other transmission errors. Signaling across the virtual wire is less sensitive to errors because the state information is transitory and will be quickly replaced with refreshed state information. Thus, even if a transmission error occurs the odds of it occurring repetitively are quite small.
  • arbitration reset gaps can be reduced or eliminated. Specifically, if no arbitration requests are pending or received during a packet time the nominal root can initiate a transition to a next fairness interval without waiting for an arbitration reset gap. However, the nominal root should ensure that enough time has elapsed since the last fairness transition was signaled to -10-
  • the minimum length of a fairness interval is a worst case propagation delay of the bus plus the arbitration response time.
  • the nominal root identifies if an arbitration request has been received at decision block 240. If an arbitration request has been received the nominal root resolves the arbitration request and sends out a grant at functional block 242. If no arbitration request has been received the nominal root determines if a minimum fairness interval has elapsed at decision block 244. If the minimum fairness interval has elapsed the nominal root initiates a transition into a next fairness interval at functional block 246 then, hereinafter initiating the transition or if the minimum fairness interval has not elapsed, a nominal root sends the grant token towards the physical root node at functional block 248, thereby relinquishing nominal root status.
  • the nominal root does not initiate a transition to the next fairness interval but still forwards the GNT token toward the physical root node.
  • the physical root node Upon receipt of the GNT token with no pending requests the physical root node initiates a transition to the next fairness interval.
  • a time out counter is reset. Then, at decision block 210, the physical root determines if it has seen packet traffic on the bus. If it has, it resets the time out counter and continues to watch for additional bus traffic. If it does not, it checks to see if a GNT has been received at decision block 212. If it has, it resets the counter and continues to watch for bus traffic. If it has not, a decision is made whether a time-out time has been exceeded at decision block 214. If it has not, the physical root continues to watch for bus traffic but does not reset the counter. If it has, the physical root assumes nominal root status at functional block 216, then begins arbitration and grants the bus to the winner at functional block 218.
  • the nominal root node initiates a transition into a next fairness interval but does not forward the GNT token toward the nominal root.
  • This embodiment lacks the error recovery mechanism noted above, but is still within the scope and contemplation of the invention.
  • the invented distributed arbitration technique is applicable to both asynchronous and isocronous transaction types. Additionally, a node could "remember" the direction the GNT token was sent and only send arbitration information along that branch. The GNT token may also be directed to a specific node rather than just the highest priority branch. Though some of these features may not always optimize performance they are still within the scope and contemplation of the invention.

Abstract

Distributed arbitration in a full duplex bus system (32, 34). By distributing the arbitration function among the nodes of a tree topology full duplex bus system such that arbitration (16) at any particular time is handled by a node holding a grant of the bus at that time (the nominal root node), a reverse flow direction towards the nominal root node (10) is available for arbitration flow. This allows the discrete arbitration phase to be eliminated and generally improves bus efficiency.

Description

-1-
DISTRIBUTED ARBITRATION ON A FULL DUPLEX BUS
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates to data transfer systems. More specifically the invention relates to arbitration on a full duplex bus.
2. Related Art
For high speed data transfers over a distance, various high speed serial data transfer mechanisms have been developed. The IEEE Standard for a High Performance Serial Bus, IEEE Std. 1394-1995 published August 30, 1996 (1394- 1995 Standard) and its progeny provide a high speed serial protocol which permits implementation of high speed data transfers. The existing progeny includes P1394a Draft Standard for a High Performance Serial Bus (1394a Standard) and P1394b Draft Standard for a High Performance Serial Bus (1394b Standard). Generically, systems implementing 1394-1995, 1394a, 1394b or subsequent revisions and modifications thereof are referred to herein as 1394 systems.
In 1394 systems a plurality of nodes are organized into a tree topology. Additionally, all nodes are initially deemed peer to peer but on bus reset, one node assumes root status while the remaining nodes become branches and leaves of the topology. Both 1394-1995 and 1394a are half-duplex protocols. Thus, data may only flow in one direction at any given time. Both of these protocols employ a discrete arbitration phase during which all nodes seeking access to the bus send arbitration requests to the root node. The root node then resolves the arbitration and grants the bus to one of the arbitrating nodes. During this discrete arbitration phase no other useful work can be done on the bus. Desire to eliminate the discrete arbitration phase has spawned various embedded token approaches in which arbitration requests are embedded as tokens within the data packet itself. The 1394b provides a full-duplex serial bus protocol. This has permitted a combination of embedded token and propagation of requests on the unused signal line to eliminate the discrete arbitration phase. Specifically, when the packet is being sent by a parent node, requests from the children nodes are free to propagate on the unused signal line going back to the parent node. If however, the packet is directed to a parent node the request must be embedded within the data stream. All requests are still handled by the sole root node which remains fixed after system initialization. Accordingly, token embedding will occur on nearly all transactions on at least some bus segments.
Embedding tokens requires that the elasticity buffer of each PHY have extra capacity so as to allow insertion of the extra symbol into the data stream. The larger elasticity buffer increases the latency of repetition through each PHY and therefore increases latency of the overall bus system. Moreover, because arbitration tokens must frequently be embedded in the packet, there is a practical limit to the size and number of tokens that can be used for arbitration.
The embedded token approach presumes that only a single arbitration request can be made during a packet time. Since current protocols favor the first received arbitration request, a tension exists between sending an arbitration request as soon as a desire to arbitrate is known and waiting to see if a higher priority requests arrives from a child node before making the arbitration request. Additionally, once a request has been issued it cannot be withdrawn or modified in any manner until the beginning of another transmitted packet is detected on the bus, at which time any denied node must reissue its arbitration request.
In view of the foregoing it would be desirable to be able to improve the efficiency of arbitration in a full duplex bus system without increasing latency of the system.
BRIEF SUMMARY OF THE INVENTION
A method and apparatus for improving bus efficiency is disclosed. A full-duplex serial bus couples together a plurality of nodes in a tree topology. A -3-
node transmitting a current packet is a nominal root node toward which the other node transmits current arbitration information.
BRIEF DESCRIPTION OF THE DRAWINGS
Figure 1 is a block diagram of a physical layer of one embodiment of the invention.
Figure 2 is a block diagram of a tree topology of one embodiment of the invention during a first unit of time.
Figure 3 is a block diagram of the tree topology of Figure 2 during a second unit of time.
Figure 4 is a block diagram of the tree topology of Figure 2 during a third unit of time.
Figure 5 is a block diagram of the tree topology of Figure 2 during an alternative third unit of time.
Figure 6 is a block diagram of the tree topology of Figure 2 during a alternative second time unit in which the packet sent in the first unit did not end a subaction.
Figure 7 is a block diagram of the tree topology of Figure 6 during an alternative third unit of time.
Figure 8 is a block diagram of the tree topology of Figure 6 during a fourth unit of time.
Figure 9 is a flow chart of arbitration flow in a nominal root node of one embodiment of the invention.
Figure 10 is a flow chart of error recovery in a physical root node of one embodiment of the invention. DETAILED DESCRIPTION OF THE INVENTION
By distributing the arbitration function among the nodes of a tree topology full-duplex bus system such that arbitration at any particular time is handled by a node holding a grant of the bus at that time (the nominal root node), a reverse flow direction towards the nominal root node is available for arbitration flow. This allows the discrete arbitration phase to be eliminated and generally improves bus efficiency.
Now referring to Figure 1, a physical layer (PHY) 10 has one or more ports which can be connected to a serial bus not shown. For each such port, per port logic 12 is provided as part of the PHY 10. The PHY 10 receives a receive signal 32 and transmits a transmit signal 34 through each active port. Per port logic 12 includes a decoder 22 to decode and descramble the incoming receive signal 32. In one embodiment the decoder 22 is an 8B10B decoder and descrambler, which performs 8-bit 10-bit decoding. This means each 10-bit value coming in as the receive signal 32 is decoded into an 8-bit value. The decoder 22 is coupled to a port state machine 26 which receives a control value decoded by the decoder. Similarly, an encoder 24 is used to encode and scramble the outgoing transmit signal 34. In one embodiment of the invention the encoder performs 8B10B encoding. This is analogous to the decode case, each byte of data to be transmitted is encoded as a 10-bit value. Thus, a number of codings exist that are not used for normal data encoding.
Additionally, the decoder 22 is coupled to an elasticity buffer 18. The elasticity buffer 18 buffers data decoded from the received signal 32 while that data is awaiting transfer to the link and /or repetition out on one or more ports of the PHY 10 as the transmit signal 34. The PHY state machine 14 and the arbitration state machine 16 may be combined as a single state machine or may be implemented as two separate state machines. The PHY state machine 14 provides the intelligence for the PHY including generation of any PHY generated packets. The arbitration state machine 16 assesses incoming arbitration information and provides outgoing arbitration requests. If the node is originating a packet on the bus it is the nominal root node. The nominal root node has complete arbitration state information for the topology. Based on this -5-
information the arbitration state machine 16 of the nominal root node grants the arbitration request of a highest priority branch. Since nominal root status passes with the grant of the bus, each node should be able to act as arbitrator for the topology.
In one embodiment of the invention, the PHY state machine identifies if a packet to be transmitted is a last packet of a subaction. In the case of a link generated packet it is preferred that the link or some higher layer notify the PHY 10 either through the PHY state machine 14 or possibly the encoder 24 directly, that the packet being sent is the last packet of the subaction. In this way the PHY state machine 14 can cause the encoder 24 to (or the encoder can on its own initiative) insert an end of subaction (EOS) token at the end of a packet to be transmitted. Copending application entitled "Improved Arbitration
Techniques For A High Speed Serial Bus", Serial No. discloses one method of generating EOS tokens. In one embodiment the EOS token acts as an explicit grant token and is only sent down a highest priority branch. The remaining branches receive the usual data delimiting token, end of data token (EOD). It is also within the scope and contemplation of the invention to use the normal EOD token alone or in combination with an explicit grant token and deny token. Thus, the EOS token is not required but an explicit grant implicitly denotes the end of a subaction. As used herein grant (GNT) token refers to either an explicit grant or an implicit grant e.g. caused by an EOS token. Similarly a deny (DEN) token refers to either explicit deny token or an implicit denial such as by using an EOD token down all branches except one which receives a GNT token.
Figure 2 shows a system that includes a plurality of nodes 50-58. The nodes 50-58 are organized in a tree topology. In this topology node 50 is the physical root node. However, employing the invented distributed arbitration technique, which node is the nominal root, nominal branches and nominal leaves depends on which node is permitted to originate a packet on the bus. The nodes are all interconnected by a full duplex serial bus 100. In one embodiment, serial bus 100 follows the 1394b protocol. Each node has one or more ports 30 through which communication between serial bus 100 and PHY 10 is conducted. The PHY 10 communicates with a link layer 36, which in turn communicates with a transaction layer 40. A link layer 36 includes a subaction end identifier (SEID) 38 to identify which link generated packets are last packets of subactions. The SEID 38 may communicate with the PHY state machine or directly with the encoder. As a result, the transmitter knows if the transmitted packet is a last packet of a subaction. This knowledge permits the transmitter to appropriately issue a GNT token.
In Figure 2, node 54 is transmitting a last packet of a subaction (PACKET A) out all of its ports. Node 54 is therefore the nominal root node and receives arbitration information from each child node such that node 54 has the complete arbitration state of the topology available to it. Because node 54 is a nominal root node and is the only node entitled to transmit a packet on the bus, the opposite directional path towards node 54 from nodes 50, 56 & 58 is available for arbitration state information. Similarly, the path from node 52 to node 50 is also available for arbitration state information thus, node 52 continually forwards the arbitration state information for node 52 to node 50. Node 50 then sends arbitration state information for node 50 and any children nodes in this case its sole child node 52 to node 54. Nodes 56 and 58 send corresponding arbitration state information directly to node 54. It is within the scope and contemplation of the invention that a node not wishing to arbitrate could send no state information or it could send state information reflecting no request at the time. Because node 54 receives the arbitration state information concurrently with packet transmission and node 54 being the nominal root is deemed the arbitrator for the topology, it is able to resolve the arbitration without a discrete arbitration phase.
Now referring to Figure 3, which shows the tree topology of Figure 2 at a later instant in time. Node 54 has completed transmission of PACKETA which ends in or is followed by a GNT token granting the bus to a particular branch or the DEN token which is sent down all lower priority branches. In this case, the branch containing node 50 received the GNT token. Once the GNT and DEN tokens are sent node 54 is no longer the nominal root and begins sending arbitration information out each of its ports. Thus, the GNT token is followed immediately by arbitration state information for nodes 54, 56 and 58. The deny token to node 56 is followed by arbitration state information for nodes 50, 52, 54 -7-
and 58 while the deny token sent to node 58 is followed by arbitration state information for nodes 50, 52, 54 and 56. In this manner the recipient of the GNT token should, shortly after the grant, receive current state information for the topology. This continues until a packet arrives. Once the NEXT PACKET arrives the packet will be repeated to downstream nodes and the arbitration state information will continue to be sent upstream (in the opposite direction as the packet is moving).
The arbitration state information might be regarded as a logic level on a virtual wire. As such, the node transmitting the arbitration information can change the arbitration state at any time. Thus, if a node's real time priority changes it is free to change its arbitration request even within a subaction. This of course was not possible with prior art and embedded token techniques which mandated only a single request be sent during any particular subaction. Notably, nodes 56 and 58 continue to transmit their state information to node 54 permitting node 54 to constantly update the arbitration state information provided to node 50 along the virtual wire. PACKETA having been repeated by node 50 propagates to node 52. Node 52 continues to send arbitration state information to node 50. Upon receiving the GNT token node 50 may either take the token for itself thereby becoming the nominal root node or it may forward it on to a child having a higher priority arbitration request (here the only possibility is node 52). Presuming that both nodes 50 and 52 have packets to transmit in the fairness interval, bus efficiency is enhanced by node 50 taking the bus first. This is because bus efficiency is negatively impacted by the duration of idle time between two sequential transmitted packets. In turn, idle time is a function of the network distance between the originators of the packets. Consequently, it is desirable to show preference to requesting nodes that are physically closer to the previous packet initiator. Using the invented distributed arbitration technique, the decision point begins with the last packet originator and follows the last packet of the subaction along the highest priority arbitration path. Thus, nodes closer to the originator have the first opportunity to win the bus. Conversely, the root in the prior art embedded token approach usually grants the bus before knowing where the initiator for the last packet in the subaction is located. Thus, large idle times may exist when sequential packet initiators are significant distances apart. This point can be clarified by referring to Figure 4 and Figure 5. In Figure 4 node 50 claims the GNT while in Figure 5 node 50 forwards the GNT to node 52. In either case the data flow between nodes 54, 56 and 58 remains the same. Referring to Figure 4 separately, the NEXT PACKET is transmitted out both ports by node 50 to nodes 54 and 52. With respect to node 52 the NEXT PACKET falls immediately on the heels of the DEN token generated when node 50 accepted the grant token in Figure 3. Thus, from the perspective of node 52 it sees the continuous stream PACEKTA, DEN token, NEXT PACKET. Thus, the bus is never idle. Conversely, when the grant is forwarded to node 52 as shown in Figure 5, (assuming each hop through the PHY takes one unit of time), no useful work occurs on the bus during the time unit that the GNT token is forwarded to node 52. Thus, the bus would be idle for one unit of time because the NEXT PACKET transmitted from node 52 to node 50 would not appear on the bus until the time unit following that shown in Figure 5.
Now, referring to Figure 6 which presumes that PACKETA (of Figure 2) requires an acknowledgment (ACK), Figure 6 is the same as Figure 3 except that since the PACKETA must be acknowledged, no GNT token is sent. Therefore, node 54 transmits a DEN token along with arbitration state information to node 50.
Now referring to Figure 7, node 56 was the target for PACKETA, which we have presumed required an ACK. Even though it did not receive an explicit grant token, node 56 implicitly becomes the nominal root with the right to transmit an ACK packet. In Figure 7 the ACK packet is transmitted from node 56 to node 54. Node 50 propogates the DEN token and arbitration state information to node 52. The remaining paths carry arbitration state information between the respective nodes.
Now referring to Figure 8, node 56 sends a GNT token followed immediately by arbitration state information to node 54. Node 54 repeats the previously received ACK to nodes 50 and 58. Once node 54 receives the grant token it may decide to keep it or pass it along in the manner described above. In a subsequent unit of time the ACK will be propagated to node 52, such that -9-
all nodes will have seen the ACK. This presumes that the ACK is transmitted at a rate all nodes can handle. Packet data will not propagate to a node incapable of receiving it.
The distributed arbitration system eliminates the need to embed tokens in the data stream. Because the nominal root shifts from node to node it is guaranteed that the flow path from all other nodes towards the nominal root will be available for arbitration state information. Therefore, unlike the prior art proposed embedded token approach, no increase of the size of elasticity buffers within each node is required. Thus, latency of the system is not increased as would be the case if larger elasticity buffers were used. Moreover, because the arbitration data need not be embedded within packets or added to the elasticity buffer, the size and number of tokens used for arbitration is not as constrained as the prior art case.
The availability of the virtual wire, permits the arbitration state to contain encoded priority information. As time passes, the priority of the underlying arbitration request may increase (such as when it becomes time to send a cycle start packet) or may decrease (in the case the request is withdrawn). The change is propagated to all other nodes by the virtual wire. The embedded token approach does not provide an efficient way to achieve this function since a token cannot be modified once it has been submitted. Similarly, once a grant is given in an embedded token system, it cannot be withdrawn based on a later arriving higher priority request. Moreover, because the embedded token approach uses only a single token it requires heavy error handling support to address lost tokens and other transmission errors. Signaling across the virtual wire is less sensitive to errors because the state information is transitory and will be quickly replaced with refreshed state information. Thus, even if a transmission error occurs the odds of it occurring repetitively are quite small.
Additionally, arbitration reset gaps can be reduced or eliminated. Specifically, if no arbitration requests are pending or received during a packet time the nominal root can initiate a transition to a next fairness interval without waiting for an arbitration reset gap. However, the nominal root should ensure that enough time has elapsed since the last fairness transition was signaled to -10-
allow all nodes to submit an updated request. In one embodiment the minimum length of a fairness interval is a worst case propagation delay of the bus plus the arbitration response time.
Now referring to Figure 9, in one embodiment of the invention, the nominal root identifies if an arbitration request has been received at decision block 240. If an arbitration request has been received the nominal root resolves the arbitration request and sends out a grant at functional block 242. If no arbitration request has been received the nominal root determines if a minimum fairness interval has elapsed at decision block 244. If the minimum fairness interval has elapsed the nominal root initiates a transition into a next fairness interval at functional block 246 then, hereinafter initiating the transition or if the minimum fairness interval has not elapsed, a nominal root sends the grant token towards the physical root node at functional block 248, thereby relinquishing nominal root status. If no requests arrive such that an intervening node claims the GNT token it will propagate to the physical root. In another embodiment, the nominal root does not initiate a transition to the next fairness interval but still forwards the GNT token toward the physical root node. Upon receipt of the GNT token with no pending requests the physical root node initiates a transition to the next fairness interval. Both of these embodiments have the advantage that they provide an error recovery mechanism in the event the grant is corrupted during transmission. Specifically, once it transmits the grant the granting node loses nominal root status, but no new nominal root is established.
Thus, now referring to Figure 10 at functional block 208, a time out counter is reset. Then, at decision block 210, the physical root determines if it has seen packet traffic on the bus. If it has, it resets the time out counter and continues to watch for additional bus traffic. If it does not, it checks to see if a GNT has been received at decision block 212. If it has, it resets the counter and continues to watch for bus traffic. If it has not, a decision is made whether a time-out time has been exceeded at decision block 214. If it has not, the physical root continues to watch for bus traffic but does not reset the counter. If it has, the physical root assumes nominal root status at functional block 216, then begins arbitration and grants the bus to the winner at functional block 218. The -11-
winner then becomes the nominal root. In this way the bus is prevented from falling into and remaining in an indeterminate state.
In another alternative embodiment the nominal root node initiates a transition into a next fairness interval but does not forward the GNT token toward the nominal root. This embodiment lacks the error recovery mechanism noted above, but is still within the scope and contemplation of the invention.
One of ordinary skill in the art will recognize that the invented distributed arbitration technique is applicable to both asynchronous and isocronous transaction types. Additionally, a node could "remember" the direction the GNT token was sent and only send arbitration information along that branch. The GNT token may also be directed to a specific node rather than just the highest priority branch. Though some of these features may not always optimize performance they are still within the scope and contemplation of the invention.
In the foregoing specification, the invention has been described with reference to specific embodiments thereof. It will, however, be evident that various modifications and changes can be made thereto without departing from the broader spirit and scope of the invention as set forth in the appended claims. The specification and drawings are, accordingly, to be regarded in an illustrative rather than a restrictive sense. Therefore, the scope of the invention should be limited only by the appended claims.

Claims

-12-CLAIMSWhat is claimed is:
1. A method comprising the steps of: establishing a node as a nominal root node, the nominal root node being a node with a right to transmit a packet on a bus; and dynamically changing the nominal root node responsive to a change in right to transmit on the bus.
2. A method of claim 1 further comprising the steps of: preparing, in the nominal root node, a last packet of a subaction to be transmitted over a serial bus; transmitting the packet over the serial bus; accepting arbitration requests over the serial bus while the packet is prepared and transmitted; and processing the arbitration requests in the nominal root node.
3. The method of claim 2 further comprising the step of: transmitting an arbitration request out all ports following the packet transmission.
4. The method of claim 2 further comprising the step of: initiating a transition into a next fairness interval if no arbitration request is received while the packet is prepared and transmitted.
5. The method of claim 3 further comprising the step of: repeatedly sending a best real time arbitration request out an upstream port until a grant token is received.
6. The method of claim 2 further comprising the step of: attaching a grant (GNT) token to the packet as sent down a highest priority branch; and -13- attaching a deny (DEN) token to the packet as sent down all other branches.
7. The method of claim 5 wherein the GNT token is an end of subaction (EOS) token and the deny is an end of data (EOD) token.
8. The method of claim 2 wherein a plurality of nodes are organized into a tree topology and wherein a nominal root node is a node attached to originate a packet on the bus at a particular instant in time.
9. The method of claim 2 further comprising the step of: passing the grant toward the nominal root if no arbitration requests are received.
10. An apparatus comprising: a first port; and a physical layer (PHY) coupled to the first port that encodes a last packet of a subaction for transmission on a serial bus, the PHY arbitrating a next access to the serial bus and attaching a grant token to the last packet of the subaction to be transmitted out a highest priority port.
11. An apparatus of claim 10 wherein the PHY comprises an arbitration state machine continually receiving arbitration state information from which the highest priority port is identified.
12. The apparatus of claim 11 wherein the arbitration state machine generates current arbitration state information for the PHY when the PHY is not a PHY entitled to transmit a packet on the bus.
13. The apparatus of claim 11 wherein if no arbitration request for a current fairness interval is received by the arbitration state machine while the packet is prepared and transmitted the PHY initiates a transition into a next fairness interval.
14. A system comprising: a full duplex serial bus; and a plurality of nodes coupled together in a tree topology by the serial bus wherein a node transmitting a current packet is a nominal root node of the tree topology and wherein each other node repeatedly transmits current arbitration information toward the nominal root node.
15. The system of claim 14 wherein the nominal root node attaches a grant token to a last packet of a subaction transmitted down a highest priority branch and follows the packet with current arbitration information.
16. The system of claim 15 wherein a node claiming the grant token becomes the nominal root node.
17. The system of claim 14 wherein if the nominal root node has received no arbitration requests for a first fairness interval within a time required to prepare and transmit a current packet the nominal root node advances the system to a next fairness interval.
18. The system of claim 15 wherein a branch node receiving a packet with the grant token may acquire nominal root status or forward the grant token to a leaf node which may then acquire nominal root status.
19. The system of claim 15 wherein an arbitrating node closest to the nominal root node is favored to receive the grant token.
20. The system of claim 14 wherein the nominal root node passes the grant token toward a physical root node if no arbitration requests are received within a time required to prepare and transmit a last packet of a subaction.
PCT/US1999/002043 1998-02-02 1999-01-28 Distributed arbitration on a full duplex bus WO1999039479A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
AU24871/99A AU2487199A (en) 1998-02-02 1999-01-28 Distributed arbitration on a full duplex bus
EP99904479A EP1053617A4 (en) 1998-02-02 1999-01-28 Distributed arbitration on a full duplex bus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US09/017,451 1998-02-02
US09/017,451 US6411628B1 (en) 1998-02-02 1998-02-02 Distributed arbitration on a full duplex bus

Publications (1)

Publication Number Publication Date
WO1999039479A1 true WO1999039479A1 (en) 1999-08-05

Family

ID=21782659

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/US1999/002043 WO1999039479A1 (en) 1998-02-02 1999-01-28 Distributed arbitration on a full duplex bus

Country Status (4)

Country Link
US (2) US6411628B1 (en)
EP (1) EP1053617A4 (en)
AU (1) AU2487199A (en)
WO (1) WO1999039479A1 (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002073900A1 (en) * 2001-03-09 2002-09-19 Koninklijke Philips Electronics N.V. System of apparatuses that communicate via a bus structure
FR2833124A1 (en) * 2001-12-04 2003-06-06 Canon Kk Communications network digital word transmission having default first states and second states generating reduced state table representing/ forming network element blocks/providing network element state information.

Families Citing this family (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6411628B1 (en) * 1998-02-02 2002-06-25 Intel Corporation Distributed arbitration on a full duplex bus
JP2000013423A (en) * 1998-06-26 2000-01-14 Sony Corp Device and method for processing information and providing medium
US7158532B2 (en) * 1998-07-06 2007-01-02 Intel Corporation Half duplex link with isochronous and asynchronous arbitration
US6691096B1 (en) 1999-10-28 2004-02-10 Apple Computer, Inc. General purpose data container method and apparatus for implementing AV/C descriptors
US6618750B1 (en) 1999-11-02 2003-09-09 Apple Computer, Inc. Method and apparatus for determining communication paths
US6587904B1 (en) * 1999-11-05 2003-07-01 Apple Computer, Inc. Method and apparatus for preventing loops in a full-duplex bus
US6636914B1 (en) 1999-11-05 2003-10-21 Apple Computer, Inc. Method and apparatus for arbitration and fairness on a full-duplex bus using dual phases
US6639918B1 (en) 2000-01-18 2003-10-28 Apple Computer, Inc. Method and apparatus for border node behavior on a full-duplex bus
US7266617B1 (en) * 2000-01-18 2007-09-04 Apple Inc. Method and apparatus for border node behavior on a full-duplex bus
US7050453B1 (en) * 2000-02-17 2006-05-23 Apple Computer, Inc. Method and apparatus for ensuring compatibility on a high performance serial bus
US6831928B1 (en) * 2000-02-17 2004-12-14 Apple Computer, Inc. Method and apparatus for ensuring compatibility on a high performance serial bus
JP2001292146A (en) * 2000-04-07 2001-10-19 Sony Corp Electronic unit and processing method in bus initialized phase for interface device of digital serial data
US6618785B1 (en) * 2000-04-21 2003-09-09 Apple Computer, Inc. Method and apparatus for automatic detection and healing of signal pair crossover on a high performance serial bus
US6718497B1 (en) 2000-04-21 2004-04-06 Apple Computer, Inc. Method and apparatus for generating jitter test patterns on a high performance serial bus
US7310670B1 (en) * 2000-04-25 2007-12-18 Thomson Licensing S.A. Multi-channel power line exchange protocol
US6735654B2 (en) * 2001-03-19 2004-05-11 Sun Microsystems, Inc. Method and apparatus for efficiently broadcasting transactions between an address repeater and a client
US6826643B2 (en) 2001-03-19 2004-11-30 Sun Microsystems, Inc. Method of synchronizing arbiters within a hierarchical computer system
US6877055B2 (en) 2001-03-19 2005-04-05 Sun Microsystems, Inc. Method and apparatus for efficiently broadcasting transactions between a first address repeater and a second address repeater
US6889343B2 (en) 2001-03-19 2005-05-03 Sun Microsystems, Inc. Method and apparatus for verifying consistency between a first address repeater and a second address repeater
US20020133652A1 (en) * 2001-03-19 2002-09-19 Tai Quan Apparatus for avoiding starvation in hierarchical computer systems that prioritize transactions
US20040210696A1 (en) * 2003-04-18 2004-10-21 Meyer Michael J. Method and apparatus for round robin resource arbitration
US7668099B2 (en) 2003-06-13 2010-02-23 Apple Inc. Synthesis of vertical blanking signal
US7353284B2 (en) 2003-06-13 2008-04-01 Apple Inc. Synchronized transmission of audio and video data from a computer to a client via an interface
US8275910B1 (en) 2003-07-02 2012-09-25 Apple Inc. Source packet bridge
US7613767B2 (en) * 2003-07-11 2009-11-03 Microsoft Corporation Resolving a distributed topology to stream data
US7788567B1 (en) * 2003-11-18 2010-08-31 Apple Inc. Symbol encoding for tolerance to single byte errors
US7995606B1 (en) 2003-12-03 2011-08-09 Apple Inc. Fly-by and ack-accelerated arbitration for broadcast packets
US7733962B2 (en) 2003-12-08 2010-06-08 Microsoft Corporation Reconstructed frame caching
US7900140B2 (en) * 2003-12-08 2011-03-01 Microsoft Corporation Media processing methods, systems and application program interfaces
US7712108B2 (en) * 2003-12-08 2010-05-04 Microsoft Corporation Media processing methods, systems and application program interfaces
US7735096B2 (en) * 2003-12-11 2010-06-08 Microsoft Corporation Destination application program interfaces
US7502338B1 (en) 2003-12-19 2009-03-10 Apple Inc. De-emphasis training on a point-to-point connection
US7237135B1 (en) * 2003-12-29 2007-06-26 Apple Inc. Cyclemaster synchronization in a distributed bridge
US7308517B1 (en) * 2003-12-29 2007-12-11 Apple Inc. Gap count analysis for a high speed serialized bus
US20050185718A1 (en) * 2004-02-09 2005-08-25 Microsoft Corporation Pipeline quality control
US7934159B1 (en) 2004-02-19 2011-04-26 Microsoft Corporation Media timeline
US7941739B1 (en) 2004-02-19 2011-05-10 Microsoft Corporation Timeline source
US7664882B2 (en) * 2004-02-21 2010-02-16 Microsoft Corporation System and method for accessing multimedia content
US7669206B2 (en) * 2004-04-20 2010-02-23 Microsoft Corporation Dynamic redirection of streaming media between computing devices
US7739436B2 (en) * 2004-11-01 2010-06-15 Sonics, Inc. Method and apparatus for round robin resource arbitration with a fast request to grant response
US7889681B2 (en) * 2005-03-03 2011-02-15 Cisco Technology, Inc. Methods and devices for improving the multiple spanning tree protocol
US7792137B2 (en) * 2006-07-05 2010-09-07 Abidanet, Llc Self-organized and self-managed ad hoc communications network
US8483108B2 (en) * 2006-07-24 2013-07-09 Apple Inc. Apparatus and methods for de-emphasis training on a point-to-point connection
US20080130667A1 (en) * 2006-11-30 2008-06-05 International Business Machines Corporation Distributed arbitration mechanism for ring networks
US10579428B2 (en) 2017-12-01 2020-03-03 International Business Machines Corporation Data token management in distributed arbitration systems
EP3499806B1 (en) * 2017-12-13 2020-08-05 Nxp B.V. Node and method for conducting measurements and signal analyses on a multi-master access bus

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5167019A (en) * 1989-06-23 1992-11-24 Digital Equipment Corporation Apparatus and method for interconnecting a plurality of devices to a single node in a node-limited serial data bus computer network
US5495481A (en) * 1994-09-30 1996-02-27 Apple Computer, Inc. Method and apparatus for accelerating arbitration in a serial bus by detection of acknowledge packets

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS60141049A (en) * 1983-12-28 1985-07-26 Hitachi Ltd Loop network controlling system
US4785396A (en) * 1986-01-28 1988-11-15 Intel Corporation Push-pull serial bus coupled to a plurality of devices each having collision detection circuit and arbitration circuit
US5245609A (en) * 1991-01-30 1993-09-14 International Business Machines Corporation Communication network and a method of regulating the transmission of data packets in a communication network
JPH04332065A (en) * 1991-05-08 1992-11-19 Matsushita Electric Ind Co Ltd Method for transferring data
US5394556A (en) * 1992-12-21 1995-02-28 Apple Computer, Inc. Method and apparatus for unique address assignment, node self-identification and topology mapping for a directed acyclic graph
US5630173A (en) 1992-12-21 1997-05-13 Apple Computer, Inc. Methods and apparatus for bus access arbitration of nodes organized into acyclic directed graph by cyclic token passing and alternatively propagating request to root node and grant signal to the child node
GB2278259B (en) * 1993-05-21 1997-01-15 Northern Telecom Ltd Serial bus system
US5666488A (en) * 1994-11-22 1997-09-09 Lucent Technologies Inc. Port expansion network and method for lAN hubs
US5784648A (en) * 1995-12-01 1998-07-21 Apple Computer, Inc. Token style arbitration on a serial bus by passing an unrequested bus grand signal and returning the token by a token refusal signal
US5898694A (en) * 1996-12-30 1999-04-27 Cabletron Systems, Inc. Method of round robin bus arbitration
US6411628B1 (en) * 1998-02-02 2002-06-25 Intel Corporation Distributed arbitration on a full duplex bus

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5167019A (en) * 1989-06-23 1992-11-24 Digital Equipment Corporation Apparatus and method for interconnecting a plurality of devices to a single node in a node-limited serial data bus computer network
US5495481A (en) * 1994-09-30 1996-02-27 Apple Computer, Inc. Method and apparatus for accelerating arbitration in a serial bus by detection of acknowledge packets

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP1053617A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2002073900A1 (en) * 2001-03-09 2002-09-19 Koninklijke Philips Electronics N.V. System of apparatuses that communicate via a bus structure
FR2833124A1 (en) * 2001-12-04 2003-06-06 Canon Kk Communications network digital word transmission having default first states and second states generating reduced state table representing/ forming network element blocks/providing network element state information.

Also Published As

Publication number Publication date
US7023874B2 (en) 2006-04-04
US6411628B1 (en) 2002-06-25
US20020085581A1 (en) 2002-07-04
EP1053617A4 (en) 2002-06-26
EP1053617A1 (en) 2000-11-22
AU2487199A (en) 1999-08-16

Similar Documents

Publication Publication Date Title
US6411628B1 (en) Distributed arbitration on a full duplex bus
US6038234A (en) Early arbitration on a full duplex bus
US6356558B1 (en) Arbitration techniques for a high speed serial bus
US5701305A (en) Error recovery in a network having cascaded hubs
US6385679B1 (en) Fly-by serial bus arbitration
US5940399A (en) Methods of collision control in CSMA local area network
US5784648A (en) Token style arbitration on a serial bus by passing an unrequested bus grand signal and returning the token by a token refusal signal
US5598406A (en) High speed data transfer over twisted pair cabling
US6330245B1 (en) Hub system with ring arbitration
JP3909351B2 (en) Circular priority placement in Ethernet networks
JPH0795767B2 (en) Optimized method of data communication and system using the method
EP1987637B1 (en) System and method for transferring data packets through a communication system
KR100352568B1 (en) Circuit and method for reliably performing bus reset regardless of cable length
US6111890A (en) Gigabuffer lite repeater scheme
US7076716B1 (en) Early acknowledgement of primary packets
US5768250A (en) Error recovery in a network having cascaded hubs
RU126162U1 (en) COMMUNICATION INTERFACE DEVICE FOR NETWORK Space Wire
EP1157516B1 (en) Method and apparatus for transferring data on a bus to or from a device to be controlled by said bus
KR100352567B1 (en) Circuit and method for exchanging signals between nerwork nodes
JP4045714B2 (en) Optical wireless transmission apparatus and optical wireless transmission method
US20110292944A1 (en) Fly-by and ack-accelerated arbitration for broadcast packets
KR100320739B1 (en) Ieee 1394 system for long distance connection and embodying method thereof
JPH047620B2 (en)
JP2001320438A (en) Communication system
Hoang et al. Computer Communication Networks—Lecture Notes

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): AL AM AT AT AU AZ BA BB BG BR BY CA CH CN CU CZ CZ DE DE DK DK EE EE ES FI 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 MD MG MK MN MW MX NO NZ PL PT RO RU SD SE SG SI SK SK SL TJ TM TR TT UA UG US UZ VN YU ZW

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): GH GM KE LS MW SD SZ UG 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 BF BJ CF CG CI CM GA GN GW ML MR NE SN TD TG

121 Ep: the epo has been informed by wipo that ep was designated in this application
DFPE Request for preliminary examination filed prior to expiration of 19th month from priority date (pct application filed before 20040101)
NENP Non-entry into the national phase

Ref country code: KR

WWE Wipo information: entry into national phase

Ref document number: 1999904479

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 1999904479

Country of ref document: EP

REG Reference to national code

Ref country code: DE

Ref legal event code: 8642