WO2016070630A1 - 传输信号的装置、传输链路和传输信号的方法 - Google Patents

传输信号的装置、传输链路和传输信号的方法 Download PDF

Info

Publication number
WO2016070630A1
WO2016070630A1 PCT/CN2015/081674 CN2015081674W WO2016070630A1 WO 2016070630 A1 WO2016070630 A1 WO 2016070630A1 CN 2015081674 W CN2015081674 W CN 2015081674W WO 2016070630 A1 WO2016070630 A1 WO 2016070630A1
Authority
WO
WIPO (PCT)
Prior art keywords
clusters
signal
signals
axi bus
transmitting
Prior art date
Application number
PCT/CN2015/081674
Other languages
English (en)
French (fr)
Inventor
罗达新
Original Assignee
华为技术有限公司
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 华为技术有限公司 filed Critical 华为技术有限公司
Publication of WO2016070630A1 publication Critical patent/WO2016070630A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38—Information transfer, e.g. on bus
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38—Information transfer, e.g. on bus
    • G06F13/40—Bus structure
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L1/00—Arrangements for detecting or preventing errors in the information received

Definitions

  • the present invention relates to the field of information technology and, more particularly, to a device for transmitting signals, a transmission link, and a method for transmitting signals.
  • the interconnects are electrically interconnected, that is, the copper wires on the printed circuit board (PCB) board or the silicon interconnects inside the silicon-based chip are used for electrical signal transmission.
  • PCB printed circuit board
  • the interconnects inside the silicon-based chip are used for electrical signal transmission.
  • a parallel signal that conforms to the Joint Electron Tube Engineering Council (JEDEC) standard is transmitted between the CPU and the memory through a copper wire, and the signal can only control the distance on the board ( Within a few tens of cm), it cannot be transmitted over long distances.
  • JEDEC Joint Electron Tube Engineering Council
  • Embodiments of the present invention provide a device for transmitting a signal, a transmission link, and a method for transmitting a signal, which are capable of transmitting a bus signal over a long distance.
  • an apparatus for transmitting a signal comprising:
  • a converter configured to receive an advanced expandable interface AXI bus signal, and divide the AXI bus signal into a plurality of clusters, wherein a timing relationship between a signal of each of the plurality of clusters and signals of other clusters is not interdependent;
  • a transmission module configured to sequentially transmit, to the receiving end, a signal of each of the plurality of clusters.
  • the converter is specifically configured to divide the AXI bus signal into three clusters of a read address, a write address, and a write data.
  • the converter is specifically configured to divide the AXI bus signal into two clusters of read address and write address write data.
  • the signal of each of the multiple clusters includes a cluster identifier, where the cluster identifier is used for the The receiving end combines the signals of the plurality of clusters into the AXI bus signal.
  • the transmission module is configured to adopt a streaming manner
  • the receiving end transmits a signal of each of the plurality of clusters.
  • the transmission module includes:
  • a serializer for performing parallel-to-serial conversion on signals of each of the plurality of clusters
  • an optical transmitter configured to perform electro-optical conversion on the signal of each of the plurality of clusters, and transmit the signal to the receiving end through the optical transmission medium.
  • the converter is configured to receive the AXI bus of multiple primary terminals simultaneously signal.
  • the apparatus further includes:
  • An arbiter configured to determine a transmission order of each of the plurality of clusters
  • the transmission module is specifically configured to sequentially transmit signals of each of the plurality of clusters to the receiving end according to a transmission sequence determined by the arbiter.
  • an apparatus for transmitting a signal including:
  • a transmission module configured to receive a signal of each of a plurality of clusters sequentially transmitted by the transmitting end, where The plurality of clusters are divided by the transmitting end by an advanced expandable interface AXI bus signal, and the timing relationship between the signals of each cluster of the plurality of clusters and the signals of other clusters is not interdependent;
  • a converter for combining signals of the plurality of clusters into the AXI bus signal.
  • the plurality of clusters includes three clusters of a read address, a write address, and a write data.
  • the plurality of clusters includes two clusters of read address and write address write data.
  • the signal of each of the multiple clusters includes a cluster identifier
  • the converter is specifically configured to combine the signals of the plurality of clusters into the AXI bus signal according to the cluster identifier.
  • the signal of each of the multiple clusters is The transmitting end performs encoding, parallel string conversion and electro-optical conversion, and transmits through the optical transmission medium;
  • the transmission module includes:
  • An optical receiver configured to receive a signal of each of the plurality of clusters, and perform photoelectric conversion on a signal of each of the plurality of clusters
  • a deserializer for performing serial-to-parallel conversion on signals of each of the plurality of clusters
  • a decoder for decoding signals of each of the plurality of clusters.
  • a transmission link including:
  • a main-end converter for receiving an advanced expandable interface AXI bus signal, dividing the AXI bus signal into a plurality of clusters, wherein a timing relationship between signals of each of the plurality of clusters and signals of other clusters is not mutually rely;
  • a primary transmission module configured to sequentially transmit, by the transmission medium, a signal of each of the plurality of clusters to the secondary transmission module;
  • a transmission medium for transmitting a signal of each of the plurality of clusters
  • a slave transmission module configured to receive a signal of each of the plurality of clusters
  • a slave converter for combining the signals of the plurality of clusters into the AXI bus signal.
  • the primary-side converter is specifically configured to divide the AXI bus signal into three clusters of a read address, a write address, and a write data.
  • the primary-side converter is specifically configured to divide the AXI bus signal into two clusters of read address and write address write data.
  • the signal of each of the multiple clusters includes a cluster identifier
  • the slave converter is specifically configured to combine the signals of the plurality of clusters into the AXI bus signal according to the cluster identifier.
  • the primary transmission module is configured to adopt a streaming manner A signal of each of the plurality of clusters is transmitted to the slave transmission module through the transmission medium in sequence.
  • the transmission medium is an optical transmission medium
  • the primary transmission module includes:
  • a serializer for performing parallel-to-serial conversion on signals of each of the plurality of clusters
  • An optical transmitter configured to perform electro-optical conversion on a signal of each of the plurality of clusters, and transmit the signal to the slave transmission module through the optical transmission medium;
  • the slave transmission module includes:
  • An optical receiver configured to receive a signal of each of the plurality of clusters, and perform photoelectric conversion on a signal of each of the plurality of clusters
  • a deserializer for performing serial-to-parallel conversion on signals of each of the plurality of clusters
  • a decoder for decoding signals of each of the plurality of clusters.
  • the primary end converter is configured to receive multiple primary terminals simultaneously AXI bus signal.
  • the transmission link further includes:
  • An arbiter configured to determine a transmission order of each of the plurality of clusters
  • the primary transmission module is specifically configured to sequentially transmit, to the secondary transmission module, signals of each of the plurality of clusters according to a transmission sequence determined by the arbiter.
  • a method of transmitting a signal including:
  • the AXI bus signal is divided into a plurality of clusters, wherein a timing relationship between signals of each of the plurality of clusters and signals of other clusters is not interdependent;
  • the signals of each of the plurality of clusters are transmitted to the receiving end in turn.
  • the AXI bus signal is divided into multiple clusters, including:
  • the AXI bus signal is divided into three clusters of a read address, a write address, and a write data.
  • the AXI bus signal is divided into multiple clusters, including:
  • the AXI bus signal is divided into two clusters of read address and write address write data.
  • the signal of each of the multiple clusters includes a cluster identifier, where the cluster identifier is used for the The receiving end combines the signals of the plurality of clusters into the AXI bus signal.
  • each of the multiple clusters is sequentially transmitted to the receiving end Cluster signals, including:
  • the signals of each of the plurality of clusters are sequentially transmitted to the receiving end by means of streaming.
  • each of the multiple clusters is sequentially transmitted to the receiving end Cluster signals, including:
  • the signals of each of the plurality of clusters are sequentially encoded, parallel-converted, and electro-optically converted, and transmitted to the receiving end through the optical transmission medium.
  • the receiving the advanced scalable interface AXI bus signal includes:
  • each of the multiple clusters is sequentially transmitted to the receiving end Before a cluster of signals, the method further includes:
  • the signals of each of the plurality of clusters are transmitted to the receiving end in turn according to the determined transmission order.
  • a method of transmitting a signal including:
  • the signals of the plurality of clusters are combined into the AXI bus signal.
  • the plurality of clusters includes three clusters of a read address, a write address, and write data.
  • the plurality of clusters includes two clusters of read address and write address write data.
  • the signal of each of the multiple clusters includes a cluster identifier
  • Combining the plurality of clusters into the AXI bus signal includes:
  • the signals of the plurality of clusters are combined into the AXI bus signal according to the cluster identifier.
  • the signal of each of the multiple clusters is The transmitting end performs encoding, parallel string conversion and electro-optical conversion, and transmits through the optical transmission medium;
  • Receiving signals of each of the plurality of clusters sequentially transmitted by the transmitting end including:
  • a signal of each of the plurality of clusters is received, and signals of each of the plurality of clusters are photoelectrically converted, serial-to-parallel converted, and decoded.
  • a computer includes: a CPU and a memory, and a transmission medium connecting the CPU and the memory, wherein the CPU includes the apparatus for transmitting a signal according to the first aspect, the memory includes the second aspect A means for transmitting a signal for transmitting a signal between the CPU and the memory.
  • the embodiment of the present invention divides the AXI bus signal into clusters whose timing relationships are not mutually dependent, and sequentially transmits signals of each of the plurality of clusters to the receiving end, which may be in a long distance transmission medium.
  • the signals of the respective clusters are transmitted in sequence, so that the bus signals can be transmitted over long distances.
  • FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present invention.
  • FIG. 2 is a schematic block diagram of an apparatus for transmitting signals according to an embodiment of the present invention.
  • FIG. 3 is a schematic block diagram of an apparatus for transmitting a signal according to another embodiment of the present invention.
  • FIG. 4 is a schematic block diagram of an apparatus for transmitting a signal according to still another embodiment of the present invention.
  • FIG. 5 is a schematic illustration of the sequence of operations of an embodiment of the present invention.
  • FIG. 6 is a schematic block diagram of an apparatus for transmitting a signal according to still another embodiment of the present invention.
  • FIG. 7 is a schematic block diagram of an apparatus for transmitting a signal according to still another embodiment of the present invention.
  • Figure 8 is a schematic block diagram of a transmission link in accordance with one embodiment of the present invention.
  • FIG. 9 is a schematic block diagram of a transmission link according to another embodiment of the present invention.
  • FIG. 10 is a schematic block diagram of a transmission link according to still another embodiment of the present invention.
  • FIG. 11 is a schematic flow chart of a method of transmitting a signal according to an embodiment of the present invention.
  • FIG. 12 is a schematic flowchart of a method for transmitting a signal according to another embodiment of the present invention.
  • FIG. 1 is a schematic diagram of an application scenario according to an embodiment of the present invention.
  • the master terminal 110 and the slave terminal 120 transmit bus signals, such as Advanced EXtensible Interface (AXI) bus signals, over the transmission link 130.
  • the master 110 is a processor, such as a CPU; the slave 120 can be a memory or a peripheral.
  • the AXI bus signal can be a memory read/write signal or a read/write signal between the CPU and the peripheral.
  • the embodiment of the present invention can be applied not only to a scenario of a primary end and a secondary end, but also to a scenario of multiple primary ends and multiple secondary ends.
  • FIG. 2 shows a schematic block diagram of an apparatus 200 for transmitting signals in accordance with an embodiment of the present invention.
  • the device 200 is located on the primary side (e.g., after the primary 110 in Figure 1) for transmitting the AXI bus signal of the primary to the secondary.
  • the apparatus 200 includes:
  • the converter 210 is configured to receive an AXI bus signal, and divide the AXI bus signal into a plurality of clusters, wherein a timing relationship between a signal of each of the plurality of clusters and signals of other clusters is not interdependent;
  • the transmission module 220 is configured to sequentially transmit signals of each of the plurality of clusters to the receiving end.
  • the converter 210 can be connected to the primary end to receive the AXI bus signal of the primary end.
  • the converter 210 can simultaneously receive AXI bus signals from multiple primary terminals. After receiving the AXI bus signal of the primary end, the converter 210 divides the AXI bus signal into timing relationships and does not depend on multiple clusters.
  • the converter 210 is specifically configured to divide the AXI bus signal into three clusters of a read address, a write address, and a write data.
  • the AXI bus signal from the master to the slave is divided into three clusters of a read address, a write address, and a write data.
  • the timing relationships between the three clusters are not dependent on each other.
  • the signal of each of the plurality of clusters includes a cluster identifier, and the cluster identifier is used by the receiving end to combine the signals of the plurality of clusters into the AXI bus signal.
  • the following signals can be included in the read address cluster:
  • ARID read address ID
  • ARPROT type of protection
  • ARVALID the read address is valid
  • ARADDR read address
  • AWID write address ID
  • AWLEN the length of the burst write
  • AWSIZE the size of the burst write
  • the cluster identifier may not be included in each cluster.
  • the transmitting end and the receiving end may transmit the respective clusters in a predetermined order, so that the receiving end can determine each cluster.
  • the above three clusters are signals from the master to the slave.
  • only one cluster can be used, for example, it can be called a read data cluster.
  • the following data can be included in the read data cluster:
  • RID read ID
  • RVALID the read data is valid
  • RDATA read data
  • Each of the above clusters can be 64-bit data, and clusters of less than 64 bits can be complemented by 0 or 1, and if there are more than 64 bits, some useless signals (such as the high bits of AWCACHE) can be deleted as appropriate.
  • the converter 210 can also perform special processing on some special signals.
  • these signals are write data-related handshake signals and can be omitted.
  • the slave converter can generate these three handshake signals at the same time when there is write data.
  • the slave can be forced to be high before the corresponding signal is returned, so that the converter 210 can receive the next read/write signal from the master.
  • multiple AXI bus signals can also be received simultaneously.
  • the VALID class and RESP class signals from the end to the master such as BVALID/RVALID/BRESP/RRESP, when it continues to appear high for several cycles, it is changed to a high value of only one cycle.
  • the converter 210 is specifically configured to divide the AXI bus signal into two clusters of read address and write address write data.
  • the write address signal and the write data signal are divided into one cluster, that is, the write address write data cluster. Since the write address signal and the write data signal have a sequential order, the same cluster can be time-multiplexed. Read the address signal as another cluster. The timing relationships between the two clusters are not dependent on each other.
  • the signal of each of the plurality of clusters includes a cluster identifier, and the cluster identifier is used by the receiving end to combine the signals of the plurality of clusters into the AXI bus signal.
  • a write address write data cluster can merge the write address cluster and the write data cluster in the foregoing example.
  • the read address cluster can be the same as the read address cluster in the previous example.
  • the converter 210 can also perform special processing on some special signals, which is similar to the foregoing embodiment, and will not be further described herein for brevity.
  • the transmission module 220 After the converter 210 divides the AXI bus signal into a plurality of clusters, the transmission module 220 sequentially transmits signals of each of the plurality of clusters to the receiving end.
  • the receiving end is located at the slave end side (for example, before the slave terminal 120 in FIG. 1) and is a device for transmitting signals from the end side.
  • the transmission module 220 may sequentially transmit a signal of each of the plurality of clusters to the receiving end by means of streaming. That is to say, the transmission module 220 sequentially transmits each cluster by means of streaming according to the granularity of the cluster, for example, encoding and parallel-converting the signals of each cluster, and transmitting to the receiving end through the transmission medium.
  • the transmission medium may be an electrical transmission medium or an optical transmission medium, where the optical transmission medium may be an optical fiber or an optical waveguide or the like.
  • the transmission module 220 includes an encoder 221, a serializer 222, and an optical transmitter 223.
  • the encoder 221 is configured to encode signals of each of the plurality of clusters.
  • the encoder 221 can adopt a codec mode of 64b/66b or 8b/10b.
  • the serializer 222 is configured to perform parallel-to-serial conversion on the signals of each of the plurality of clusters.
  • the optical transmitter 223 is configured to perform electro-optical conversion on the signals of each of the plurality of clusters, and transmit the signals to the receiving end through the optical transmission medium.
  • the transmission module 220 can also receive signals from the terminal, such as the aforementioned read data cluster.
  • the transmission module 220 may further include an optical receiver, a deserializer, and a decoder.
  • the optical receiver and the optical transmitter may constitute an optical transceiver, and the deserializer and the serializer may form a serializer/deserializer.
  • the decoder, decoder and encoder can form a codec.
  • This embodiment uses optical transmission to transmit signals of each cluster, and can take advantage of the high transmission rate of optical transmission.
  • the apparatus 200 may further include an arbiter 230.
  • the arbiter 230 is configured to determine a transmission order of each of the plurality of clusters.
  • the transmission module 220 is specifically configured to sequentially transmit signals of each of the plurality of clusters to the receiving end according to the transmission sequence determined by the arbiter 230.
  • the embodiment of the present invention can be used for both a scenario of a primary end and a scenario of multiple primary ends.
  • the arbiter 230 may store the contents of each cluster (write data, write address, read address) transferred to the slave direction in a register sequence as shown in FIG.
  • Each unit represents an operation (one cluster), and each operation is assigned a corresponding counter. If the counter can be 8 bits, the first 4 bits are the contents of the QOS in the AXI bus, which represents the priority of the operation; the last 4 bits are initially 0, and the counter is automatically incremented by 1 after each operation.
  • the arbiter 230 determines which operation is preferentially transmitted based on the size of the counter. If the two counters are the same size, the read operation takes precedence (no read operations with equal counter sizes). When a new operation is added, it is sorted by size according to the value of its counter, and the value of the counter of the sequence header is kept at the maximum.
  • the device for transmitting signals divides the AXI bus signal into a plurality of clusters whose timing relationships are not mutually dependent, and sequentially transmits signals of each of the plurality of clusters to the receiving end, which can be used in a long distance transmission medium.
  • the signals of the respective clusters are sequentially transmitted, so that the bus signals can be transmitted over long distances.
  • FIG. 6 shows a schematic block diagram of an apparatus 600 for transmitting signals in accordance with an embodiment of the present invention.
  • the device 600 is located from the end side (e.g., before the slave end 120 in Figure 1).
  • the apparatus 600 includes:
  • the transmitting module 610 is configured to receive a signal of each of the plurality of clusters sequentially transmitted by the transmitting end, where The plurality of clusters are divided by the transmitting end to obtain an AXI bus signal, and the timing relationship between the signals of each of the plurality of clusters and the signals of other clusters are not mutually dependent;
  • the converter 620 is configured to combine the signals of the plurality of clusters into the AXI bus signal.
  • the transmitting end is located at the primary end side (for example, after the primary end 110 in FIG. 1), and is a device for transmitting signals on the primary side, such as the device 200 for transmitting signals.
  • the transmitting end divides the AXI bus signal into a plurality of clusters whose timing relationships are not mutually dependent, and sequentially transmits signals of each of the plurality of clusters to the device 600, and the transmitting module 610 receives each cluster of the plurality of clusters.
  • converter 620 After the signal, converter 620 combines the signals of the plurality of clusters into an AXI bus signal.
  • the plurality of clusters includes three clusters of a read address, a write address, and write data.
  • the plurality of clusters includes two clusters of read address and write address write data.
  • a cluster identifier is included in a signal of each of the plurality of clusters
  • the converter 620 is specifically configured to combine the signals of the plurality of clusters into the AXI bus signal according to the cluster identifier.
  • the converter 620 identifies different clusters according to the cluster identifier, and then reassembles the clusters into AXI bus signals for transmission to the slaves.
  • the signal of each of the plurality of clusters is encoded by the transmitting end, serial-to-serial converted, and electro-optic converted, and transmitted through the optical transmission medium.
  • the transmission module 610 includes:
  • the optical receiver 611 is configured to receive a signal of each of the plurality of clusters, and perform photoelectric conversion on the signals of each of the plurality of clusters;
  • a deserializer 612 configured to perform serial-to-parallel conversion on signals of each of the plurality of clusters
  • the decoder 613 is configured to decode signals of each of the plurality of clusters.
  • the transmission module 610 can also send signals to the primary end, such as the aforementioned read data cluster.
  • the transmission module 610 may further include an encoder, a serializer, and an optical transmitter, and the optical transmission
  • the optical transceiver and the optical receiver can form an optical transceiver
  • the serializer and the deserializer can form a serializer/deserializer
  • the encoder and the decoder can form a codec.
  • the device 600 for transmitting signals may correspond to the receiving end in the foregoing embodiment of the apparatus 200 for transmitting signals.
  • the device 600 for transmitting signals may correspond to the receiving end in the foregoing embodiment of the apparatus 200 for transmitting signals.
  • reference may be made to the corresponding description of the foregoing embodiments, and details are not described herein for brevity.
  • the device for transmitting a signal combines the signals of the plurality of clusters into the AXI bus signal by receiving signals of each cluster in the clusters in which the plurality of timing relationships of the AXI bus signals sequentially transmitted by the transmitting end are not mutually dependent.
  • the signals of the respective clusters can be transmitted in a long-distance transmission medium, so that the bus signals can be transmitted over long distances.
  • FIG. 8 shows a schematic block diagram of a transmission link 800 in accordance with an embodiment of the present invention.
  • the transmission link 800 is located between the primary and secondary (e.g., transmission link 130 in FIG. 1). As shown in FIG. 8, the transmission link 800 includes:
  • the main converter 810 is configured to receive an AXI bus signal, and divide the AXI bus signal into a plurality of clusters, wherein a timing relationship between a signal of each of the plurality of clusters and signals of other clusters is not interdependent;
  • the primary end transmission module 820 is configured to sequentially transmit, by the transmission medium, a signal of each of the plurality of clusters to the secondary transmission module;
  • a transmission medium 830 configured to transmit a signal of each of the plurality of clusters
  • the slave transmission module 840 is configured to receive a signal of each of the plurality of clusters
  • the slave converter 850 is configured to combine the signals of the plurality of clusters into the AXI bus signal.
  • the primary converter 810 is specifically configured to divide the AXI bus signal into three clusters of a read address, a write address, and a write data.
  • the primary converter 810 is specifically configured to divide the AXI bus signal into two clusters of read address and write address write data.
  • a cluster identifier is included in a signal of each of the plurality of clusters
  • the slave converter 850 is specifically configured to combine the signals of the plurality of clusters into the AXI bus signal according to the cluster identifier.
  • the primary transmission module 820 is configured to sequentially transmit, by using the transmission medium 830, the signal of each of the multiple clusters to the secondary transmission module 840 by using a streaming manner.
  • the transmission medium 830 is an optical transmission medium
  • the primary transmission module 820 includes:
  • An encoder 821 configured to encode a signal of each of the plurality of clusters
  • a serializer 822 configured to perform parallel-to-serial conversion on signals of each of the plurality of clusters
  • the optical transmitter 823 is configured to perform electro-optic conversion on the signal of each of the plurality of clusters, and transmit the signal to the slave transmission module 840 through the optical transmission medium;
  • the slave transmission module 840 includes:
  • the optical receiver 841 is configured to receive a signal of each of the plurality of clusters, and perform photoelectric conversion on the signals of each of the plurality of clusters;
  • a deserializer 842 configured to perform serial-to-parallel conversion on signals of each of the plurality of clusters
  • the decoder 843 is configured to decode signals of each of the plurality of clusters.
  • the primary transmission module 820 can also receive signals from the secondary end, and the secondary transmission module 840 can also send signals to the primary terminal, such as the aforementioned read data cluster.
  • the primary transmission module 820 may further include an optical receiver, a deserializer, and a decoder.
  • the secondary transmission module 840 may further include an encoder, a serializer, and an optical transmitter.
  • the optical transmitter and the optical receiver may be The optical transceiver, the serializer and the deserializer can form a serializer/deserializer, and the encoder and decoder can form a codec.
  • the primary converter 810 is configured to simultaneously receive AXI bus signals of multiple primary terminals.
  • the transmission link 800 further includes:
  • An arbiter 860 configured to determine a transmission order of each of the plurality of clusters
  • the primary transmission module 820 is specifically configured to sequentially transmit signals of each of the plurality of clusters to the secondary transmission module 840 according to the transmission sequence determined by the arbiter 860.
  • the transmission link 800 of the embodiment of the present invention may include the apparatus 200 for transmitting signals, the apparatus 600 for transmitting signals, and the transmission medium according to the foregoing embodiments of the present invention.
  • the primary end converter 810, the primary transmission module 820, and the arbiter 860 correspond to the converter 210, the transmission module 220 and the arbiter 230 in the device 200, the slave transmission module 840 and the slave converter 850 can correspond to the transmission module 610 and the converter 620 in the device 600, and related functions can refer to the foregoing implementations.
  • the examples are not described herein for brevity.
  • the transmission link of the embodiment of the present invention can separately transmit each of the plurality of clusters by sequentially dividing the AXI bus signal into clusters in which the timing relationships are not mutually dependent, and sequentially transmitting the signals in each of the plurality of clusters.
  • the signals of the clusters enable the transmission of bus signals over long distances.
  • FIG. 11 shows a schematic flow diagram of a method 1100 of transmitting a signal in accordance with an embodiment of the present invention.
  • the method 1100 is performed by a transmitting end (e.g., a device transmitting a signal on the primary side).
  • the method 1100 includes:
  • the AXI bus signal is divided into a plurality of clusters, wherein a timing relationship between signals of each of the plurality of clusters and signals of other clusters is not mutually dependent;
  • the AXI bus signal is divided into a plurality of clusters whose timing relationships are not mutually dependent, and the signals of each of the plurality of clusters are sequentially transmitted to the receiving end, and the transmission medium can be at a long distance.
  • the signals of the respective clusters are sequentially transmitted, so that the bus signals can be transmitted over long distances.
  • the AXI bus signal is divided into multiple clusters, including:
  • the AXI bus signal is divided into three clusters of a read address, a write address, and a write data.
  • the AXI bus signal is divided into multiple clusters, including:
  • the AXI bus signal is divided into two clusters of read address and write address write data.
  • the signal of each cluster of the plurality of clusters includes a cluster label
  • the cluster identifier is used by the receiving end to combine the signals of the plurality of clusters into the AXI bus signal.
  • the signals of each of the plurality of clusters are sequentially transmitted to the receiving end, including:
  • the signals of each of the plurality of clusters are sequentially transmitted to the receiving end by means of streaming.
  • the signals of each of the plurality of clusters are sequentially transmitted to the receiving end, including:
  • the signals of each of the plurality of clusters are sequentially encoded, parallel-converted, and electro-optically converted, and transmitted to the receiving end through the optical transmission medium.
  • receiving an advanced expandable interface AXI bus signal includes:
  • the method 1100 further includes:
  • the signals of each of the plurality of clusters are transmitted to the receiving end in turn according to the determined transmission order.
  • the corresponding process of the method 1100 for transmitting a signal in the embodiment of the present invention may be performed by the device 200 for transmitting a signal according to the foregoing embodiment of the present invention.
  • the device 200 for transmitting a signal may be performed by the device 200 for transmitting a signal according to the foregoing embodiment of the present invention.
  • FIG. 12 shows a schematic flow diagram of a method 1200 of transmitting a signal in accordance with an embodiment of the present invention.
  • the method 1200 is performed by a receiving end (e.g., a device that transmits signals from the end side). As shown in FIG. 12, the method 1200 includes:
  • S1210 Receive a signal of each cluster of the plurality of clusters sequentially transmitted by the transmitting end, where the plurality of clusters are divided by the transmitting end by an advanced expandable interface AXI bus signal, and signals of each cluster of the plurality of clusters The timing relationship with the signals of other clusters is not interdependent;
  • the method for transmitting a signal combines the signals of the plurality of clusters into the AXI bus signal by receiving signals of each cluster in the clusters in which the plurality of timing relationships of the AXI bus signals sequentially transmitted by the transmitting end are not mutually dependent.
  • the signals of the respective clusters can be transmitted in a long-distance transmission medium, so that the bus signals can be transmitted over long distances.
  • the plurality of clusters includes three clusters of a read address, a write address, and write data.
  • the plurality of clusters comprise two clusters of read address and write address write data.
  • the signal of each of the plurality of clusters includes a cluster identifier
  • Combining the plurality of clusters into the AXI bus signal includes:
  • the signals of the plurality of clusters are combined into the AXI bus signal according to the cluster identifier.
  • the signal of each of the plurality of clusters is encoded by the transmitting end, serially converted, and electrically converted, and transmitted through the optical transmission medium;
  • Receiving signals of each of the plurality of clusters sequentially transmitted by the transmitting end including:
  • a signal of each of the plurality of clusters is received, and signals of each of the plurality of clusters are photoelectrically converted, serial-to-parallel converted, and decoded.
  • the corresponding flow of the method 1200 for transmitting a signal in the embodiment of the present invention may be performed by the apparatus 600 for transmitting a signal according to the foregoing embodiment of the present invention.
  • the apparatus 600 for transmitting a signal may be performed by the apparatus 600 for transmitting a signal according to the foregoing embodiment of the present invention.
  • the embodiment of the present invention further provides a computer, including: a CPU and a memory, and a transmission medium connecting the CPU and the memory, wherein the CPU includes the apparatus 200 for transmitting signals according to the foregoing embodiment of the present invention, and the memory includes the foregoing implementation of the present invention.
  • the apparatus 600 for transmitting signals, the transmission medium is for transmitting a signal between a CPU and a memory.
  • the CPU transmits a signal to the memory through the apparatus 200 for transmitting a signal according to an embodiment of the present invention, and the memory receives the signal transmitted by the CPU through the apparatus 600 for transmitting a signal according to the embodiment of the present invention.
  • the disclosed systems, devices, and methods may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, or an electrical, mechanical or other form of connection.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present invention.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention contributes in essence or to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Optical Communication System (AREA)
  • Information Transfer Systems (AREA)
  • Bus Control (AREA)

Abstract

本发明公开了一种传输信号的装置、传输链路和传输信号的方法。该传输信号的装置包括：转换器，用于接收AXI总线信号，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；传输模块，用于依次向接收端传输该多个簇中每一簇的信号。本发明实施例的传输信号的装置、传输链路和传输信号的方法，能够远距离传输总线信号。

Description

传输信号的装置、传输链路和传输信号的方法
本申请要求于2014年11月5日提交中国专利局、申请号为201410619187.3、发明名称为“传输信号的装置、传输链路和传输信号的方法”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及信息技术领域，并且更具体地，涉及传输信号的装置、传输链路和传输信号的方法。
背景技术
目前的计算机结构中，互连线采用电互连，即用印刷电路板(Printed Circuit Board，PCB)板上的铜线或者硅基芯片内部的硅互连线进行电信号的传输。例如，在CPU-内存互连中，CPU和内存之间通过铜线来传输符合联合电子管工程委员会(Joint Electron Tube Engineering Council，JEDEC)标准的并行信号，该信号只能控制在单板的距离(几十cm以内)内传输，无法进行远距离传输。
发明内容
本发明实施例提供了一种传输信号的装置、传输链路和传输信号的方法，能够远距离传输总线信号。
第一方面，提供了一种传输信号的装置，包括：
转换器，用于接收先进的可扩展接口AXI总线信号，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
传输模块，用于依次向接收端传输该多个簇中每一簇的信号。
结合第一方面，在第一种可能的实现方式中，该转换器具体用于将该AXI总线信号分为读地址、写地址和写数据三个簇。
结合第一方面，在第二种可能的实现方式中，该转换器具体用于将该AXI总线信号分为读地址和写地址写数据两个簇。
结合第一方面或第一方面的第一或二种可能的实现方式，在第三种可能的实现方式中，该多个簇中每一簇的信号中包括簇标识，该簇标识用于该接收端将该多个簇的信号组合为该AXI总线信号。
结合第一方面或第一方面的第一至三种可能的实现方式中的任一种可能的实现方式，在第四种可能的实现方式中，该传输模块用于采用流传输的方式依次向该接收端传输该多个簇中每一簇的信号。
结合第一方面或第一方面的第一至四种可能的实现方式中的任一种可能的实现方式，在第五种可能的实现方式中，该传输模块包括：
编码器，用于对该多个簇中每一簇的信号进行编码；
串行器，用于对该多个簇中每一簇的信号进行并串转换；
光发送器，用于对该多个簇中每一簇的信号进行电光转换，通过光传输介质传输到该接收端。
结合第一方面或第一方面的第一至五种可能的实现方式中的任一种可能的实现方式，在第六种可能的实现方式中，该转换器用于同时接收多个主端的AXI总线信号。
结合第一方面或第一方面的第一至六种可能的实现方式中的任一种可能的实现方式，在第七种可能的实现方式中，该装置还包括：
仲裁器，用于确定该多个簇中每一簇的传输顺序；
该传输模块具体用于按照该仲裁器确定的传输顺序依次向该接收端传输该多个簇中每一簇的信号。
第二方面，提供了一种传输信号的装置，包括：
传输模块，用于接收发送端依次传输的多个簇中每一簇的信号，其中， 该多个簇由该发送端将先进的可扩展接口AXI总线信号划分得到，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
转换器，用于将该多个簇的信号组合为该AXI总线信号。
结合第二方面，在第一种可能的实现方式中，该多个簇包括读地址、写地址和写数据三个簇。
结合第二方面，在第二种可能的实现方式中，该多个簇包括读地址和写地址写数据两个簇。
结合第二方面或第二方面的第一或二种可能的实现方式，在第三种可能的实现方式中，该多个簇中每一簇的信号中包括簇标识；
该转换器具体用于根据该簇标识将该多个簇的信号组合为该AXI总线信号。
结合第二方面或第二方面的第一至三种可能的实现方式中的任一种可能的实现方式，在第四种可能的实现方式中，该多个簇中每一簇的信号由该发送端进行编码、并串转换和电光转换，通过光传输介质传输；
该传输模块包括：
光接收器，用于接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换；
解串器，用于对该多个簇中每一簇的信号进行串并转换；
解码器，用于对该多个簇中每一簇的信号进行解码。
第三方面，提供了一种传输链路，包括：
主端转换器，用于接收先进的可扩展接口AXI总线信号，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
主端传输模块，用于依次通过传输介质向从端传输模块传输该多个簇中每一簇的信号；
传输介质，用于传输该多个簇中每一簇的信号；
从端传输模块，用于接收该多个簇中每一簇的信号；
从端转换器，用于将该多个簇的信号组合为该AXI总线信号。
结合第三方面，在第一种可能的实现方式中，该主端转换器具体用于将该AXI总线信号分为读地址、写地址和写数据三个簇。
结合第三方面，在第二种可能的实现方式中，该主端转换器具体用于将该AXI总线信号分为读地址和写地址写数据两个簇。
结合第三方面或第三方面的第一或二种可能的实现方式，在第三种可能的实现方式中，该多个簇中每一簇的信号中包括簇标识；
该从端转换器具体用于根据该簇标识将该多个簇的信号组合为该AXI总线信号。
结合第三方面或第三方面的第一至三种可能的实现方式中的任一种可能的实现方式，在第四种可能的实现方式中，该主端传输模块用于采用流传输的方式依次通过该传输介质向该从端传输模块传输该多个簇中每一簇的信号。
结合第三方面或第三方面的第一至四种可能的实现方式中的任一种可能的实现方式，在第五种可能的实现方式中，该传输介质为光传输介质；
该主端传输模块包括：
编码器，用于对该多个簇中每一簇的信号进行编码；
串行器，用于对该多个簇中每一簇的信号进行并串转换；
光发送器，用于对该多个簇中每一簇的信号进行电光转换，通过该光传输介质传输到该从端传输模块；
该从端传输模块包括：
光接收器，用于接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换；
解串器，用于对该多个簇中每一簇的信号进行串并转换；
解码器，用于对该多个簇中每一簇的信号进行解码。
结合第三方面或第三方面的第一至五种可能的实现方式中的任一种可能的实现方式，在第六种可能的实现方式中，该主端转换器用于同时接收多个主端的AXI总线信号。
结合第三方面或第三方面的第一至六种可能的实现方式中的任一种可能的实现方式，在第七种可能的实现方式中，该传输链路还包括：
仲裁器，用于确定该多个簇中每一簇的传输顺序；
该主端传输模块具体用于按照该仲裁器确定的传输顺序依次向该从端传输模块传输该多个簇中每一簇的信号。
第四方面，提供了一种传输信号的方法，包括：
接收先进的可扩展接口AXI总线信号；
将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
依次向接收端传输该多个簇中每一簇的信号。
结合第四方面，在第一种可能的实现方式中，将该AXI总线信号分为多个簇，包括：
将该AXI总线信号分为读地址、写地址和写数据三个簇。
结合第四方面，在第二种可能的实现方式中，将该AXI总线信号分为多个簇，包括：
将该AXI总线信号分为读地址和写地址写数据两个簇。
结合第四方面或第四方面的第一或二种可能的实现方式，在第三种可能的实现方式中，该多个簇中每一簇的信号中包括簇标识，该簇标识用于该接收端将该多个簇的信号组合为该AXI总线信号。
结合第四方面或第四方面的第一至三种可能的实现方式中的任一种可能的实现方式，在第四种可能的实现方式中，依次向接收端传输该多个簇中每一簇的信号，包括：
采用流传输的方式依次向该接收端传输该多个簇中每一簇的信号。
结合第四方面或第四方面的第一至四种可能的实现方式中的任一种可能的实现方式，在第五种可能的实现方式中，依次向接收端传输该多个簇中每一簇的信号，包括：
依次对该多个簇中每一簇的信号进行编码、并串转换和电光转换，通过光传输介质传输到该接收端。
结合第四方面或第四方面的第一至五种可能的实现方式中的任一种可能的实现方式，在第六种可能的实现方式中，接收先进的可扩展接口AXI总线信号，包括：
同时接收多个主端的AXI总线信号。
结合第四方面或第四方面的第一至六种可能的实现方式中的任一种可能的实现方式，在第七种可能的实现方式中，在依次向接收端传输该多个簇中每一簇的信号之前，该方法还包括：
确定该多个簇中每一簇的传输顺序；
依次向接收端传输该多个簇中每一簇的信号，包括：
按照确定的传输顺序依次向该接收端传输该多个簇中每一簇的信号。
第五方面，提供了一种传输信号的方法，包括：
接收发送端依次传输的多个簇中每一簇的信号，其中，该多个簇由该发送端将先进的可扩展接口AXI总线信号划分得到，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
将该多个簇的信号组合为该AXI总线信号。
结合第五方面，在第一种可能的实现方式中，该多个簇包括读地址、写地址和写数据三个簇。
结合第五方面，在第二种可能的实现方式中，该多个簇包括读地址和写地址写数据两个簇。
结合第五方面或第五方面的第一或二种可能的实现方式，在第三种可能的实现方式中，该多个簇中每一簇的信号中包括簇标识；
将该多个簇组合为该AXI总线信号，包括：
根据该簇标识将该多个簇的信号组合为该AXI总线信号。
结合第五方面或第五方面的第一至三种可能的实现方式中的任一种可能的实现方式，在第四种可能的实现方式中，该多个簇中每一簇的信号由该发送端进行编码、并串转换和电光转换，通过光传输介质传输；
接收发送端依次传输的多个簇中每一簇的信号，包括：
接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换、串并转换和解码。
第六方面，提供了一种计算机，包括：CPU和内存，以及连接该CPU和该内存的传输介质，其中，该CPU包括上述第一方面的传输信号的装置，该内存包括上述第二方面的传输信号的装置，该传输介质用于传输该CPU和该内存之间的信号。
基于上述技术方案，本发明实施例通过将AXI总线信号分为多个时序关系不相互依赖的簇，依次向接收端传输该多个簇中每一簇的信号，可以在远距离的传输介质中依次传输各个簇的信号，从而能够远距离传输总线信号。
附图说明
为了更清楚地说明本发明实施例的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例的应用场景的示意图。
图2是本发明一个实施例的传输信号的装置的示意性框图。
图3是本发明另一实施例的传输信号的装置的示意性框图。
图4是本发明又一实施例的传输信号的装置的示意性框图。
图5是本发明实施例的操作序列的示意图。
图6是本发明又一实施例的传输信号的装置的示意性框图。
图7是本发明又一实施例的传输信号的装置的示意性框图。
图8是本发明一个实施例的传输链路的示意性框图。
图9是本发明另一实施例的传输链路的示意性框图。
图10是本发明又一实施例的传输链路的示意性框图。
图11是本发明一个实施例的传输信号的方法的示意性流程图。
图12是本发明另一实施例的传输信号的方法的示意性流程图。
具体实施方式
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例是本发明的一部分实施例，而不是全部实施例。基于本发明中的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例，都应属于本发明保护的范围。
图1是本发明实施例的应用场景的示意图。图1中，主(master)端110和从(slave)端120通过传输链路130传输总线信号，例如先进的可扩展接口(Advanced eXtensible Interface，AXI)总线信号。主端110为处理器，例如CPU；从端120可以为内存或者外设。也就是说，AXI总线信号可以为内存读写信号，或者CPU与外设间的读写信号。应理解，本发明实施例不但可以用于一个主端和一个从端的场景，还可以用于多个主端和多个从端的场景。
图2示出了根据本发明实施例的传输信号的装置200的示意性框图。该装置200位于主端侧(例如图1中的主端110之后)，用于将主端的AXI总线信号传输给从端。如图2所示，该装置200包括：
转换器210，用于接收AXI总线信号，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
传输模块220，用于依次向接收端传输该多个簇中每一簇的信号。
转换器210可与主端连接，接收主端的AXI总线信号。可选地，在多个 主端的场景中，转换器210可同时接收多个主端的AXI总线信号。转换器210接收到主端的AXI总线信号后，将该AXI总线信号分为时序关系不相互依赖多个簇。
可选地，作为本发明的一个实施例，该转换器210具体用于将该AXI总线信号分为读地址、写地址和写数据三个簇。
在本实施例中，将主端到从端的AXI总线信号分为读地址、写地址和写数据三个簇。这三个簇之间时序关系不相互依赖。
可选地，多个簇中每一簇的信号中包括簇标识，该簇标识用于接收端将该多个簇的信号组合为该AXI总线信号。
例如，读地址簇中可以包括下列信号：
DATA_AR，簇标识；
ARID，读地址ID；
ARLEN，突发式读长度；
ARSIZE，突发式读大小；
ARBURST，突发式读类型；
ARCACHE，Cache类型；
ARPROT，保护类型；
ARVALID，读地址有效；
RREADY，读数据就绪；
ARADDR，读地址。
写地址簇中可以包括下列信号：
DATA_AW，簇标识；
AWID，写地址ID；
AWLEN，突发式写的长度；
AWSIZE，突发式写的大小；
AWBURST，突发式写的类型；
AWCACHE，Cache类型；
AWPROT，保护类型；
AWVALID，写地址有效
AWADDR，写地址。
写数据簇中可以包括下列信号：
DATA_WD，簇标识；
WSTRB，写阀门；
WLAST，写的最后一个数据；
WVALID，写有效；
BREADY，接受响应就绪；
WDATA，写的数据。
应理解，各个簇中也可以不包括簇标识，在这种情况下，发送端和接收端可以按照预定的顺序传输各个簇，从而接收端可以判断出各个簇。
上述三个簇为主端到从端的信号，另外，对于从端到主端的信号，可以只用一个簇，例如可以称为读数据簇。
例如，读数据簇中可以包括下列信号：
AWREADY，写地址准备好；
WREADY，写就绪；
BID，响应ID；
BRESP，写响应；
BVALID，写响应有效；
ARREADY，读地址就绪；
RID，读ID；
RRESP，读响应；
RLAST，读事务传送的最后一个数据；
RVALID，读数据有效；
RDATA，读数据。
上述每个簇可以为64位数据，不足64位的簇可以用0或者1补足，而如果出现超出64位的情况，可以视情况删除一些无用信号(如AWCACHE的高位)。
可选地，转换器210还可以对一些特殊的信号做特殊处理。例如，对于主端到从端的WVALID/WLAST/BREADY，这些信号是写数据相关的握手信号，可以省去。从端的转换器可以在当有写数据到达时，同时产生高电平的这三个握手信号。对于从端到主端的READY类信号，如AWREADY/WREADY/ARREADY，从端未回复相应信号之前，可强制将其置为高电平，从而转换器210可以从主端接收下一个读写信号，在多个主端的场景中，也可以同时接收多个主端的AXI总线信号。对于从端到主端的VALID类和RESP类信号，如BVALID/RVALID/BRESP/RRESP，当其连续出现几个周期的高电平时，将其改变为只有一个周期的高电平值。
可选地，作为本发明的另一个实施例，该转换器210具体用于将该AXI总线信号分为读地址和写地址写数据两个簇。
在本实施例中，将写地址信号和写数据信号分到一个簇，即写地址写数据簇。由于写地址信号和写数据信号具有时序上的先后顺序，因此可以时分复用同一个簇。读地址信号作为另一个簇。这两个簇之间时序关系不相互依赖。
可选地，多个簇中每一簇的信号中包括簇标识，该簇标识用于接收端将该多个簇的信号组合为该AXI总线信号。
例如，写地址写数据簇可以将前述例子中的写地址簇和写数据簇合并， 读地址簇可以与前述例子中的读地址簇相同。
与前述实施例类似，对于从端到主端的信号，也可以只用一个簇，例如前述的读数据簇。可选地，转换器210也可以对一些特殊的信号做特殊处理，这与前述实施例类似，为了简洁在此不再赘述。
转换器210将该AXI总线信号分为多个簇后，传输模块220依次向接收端传输该多个簇中每一簇的信号。
接收端位于从端侧(例如图1中的从端120之前)，为从端侧的传输信号的装置。
传输模块220可采用流传输的方式依次向该接收端传输该多个簇中每一簇的信号。也就是说，传输模块220按照簇的粒度，采用流传输的方式依次传输各个簇，例如对每一簇的信号进行编码和并串转换，再通过传输介质传输到接收端。传输介质可以为电传输介质或光传输介质，其中光传输介质可以为光纤或光波导等。
可选地，如图3所示，在本发明的一个实施例，该传输模块220包括：编码器221、串行器222和光发送器223。
编码器221用于对该多个簇中每一簇的信号进行编码。例如，编码器221可以采用64b/66b或者8b/10b的编解码方式。
串行器222用于对该多个簇中每一簇的信号进行并串转换。
光发送器223用于对该多个簇中每一簇的信号进行电光转换，通过光传输介质传输到该接收端。
应理解，传输模块220还可以接收从端过来的信号，例如前述读数据簇。在这种情况下，传输模块220还可以包括光接收器、解串器和解码器，光接收器和光发送器可以组成光收发器，解串器和串行器可以组成串行器/解串器，解码器和编码器可以组成编解码器。
本实施例采用光传输方式传输每一簇的信号，能够利用光传输的高传输速率的优势。
可选地，如图4所示，在本发明的一个实施例，该装置200还可以包括仲裁器230。
仲裁器230用于确定该多个簇中每一簇的传输顺序。
在这种情况下，该传输模块220具体用于按照该仲裁器230确定的传输顺序依次向该接收端传输该多个簇中每一簇的信号。
本发明实施例既可以用于一个主端的场景，也可以用于多个主端的场景。在只有一个主端时，因为同一时间只会有一个操作信号在传输，不需要仲裁器，或不需要仲裁器的仲裁作用；在有多个主端时，可以通过仲裁器230确定传输顺序。
例如，仲裁器230可将每个往从端方向传输的簇(写数据、写地址、读地址)的内容用寄存器序列存储起来，如图5所示。每个单元代表一次操作(一个簇)，每个操作都分配相应的计数器。如计数器可以为8位，前4位是AXI总线中QOS的内容，代表了该操作的优先级；后4位初始值为0，当每次操作结束后，计数器自动加1。仲裁器230根据计数器的大小，判断出哪个操作优先传输。如果两个计数器大小相当，则读操作优先(不会出现两个计数器大小相等的读操作)。当加入新的操作时，直接根据其计数器的值按照大小排序放到序列中，保持序列头的计数器的值一直为最大。
本发明实施例的传输信号的装置，通过将AXI总线信号分为多个时序关系不相互依赖的簇，依次向接收端传输该多个簇中每一簇的信号，可以在远距离的传输介质中依次传输各个簇的信号，从而能够远距离传输总线信号。
以上描述了主端侧的传输信号的装置，下面描述从端侧的传输信号的装置。
图6示出了根据本发明实施例的传输信号的装置600的示意性框图。该装置600位于从端侧(例如图1中的从端120之前)。如图2所示，该装置600包括：
传输模块610，用于接收发送端依次传输的多个簇中每一簇的信号，其中， 该多个簇由该发送端将AXI总线信号划分得到，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
转换器620，用于将该多个簇的信号组合为该AXI总线信号。
该发送端位于主端侧(例如图1中的主端110之后)，为主端侧的传输信号的装置，例如传输信号的装置200。
该发送端将AXI总线信号分为多个时序关系不相互依赖的簇，依次向该装置600传输该多个簇中每一簇的信号，传输模块610接收到该多个簇中每一簇的信号后，转换器620将该多个簇的信号组合为AXI总线信号。
可选地，作为本发明的一个实施例，该多个簇包括读地址、写地址和写数据三个簇。
可选地，作为本发明的另一个实施例，该多个簇包括读地址和写地址写数据两个簇。
可选地，该多个簇中每一簇的信号中包括簇标识；
该转换器620具体用于根据该簇标识将该多个簇的信号组合为该AXI总线信号。
转换器620根据簇标识识别不同的簇，再将各个簇重新组合为AXI总线信号传给从端。
可选地，作为本发明的一个实施例，该多个簇中每一簇的信号由该发送端进行编码、并串转换和电光转换，通过光传输介质传输。
在这种情况下，如图7所示，该传输模块610包括：
光接收器611，用于接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换；
解串器612，用于对该多个簇中每一簇的信号进行串并转换；
解码器613，用于对该多个簇中每一簇的信号进行解码。
应理解，传输模块610还可以向主端发送信号，例如前述读数据簇。在这种情况下，传输模块610还可以包括编码器、串行器和光发送器，光发送 器和光接收器可以组成光收发器，串行器和解串器可以组成串行器/解串器，编码器和解码器可以组成编解码器。
本发明实施例的传输信号的装置600可对应前述传输信号的装置200的实施例中的接收端，相关功能可参考前述实施例的相应描述，为了简洁，在此不再赘述。
本发明实施例的传输信号的装置，通过接收发送端依次传输的AXI总线信号的多个时序关系不相互依赖的簇中每一簇的信号，将该多个簇的信号组合为该AXI总线信号，可以在远距离的传输介质中传输各个簇的信号，从而能够远距离传输总线信号。
以上分别描述了主端侧和从端侧的传输信号的装置，下面描述本发明实施例的传输链路。
图8示出了根据本发明实施例的传输链路800的示意性框图。该传输链路800位于主端和从端之间(例如图1中的传输链路130)。如图8所示，该传输链路800包括：
主端转换器810，用于接收AXI总线信号，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
主端传输模块820，用于依次通过传输介质向从端传输模块传输该多个簇中每一簇的信号；
传输介质830，用于传输该多个簇中每一簇的信号；
从端传输模块840，用于接收该多个簇中每一簇的信号；
从端转换器850，用于将该多个簇的信号组合为该AXI总线信号。
可选地，作为本发明的一个实施例，该主端转换器810具体用于将该AXI总线信号分为读地址、写地址和写数据三个簇。
可选地，作为本发明的另一个实施例，该主端转换器810具体用于将该AXI总线信号分为读地址和写地址写数据两个簇。
可选地，该多个簇中每一簇的信号中包括簇标识；
该从端转换器850具体用于根据该簇标识将该多个簇的信号组合为该AXI总线信号。
可选地，该主端传输模块820用于采用流传输的方式依次通过该传输介质830向该从端传输模块840传输该多个簇中每一簇的信号。
可选地，如图9所示，在本发明一个实施例中，该传输介质830为光传输介质；
该主端传输模块820包括：
编码器821，用于对该多个簇中每一簇的信号进行编码；
串行器822，用于对该多个簇中每一簇的信号进行并串转换；
光发送器823，用于对该多个簇中每一簇的信号进行电光转换，通过该光传输介质传输到该从端传输模块840；
该从端传输模块840包括：
光接收器841，用于接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换；
解串器842，用于对该多个簇中每一簇的信号进行串并转换；
解码器843，用于对该多个簇中每一簇的信号进行解码。
应理解，主端传输模块820还可以接收从端过来的信号，从端传输模块840还可以向主端发送信号，例如前述读数据簇。在这种情况下，主端传输模块820还可以包括光接收器、解串器和解码器，从端传输模块840还可以包括编码器、串行器和光发送器，光发送器和光接收器可以组成光收发器，串行器和解串器可以组成串行器/解串器，编码器和解码器可以组成编解码器。
可选地，该主端转换器810用于同时接收多个主端的AXI总线信号。
可选地，如图10所示，在本发明一个实施例中，该传输链路800还包括：
仲裁器860，用于确定该多个簇中每一簇的传输顺序；
该主端传输模块820具体用于按照该仲裁器860确定的传输顺序依次向该从端传输模块840传输该多个簇中每一簇的信号。
本发明实施例的传输链路800可以包括前述本发明实施例的传输信号的装置200、传输信号的装置600以及传输介质，具体地，主端转换器810、主端传输模块820和仲裁器860可对应装置200中的转换器210、传输模块220和仲裁器230，从端传输模块840和从端转换器850可对应装置600中的传输模块610和转换器620，相关功能可参考前述各实施例的相应描述，为了简洁，在此不再赘述。
本发明实施例的传输链路，通过将AXI总线信号分为多个时序关系不相互依赖的簇，依次传输该多个簇中每一簇的信号，可以在远距离的传输介质中依次传输各个簇的信号，从而能够远距离传输总线信号。
以上分别描述了本发明实施例的传输信号的装置和传输链路，下面描述本发明实施例的传输信号的方法。
图11示出了根据本发明实施例的传输信号的方法1100的示意性流程图。该方法1100由发送端(例如主端侧的传输信号的装置)执行。如图11所示，该方法1100包括：
S1110，接收先进的可扩展接口AXI总线信号；
S1120，将该AXI总线信号分为多个簇，其中，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
S1130，依次向接收端传输该多个簇中每一簇的信号。
本发明实施例的传输信号的方法，通过将AXI总线信号分为多个时序关系不相互依赖的簇，依次向接收端传输该多个簇中每一簇的信号，可以在远距离的传输介质中依次传输各个簇的信号，从而能够远距离传输总线信号。
在本发明一个实施例中，可选地，将该AXI总线信号分为多个簇，包括：
将该AXI总线信号分为读地址、写地址和写数据三个簇。
在本发明一个实施例中，可选地，将该AXI总线信号分为多个簇，包括：
将该AXI总线信号分为读地址和写地址写数据两个簇。
在本发明一个实施例中，可选地，该多个簇中每一簇的信号中包括簇标 识，该簇标识用于该接收端将该多个簇的信号组合为该AXI总线信号。
在本发明一个实施例中，可选地，依次向接收端传输该多个簇中每一簇的信号，包括：
采用流传输的方式依次向该接收端传输该多个簇中每一簇的信号。
在本发明一个实施例中，可选地，依次向接收端传输该多个簇中每一簇的信号，包括：
依次对该多个簇中每一簇的信号进行编码、并串转换和电光转换，通过光传输介质传输到该接收端。
在本发明一个实施例中，可选地，接收先进的可扩展接口AXI总线信号，包括：
同时接收多个主端的AXI总线信号。
在本发明一个实施例中，可选地，在依次向接收端传输该多个簇中每一簇的信号之前，该方法1100还包括：
确定该多个簇中每一簇的传输顺序；
依次向接收端传输该多个簇中每一簇的信号，包括：
按照确定的传输顺序依次向该接收端传输该多个簇中每一簇的信号。
本发明实施例的传输信号的方法1100的相应流程可分别由前述本发明实施例的传输信号的装置200执行，具体描述可参考前述实施例，为了简洁，在此不再赘述。
图12示出了根据本发明实施例的传输信号的方法1200的示意性流程图。该方法1200由接收端(例如从端侧的传输信号的装置)执行。如图12所示，该方法1200包括：
S1210，接收发送端依次传输的多个簇中每一簇的信号，其中，该多个簇由该发送端将先进的可扩展接口AXI总线信号划分得到，该多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
S1220，将该多个簇的信号组合为该AXI总线信号。
本发明实施例的传输信号的方法，通过接收发送端依次传输的AXI总线信号的多个时序关系不相互依赖的簇中每一簇的信号，将该多个簇的信号组合为该AXI总线信号，可以在远距离的传输介质中传输各个簇的信号，从而能够远距离传输总线信号。
在本发明一个实施例中，可选地，该多个簇包括读地址、写地址和写数据三个簇。
在本发明一个实施例中，可选地，该多个簇包括读地址和写地址写数据两个簇。
在本发明一个实施例中，可选地，该多个簇中每一簇的信号中包括簇标识；
将该多个簇组合为该AXI总线信号，包括：
根据该簇标识将该多个簇的信号组合为该AXI总线信号。
在本发明一个实施例中，可选地，该多个簇中每一簇的信号由该发送端进行编码、并串转换和电光转换，通过光传输介质传输；
接收发送端依次传输的多个簇中每一簇的信号，包括：
接收该多个簇中每一簇的信号，对该多个簇中每一簇的信号进行光电转换、串并转换和解码。
本发明实施例的传输信号的方法1200的相应流程可分别由前述本发明实施例的传输信号的装置600执行，具体描述可参考前述实施例，为了简洁，在此不再赘述。
本发明实施例还提供了一种计算机，包括：CPU和内存，以及连接CPU和内存的传输介质，其中，该CPU包括前述本发明实施例的传输信号的装置200，该内存包括前述本发明实施例的传输信号的装置600，上述传输介质，用于传输CPU和内存之间的信号。该CPU通过本发明实施例的传输信号的装置200向该内存发送信号，该内存通过本发明实施例的传输信号的装置600接收该CPU发送的信号。
应理解，本发明中的具体的例子只是为了帮助本领域技术人员更好地理解本发明实施例，而非限制本发明实施例的范围。
还应理解，在本发明的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本发明实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本文中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、计算机软件或者二者的结合来实现，为了清楚地说明硬件和软件的可互换性，在上述说明中已经按照功能一般性地描述了各示例的组成及步骤。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本发明的范围。
所属领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的方法的具体流程，可以参考前述装置实施例中的相应描述，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口、装置或单元的间接耦合或通信连接，也可以是电的，机械的或其它的形式连接。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本发明实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以是两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分，或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本发明的具体实施方式，但本发明的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到各种等效的修改或替换，这些修改或替换都应涵盖在本发明的保护范围之内。因此，本发明的保护范围应以权利要求的保护范围为准。

Claims (35)

  1. 一种传输信号的装置，其特征在于，包括：
    转换器，用于接收先进的可扩展接口AXI总线信号，将所述AXI总线信号分为多个簇，其中，所述多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
    传输模块，用于依次向接收端传输所述多个簇中每一簇的信号。
  2. 根据权利要求1所述的装置，其特征在于，所述转换器具体用于将所述AXI总线信号分为读地址、写地址和写数据三个簇。
  3. 根据权利要求1所述的装置，其特征在于，所述转换器具体用于将所述AXI总线信号分为读地址和写地址写数据两个簇。
  4. 根据权利要求1至3中任一项所述的装置，其特征在于，所述多个簇中每一簇的信号中包括簇标识，所述簇标识用于所述接收端将所述多个簇的信号组合为所述AXI总线信号。
  5. 根据权利要求1至4中任一项所述的装置，其特征在于，所述传输模块用于采用流传输的方式依次向所述接收端传输所述多个簇中每一簇的信号。
  6. 根据权利要求1至5中任一项所述的装置，其特征在于，所述传输模块包括：
    编码器，用于对所述多个簇中每一簇的信号进行编码；
    串行器，用于对所述多个簇中每一簇的信号进行并串转换；
    光发送器，用于对所述多个簇中每一簇的信号进行电光转换，通过光传输介质传输到所述接收端。
  7. 根据权利要求1至6中任一项所述的装置，其特征在于，所述转换器用于同时接收多个主端的AXI总线信号。
  8. 根据权利要求1至7中任一项所述的装置，其特征在于，所述装置还包括：
    仲裁器，用于确定所述多个簇中每一簇的传输顺序；
    所述传输模块具体用于按照所述仲裁器确定的传输顺序依次向所述接收端传输所述多个簇中每一簇的信号。
  9. 一种传输信号的装置，其特征在于，包括：
    传输模块，用于接收发送端依次传输的多个簇中每一簇的信号，其中，所述多个簇由所述发送端将先进的可扩展接口AXI总线信号划分得到，所述多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
    转换器，用于将所述多个簇的信号组合为所述AXI总线信号。
  10. 根据权利要求9所述的装置，其特征在于，所述多个簇包括读地址、写地址和写数据三个簇。
  11. 根据权利要求9所述的装置，其特征在于，所述多个簇包括读地址和写地址写数据两个簇。
  12. 根据权利要求9至11中任一项所述的装置，其特征在于，所述多个簇中每一簇的信号中包括簇标识；
    所述转换器具体用于根据所述簇标识将所述多个簇的信号组合为所述AXI总线信号。
  13. 根据权利要求9至12中任一项所述的装置，其特征在于，所述多个簇中每一簇的信号由所述发送端进行编码、并串转换和电光转换，通过光传输介质传输；
    所述传输模块包括：
    光接收器，用于接收所述多个簇中每一簇的信号，对所述多个簇中每一簇的信号进行光电转换；
    解串器，用于对所述多个簇中每一簇的信号进行串并转换；
    解码器，用于对所述多个簇中每一簇的信号进行解码。
  14. 一种传输链路，其特征在于，包括：
    主端转换器，用于接收先进的可扩展接口AXI总线信号，将所述AXI总线信号分为多个簇，其中，所述多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
    主端传输模块，用于依次通过传输介质向从端传输模块传输所述多个簇中每一簇的信号；
    传输介质，用于传输所述多个簇中每一簇的信号；
    从端传输模块，用于接收所述多个簇中每一簇的信号；
    从端转换器，用于将所述多个簇的信号组合为所述AXI总线信号。
  15. 根据权利要求14所述的传输链路，其特征在于，所述主端转换器具体用于将所述AXI总线信号分为读地址、写地址和写数据三个簇。
  16. 根据权利要求14所述的传输链路，其特征在于，所述主端转换器具体用于将所述AXI总线信号分为读地址和写地址写数据两个簇。
  17. 根据权利要求14至16中任一项所述的传输链路，其特征在于，所述多个簇中每一簇的信号中包括簇标识；
    所述从端转换器具体用于根据所述簇标识将所述多个簇的信号组合为所述AXI总线信号。
  18. 根据权利要求14至17中任一项所述的传输链路，其特征在于，所述主端传输模块用于采用流传输的方式依次通过所述传输介质向所述从端传输模块传输所述多个簇中每一簇的信号。
  19. 根据权利要求14至18中任一项所述的传输链路，其特征在于，所述传输介质为光传输介质；
    所述主端传输模块包括：
    编码器，用于对所述多个簇中每一簇的信号进行编码；
    串行器，用于对所述多个簇中每一簇的信号进行并串转换；
    光发送器，用于对所述多个簇中每一簇的信号进行电光转换，通过所述光传输介质传输到所述从端传输模块；
    所述从端传输模块包括：
    光接收器，用于接收所述多个簇中每一簇的信号，对所述多个簇中每一簇的信号进行光电转换；
    解串器，用于对所述多个簇中每一簇的信号进行串并转换；
    解码器，用于对所述多个簇中每一簇的信号进行解码。
  20. 根据权利要求14至19中任一项所述的传输链路，其特征在于，所述主端转换器用于同时接收多个主端的AXI总线信号。
  21. 根据权利要求14至20中任一项所述的传输链路，其特征在于，所述 传输链路还包括：
    仲裁器，用于确定所述多个簇中每一簇的传输顺序；
    所述主端传输模块具体用于按照所述仲裁器确定的传输顺序依次向所述从端传输模块传输所述多个簇中每一簇的信号。
  22. 一种传输信号的方法，其特征在于，包括：
    接收先进的可扩展接口AXI总线信号；
    将所述AXI总线信号分为多个簇，其中，所述多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
    依次向接收端传输所述多个簇中每一簇的信号。
  23. 根据权利要求22所述的方法，其特征在于，所述将所述AXI总线信号分为多个簇，包括：
    将所述AXI总线信号分为读地址、写地址和写数据三个簇。
  24. 根据权利要求22所述的方法，其特征在于，所述将所述AXI总线信号分为多个簇，包括：
    将所述AXI总线信号分为读地址和写地址写数据两个簇。
  25. 根据权利要求22至24中任一项所述的方法，其特征在于，所述多个簇中每一簇的信号中包括簇标识，所述簇标识用于所述接收端将所述多个簇的信号组合为所述AXI总线信号。
  26. 根据权利要求22至25中任一项所述的方法，其特征在于，所述依次向接收端传输所述多个簇中每一簇的信号，包括：
    采用流传输的方式依次向所述接收端传输所述多个簇中每一簇的信号。
  27. 根据权利要求22至26中任一项所述的方法，其特征在于，所述依次向接收端传输所述多个簇中每一簇的信号，包括：
    依次对所述多个簇中每一簇的信号进行编码、并串转换和电光转换，通过光传输介质传输到所述接收端。
  28. 根据权利要求22至27中任一项所述的方法，其特征在于，所述接收先进的可扩展接口AXI总线信号，包括：
    同时接收多个主端的AXI总线信号。
  29. 根据权利要求22至28中任一项所述的方法，其特征在于，在所述依次向接收端传输所述多个簇中每一簇的信号之前，所述方法还包括：
    确定所述多个簇中每一簇的传输顺序；
    所述依次向接收端传输所述多个簇中每一簇的信号，包括：
    按照确定的传输顺序依次向所述接收端传输所述多个簇中每一簇的信号。
  30. 一种传输信号的方法，其特征在于，包括：
    接收发送端依次传输的多个簇中每一簇的信号，其中，所述多个簇由所述发送端将先进的可扩展接口AXI总线信号划分得到，所述多个簇中每一簇的信号与其他簇的信号的时序关系不相互依赖；
    将所述多个簇的信号组合为所述AXI总线信号。
  31. 根据权利要求30所述的方法，其特征在于，所述多个簇包括读地址、写地址和写数据三个簇。
  32. 根据权利要求30所述的方法，其特征在于，所述多个簇包括读地址和写地址写数据两个簇。
  33. 根据权利要求30至32中任一项所述的方法，其特征在于，所述多个簇中每一簇的信号中包括簇标识；
    所述将所述多个簇组合为所述AXI总线信号，包括：
    根据所述簇标识将所述多个簇的信号组合为所述AXI总线信号。
  34. 根据权利要求30至33中任一项所述的方法，其特征在于，所述多个簇中每一簇的信号由所述发送端进行编码、并串转换和电光转换，通过光传输介质传输；
    所述接收发送端依次传输的多个簇中每一簇的信号，包括：
    接收所述多个簇中每一簇的信号，对所述多个簇中每一簇的信号进行光电转换、串并转换和解码。
  35. 一种计算机，其特征在于，包括：CPU和内存，以及连接所述CPU和所述内存的传输介质，其中，所述CPU包括根据权利要求1至8中任一项所述的装置，所述内存包括根据权利要求9至13中任一项所述的装置，所述传输介质，用于传输所述CPU和所述内存之间的信号。
PCT/CN2015/081674 2014-11-05 2015-06-17 传输信号的装置、传输链路和传输信号的方法 WO2016070630A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201410619187.3 2014-11-05
CN201410619187.3A CN105634661A (zh) 2014-11-05 2014-11-05 传输信号的装置、传输链路和传输信号的方法

Publications (1)

Publication Number Publication Date
WO2016070630A1 true WO2016070630A1 (zh) 2016-05-12

Family

ID=55908512

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2015/081674 WO2016070630A1 (zh) 2014-11-05 2015-06-17 传输信号的装置、传输链路和传输信号的方法

Country Status (2)

Country Link
CN (1) CN105634661A (zh)
WO (1) WO2016070630A1 (zh)

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101324869A (zh) * 2008-07-03 2008-12-17 北京中星微电子有限公司 一种基于axi总线的多路复用器
WO2011061172A1 (en) * 2009-11-18 2011-05-26 St-Ericsson Sa Method and apparatus of master-to-master transfer of data on a chip and system on chip
CN102103564A (zh) * 2009-12-22 2011-06-22 中兴通讯股份有限公司 用于实现总线连接的方法及系统
CN102508808A (zh) * 2011-11-14 2012-06-20 北京北大众志微系统科技有限责任公司 一种实现主芯片与扩展芯片通信的系统及方法
CN102591829A (zh) * 2010-12-06 2012-07-18 索尼公司 互连装置和用于其的控制方法
CN102855195A (zh) * 2011-06-30 2013-01-02 重庆重邮信科通信技术有限公司 第二代低功耗双倍速率存储控制器及访问命令处理方法
CN103034610A (zh) * 2011-10-09 2013-04-10 中兴通讯股份有限公司 在分体模块间进行axi总线信号发送接收的方法及装置

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103488596B (zh) * 2013-09-03 2016-03-16 中国电子科技集团公司第四十一研究所 一种链路自适应的数据传输装置及数据传输方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101324869A (zh) * 2008-07-03 2008-12-17 北京中星微电子有限公司 一种基于axi总线的多路复用器
WO2011061172A1 (en) * 2009-11-18 2011-05-26 St-Ericsson Sa Method and apparatus of master-to-master transfer of data on a chip and system on chip
CN102103564A (zh) * 2009-12-22 2011-06-22 中兴通讯股份有限公司 用于实现总线连接的方法及系统
CN102591829A (zh) * 2010-12-06 2012-07-18 索尼公司 互连装置和用于其的控制方法
CN102855195A (zh) * 2011-06-30 2013-01-02 重庆重邮信科通信技术有限公司 第二代低功耗双倍速率存储控制器及访问命令处理方法
CN103034610A (zh) * 2011-10-09 2013-04-10 中兴通讯股份有限公司 在分体模块间进行axi总线信号发送接收的方法及装置
CN102508808A (zh) * 2011-11-14 2012-06-20 北京北大众志微系统科技有限责任公司 一种实现主芯片与扩展芯片通信的系统及方法

Also Published As

Publication number Publication date
CN105634661A (zh) 2016-06-01

Similar Documents

Publication Publication Date Title
US7155554B2 (en) Methods and apparatuses for generating a single request for block transactions over a communication fabric
US20190079677A1 (en) Host-based and client-based command scheduling in large bandwidth memory systems
KR102280718B1 (ko) 인트라-칩과 인터-칩 호핑 버스들을 통한 시스템-온-칩들 내의 그리고 시스템-온-칩들 간의 정보 전달을 위한 방법 및 장치
CN105740195B (zh) Or链式总线的增强数据总线反转编码的方法和装置
US9239808B2 (en) Serial interface for FPGA prototyping
US20110225337A1 (en) Transaction performance monitoring in a processor bus bridge
US20160098371A1 (en) Serial peripheral interface daisy chain communication with an in-frame response
CN109634900B (zh) 一种基于axi协议的多层次低延迟互连结构
US8595401B2 (en) Input output bridging
US20060095635A1 (en) Methods and apparatuses for decoupling a request from one or more solicited responses
CN114741341B (zh) 一种实现Crossbar结构仲裁的方法、系统及存储介质
US8799550B2 (en) System and method for increased efficiency PCI express transaction
US20190251048A1 (en) Accelerating distributed stream processing
US20200192842A1 (en) Memory request chaining on bus
US10574392B2 (en) System. methods and devices for transmitting and/or receiving data using an inter communication link
US9112736B2 (en) Data transfer apparatus, data transfer method, and inter-chip communication system
KR101736460B1 (ko) 크로스-다이 인터페이스 스누프 또는 글로벌 관측 메시지 오더링
US8630181B2 (en) Communication system and corresponding integrated circuit and method
US20080181242A1 (en) Communications gateway between two entities
WO2016070630A1 (zh) 传输信号的装置、传输链路和传输信号的方法
US11636061B2 (en) On-demand packetization for a chip-to-chip interface
KR20160147373A (ko) 광 신호를 이용한 sata 호스트 버스 어댑터 및 sata 저장소 연결 방법
CN104598407A (zh) 片上系统及控制方法
US9268725B2 (en) Data transferring apparatus and data transferring method
US20220405223A1 (en) Method and system for data transactions on a communications interface

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 15856761

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 15856761

Country of ref document: EP

Kind code of ref document: A1