US20070019570A1 - Reconfigurable circular bus - Google Patents

Reconfigurable circular bus Download PDF

Info

Publication number
US20070019570A1
US20070019570A1 US11/510,207 US51020706A US2007019570A1 US 20070019570 A1 US20070019570 A1 US 20070019570A1 US 51020706 A US51020706 A US 51020706A US 2007019570 A1 US2007019570 A1 US 2007019570A1
Authority
US
United States
Prior art keywords
bus
cores
circular
address
data
Prior art date
Legal status (The legal status 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 status listed.)
Abandoned
Application number
US11/510,207
Inventor
Peter Jenkins
Francis Kampf
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
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 International Business Machines Corp filed Critical International Business Machines Corp
Priority to US11/510,207 priority Critical patent/US20070019570A1/en
Publication of US20070019570A1 publication Critical patent/US20070019570A1/en
Abandoned legal-status Critical Current

Links

Images

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]
    • H04L12/42Loop networks
    • 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
    • H04L12/403Bus networks with centralised control, e.g. polling

Definitions

  • This invention relates to a system for providing communications between cores in an integrated circuit and, more particularly, to a reconfigurable circular bus.
  • a typical processing device includes various circuits such as a processor circuit, memory circuits, peripheral circuits, and the like. With recent technology, such a device may be manufactured using a printed circuit board supporting a plurality of integrated circuit chips. Each integrated circuit chip provided the functionality of one or more of the circuits. The individual circuits can be thought of as “core” circuits, or cores. When connected on a printed circuit board, the core circuits are often connected with point to point wiring.
  • FIG. 1 a block diagram for a typical SOC integrated circuit 10 is illustrated.
  • the illustrative integrated circuit 10 includes six cores 12 , 13 , 14 , 15 , 16 and 17 .
  • the cores 12 , 13 , 14 , 15 , 16 and 17 are identified under the letters A, B, C, D, E and F, respectively.
  • Each of the cores 12 - 17 is connected to a data bus 18 and an address bus 20 .
  • This prior art structure limits the amount of bandwidth available for communication between the cores 12 - 17 .
  • All cores 12 - 17 share the same wires. As a result, only one pair of cores can communicate at the same time.
  • the core connections may be tri-statable, or formed by ORing the gated outputs of all cores into one source driven back to all of the cores. Control of the buses 18 and 20 is granted by an arbiter (not shown) which grants control of the bus to one core at a time.
  • the present invention is directed to improvements in communication between cores in an integrated circuit.
  • a system for providing communication between a plurality of cores in an integrated circuit comprising a circular segmented bus operatively connected to each of the cores for transferring data between the plurality of cores.
  • Arbiter means arbitrate which of the plurality of cores can transmit data at any given time.
  • the circular segmented bus may comprise a data bus, an address bus, both a data bus and an address bus, or another type of bus.
  • the bus may comprise a split transaction data bus and address bus.
  • the circular segmented bus may comprise a circular bus and isolation means operatively positioned in the circular bus between each pair of adjacent cores.
  • the isolation means may comprise a plurality of transmission gate switches or a plurality of multiplexers.
  • the arbiter means may be operatively connected to each of the plurality of cores and receive access requests from the cores.
  • the arbiter means may dynamically segment the circular segmented bus responsive to the access request.
  • the arbiter means may dynamically segment the circular segmented bus responsive to the access request and destinations for data and to provide a maximum number of simultaneous transmissions.
  • FIG. 1 is a block diagram of a prior art system for providing communication between cores in an integrated circuit
  • FIG. 2 is a block diagram of a system for providing communication between cores in an integrated circuit in accordance with the invention
  • FIG. 3 is a flow diagram illustrating a program implemented by an arbiter/router of FIG. 2 ;
  • FIG. 4 is a block diagram, similar to FIG. 2 , illustrating a configured circular bus capable of two simultaneous transfer operations
  • FIG. 5 is a block diagram, similar to FIG. 2 , illustrating a configured circular bus capable of three simultaneous transfer operations.
  • a reconfigurable circular segmented bus which enables more than one pair of cores to share the bus at the same time.
  • the ability to support simultaneous data operations increases the bus bandwidth available to the cores.
  • an integrated circuit 30 includes six core circuits, or cores, 32 , 33 , 34 , 35 , 36 and 37 .
  • the cores 32 , 33 , 34 , 35 , 36 and 37 are additionally identified with the letters A, B, C, D, E, and F, respectively.
  • the present invention is not intended to be limited to any particular type of core circuits.
  • the cores 32 - 37 may be configured as bus master devices that initiate an operation. Such core devices may include, for example, a processor, a peripheral device, a DMA controller, or the like. Additionally, some of the cores 32 - 37 may consist of bus slave devices which responds to operations.
  • the cores 32 - 37 are interconnected via a circular segmented bus system 38 in accordance with the invention.
  • the bus system 38 includes a circular segmented data bus 40 and a circular segmented address bus 42 .
  • each of the buses 40 and 42 is functionally circular in configuration as it defines a continuous loop.
  • the use of circular buses 40 and 42 allows data to be transferred on either bus 40 or 42 in two different directions.
  • An arbiter/router 44 is connected to each of the cores 32 - 37 . Additionally, the arbiter 44 is connected to a plurality of data bus isolation circuits 46 A, 46 B, 46 C, 46 D, 46 E and 46 F. Similarly, the arbiter 44 is connected to a plurality of address bus isolation circuits 48 A, 48 B, 48 C, 48 D, 48 E and 48 F. For simplicity, when referenced generally, the isolation circuits are identified using the reference numerals without the suffix letter.
  • Each of the data isolation circuits 46 and address bus isolation circuits 48 is functionally located in the respective buses 40 and 42 between an adjacent pair of cores 32 - 37 . As such, the isolation circuits 46 and 48 segment the respective buses 40 and 42 to reconfigure the bus system 38 by selectively isolating select cores 32 - 37 from other select cores 32 - 37 , as described more particularly below.
  • the isolation circuits 46 A and 48 A are functionally located in the respective data bus 40 and address bus 42 between core A and core B.
  • the isolation circuits 46 B and 48 B are functionally located in the respective data bus 40 and address bus 42 between core B and core C.
  • the isolation circuits 46 C and 48 C are functionally located in the respective data bus 40 and address bus 42 between core C and core D.
  • the isolation circuits 46 D and 48 D are functionally located in the respective data bus 40 and address bus 42 between core E and core E.
  • the isolation circuits 46 E and 48 E are functionally located in the respective data bus 40 and address bus 42 between core E and core F.
  • the isolation circuits 46 F and 48 F are functionally located in the respective data bus 40 and address bus 42 between core F and core A.
  • the isolation circuits 46 and 48 are generally conventional in nature.
  • the isolation circuits 46 and 48 may consist of electrical switches in the bus, such as transmission gates.
  • the function of the isolation circuits 46 and 48 may be performed logically using a multiplexer based loop which provides a logical implementation of a transmission gate.
  • other types of isolation circuits may also be utilized in accordance with the invention.
  • the address ranges of the cores connected to the bus is predetermined and is not altered during operation.
  • the arbiter 44 is configured or programmed with this information and the cores 32 - 37 request access to the bus system 38 indicating the destination of the transfer. When multiple cores request bus access, the arbiter 44 determines which bus configurations will support which bus transfers and grant access to all of the cores that can operate simultaneously. Referring to FIG. 3 , a flow diagram illustrates operation of the arbiter 44 for determining the bus configuration.
  • the program begins at a start node 50 .
  • a block 52 initializes the arbiter with the address range information and other necessary information.
  • a decision block 54 determines if access requests have been received from any of the cores 32 - 37 . If not, then the program loops back continuously until a request is received. Once an access request is received, then the arbiter 44 analyzes the access request at a block 56 . The analysis includes considering what other cores have requested access, or currently have access, to the bus system 38 . The object of the analysis is to maximize the number of operations that can be performed simultaneously. Likewise, the analysis may include different priority levels for different types of operations. As a result of the analysis, the bus system 38 is configured at a block 58 . The control then returns to the decision block 54 to await additional requests.
  • FIG. 4 One example of a reconfigured circular bus for multiple transfers is illustrated in FIG. 4 .
  • core A and core F have requested access to the bus system 38 .
  • the operation requested by core A involves core B.
  • the operation requested by core F involves core D. Since these two operations do not need to share the same bus segments, both accesses are granted simultaneously.
  • the bus is reconfigured to isolate the segment joining core A and core B. Likewise, the bus segment between core F and core D is isolated. The transfers occur and the utilized bus segments are made available to other operations upon the completion of the related operation.
  • the segment of the bus system 38 joining core A and B is isolated by opening the data bus isolation switches 46 F and 46 B and opening the address bus isolation circuits 48 F and 48 B.
  • the bus segments between core F and core D are isolated by opening the data bus isolation circuits 46 F and 46 C and opening the address bus isolation circuits 48 F and 48 C. After the operation occurs, the utilized bus segments are made available to other operations.
  • the router 44 can reconfigure the bus at any time. For instance, in the above example, the operation between core F and core D may complete before the operation between core A and core B. If another operation is requested by core F, this time involving core E, and core C requests access to perform a transfer operation with core D, because the necessary bus segments are available to support both operations, the bus can be reconfigured and the arbiter 44 grants access to both additional requesting cores.
  • FIG. 5 illustrates the new configured circular bus configuration which is thus capable of three simultaneous operations. Particularly, the bus system 38 is reconfigured to isolate the segment joining core A and core B, and to isolate the segment joining core C and core D and finally, to isolate the segment joining core E and core F. This is done by opening the isolation circuits 46 B and 48 B, 46 D and 48 D and 46 F and 48 F, see FIG. 2 .
  • the specific design of the arbiter 44 is unique to each ASIC. Once the concept of a particular ASIC is known, then the implementation of the arbiter 44 will be developed from such concept.
  • the bus system 38 would consist of a split transaction address and data bus and thus address and data are not linked as an operation. All bus masters maintain connections to the address bus 42 and the arbiter 44 . A bus master would request access to the address bus 42 via a request to the arbiter 44 containing the more significant address bits. The number of bits is dependent upon the implementation and address ranges assigned to each bus slave. To minimize complexity, address ranges should be assigned on even powers of two across the various bus slaves. The arbiter 44 analyzes the requests from the various bus master cores to determine the best segmenting to serve the outstanding requests. The bus segmenting is redistributed upon the completion of each operation, which is indicated by the dropping of the request.
  • the bus master When a bus segment has been created to serve a bus master core, then the bus master is granted the bus by the arbiter 44 .
  • the bus master maintains the request for the duration of the address operation and drops the request upon completion of the address transfer.
  • the address bus consists of controls, address and transaction tag with master identification.
  • all bus masters and bus slaves maintain connections to the data bus and the arbiter 44 .
  • the request and granted handshake works in a similar manner as that of the address bus, discussed above, except the data bus request contains an I.D. of the bus master obtained during the address operation.
  • the arbiter 44 uses this information to determine the appropriate bus segmenting to service the outstanding request.
  • the bus slave maintains the request for the duration of the address operation and drops the request upon completion of the data transfer.
  • the data bus consists of controls, data and transaction tag with master identification.

Abstract

A system provides communication between a plurality of cores in an integrated circuit. The system comprises a circular segmented bus operatively connected to each of the cores for transferring data between the plurality of cores. An arbiter arbitrates which of the plurality of cores can transmit data at any given time.

Description

    CROSS REFERENCE TO RELATED APPLICATION
  • This application is a continuation of Utility application Ser. No. 10/063,456, filed Apr. 24, 2002.
  • FIELD OF THE INVENTION
  • This invention relates to a system for providing communications between cores in an integrated circuit and, more particularly, to a reconfigurable circular bus.
  • BACKGROUND OF THE INVENTION
  • A typical processing device includes various circuits such as a processor circuit, memory circuits, peripheral circuits, and the like. With recent technology, such a device may be manufactured using a printed circuit board supporting a plurality of integrated circuit chips. Each integrated circuit chip provided the functionality of one or more of the circuits. The individual circuits can be thought of as “core” circuits, or cores. When connected on a printed circuit board, the core circuits are often connected with point to point wiring.
  • More recently, system-on-a-chip (SOC) technology has been utilized. This technology is used, for example, in large ASICs (application specific integrated circuits) with many cores. The interconnection between cores becomes difficult due to wiring constraints and wiring congestion. A typical bus structure helps alleviate this problem by minimizing the wires between the various cores. Referring to FIG. 1, a block diagram for a typical SOC integrated circuit 10 is illustrated. The illustrative integrated circuit 10 includes six cores 12, 13, 14, 15, 16 and 17. Particularly, the cores 12, 13, 14, 15, 16 and 17 are identified under the letters A, B, C, D, E and F, respectively. Each of the cores 12-17 is connected to a data bus 18 and an address bus 20. This prior art structure limits the amount of bandwidth available for communication between the cores 12-17. All cores 12-17 share the same wires. As a result, only one pair of cores can communicate at the same time. The core connections may be tri-statable, or formed by ORing the gated outputs of all cores into one source driven back to all of the cores. Control of the buses 18 and 20 is granted by an arbiter (not shown) which grants control of the bus to one core at a time.
  • The present invention is directed to improvements in communication between cores in an integrated circuit.
  • SUMMARY OF THE INVENTION
  • In accordance with the invention, there is disclosed a system for providing communication between a plurality of cores in an integrated circuit. The system comprises a circular segmented bus operatively connected to each of the cores for transferring data between the plurality of cores. Arbiter means arbitrate which of the plurality of cores can transmit data at any given time.
  • The circular segmented bus may comprise a data bus, an address bus, both a data bus and an address bus, or another type of bus.
  • Additionally, the bus may comprise a split transaction data bus and address bus.
  • The circular segmented bus may comprise a circular bus and isolation means operatively positioned in the circular bus between each pair of adjacent cores. The isolation means may comprise a plurality of transmission gate switches or a plurality of multiplexers.
  • The arbiter means may be operatively connected to each of the plurality of cores and receive access requests from the cores. The arbiter means may dynamically segment the circular segmented bus responsive to the access request. The arbiter means may dynamically segment the circular segmented bus responsive to the access request and destinations for data and to provide a maximum number of simultaneous transmissions.
  • Further features and advantages of the invention will be readily apparent from the specification and from the drawing.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1 is a block diagram of a prior art system for providing communication between cores in an integrated circuit;
  • FIG. 2 is a block diagram of a system for providing communication between cores in an integrated circuit in accordance with the invention;
  • FIG. 3 is a flow diagram illustrating a program implemented by an arbiter/router of FIG. 2;
  • FIG. 4 is a block diagram, similar to FIG. 2, illustrating a configured circular bus capable of two simultaneous transfer operations; and
  • FIG. 5 is a block diagram, similar to FIG. 2, illustrating a configured circular bus capable of three simultaneous transfer operations.
  • DETAILED DESCRIPTION OF THE INVENTION
  • In accordance with the invention, a reconfigurable circular segmented bus is provided which enables more than one pair of cores to share the bus at the same time. The ability to support simultaneous data operations increases the bus bandwidth available to the cores.
  • Referring to FIG. 2, a block diagram illustrates the interconnections of the reconfigurable circular segmented bus in accordance with the invention. Particularly, an integrated circuit 30 includes six core circuits, or cores, 32, 33, 34, 35, 36 and 37. The cores 32, 33, 34, 35, 36 and 37 are additionally identified with the letters A, B, C, D, E, and F, respectively. The present invention is not intended to be limited to any particular type of core circuits. The cores 32-37 may be configured as bus master devices that initiate an operation. Such core devices may include, for example, a processor, a peripheral device, a DMA controller, or the like. Additionally, some of the cores 32-37 may consist of bus slave devices which responds to operations.
  • The cores 32-37 are interconnected via a circular segmented bus system 38 in accordance with the invention. The bus system 38 includes a circular segmented data bus 40 and a circular segmented address bus 42. As is apparent, each of the buses 40 and 42 is functionally circular in configuration as it defines a continuous loop. The use of circular buses 40 and 42 allows data to be transferred on either bus 40 or 42 in two different directions.
  • An arbiter/router 44, referred to hereinafter as an arbiter, is connected to each of the cores 32-37. Additionally, the arbiter 44 is connected to a plurality of data bus isolation circuits 46A, 46B, 46C, 46D, 46E and 46F. Similarly, the arbiter 44 is connected to a plurality of address bus isolation circuits 48A, 48B, 48C, 48D, 48E and 48F. For simplicity, when referenced generally, the isolation circuits are identified using the reference numerals without the suffix letter. Each of the data isolation circuits 46 and address bus isolation circuits 48 is functionally located in the respective buses 40 and 42 between an adjacent pair of cores 32-37. As such, the isolation circuits 46 and 48 segment the respective buses 40 and 42 to reconfigure the bus system 38 by selectively isolating select cores 32-37 from other select cores 32-37, as described more particularly below.
  • Particularly, the isolation circuits 46A and 48A are functionally located in the respective data bus 40 and address bus 42 between core A and core B. The isolation circuits 46B and 48B are functionally located in the respective data bus 40 and address bus 42 between core B and core C. The isolation circuits 46C and 48C are functionally located in the respective data bus 40 and address bus 42 between core C and core D. The isolation circuits 46D and 48D are functionally located in the respective data bus 40 and address bus 42 between core E and core E. The isolation circuits 46E and 48E are functionally located in the respective data bus 40 and address bus 42 between core E and core F. The isolation circuits 46F and 48F are functionally located in the respective data bus 40 and address bus 42 between core F and core A.
  • The isolation circuits 46 and 48 are generally conventional in nature. The isolation circuits 46 and 48 may consist of electrical switches in the bus, such as transmission gates. Alternatively, the function of the isolation circuits 46 and 48 may be performed logically using a multiplexer based loop which provides a logical implementation of a transmission gate. As is apparent, other types of isolation circuits may also be utilized in accordance with the invention.
  • In a system-on-a-chip (SOC) ASIC design, the address ranges of the cores connected to the bus is predetermined and is not altered during operation. The arbiter 44 is configured or programmed with this information and the cores 32-37 request access to the bus system 38 indicating the destination of the transfer. When multiple cores request bus access, the arbiter 44 determines which bus configurations will support which bus transfers and grant access to all of the cores that can operate simultaneously. Referring to FIG. 3, a flow diagram illustrates operation of the arbiter 44 for determining the bus configuration. The program begins at a start node 50. A block 52 initializes the arbiter with the address range information and other necessary information. A decision block 54 determines if access requests have been received from any of the cores 32-37. If not, then the program loops back continuously until a request is received. Once an access request is received, then the arbiter 44 analyzes the access request at a block 56. The analysis includes considering what other cores have requested access, or currently have access, to the bus system 38. The object of the analysis is to maximize the number of operations that can be performed simultaneously. Likewise, the analysis may include different priority levels for different types of operations. As a result of the analysis, the bus system 38 is configured at a block 58. The control then returns to the decision block 54 to await additional requests.
  • One example of a reconfigured circular bus for multiple transfers is illustrated in FIG. 4. In this figure the isolation switches 46 and 48 and interconnections to the arbiter 44 are omitted for clarity. In this example, core A and core F have requested access to the bus system 38. The operation requested by core A involves core B. The operation requested by core F involves core D. Since these two operations do not need to share the same bus segments, both accesses are granted simultaneously. The bus is reconfigured to isolate the segment joining core A and core B. Likewise, the bus segment between core F and core D is isolated. The transfers occur and the utilized bus segments are made available to other operations upon the completion of the related operation.
  • Particularly, the segment of the bus system 38 joining core A and B is isolated by opening the data bus isolation switches 46F and 46B and opening the address bus isolation circuits 48F and 48B. Likewise, the bus segments between core F and core D are isolated by opening the data bus isolation circuits 46F and 46C and opening the address bus isolation circuits 48F and 48C. After the operation occurs, the utilized bus segments are made available to other operations.
  • Since operations may not be initiated at the same time, or may be of different durations, the router 44 can reconfigure the bus at any time. For instance, in the above example, the operation between core F and core D may complete before the operation between core A and core B. If another operation is requested by core F, this time involving core E, and core C requests access to perform a transfer operation with core D, because the necessary bus segments are available to support both operations, the bus can be reconfigured and the arbiter 44 grants access to both additional requesting cores. FIG. 5 illustrates the new configured circular bus configuration which is thus capable of three simultaneous operations. Particularly, the bus system 38 is reconfigured to isolate the segment joining core A and core B, and to isolate the segment joining core C and core D and finally, to isolate the segment joining core E and core F. This is done by opening the isolation circuits 46B and 48B, 46D and 48D and 46F and 48F, see FIG. 2.
  • As is apparent, the specific design of the arbiter 44 is unique to each ASIC. Once the concept of a particular ASIC is known, then the implementation of the arbiter 44 will be developed from such concept.
  • In one embodiment of the present invention, the bus system 38 would consist of a split transaction address and data bus and thus address and data are not linked as an operation. All bus masters maintain connections to the address bus 42 and the arbiter 44. A bus master would request access to the address bus 42 via a request to the arbiter 44 containing the more significant address bits. The number of bits is dependent upon the implementation and address ranges assigned to each bus slave. To minimize complexity, address ranges should be assigned on even powers of two across the various bus slaves. The arbiter 44 analyzes the requests from the various bus master cores to determine the best segmenting to serve the outstanding requests. The bus segmenting is redistributed upon the completion of each operation, which is indicated by the dropping of the request. When a bus segment has been created to serve a bus master core, then the bus master is granted the bus by the arbiter 44. The bus master maintains the request for the duration of the address operation and drops the request upon completion of the address transfer. The address bus consists of controls, address and transaction tag with master identification.
  • Additionally, in this embodiment, all bus masters and bus slaves maintain connections to the data bus and the arbiter 44. The request and granted handshake works in a similar manner as that of the address bus, discussed above, except the data bus request contains an I.D. of the bus master obtained during the address operation. The arbiter 44 uses this information to determine the appropriate bus segmenting to service the outstanding request. The bus slave maintains the request for the duration of the address operation and drops the request upon completion of the data transfer. The data bus consists of controls, data and transaction tag with master identification.
  • Thus, in accordance with the invention, there is illustrated a system for providing communication between cores in an integrated circuit using a circular segmented bus for transferring data.

Claims (20)

1. A system for providing communication between a plurality of cores in an integrated circuit, they system comprising:
a circular segmented bus operatively connected to each of the cores for transferring data between the plurality of cores; and
arbiter means for arbitrating which of the plurality of cares can transmit data at any given time.
2. The system of claim 1 wherein the circular segmented bus comprises a data bus.
3. The system of claim 1 wherein the circular segmented bus comprises an address bus.
4. The system of claim 1 wherein the circular segmented bus comprises a data bus and an address bus.
5. The system of claim 1 wherein the circular segmented bus comprises a transmission gate switch between each pair of adjacent cores.
6. The system of claim 4 wherein the circular segmented bus comprises a plurality of multiplexers between each pair of adjacent cores.
7. The system of claim 1 wherein the cores are connected in parallel on the circular segmented bus.
8. An integrated circuit having a reconfigurable bus comprising:
a plurality of cores;
a circular bus;
means for operatively connecting the plurality of cores around the circular bus for transferring data on the circular bus between the plurality of cores;
segmenting means operatively positioned in the circular bus for controllably segmenting the circular bus; and
a router operatively connected to the plurality of cores and to the segmenting means for determining which of the plurality of cores can transmit data at any given time and controlling the segmenting means to dynamically segment the circular bus.
9. The system of claim 8 wherein the circular bus comprises a data bus.
10. The system of claim 8 wherein the circular bus comprises an address bus.
11. The system of claim 8 wherein the segmenting means comprises a plurality of transmission gate switches.
12. The system of claim 11 wherein the segmenting means comprises a plurality of multiplexers.
13. The system of claim 8 wherein the router receives access requests from the cores.
14. The system of claim 13 wherein the router dynamically segments the circular segmented bus responsive to the access requests.
15. The system of claim 13 wherein the router dynamically segments the circular segmented bus responsive to the access requests and destinations for data and to provide a maximum number of simultaneous transmissions.
16. The system of claim 13 wherein the router dynamically segments the circular segmented bus responsive to the access requests and preselect priorities of the access requests.
17. The system of claim 8 wherein the plurality of cores comprise bus master circuits and bus slave circuits.
18. The system of claim 17 wherein the circular bus comprises a split transaction data bus and address bus.
19. The system of claim 18 wherein one of the bus master circuits is operable to request access to the address bus using a request to the arbiter container more significant address bits in an address operation.
20. The system of claim 19 wherein a data bus request contains an identification of the one bus master circuit obtained during the address operation.
US11/510,207 2002-04-24 2006-08-25 Reconfigurable circular bus Abandoned US20070019570A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US11/510,207 US20070019570A1 (en) 2002-04-24 2006-08-25 Reconfigurable circular bus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US10/063,456 US7113488B2 (en) 2002-04-24 2002-04-24 Reconfigurable circular bus
US11/510,207 US20070019570A1 (en) 2002-04-24 2006-08-25 Reconfigurable circular bus

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US10/063,456 Continuation US7113488B2 (en) 2002-04-24 2002-04-24 Reconfigurable circular bus

Publications (1)

Publication Number Publication Date
US20070019570A1 true US20070019570A1 (en) 2007-01-25

Family

ID=29248081

Family Applications (2)

Application Number Title Priority Date Filing Date
US10/063,456 Active 2024-11-08 US7113488B2 (en) 2002-04-24 2002-04-24 Reconfigurable circular bus
US11/510,207 Abandoned US20070019570A1 (en) 2002-04-24 2006-08-25 Reconfigurable circular bus

Family Applications Before (1)

Application Number Title Priority Date Filing Date
US10/063,456 Active 2024-11-08 US7113488B2 (en) 2002-04-24 2002-04-24 Reconfigurable circular bus

Country Status (1)

Country Link
US (2) US7113488B2 (en)

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7113488B2 (en) * 2002-04-24 2006-09-26 International Business Machines Corporation Reconfigurable circular bus
US7093153B1 (en) * 2002-10-30 2006-08-15 Advanced Micro Devices, Inc. Method and apparatus for lowering bus clock frequency in a complex integrated data processing system
US7526350B2 (en) * 2003-08-06 2009-04-28 Creative Technology Ltd Method and device to process digital media streams
US20060041705A1 (en) * 2004-08-20 2006-02-23 International Business Machines Corporation System and method for arbitration between shared peripheral core devices in system on chip architectures
EP2477109B1 (en) 2006-04-12 2016-07-13 Soft Machines, Inc. Apparatus and method for processing an instruction matrix specifying parallel and dependent operations
EP2527972A3 (en) 2006-11-14 2014-08-06 Soft Machines, Inc. Apparatus and method for processing complex instruction formats in a multi- threaded architecture supporting various context switch modes and virtualization schemes
EP2616928B1 (en) 2010-09-17 2016-11-02 Soft Machines, Inc. Single cycle multi-branch prediction including shadow cache for early far branch prediction
US8972707B2 (en) * 2010-12-22 2015-03-03 Via Technologies, Inc. Multi-core processor with core selectively disabled by kill instruction of system software and resettable only via external pin
US8631256B2 (en) 2010-12-22 2014-01-14 Via Technologies, Inc. Distributed management of a shared power source to a multi-core microprocessor
US9460038B2 (en) 2010-12-22 2016-10-04 Via Technologies, Inc. Multi-core microprocessor internal bypass bus
EP2689326B1 (en) 2011-03-25 2022-11-16 Intel Corporation Memory fragments for supporting code block execution by using virtual cores instantiated by partitionable engines
EP2689327B1 (en) 2011-03-25 2021-07-28 Intel Corporation Executing instruction sequence code blocks by using virtual cores instantiated by partitionable engines
WO2012135041A2 (en) 2011-03-25 2012-10-04 Soft Machines, Inc. Register file segments for supporting code block execution by using virtual cores instantiated by partitionable engines
WO2012162188A2 (en) 2011-05-20 2012-11-29 Soft Machines, Inc. Decentralized allocation of resources and interconnect structures to support the execution of instruction sequences by a plurality of engines
CN103649931B (en) 2011-05-20 2016-10-12 索夫特机械公司 For supporting to be performed the interconnection structure of job sequence by multiple engines
KR101832679B1 (en) 2011-11-22 2018-02-26 소프트 머신즈, 인크. A microprocessor accelerated code optimizer
KR101703401B1 (en) 2011-11-22 2017-02-06 소프트 머신즈, 인크. An accelerated code optimizer for a multiengine microprocessor
US9569216B2 (en) 2013-03-15 2017-02-14 Soft Machines, Inc. Method for populating a source view data structure by using register template snapshots
KR20150130510A (en) 2013-03-15 2015-11-23 소프트 머신즈, 인크. A method for emulating a guest centralized flag architecture by using a native distributed flag architecture
US10275255B2 (en) 2013-03-15 2019-04-30 Intel Corporation Method for dependency broadcasting through a source organized source view data structure
US9904625B2 (en) 2013-03-15 2018-02-27 Intel Corporation Methods, systems and apparatus for predicting the way of a set associative cache
US9891924B2 (en) 2013-03-15 2018-02-13 Intel Corporation Method for implementing a reduced size register view data structure in a microprocessor
WO2014150991A1 (en) 2013-03-15 2014-09-25 Soft Machines, Inc. A method for implementing a reduced size register view data structure in a microprocessor
WO2014150806A1 (en) 2013-03-15 2014-09-25 Soft Machines, Inc. A method for populating register view data structure by using register template snapshots
US10140138B2 (en) 2013-03-15 2018-11-27 Intel Corporation Methods, systems and apparatus for supporting wide and efficient front-end operation with guest-architecture emulation
US9886279B2 (en) 2013-03-15 2018-02-06 Intel Corporation Method for populating and instruction view data structure by using register template snapshots
KR102063656B1 (en) 2013-03-15 2020-01-09 소프트 머신즈, 인크. A method for executing multithreaded instructions grouped onto blocks
US9811342B2 (en) 2013-03-15 2017-11-07 Intel Corporation Method for performing dual dispatch of blocks and half blocks
WO2014150971A1 (en) 2013-03-15 2014-09-25 Soft Machines, Inc. A method for dependency broadcasting through a block organized source view data structure
US11516087B2 (en) 2020-11-30 2022-11-29 Google Llc Connecting processors using twisted torus configurations
US11580058B1 (en) * 2021-08-30 2023-02-14 International Business Machines Corporation Hierarchical ring-based interconnection network for symmetric multiprocessors

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4821174A (en) * 1984-03-20 1989-04-11 Westinghouse Electric Corp. Signal processing system including a bus control module
US5555540A (en) * 1995-02-17 1996-09-10 Sun Microsystems, Inc. ASIC bus structure
US5613077A (en) * 1991-11-05 1997-03-18 Monolithic System Technology, Inc. Method and circuit for communication between a module and a bus controller in a wafer-scale integrated circuit system
US5689661A (en) * 1993-03-31 1997-11-18 Fujitsu Limited Reconfigurable torus network having switches between all adjacent processor elements for statically or dynamically splitting the network into a plurality of subsystems
US5729756A (en) * 1993-05-14 1998-03-17 Fujitsu Limited Torus networking method and apparatus having a switch for performing an I/O operation with an external device and changing torus size
US5878265A (en) * 1997-07-14 1999-03-02 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing polygonal hub topology
US5901295A (en) * 1995-04-28 1999-05-04 Apple Computer, Inc. Address and data bus arbiter for pipelined transactions on a split bus
US5908468A (en) * 1997-10-24 1999-06-01 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing a multiple traffic circle topology
US5936953A (en) * 1997-12-18 1999-08-10 Raytheon Company Multi-mode, multi-channel communication bus
US5974487A (en) * 1997-07-14 1999-10-26 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing a mesh of rings topology
US6018782A (en) * 1997-07-14 2000-01-25 Advanced Micro Devices, Inc. Flexible buffering scheme for inter-module on-chip communications
US6021455A (en) * 1995-09-05 2000-02-01 Hitachi, Ltd. Method and system for arbitrating a bus according to the status of a buffer and destination information
US6111859A (en) * 1997-01-16 2000-08-29 Advanced Micro Devices, Inc. Data transfer network on a computer chip utilizing combined bus and ring topologies
US6266797B1 (en) * 1997-01-16 2001-07-24 Advanced Micro Devices, Inc. Data transfer network on a computer chip using a re-configurable path multiple ring topology
US6314484B1 (en) * 1997-07-18 2001-11-06 Bull Hn Information Systems Italia S.P.A. Computer system with a bus having a segmented structure
US6662256B1 (en) * 1999-04-29 2003-12-09 Canon Kabushiki Kaisha Sequential bus architecture
US6724772B1 (en) * 1998-09-04 2004-04-20 Advanced Micro Devices, Inc. System-on-a-chip with variable bandwidth
US6735651B1 (en) * 1999-07-30 2004-05-11 International Business Machines Corporation Multi-chip module having chips coupled in a ring
US7113488B2 (en) * 2002-04-24 2006-09-26 International Business Machines Corporation Reconfigurable circular bus

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4821174A (en) * 1984-03-20 1989-04-11 Westinghouse Electric Corp. Signal processing system including a bus control module
US5613077A (en) * 1991-11-05 1997-03-18 Monolithic System Technology, Inc. Method and circuit for communication between a module and a bus controller in a wafer-scale integrated circuit system
US5689661A (en) * 1993-03-31 1997-11-18 Fujitsu Limited Reconfigurable torus network having switches between all adjacent processor elements for statically or dynamically splitting the network into a plurality of subsystems
US5729756A (en) * 1993-05-14 1998-03-17 Fujitsu Limited Torus networking method and apparatus having a switch for performing an I/O operation with an external device and changing torus size
US5555540A (en) * 1995-02-17 1996-09-10 Sun Microsystems, Inc. ASIC bus structure
US5901295A (en) * 1995-04-28 1999-05-04 Apple Computer, Inc. Address and data bus arbiter for pipelined transactions on a split bus
US6021455A (en) * 1995-09-05 2000-02-01 Hitachi, Ltd. Method and system for arbitrating a bus according to the status of a buffer and destination information
US6111859A (en) * 1997-01-16 2000-08-29 Advanced Micro Devices, Inc. Data transfer network on a computer chip utilizing combined bus and ring topologies
US6266797B1 (en) * 1997-01-16 2001-07-24 Advanced Micro Devices, Inc. Data transfer network on a computer chip using a re-configurable path multiple ring topology
US5974487A (en) * 1997-07-14 1999-10-26 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing a mesh of rings topology
US6018782A (en) * 1997-07-14 2000-01-25 Advanced Micro Devices, Inc. Flexible buffering scheme for inter-module on-chip communications
US5878265A (en) * 1997-07-14 1999-03-02 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing polygonal hub topology
US6314484B1 (en) * 1997-07-18 2001-11-06 Bull Hn Information Systems Italia S.P.A. Computer system with a bus having a segmented structure
US5908468A (en) * 1997-10-24 1999-06-01 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing a multiple traffic circle topology
US5936953A (en) * 1997-12-18 1999-08-10 Raytheon Company Multi-mode, multi-channel communication bus
US6724772B1 (en) * 1998-09-04 2004-04-20 Advanced Micro Devices, Inc. System-on-a-chip with variable bandwidth
US6662256B1 (en) * 1999-04-29 2003-12-09 Canon Kabushiki Kaisha Sequential bus architecture
US6735651B1 (en) * 1999-07-30 2004-05-11 International Business Machines Corporation Multi-chip module having chips coupled in a ring
US7113488B2 (en) * 2002-04-24 2006-09-26 International Business Machines Corporation Reconfigurable circular bus

Also Published As

Publication number Publication date
US20030202530A1 (en) 2003-10-30
US7113488B2 (en) 2006-09-26

Similar Documents

Publication Publication Date Title
US7113488B2 (en) Reconfigurable circular bus
EP1131729B1 (en) Communications system and method with multilevel connection identification
KR100628994B1 (en) Reusable Modules for Complex Integrated Circuit Devices
JP5036120B2 (en) Communication system and method with unblocked shared interface
US5659718A (en) Synchronous bus and bus interface device
US7145903B2 (en) Multi-master bus architecture for system-on-chip designs
EP0451938A2 (en) Multiple cluster signal processor
GB1593404A (en) Logic circuitry for use in a computer
JPH0773137A (en) Method, adaptor and system for arbitration of multilevel bus
US6628662B1 (en) Method and system for multilevel arbitration in a non-blocking crossbar switch
EP1653370B1 (en) Bus controller
US7640387B2 (en) Method and apparatus for implementing heterogeneous interconnects
JPH052552A (en) Workstation having burst mode capacity
US5557756A (en) Chained arbitration
US6634016B1 (en) Arrangement for partitioning logic into multiple field programmable gate arrays
JP3039451B2 (en) Priority arbitration device
US6389492B1 (en) Apparatus for flexibly allocating request/grant pins between multiple bus controllers
KR20050064694A (en) Partition type bus control device
JPH0573512A (en) Multiprocessor system
JPH076129A (en) Communication bus connecting device
JPH1115779A (en) Bus control system
JPH11122274A (en) Data communication equipment

Legal Events

Date Code Title Description
STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION