US20040260858A1 - Configurable glueless microprocessor interface - Google Patents

Configurable glueless microprocessor interface Download PDF

Info

Publication number
US20040260858A1
US20040260858A1 US09/920,246 US92024601A US2004260858A1 US 20040260858 A1 US20040260858 A1 US 20040260858A1 US 92024601 A US92024601 A US 92024601A US 2004260858 A1 US2004260858 A1 US 2004260858A1
Authority
US
United States
Prior art keywords
interface
processor
bus
signal
coupled
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.)
Granted
Application number
US09/920,246
Other versions
US6842816B1 (en
Inventor
Donald Primrose
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.)
Xylon LLC
Original Assignee
Triquint Semiconductor Inc
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
Priority to US09/920,246 priority Critical patent/US6842816B1/en
Application filed by Triquint Semiconductor Inc filed Critical Triquint Semiconductor Inc
Assigned to NETWORK ELEMENTS, INC. reassignment NETWORK ELEMENTS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: PRIMROSE, DONALD R.
Publication of US20040260858A1 publication Critical patent/US20040260858A1/en
Application granted granted Critical
Publication of US6842816B1 publication Critical patent/US6842816B1/en
Assigned to TRIQUINT SEMICONDUCTOR, INC. reassignment TRIQUINT SEMICONDUCTOR, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: NETWORK ELEMENTS, INC.
Assigned to NULL NETWORKS LLC reassignment NULL NETWORKS LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TRIQUINT SEMICONDUCTOR, INC.
Assigned to NULL NETWORKS LLC reassignment NULL NETWORKS LLC ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: TRIQUINT SEMICONDUCTOR, INC.
Priority to US11/652,469 priority patent/USRE40660E1/en
Assigned to XYLON LLC reassignment XYLON LLC MERGER (SEE DOCUMENT FOR DETAILS). Assignors: NULL NETWORKS LLC
Adjusted expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F13/38Information transfer, e.g. on bus
    • G06F13/40Bus structure
    • G06F13/4063Device-to-bus coupling
    • G06F13/4068Electrical coupling

Definitions

  • the present invention relates to the field of electronic circuits. More specifically, the present invention relates to a configurable glueless microprocessor interface.
  • the Internet may be considered a global network of networks interconnected through countless numbers of network switching devices. These switching devices typically direct and/or route data from transmitting devices logically located within a first datacom/telecom network to receiving devices logically located within one or more additional datacom/telecom networks, regardless of their respective geographic locations.
  • the Internet has undergone remarkable growth in recent years. Whether this rapid growth has resulted in the advancement of network processing technologies, or advancements in network processing technologies have in turn spurred the Internet's rapid growth, the fact remains that modern day network switching devices are continually being called upon to direct greater amounts of increasingly complex data. Accordingly, it is becoming increasingly important that network communications be carried efficiently at high speed across a wide variety of local, regional, and wide area networks, including those comprising the Internet.
  • one or more companion processors also referred to as host processors
  • Basic implementations of these switches/routers typically route all packets through the host processor(s) to enable the host processor(s) to selectively divert some of the packets of selected ones of the various routing paths (for additional processing or dropping the packets), or to selectively inject additional packets into the packet streams of selected ones of the various routing paths.
  • additional switching/routing resources may be employed to facilitate routing of some of the packets of selected ones of the routing paths to the host processor(s) for “processing” (“diversion”), and routing of the packets injected by the host processor(s) onto the routing paths of their selection (“insertion”).
  • the host interface also allows the host processor to control the operational mode of the device, query the operational status of the device, and gain access to statistics, such as byte and packet counters, required by certain networking standards.
  • Host processors are often interfaced with network switching devices through various amounts of glue logic.
  • Manufacturers and system integrators choose to utilize certain microprocessor architectures depending upon the specific functionality and features desired.
  • a first type of processor architecture (commonly available from Intel Corp., of Santa Clara, Calif.) uses a separate address and data bus for memory addressing
  • a second type of processor architecture (commonly available from Motorola Inc., of Schaumburg, Ill.), uses a multiplexed address/data bus.
  • a multiplexed address and data bus allows for a reduced pin count enabling a smaller component package size and therefore lower cost.
  • the downside of a multiplexed address and data bus is that additional clock cycles are required to complete a transaction.
  • an address is typically driven onto the bus on a first clock edge, with the next clock edge signaling the beginning of one or more data phases in which data is to be transferred over the same bus.
  • Separate address and data paths on the other hand dedicate bandwidth to each phase of the data transfer, speeding internal data handling, and resulting in higher system performance.
  • Processors may also differ in the way they signal transactions. For example, certain types of processors utilize a transfer start indication signal in cooperation with a read/write signal to indicate the start of a read/write cycle, whereas other types of processors utilize separate read/write strobes to indicate the start of a read/write cycle.
  • network switching devices are designed to operate with host processors having a fixed architecture type. For example, if a network switch were designed to operate in cooperation with an Intel class processor functioning as a host processor, then simple substitution of a Motorola class host processor would not be possible without additional, and perhaps extensive glue logic being added. Accordingly, interoperability amongst processors and network switching devices is limited due to the proprietary signaling requirements of the various processors.
  • FIG. 1 is a block diagram illustrating an overview of the present invention in accordance with one embodiment
  • FIG. 2 illustrates a more detailed view of the control interface of FIG. 1, in accordance with one embodiment
  • FIG. 3 illustrates one embodiment of delay circuitry of the control interface of FIG. 1;
  • FIG. 4 is a block diagram illustrating two operating modes for the control interface of FIG. 1, in accordance with one embodiment
  • FIG. 5 is a block diagram illustrating two additional operating modes for the control interface of FIG. 1;
  • FIGS. 6 A-D represent timing diagrams illustrating the various read and write cycle signaling of the host side of control interface 105 , in accordance with various operational modes;
  • FIG. 7 represents a timing diagram illustrating the various read and write cycle signaling of the host side of control interface 105 ;
  • FIGS. 8 and 9 illustrate various example applications of the control interface of the present invention.
  • the present invention includes a host control interface for use in interfacing an external host processor with internal control/status registers of an integrated circuit.
  • the control interface selectively couples the integrated circuit with an interchangeable one of a variety of host processor types.
  • the control interface supports processors having a multiplexed address/data port as well as processors having separate address and data ports.
  • the control interface supports processors utilizing a transfer start indication signal in cooperation with a read/write signal, as well as processors utilizing separate read/write strobes.
  • FIG. 1 is a block diagram illustrating an overview of the present invention, in accordance with one embodiment.
  • integrated circuit (“IC”) 100 includes control interface 105 of the present invention, which selectively couples IC 100 to an interchangeable one or more host processors 102 .
  • control interface 105 is disposed “on chip” with IC 100 .
  • Control interface 105 represents a synchronous interface that can be connected to one or more external host processors or equivalent host logic to configure and control a device such as IC 100 .
  • Read and write bus transactions driven by a host processor are interpreted by the control interface logic and reformatted into a synchronous read/write protocol connected to various control/status registers within IC 100 (not shown).
  • control interface 105 utilizes a separate read and write data bus to eliminate bus contention issues.
  • host processor 102 represents one or more processors having an identified architecture type.
  • host processor 102 is identified as corresponding to one of a variety of architecture types including those that utilize a multiplexed address and data bus, those that utilize separate address and data buses, those that utilize a transfer start indication signal in cooperation with a read/write indicator, those that utilize separate read and write strobes, and those utilizing various combinations there between.
  • control interface 105 includes mode selection logic 107 to configure control interface 105 to operate in one of a plurality of operational modes based at least in part upon the identified architecture type of host processor 102 .
  • control interface 105 further includes delay circuitry 109 to provide programmable write latencies based at least in part upon the operating characteristics of host processor 102 .
  • FIG. 2 illustrates a more detailed view of control interface 105 of FIG. 1, in accordance with one embodiment.
  • control interface 105 includes a first interface (“host interface”) to be coupled to host processor 102 , and a second interface (“IC interface”) to be coupled to IC 100 .
  • the host interface includes host address/data bus 120 , host address bus 122 , read/write control signals 124 and read address/data bus 126 .
  • the IC interface includes write data bus 121 , IC address bus 123 , write control signal 125 , read control signal 127 , and read data bus 129 .
  • IC address bus 123 is a 10-bit address bus that facilitates addressing by control interface 105 of up to 1024 unique register locations within IC 100 . It should be noted however that other bus configurations and addressing schemes may be implemented without departing from the spirit and scope of the invention.
  • host address/data bus 120 is communicatively coupled to write data bus 121 as well as multiplexer (MUX) 110 .
  • addresses and data received on host address/data bus 120 i.e. from host processor 102
  • host address bus 122 is also coupled to MUX 110 as an input source.
  • MUX 110 selects information from either host address/data bus 120 or host address bus 122 to pass as output to delay circuitry 109 A, based upon the value of at least one mode control signal 130 (to be discussed in further detail below).
  • the state of mode control signal 130 is determined based upon the architecture type of host processor 102 .
  • Delay circuitry 109 A (as well as 109 B) represents circuitry and/or logic to programmably delay transmission of signals from the host interface to the IC interface in order to interchangeably accommodate various timing requirements of a variety of processors.
  • FIG. 3 illustrates one embodiment of delay circuitry 109 A and 109 B.
  • data registers 131 - 133 are cascaded together with variously positioned output taps 134 - 136 being independently connected to MUX 138 .
  • MUX 138 is controlled by a 2-bit latency control signal, which selects between the variously illustrated output. taps based upon a preferred latency determined with respect to processor 102 .
  • Delay bypass line 137 is additionally provided to circumvent data registers 131 - 133 altogether, resulting in zero additional latency.
  • the amount of latency desired is determined based upon the architecture of host processor 102 .
  • address information is typically driven on the multiplexed bus during a first clock cycle and data is driven on the same bus for at least the following clock cycle.
  • delay circuitry 109 A and 109 B may be programmed to provide zero latency up to a three-cycle delay, however other embodiments may provide a greater or fewer number of delay intervals.
  • delay circuitry 109 A and 109 B default to a latency that accounts for the slowest of potential host processor types that may likely be used (i.e. worst case scenario). In one embodiment, a default latency of three cycles is implemented. If a particular processor is capable of functioning with less latency than that stipulated by default, the processor may subsequently adjust the stored latency value(s) by writing a representative value to a particular configuration register provided by integrated circuit 100 or control interface 105 to set the above-mentioned latency control signal.
  • control interface 105 further includes write cycle decode logic 112 and read cycle decode logic 114 .
  • Write cycle decode logic 112 receives read/write control signals 124 as input, and outputs write control signal 125 to IC 100 based upon the operational mode specified by mode control signal 130 . For example, if mode control signal 130 indicates one mode of operation, write cycle decode will output a write control indication on write control line 125 when both a transfer start indication and a write indication are present on read/write control bus 124 .
  • mode control signal 130 indicates another mode of operation
  • write cycle decode will output a write control indication on write control line 125 when a mere write strobe is present.
  • the read cycle decode logic receives read/write control signals 124 as input, and outputs read control signal 127 to IC 100 also based upon the operational mode specified by mode control signal 130 . For example, if mode control signal 130 indicates a first mode of operation, read cycle decode will output a read control indication on read control line 127 when both a transfer start indication and a read indication are present on read/write control bus 124 . Similarly, if mode control signal 130 indicates a second mode of operation, read cycle decode will output a read control indication on read control line 127 when a mere read strobe is present.
  • Mode control signal 130 represents a mechanism through which control interface 105 may be programmed to operate in one of a plurality of operational modes in accordance with one of a plurality of signaling protocols and/or processor architectures.
  • mode control signal 130 represents two control signals implemented in the form of one or more independently programmable binary switches, such as “DIP” switches, that may be manually set to signal a selected one of a plurality of operating modes under which control interface 105 is to operate (e.g. based upon the constitution of processor 102 ).
  • mode control signal 130 may be implemented in the form of one or more independently and automatically programmable data registers to cause control interface 105 to operate in a specified operating mode based upon an identified architecture type of processor 102 .
  • mode control signals 130 may be adapted to decode such information and identify an operating mode for control interface 105 based upon that information.
  • mode control signal 130 represents two control signals enabling four independently programmable operating modes for control interface 105 .
  • a first control signal is used to select between a first operating mode whereby multiplexed address and data signals are received on host address/data bus 120
  • a second operating mode whereby addresses are received on host address/data bus 120 and data signals are received on separate host address bus 122 .
  • a second control signal is used to select between a third operating mode whereby a transfer start indication is used in cooperation with a read/write indication to signify the start of either a read or a write transaction, and a fourth operating mode whereby separate read and write strobes are used to signal the start of a read/write transaction.
  • each mode control signal may be independently set or cleared based upon the architecture of processor 102 .
  • FIG. 4 is a block diagram illustrating two operating modes for control interface 105 , in accordance with one embodiment.
  • the components depicted in FIG. 4 are functionally identical to their analogues of FIG. 2, but have been redrawn for the purpose of clarity.
  • three signal paths have additionally been indicated by the encircled labels of ( 1 ), ( 2 ), and ( 3 ).
  • signal paths ( 1 ) and ( 2 ) together indicate signal paths that would be followed by data and addresses received from a processor utilizing a multiplexed address and data bus, assuming MUX 110 (and by extension control interface 105 ) is set via mode control signal 130 to operate in a first operational mode.
  • Signal paths ( 1 ) and ( 3 ) indicate signal paths that would be followed by data and addresses received from a processor utilizing separate data and address buses, assuming MUX 110 is set via mode control signal 130 to operate in a second operational mode, for example. Accordingly, MUX 110 selects between two signal paths (e.g., ( 2 ) and ( 3 )) based at least in part upon the architecture of the host processor.
  • FIG. 5 is a block diagram illustrating two additional operating modes for control interface 105 .
  • the components depicted in FIG. 5 are functionally identical to their analogues of FIG. 2, but have also been redrawn for the purpose of clarity.
  • FIG. 5 further includes transfer acknowledge decode logic 148 , as well as three input signals (IN_CS, IN_RD, IN_WR) corresponding to the generalized read/write control signals 124 .
  • mode control signal 130 b selects between a third operating mode whereby a transfer start indication is used in cooperation with a read/write indication to signify the start of either a read or a write transaction, and a fourth operating mode whereby separate read and write strobes are used to signal the start of a read/write transaction.
  • the IN_RD signal line carries transfer start indications
  • the IN_WR signal line carries read/write indications.
  • mode control signal 130 b selects the fourth operating mode for example, the IN_RD signal line carries read strobes and the IN_WR signal line carries write strobes.
  • IN_CS represents a chip select signal line that is useful in the event that one or more additional control interfaces and/or integrated circuits are utilized increasing the addressing requirements of the host processor. Accordingly, IN_CS may be used to enable and disable write cycle decode logic 112 and read cycle decode logic 114 .
  • the transfer acknowledge signal 150 indicates to the host processor that a previous read or write operation was acknowledged by IC 100 . In one embodiment, transfer acknowledge signal 150 is asserted only when the write latency is greater than zero and when read data is valid on e.g. read bus 129 .
  • FIGS. 6 A-D represent timing diagrams illustrating the various read and write cycle signaling of the host side of control interface 105 , in accordance with various operational modes.
  • FIG. 6A is a timing diagram illustrating the operation of control interface 105 in accordance with a first operating mode where separate address and data bus is used in conjunction with transfer start and read/write signaling.
  • FIG. 6B is a timing diagram illustrating the operation of control interface 105 in accordance with a second operating mode where a multiplexed address and data bus is used in conjunction with transfer start and read/write signaling.
  • FIG. 6C is a timing diagram illustrating the operation of control interface 105 in accordance with a first operating mode where separate address and data bus is used in conjunction with read/write strobes.
  • FIG. 6D is a timing diagram illustrating the operation of control interface 105 in accordance with a second operating mode where a multiplexed address and data bus is used in conjunction with read/write strobes.
  • FIG. 7 represents a timing diagram illustrating the various read and write cycle signaling of the IC interface side of control interface 105 . From FIG. 7 it can be seen that an address is driven on address bus 123 at the same time read control signal 127 is asserted. During the following clock cycle, the read data is available on read data bus 129 . Further, it can be seen that control interface 105 drives a write address on address bus 123 at the same time the write data is driven on write data bus 121 . When the address and data are valid, control interface 105 asserts write control signal 125 to begin the transaction.
  • FIGS. 8 and 9 illustrate various example applications of the control interface of the present invention.
  • an optical networking module is shown including optical-electrical components 184 , optical components 182 , and support and control electronics 185 , which are coupled to host processor 102 via interface logic of the present invention.
  • Optical components 182 are employed to facilitate the sending and receiving of optical signals encoded with data transmitted in accordance with a selected one of a plurality of protocols known in the art.
  • Optical-electrical components 184 are employed to encode the egress data onto the optical signals, and decode the encoded ingress data.
  • the supported datacom and telecom protocols include but are not limited to SONET/SDH, 10Gbase-LR, 10Gbase-LW, Ethernet on SONET, Packet on SONET, and so forth.
  • Support control electronics 185 are employed to facilitate management of the various aspects of optical components 182 and optical-electrical components 184 .
  • Processor 102 is employed to perform data link and physical sub-layer processing on the egress and ingress data in accordance with a selected one of a plurality of supported datacom/telecom protocols, and to facilitate management of processor 102 itself and optical, optical-electrical components 182 and 184 (through support control electronics 185 ).
  • optical components 182 , optical-electrical components 184 , support control electronics 185 and processor 102 are encased in a body (not shown) forming a singular optical networking module.
  • the integrated optical networking module is also equipped to provide data link and physical sub-layer processing on egress and ingress data selectively for a number of protocols.
  • processor 102 is interchangeably coupled to the optical networking module, and may be replaced by one or more additional processors of varying architecture types.
  • FIG. 9 illustrates microprocessor 190 including various resources such as embedded memory, and control interface 105 of the present invention.
  • Microprocessor 190 is shown interchangeably coupled to host processor 102 , which through control interface 105 , may gain access to the various resources of microprocessor 190 independent of the architectural differences between host processor 102 and microprocessor 190 .

Abstract

A host control interface for use in interfacing an external host processor with internal control/status registers of an integrated circuit is provided. In accordance with the teachings of the present invention, the control interface selectively couples the integrated circuit with an interchangeable one of a variety of host processor types. In one embodiment, the control interface supports processors having a multiplexed address/data port as well as processors having separate address and data ports. Similarly, in one embodiment, the control interface supports processors utilizing a transfer start indication signal in cooperation with a read/write signal, as well as processors utilizing separate read/write strobes.

Description

    BACKGROUND OF THE INVENTION
  • 1. Field of the Invention [0001]
  • The present invention relates to the field of electronic circuits. More specifically, the present invention relates to a configurable glueless microprocessor interface. [0002]
  • 2. Background Information [0003]
  • The Internet may be considered a global network of networks interconnected through countless numbers of network switching devices. These switching devices typically direct and/or route data from transmitting devices logically located within a first datacom/telecom network to receiving devices logically located within one or more additional datacom/telecom networks, regardless of their respective geographic locations. The Internet has undergone remarkable growth in recent years. Whether this rapid growth has resulted in the advancement of network processing technologies, or advancements in network processing technologies have in turn spurred the Internet's rapid growth, the fact remains that modern day network switching devices are continually being called upon to direct greater amounts of increasingly complex data. Accordingly, it is becoming increasingly important that network communications be carried efficiently at high speed across a wide variety of local, regional, and wide area networks, including those comprising the Internet. [0004]
  • When switching or routing network traffic, a need often arises to divert a portion of the data packets being routed/switched onto a particular routing path to perform additional processing (or to drop the packets), or to insert additional packets into the packet streams being received off a routing path. To provide the desired packet diversion and/or insertion functionality, one or more companion processors (also referred to as host processors) are sometimes provided. Basic implementations of these switches/routers typically route all packets through the host processor(s) to enable the host processor(s) to selectively divert some of the packets of selected ones of the various routing paths (for additional processing or dropping the packets), or to selectively inject additional packets into the packet streams of selected ones of the various routing paths. In other more advanced implementations, additional switching/routing resources (such as programmable switching/routing tables) may be employed to facilitate routing of some of the packets of selected ones of the routing paths to the host processor(s) for “processing” (“diversion”), and routing of the packets injected by the host processor(s) onto the routing paths of their selection (“insertion”). In addition to facilitating the diversion and/or insertion of packets, the host interface also allows the host processor to control the operational mode of the device, query the operational status of the device, and gain access to statistics, such as byte and packet counters, required by certain networking standards. [0005]
  • Host processors are often interfaced with network switching devices through various amounts of glue logic. Manufacturers and system integrators choose to utilize certain microprocessor architectures depending upon the specific functionality and features desired. For example, a first type of processor architecture (commonly available from Intel Corp., of Santa Clara, Calif.) uses a separate address and data bus for memory addressing, whereas a second type of processor architecture (commonly available from Motorola Inc., of Schaumburg, Ill.), uses a multiplexed address/data bus. A multiplexed address and data bus allows for a reduced pin count enabling a smaller component package size and therefore lower cost. The downside of a multiplexed address and data bus is that additional clock cycles are required to complete a transaction. For example, an address is typically driven onto the bus on a first clock edge, with the next clock edge signaling the beginning of one or more data phases in which data is to be transferred over the same bus. Separate address and data paths on the other hand dedicate bandwidth to each phase of the data transfer, speeding internal data handling, and resulting in higher system performance. Processors may also differ in the way they signal transactions. For example, certain types of processors utilize a transfer start indication signal in cooperation with a read/write signal to indicate the start of a read/write cycle, whereas other types of processors utilize separate read/write strobes to indicate the start of a read/write cycle. [0006]
  • Typically, network switching devices are designed to operate with host processors having a fixed architecture type. For example, if a network switch were designed to operate in cooperation with an Intel class processor functioning as a host processor, then simple substitution of a Motorola class host processor would not be possible without additional, and perhaps extensive glue logic being added. Accordingly, interoperability amongst processors and network switching devices is limited due to the proprietary signaling requirements of the various processors.[0007]
  • BRIEF DESCRIPTION OF DRAWINGS
  • The present invention will be described by way of exemplary embodiments, but not limitations, illustrated in the accompanying drawings in which like references denote similar elements, and in which: [0008]
  • FIG. 1 is a block diagram illustrating an overview of the present invention in accordance with one embodiment; [0009]
  • FIG. 2 illustrates a more detailed view of the control interface of FIG. 1, in accordance with one embodiment; [0010]
  • FIG. 3 illustrates one embodiment of delay circuitry of the control interface of FIG. 1; [0011]
  • FIG. 4 is a block diagram illustrating two operating modes for the control interface of FIG. 1, in accordance with one embodiment; [0012]
  • FIG. 5 is a block diagram illustrating two additional operating modes for the control interface of FIG. 1; [0013]
  • FIGS. [0014] 6A-D represent timing diagrams illustrating the various read and write cycle signaling of the host side of control interface 105, in accordance with various operational modes;
  • FIG. 7 represents a timing diagram illustrating the various read and write cycle signaling of the host side of [0015] control interface 105; and
  • FIGS. 8 and 9 illustrate various example applications of the control interface of the present invention.[0016]
  • DETAILED DESCRIPTION OF THE INVENTION
  • The present invention includes a host control interface for use in interfacing an external host processor with internal control/status registers of an integrated circuit. In accordance with the teachings of the present invention, the control interface selectively couples the integrated circuit with an interchangeable one of a variety of host processor types. In one embodiment, the control interface supports processors having a multiplexed address/data port as well as processors having separate address and data ports. Similarly, in one embodiment, the control interface supports processors utilizing a transfer start indication signal in cooperation with a read/write signal, as well as processors utilizing separate read/write strobes. In the following description, various aspects of the present invention will be described. However, the present invention may be practiced with only some aspects of the present invention. For purposes of explanation, specific numbers, materials and configurations are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be practiced without the specific details. In other instances, well-known features are omitted or simplified in order not to obscure the present invention. Further, the description repeatedly uses the phrase “in one embodiment”, which ordinarily does not refer to the same embodiment, although it may. [0017]
  • FIG. 1 is a block diagram illustrating an overview of the present invention, in accordance with one embodiment. As shown, integrated circuit (“IC”) [0018] 100, includes control interface 105 of the present invention, which selectively couples IC 100 to an interchangeable one or more host processors 102. In one embodiment, control interface 105 is disposed “on chip” with IC 100. Control interface 105 represents a synchronous interface that can be connected to one or more external host processors or equivalent host logic to configure and control a device such as IC 100. Read and write bus transactions driven by a host processor are interpreted by the control interface logic and reformatted into a synchronous read/write protocol connected to various control/status registers within IC 100 (not shown). In one embodiment, control interface 105 utilizes a separate read and write data bus to eliminate bus contention issues.
  • As will be discussed in further detail below, [0019] host processor 102 represents one or more processors having an identified architecture type. In one embodiment, host processor 102 is identified as corresponding to one of a variety of architecture types including those that utilize a multiplexed address and data bus, those that utilize separate address and data buses, those that utilize a transfer start indication signal in cooperation with a read/write indicator, those that utilize separate read and write strobes, and those utilizing various combinations there between. In the illustrated embodiment of the invention, control interface 105 includes mode selection logic 107 to configure control interface 105 to operate in one of a plurality of operational modes based at least in part upon the identified architecture type of host processor 102. In the illustrated embodiment, control interface 105 further includes delay circuitry 109 to provide programmable write latencies based at least in part upon the operating characteristics of host processor 102.
  • FIG. 2 illustrates a more detailed view of [0020] control interface 105 of FIG. 1, in accordance with one embodiment. As illustrated, control interface 105 includes a first interface (“host interface”) to be coupled to host processor 102, and a second interface (“IC interface”) to be coupled to IC 100. The host interface includes host address/data bus 120, host address bus 122, read/write control signals 124 and read address/data bus 126. The IC interface includes write data bus 121, IC address bus 123, write control signal 125, read control signal 127, and read data bus 129. In one embodiment, IC address bus 123 is a 10-bit address bus that facilitates addressing by control interface 105 of up to 1024 unique register locations within IC 100. It should be noted however that other bus configurations and addressing schemes may be implemented without departing from the spirit and scope of the invention.
  • As illustrated in FIG. 2, host address/[0021] data bus 120 is communicatively coupled to write data bus 121 as well as multiplexer (MUX) 110. In one embodiment, addresses and data received on host address/data bus 120 (i.e. from host processor 102) are driven to write data bus 121 in addition to being provided as input into MUX 110. In addition to host address/data bus 120, host address bus 122 is also coupled to MUX 110 as an input source. In one embodiment, MUX 110 selects information from either host address/data bus 120 or host address bus 122 to pass as output to delay circuitry 109A, based upon the value of at least one mode control signal 130 (to be discussed in further detail below). In one embodiment, the state of mode control signal 130 is determined based upon the architecture type of host processor 102.
  • [0022] Delay circuitry 109A (as well as 109B) represents circuitry and/or logic to programmably delay transmission of signals from the host interface to the IC interface in order to interchangeably accommodate various timing requirements of a variety of processors. FIG. 3 illustrates one embodiment of delay circuitry 109A and 109B. In the illustrated embodiment, data registers 131-133 are cascaded together with variously positioned output taps 134-136 being independently connected to MUX 138. In the illustrated embodiment, MUX 138 is controlled by a 2-bit latency control signal, which selects between the variously illustrated output. taps based upon a preferred latency determined with respect to processor 102. For example, if output tap 134 were selected via MUX 138, a given input signal into the delay circuitry would be delayed by at least one clock cycle before being output from MUX 138. Similarly, if output tap 135 were to be selected, a given input signal would be delayed by at least two clock cycles before being output from MUX 138. Delay bypass line 137 is additionally provided to circumvent data registers 131-133 altogether, resulting in zero additional latency.
  • In one embodiment, the amount of latency desired is determined based upon the architecture of [0023] host processor 102. For example, in processors utilizing a multiplexed address/data bus, address information is typically driven on the multiplexed bus during a first clock cycle and data is driven on the same bus for at least the following clock cycle. In such cases, it may be desirable to delay the address information one or more cycles so that it is driven on the address bus at the same time valid write data is driven on the data bus. In the illustrated embodiment, delay circuitry 109A and 109B may be programmed to provide zero latency up to a three-cycle delay, however other embodiments may provide a greater or fewer number of delay intervals. In one embodiment, delay circuitry 109A and 109B default to a latency that accounts for the slowest of potential host processor types that may likely be used (i.e. worst case scenario). In one embodiment, a default latency of three cycles is implemented. If a particular processor is capable of functioning with less latency than that stipulated by default, the processor may subsequently adjust the stored latency value(s) by writing a representative value to a particular configuration register provided by integrated circuit 100 or control interface 105 to set the above-mentioned latency control signal.
  • Reference is once again made to FIG. 2, wherein [0024] control interface 105 is shown. In addition to the logic described above, control interface 105 further includes write cycle decode logic 112 and read cycle decode logic 114. Write cycle decode logic 112 receives read/write control signals 124 as input, and outputs write control signal 125 to IC 100 based upon the operational mode specified by mode control signal 130. For example, if mode control signal 130 indicates one mode of operation, write cycle decode will output a write control indication on write control line 125 when both a transfer start indication and a write indication are present on read/write control bus 124. Similarly, if mode control signal 130 indicates another mode of operation, write cycle decode will output a write control indication on write control line 125 when a mere write strobe is present. The read cycle decode logic receives read/write control signals 124 as input, and outputs read control signal 127 to IC 100 also based upon the operational mode specified by mode control signal 130. For example, if mode control signal 130 indicates a first mode of operation, read cycle decode will output a read control indication on read control line 127 when both a transfer start indication and a read indication are present on read/write control bus 124. Similarly, if mode control signal 130 indicates a second mode of operation, read cycle decode will output a read control indication on read control line 127 when a mere read strobe is present.
  • [0025] Mode control signal 130 represents a mechanism through which control interface 105 may be programmed to operate in one of a plurality of operational modes in accordance with one of a plurality of signaling protocols and/or processor architectures. In one embodiment, mode control signal 130 represents two control signals implemented in the form of one or more independently programmable binary switches, such as “DIP” switches, that may be manually set to signal a selected one of a plurality of operating modes under which control interface 105 is to operate (e.g. based upon the constitution of processor 102). In an alternative embodiment, mode control signal 130 may be implemented in the form of one or more independently and automatically programmable data registers to cause control interface 105 to operate in a specified operating mode based upon an identified architecture type of processor 102. For example, in the event processor 102 is equipped with one or more connection pins that provide external devices with information identifying one or more aspects of the processor's architecture, mode control signals 130 may be adapted to decode such information and identify an operating mode for control interface 105 based upon that information.
  • In one embodiment of the invention, [0026] mode control signal 130 represents two control signals enabling four independently programmable operating modes for control interface 105. For example, a first control signal is used to select between a first operating mode whereby multiplexed address and data signals are received on host address/data bus 120, and a second operating mode whereby addresses are received on host address/data bus 120 and data signals are received on separate host address bus 122. Similarly, a second control signal is used to select between a third operating mode whereby a transfer start indication is used in cooperation with a read/write indication to signify the start of either a read or a write transaction, and a fourth operating mode whereby separate read and write strobes are used to signal the start of a read/write transaction. In accordance with one embodiment of the invention, each mode control signal may be independently set or cleared based upon the architecture of processor 102.
  • FIG. 4 is a block diagram illustrating two operating modes for [0027] control interface 105, in accordance with one embodiment. The components depicted in FIG. 4 are functionally identical to their analogues of FIG. 2, but have been redrawn for the purpose of clarity. In FIG. 4, three signal paths have additionally been indicated by the encircled labels of (1), (2), and (3). In accordance with the teachings of the present invention, signal paths (1) and (2) together indicate signal paths that would be followed by data and addresses received from a processor utilizing a multiplexed address and data bus, assuming MUX 110 (and by extension control interface 105) is set via mode control signal 130 to operate in a first operational mode. Signal paths (1) and (3) indicate signal paths that would be followed by data and addresses received from a processor utilizing separate data and address buses, assuming MUX 110 is set via mode control signal 130 to operate in a second operational mode, for example. Accordingly, MUX 110 selects between two signal paths (e.g., (2) and (3)) based at least in part upon the architecture of the host processor.
  • FIG. 5 is a block diagram illustrating two additional operating modes for [0028] control interface 105. As with FIG. 4, the components depicted in FIG. 5 are functionally identical to their analogues of FIG. 2, but have also been redrawn for the purpose of clarity. In addition to those components shown in FIG. 2 however, FIG. 5 further includes transfer acknowledge decode logic 148, as well as three input signals (IN_CS, IN_RD, IN_WR) corresponding to the generalized read/write control signals 124. In accordance with one embodiment of the invention, mode control signal 130 b selects between a third operating mode whereby a transfer start indication is used in cooperation with a read/write indication to signify the start of either a read or a write transaction, and a fourth operating mode whereby separate read and write strobes are used to signal the start of a read/write transaction. In the illustrated embodiment, if mode control signal 130 b selects the third operating mode for example, the IN_RD signal line carries transfer start indications and the IN_WR signal line carries read/write indications. Similarly, if mode control signal 130 b selects the fourth operating mode for example, the IN_RD signal line carries read strobes and the IN_WR signal line carries write strobes. IN_CS represents a chip select signal line that is useful in the event that one or more additional control interfaces and/or integrated circuits are utilized increasing the addressing requirements of the host processor. Accordingly, IN_CS may be used to enable and disable write cycle decode logic 112 and read cycle decode logic 114. The transfer acknowledge signal 150 indicates to the host processor that a previous read or write operation was acknowledged by IC 100. In one embodiment, transfer acknowledge signal 150 is asserted only when the write latency is greater than zero and when read data is valid on e.g. read bus 129.
  • FIGS. [0029] 6A-D represent timing diagrams illustrating the various read and write cycle signaling of the host side of control interface 105, in accordance with various operational modes. FIG. 6A is a timing diagram illustrating the operation of control interface 105 in accordance with a first operating mode where separate address and data bus is used in conjunction with transfer start and read/write signaling. FIG. 6B is a timing diagram illustrating the operation of control interface 105 in accordance with a second operating mode where a multiplexed address and data bus is used in conjunction with transfer start and read/write signaling. FIG. 6C is a timing diagram illustrating the operation of control interface 105 in accordance with a first operating mode where separate address and data bus is used in conjunction with read/write strobes. FIG. 6D is a timing diagram illustrating the operation of control interface 105 in accordance with a second operating mode where a multiplexed address and data bus is used in conjunction with read/write strobes.
  • FIG. 7 represents a timing diagram illustrating the various read and write cycle signaling of the IC interface side of [0030] control interface 105. From FIG. 7 it can be seen that an address is driven on address bus 123 at the same time read control signal 127 is asserted. During the following clock cycle, the read data is available on read data bus 129. Further, it can be seen that control interface 105 drives a write address on address bus 123 at the same time the write data is driven on write data bus 121. When the address and data are valid, control interface 105 asserts write control signal 125 to begin the transaction.
  • Sample Applications
  • The control interface described above may provide flexible and interchangeable interface functionality to a broad category of devices. FIGS. 8 and 9 illustrate various example applications of the control interface of the present invention. In FIG. 8, an optical networking module is shown including optical-[0031] electrical components 184, optical components 182, and support and control electronics 185, which are coupled to host processor 102 via interface logic of the present invention. Optical components 182 are employed to facilitate the sending and receiving of optical signals encoded with data transmitted in accordance with a selected one of a plurality of protocols known in the art. Optical-electrical components 184 are employed to encode the egress data onto the optical signals, and decode the encoded ingress data. In one embodiment, the supported datacom and telecom protocols include but are not limited to SONET/SDH, 10Gbase-LR, 10Gbase-LW, Ethernet on SONET, Packet on SONET, and so forth. Support control electronics 185 are employed to facilitate management of the various aspects of optical components 182 and optical-electrical components 184. Processor 102 is employed to perform data link and physical sub-layer processing on the egress and ingress data in accordance with a selected one of a plurality of supported datacom/telecom protocols, and to facilitate management of processor 102 itself and optical, optical-electrical components 182 and 184 (through support control electronics 185).
  • In one embodiment, [0032] optical components 182, optical-electrical components 184, support control electronics 185 and processor 102 are encased in a body (not shown) forming a singular optical networking module. In addition to being equipped to provide optical to electrical and electrical to optical conversions, clock and data recovery, and so forth, the integrated optical networking module is also equipped to provide data link and physical sub-layer processing on egress and ingress data selectively for a number of protocols. In one embodiment, processor 102 is interchangeably coupled to the optical networking module, and may be replaced by one or more additional processors of varying architecture types.
  • FIG. 9 illustrates [0033] microprocessor 190 including various resources such as embedded memory, and control interface 105 of the present invention. Microprocessor 190 is shown interchangeably coupled to host processor 102, which through control interface 105, may gain access to the various resources of microprocessor 190 independent of the architectural differences between host processor 102 and microprocessor 190.
  • Conclusion and Epilogue
  • Thus, as can be seen from the above descriptions, a novel control interface having selectable operating modes to facilitate interchangeable operation with multiple host processor architectures has been described. While the present invention has been described in terms of the foregoing embodiments, those skilled in the art will recognize that the invention is not limited to these embodiments. The present invention may be practiced with modification and alteration within the spirit and scope of the appended claims. Thus, the description is to be regarded as illustrative instead of restrictive on the present invention. [0034]

Claims (26)

1. An integrated circuit comprising:
switching logic; and
a control interface having:
a first interface for connection to an interchangeable one of a first bus of a first processor, and a first and second bus of a second processor,
a second interface for connection to a data bus and an address bus of said switching logic, and
selection logic coupled to said first and second interfaces and equipped to receive a control signal identifying one of a first control mode to couple said first bus of said first processor to both said data bus and said address bus of said switching logic, and a second control mode to couple said first bus of said second processor to said data bus of said switching logic and to couple said second bus of said second processor to said address bus of said switching logic.
2. The integrated circuit of claim 1, wherein said control interface operates in said first control mode when said first interface is coupled to a multiplexed address and data bus of said first processor.
3. The integrated circuit of claim 1, wherein said control interface operates in said second control mode when said first interface is coupled to separate address and data buses of said second processor.
4. An integrated circuit comprising:
switching logic; and
a control interface having:
a first interface for connection to an interchangeable one of a first bus of a first processor, and a first and second bus of a second processor,
a second interface for connection to a data bus and an address bus of said switching logic,
selection logic coupled to said first and second interfaces and equipped to receive a control signal identifying one of a first control mode to couple said first bus of said first processor to both said data bus and said address bus of said switching logic, and a second control mode to couple said first bus of said second processor to said data bus of said switching logic and to couple said second bus of said second processor to said address bus of said switching logic, and
delay circuitry to programmably delay transmission of an address from one of said first and second processors to said address bus of said switching logic.
5. The integrated circuit of claim 1, further comprising:
a read data bus coupled to said first interface and said second interface to transmit multiplexed data and address signals between said switching logic coupled to said second interface and said first processor coupled to said first interface when said control signal identifies said first control mode, and to transmit data signals between said switching logic coupled to said second interface and said second processor coupled to said first interface when said control signal identifies said second control mode.
6. The integrated circuit of claim 1, wherein said control signal is received from an identified one of said first processor and said second processor.
7. A control interface for transmitting signals between an integrated circuit and an identifiable one of at least a first processor type operating in accordance with a first protocol and a second processor type operating in accordance with a second protocol, comprising:
a first signal path to couple one of a first bus of said first processor type and a second bus of said second processor type, with a data bus of said integrated circuit based at least in part upon an identified processor type;
a second signal path to couple said first bus of said first processor type with an address bus of said integrated circuit;
a third signal path to couple a third bus of said second processor type with said address bus of said integrated circuit; and
selection logic to select between said second and said third signal paths based at least in part upon said identified processor type.
8. The control interface of claim 7, wherein if said selection logic selects said second signal path then said third signal path is not utilized.
9. The control interface of claim 8, further comprising:
identification logic to identify which of said first processor type and said second processor type is coupled to said control interface.
10. The control interface of claim 7, wherein said first signal path transmits data signals to said integrated circuit, and said second and third signal paths transport address signals to said integrated circuit.
11. (canceled)
12. (canceled)
13. A control interface to be coupled to and transmit signals between a logic device and at least one of a first processor operating in accordance with a first protocol and a second processor operating in accordance with a second protocol, comprising:
a first signal line to receive a read strobe signal and a transfer start indication signal;
a second signal line to receive a write strobe signal and a read/write indicator signal to indicate read/write transactions;
first selection logic to signal a write transaction to said logic device if said control interface is coupled to said first processor and said write strobe signal is received on said second signal line, or said control interface is coupled to said second processor and a transfer start indication signal is received on said first signal line and a write transaction is indicated by said read/write indicator signal on said second signal line;
second selection logic to signal a read transaction to said logic device if said control interface is coupled to said first processor and said read strobe signal is received on said first signal line, or said control interface is coupled to said second processor and a transfer start indication signal is received on said first signal line and a read transaction is indicated by said read/write indicator signal on said second signal line; and
programmable delay circuitry to dynamically delay said write transaction.
14. The control interface of claim 13, wherein said programmable delay circuitry comprises circuitry to delay said write transaction from one to three clock cycles based at least in part upon timing requirements of said first or second processor.
15. An apparatus comprising:
a first interface to couple said apparatus to one of a plurality of host devices and a second interface to couple said apparatus to a second device,
said first interface being equipped to interchangeably receive either multiplexed address and data signals from a first bus of a first host device of said plurality of host devices for transmission to an address bus and a data bus of said second device, or address signals from a second bus of a second host device of said plurality of host devices for transmission to said address bus of said second device and data signals from a third bus of said second host device for transmission to said data bus of said second device; and
said first interface being further equipped to receive one or more control signals including a read strobe signal and a write strobe signal if said apparatus is coupled to one of said plurality of host devices operating in accordance with a first protocol, and to receive one or more control signals including a transfer start indication signal and a read/write indicator signal if said apparatus is coupled to one of said plurality of host devices operating in accordance with a second protocol.
16. The apparatus of claim 15, wherein said first interface is equipped to interchangeably coupled said apparatus to one of a plurality of processors.
17. An apparatus comprising:
a first interface to couple said apparatus to one of a plurality of host devices and a second interface to couple said apparatus to a second device,
said first interface being equipped to interchangeably receive either multiplexed address and data signals from a first bus of a first host device of said plurality of host devices for transmission to an address bus and a data bus of said second device, or address signals from a second bus of a second host device of said plurality of host devices for transmission to said address bus of said second device and data signals from a third bus of said second host device for transmission to said data bus of said second device;
said first interface being further equipped to receive one or more control signals including a read strobe signal and a write strobe signal if said apparatus is coupled to one of said plurality of host devices operating in accordance with a first protocol, and to receive one or more control signals including a transfer start indication signal and a read/write indicator signal if said apparatus is coupled to one of said plurality of host devices operating in accordance with a second protocol;
first delay circuitry to programmably delay address signals to be transmitted to said address bus of said second device; and
second delay circuitry to programmably delay write transactions to be transmitted to said second device.
18. The apparatus of claim 17, wherein said first and second delay circuitry is programmed to delay said address signals and said write transactions based at least in part upon operating characteristics of a host device coupled to said first interface.
19. The apparatus of claim 18, wherein said first delay circuitry and said second delay circuitry are programmed to delay an equal number of clock cycles.
20. A processor comprising:
internal resources; and
interface logic to selectively couple said processor to an interchangeable one of a plurality of host processors, by providing a first interface for connection to a first bus of a first host processor having a first architecture type, or a first and second bus of a second host processor having a second architecture type to provide a selected one of said first and second host processors with access to said resources.
21. The integrated circuit of claim 4, wherein said control interface operates in said first control mode when said first interface is coupled to a multiplexed address and data bus of said first processor.
22. The integrated circuit of claim 4, wherein said control interface operates in said second control mode when said first interface is coupled to separate address and data buses of said second processor.
23. The integrated circuit of claim 4, further comprising:
a read data bus coupled to said first interface and said second interface to transmit multiplexed data and address signals between said switching logic coupled to said second interface and said first processor coupled to said first interface when said control signal identifies said first control mode, and to transmit data signals between said switching logic coupled to said second interface and said second processor coupled to said first interface when said control signal identifies said second control mode.
24. The integrated circuit of claim 4, wherein said control signal is received from an identified on of said first processor and said second processor.
25. The control interface of claim 13, further comprising:
indicator logic coupled to said first selection logic and said second selection logic to identify whether said control interface is coupled to said first processor or said second processor.
26. The apparatus of claim 17, wherein said first interface is equipped to interchangeably coupled said apparatus to one of a plurality of processors.
US09/920,246 2001-07-31 2001-07-31 Configurable glueless microprocessor interface Ceased US6842816B1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US09/920,246 US6842816B1 (en) 2001-07-31 2001-07-31 Configurable glueless microprocessor interface
US11/652,469 USRE40660E1 (en) 2001-07-31 2007-01-10 Configurable glueless microprocessor interface

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US09/920,246 US6842816B1 (en) 2001-07-31 2001-07-31 Configurable glueless microprocessor interface

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US11/652,469 Reissue USRE40660E1 (en) 2001-07-31 2007-01-10 Configurable glueless microprocessor interface

Publications (2)

Publication Number Publication Date
US20040260858A1 true US20040260858A1 (en) 2004-12-23
US6842816B1 US6842816B1 (en) 2005-01-11

Family

ID=33518322

Family Applications (2)

Application Number Title Priority Date Filing Date
US09/920,246 Ceased US6842816B1 (en) 2001-07-31 2001-07-31 Configurable glueless microprocessor interface
US11/652,469 Expired - Lifetime USRE40660E1 (en) 2001-07-31 2007-01-10 Configurable glueless microprocessor interface

Family Applications After (1)

Application Number Title Priority Date Filing Date
US11/652,469 Expired - Lifetime USRE40660E1 (en) 2001-07-31 2007-01-10 Configurable glueless microprocessor interface

Country Status (1)

Country Link
US (2) US6842816B1 (en)

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060136651A1 (en) * 2004-12-16 2006-06-22 Rdc Semiconductor Co., Ltd. Selectively-switchable bus connecting device for chip device
US20060133126A1 (en) * 2004-12-22 2006-06-22 Renesas Technology Corp. Semiconductor memory device capable of switching from multiplex method to non-multiplex method
US20060233165A1 (en) * 2003-09-30 2006-10-19 Andrew Jarabek Managing data in a subtended switch
US20070071032A1 (en) * 2004-01-28 2007-03-29 Rambu Inc. Adaptive-allocation of i/o bandwidth using a configurable interconnect topology
US20070124509A1 (en) * 2005-10-14 2007-05-31 Oqo, Inc. Service processor for controlling a user interface
US20070230549A1 (en) * 2004-01-28 2007-10-04 Rambus Inc. Periodic calibration for communication channels by drift tracking
WO2016032828A1 (en) * 2014-08-29 2016-03-03 Cypress Semiconductor Company Integrated circuit device with programmable analog subsystem
US9628257B2 (en) 2004-01-28 2017-04-18 Rambus Inc. Communication channel calibration for drift conditions
US9710011B2 (en) 2004-03-17 2017-07-18 Rambus Inc. Drift tracking feedback for communication channels
CN107003971A (en) * 2014-12-27 2017-08-01 英特尔公司 Method, device, the system of embedded stream passage in being interconnected for high-performance
US10673582B2 (en) 2004-01-28 2020-06-02 Rambus Inc. Communication channel calibration for drift conditions

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2005071556A1 (en) * 2004-01-22 2005-08-04 Qualcomm Incorporated A two channel bus structure to support address information, data, and transfer qualifiers
US7209998B2 (en) * 2004-02-04 2007-04-24 Qualcomm Incorporated Scalable bus structure
JP2007148622A (en) * 2005-11-25 2007-06-14 Matsushita Electric Ind Co Ltd Interface setting method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4935894A (en) * 1987-08-31 1990-06-19 Motorola, Inc. Multi-processor, multi-bus system with bus interface comprising FIFO register stocks for receiving and transmitting data and control information
US4967346A (en) * 1988-03-14 1990-10-30 Advanced Micro Devices, Inc. Universal microprocessor interface circuit
US5305317A (en) * 1992-02-28 1994-04-19 Texas Instruments Incorporated Local area network adaptive circuit for multiple network types
US5740466A (en) * 1992-06-26 1998-04-14 Cirrus Logic, Inc. Flexible processor-driven SCSI controller with buffer memory and local processor memory coupled via separate buses
US5916312A (en) * 1997-05-06 1999-06-29 Sony Corporation ASIC having flexible host CPU interface for ASIC adaptable for multiple processor family members
US5918023A (en) * 1997-06-09 1999-06-29 Compaq Computer Corporation System design to support either Pentium Pro processors, Pentium II processors, and future processor without having to replace the system board

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4935894A (en) * 1987-08-31 1990-06-19 Motorola, Inc. Multi-processor, multi-bus system with bus interface comprising FIFO register stocks for receiving and transmitting data and control information
US4967346A (en) * 1988-03-14 1990-10-30 Advanced Micro Devices, Inc. Universal microprocessor interface circuit
US5305317A (en) * 1992-02-28 1994-04-19 Texas Instruments Incorporated Local area network adaptive circuit for multiple network types
US5740466A (en) * 1992-06-26 1998-04-14 Cirrus Logic, Inc. Flexible processor-driven SCSI controller with buffer memory and local processor memory coupled via separate buses
US5916312A (en) * 1997-05-06 1999-06-29 Sony Corporation ASIC having flexible host CPU interface for ASIC adaptable for multiple processor family members
US5918023A (en) * 1997-06-09 1999-06-29 Compaq Computer Corporation System design to support either Pentium Pro processors, Pentium II processors, and future processor without having to replace the system board

Cited By (35)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20060233165A1 (en) * 2003-09-30 2006-10-19 Andrew Jarabek Managing data in a subtended switch
US7359379B2 (en) * 2003-09-30 2008-04-15 Nortel Networks Limited Managing data in a subtended switch
US9628257B2 (en) 2004-01-28 2017-04-18 Rambus Inc. Communication channel calibration for drift conditions
US10673582B2 (en) 2004-01-28 2020-06-02 Rambus Inc. Communication channel calibration for drift conditions
US11664907B2 (en) 2004-01-28 2023-05-30 Rambus Inc. Periodic calibration for communication channels by drift tracking
US9667359B2 (en) 2004-01-28 2017-05-30 Rambus Inc. Periodic calibration for communication channels by drift tracking
US11552748B2 (en) 2004-01-28 2023-01-10 Rambus Inc. Communication channel calibration for drift conditions
US7420990B2 (en) * 2004-01-28 2008-09-02 Rambus Inc. Adaptive-allocation of I/O bandwidth using a configurable interconnect topology
US20080276020A1 (en) * 2004-01-28 2008-11-06 Rambus Inc. Adaptive-Allocation Of I/O Bandwidth Using A Configurable Interconnect Topology
US9667406B2 (en) 2004-01-28 2017-05-30 Rambus Inc. Communication channel calibration for drift conditions
US8149874B2 (en) 2004-01-28 2012-04-03 Rambus Inc. Adaptive-allocation of I/O bandwidth using a configurable interconnect topology
US11258522B2 (en) 2004-01-28 2022-02-22 Rambus Inc. Periodic calibration for communication channels by drift tracking
US8644419B2 (en) 2004-01-28 2014-02-04 Rambus Inc. Periodic calibration for communication channels by drift tracking
US8929424B2 (en) 2004-01-28 2015-01-06 Rambus Inc. Periodic calibration for communication channels by drift tracking
US9160466B2 (en) 2004-01-28 2015-10-13 Rambus Inc. Periodic calibration for communication channels by drift tracking
US11108510B2 (en) 2004-01-28 2021-08-31 Rambus Inc. Communication channel calibration for drift conditions
US10819447B2 (en) 2004-01-28 2020-10-27 Rambus Inc. Periodic calibration for communication channels by drift tracking
US20070071032A1 (en) * 2004-01-28 2007-03-29 Rambu Inc. Adaptive-allocation of i/o bandwidth using a configurable interconnect topology
US20070230549A1 (en) * 2004-01-28 2007-10-04 Rambus Inc. Periodic calibration for communication channels by drift tracking
US8073009B2 (en) 2004-01-28 2011-12-06 Rambus Inc. Adaptive allocation of I/O bandwidth using a configurable interconnect topology
US10523344B2 (en) 2004-01-28 2019-12-31 Rambus Inc. Periodic calibration for communication channels by drift tracking
US10320496B2 (en) 2004-01-28 2019-06-11 Rambus Inc. Periodic calibration for communication channels by drift tracking
US10305674B2 (en) 2004-01-28 2019-05-28 Rambus Inc. Communication channel calibration for drift conditions
US10503201B2 (en) 2004-03-17 2019-12-10 Rambus Inc. Drift tracking feedback for communication channels
US9710011B2 (en) 2004-03-17 2017-07-18 Rambus Inc. Drift tracking feedback for communication channels
US11327524B2 (en) 2004-03-17 2022-05-10 Rambus Inc. Drift tracking feedback for communication channels
US11669124B2 (en) 2004-03-17 2023-06-06 Rambus Inc. Drift tracking feedback for communication channels
US20060136651A1 (en) * 2004-12-16 2006-06-22 Rdc Semiconductor Co., Ltd. Selectively-switchable bus connecting device for chip device
US20060133126A1 (en) * 2004-12-22 2006-06-22 Renesas Technology Corp. Semiconductor memory device capable of switching from multiplex method to non-multiplex method
US8405603B2 (en) * 2005-10-14 2013-03-26 Google Inc. Service processor for controlling a user interface
US20070124509A1 (en) * 2005-10-14 2007-05-31 Oqo, Inc. Service processor for controlling a user interface
WO2016032828A1 (en) * 2014-08-29 2016-03-03 Cypress Semiconductor Company Integrated circuit device with programmable analog subsystem
US9634667B2 (en) 2014-08-29 2017-04-25 Cypress Semiconductor Corporation Integrated circuit device with programmable analog subsystem
EP3238385A4 (en) * 2014-12-27 2018-08-01 Intel Corporation A method, apparatus, system for embedded stream lanes in a high-performance interconnect
CN107003971A (en) * 2014-12-27 2017-08-01 英特尔公司 Method, device, the system of embedded stream passage in being interconnected for high-performance

Also Published As

Publication number Publication date
USRE40660E1 (en) 2009-03-10
US6842816B1 (en) 2005-01-11

Similar Documents

Publication Publication Date Title
USRE40660E1 (en) Configurable glueless microprocessor interface
EP0823168B1 (en) Low latency, high clock frequency plesioasynchronous packet-based crossbar switching chip system and method
US6345310B1 (en) Architecture for a multiple port adapter having a single media access control (MAC) with a single I/O port
US7917658B2 (en) Switching apparatus and method for link initialization in a shared I/O environment
US6373848B1 (en) Architecture for a multi-port adapter with a single media access control (MAC)
EP2333672B1 (en) Inter-die interconnection interface
US6393548B1 (en) Variable 16 or 32 bit PCI interface which supports steering and swapping of data
KR20030084974A (en) Buffer network for correcting fluctuations in a parallel/serial interface
US20070189299A1 (en) Receiving data from virtual channels
US20110179212A1 (en) Bus arbitration for sideband signals
US20100005205A1 (en) Device For Processing A Stream Of Data Words
US20060291464A1 (en) Data link/physical layer packet buffering and flushing
US7224691B1 (en) Flow control systems and methods for multi-level buffering schemes
US6801975B1 (en) Parallel SCSI host adapter and method for fast capture of shadow state data
US20060029095A1 (en) Method and system for fast Ethernet serial port multiplexing to reduce I/O pin count
KR100708425B1 (en) Apparatus and method for sharing memory using a single ring data bus connection configuration
US6957309B1 (en) Method and apparatus for re-accessing a FIFO location
KR20030084971A (en) A communication system
US6718417B1 (en) Physical layer and data link interface with flexible bus width
KR100268885B1 (en) Asynchronous data communication element
US7107381B2 (en) Flexible data transfer to and from external device of system-on-chip
US8521937B2 (en) Method and apparatus for interfacing multiple dies with mapping to modify source identity
EP1158735A1 (en) TDMA bus interface, system for communicating data, and method
US20030065869A1 (en) PCI/LVDS half bridge
US6857033B1 (en) I/O node for a computer system including an integrated graphics engine and an integrated I/O hub

Legal Events

Date Code Title Description
AS Assignment

Owner name: NETWORK ELEMENTS, INC., OREGON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:PRIMROSE, DONALD R.;REEL/FRAME:012048/0718

Effective date: 20010731

STCF Information on status: patent grant

Free format text: PATENTED CASE

AS Assignment

Owner name: TRIQUINT SEMICONDUCTOR, INC., OREGON

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:NETWORK ELEMENTS, INC.;REEL/FRAME:016182/0609

Effective date: 20041217

AS Assignment

Owner name: NULL NETWORKS LLC, NEVADA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TRIQUINT SEMICONDUCTOR, INC.;REEL/FRAME:017136/0951

Effective date: 20050908

AS Assignment

Owner name: NULL NETWORKS LLC, NEVADA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:TRIQUINT SEMICONDUCTOR, INC.;REEL/FRAME:017706/0550

Effective date: 20050908

RF Reissue application filed

Effective date: 20060103

FPAY Fee payment

Year of fee payment: 4

AS Assignment

Owner name: XYLON LLC, NEVADA

Free format text: MERGER;ASSIGNOR:NULL NETWORKS LLC;REEL/FRAME:037057/0156

Effective date: 20150813