摘要:
A distributed system structure for a large-way, symmetric multiprocessor system using a bus-based cache-coherence protocol is provided. The distributed system structure contains an address switch, multiple memory subsystems, and multiple master devices, either processors, I/O agents, or coherent memory adapters, organized into a set of nodes supported by a node controller. The node controller receives transactions from a master device, communicates with a master device as another master device or as a slave device, and queues transactions received from a master device. Since the achievement of coherency is distributed in time and space, the node controller helps to maintain cache coherency. In addition, a bus arbiter in the node controller parks a data bus towards a memory subsystem. The node controller does not use data buffer reservations. The data bus grant line to the memory controller is overloaded to use it as a back-pressure, get-off-the-bus signal as well as a normal data bus grant line. The fairness of the bus is thereby increased by creating a mechanism for getting a “parked” device off the data bus without the use of another dedicated signal between physical components. To ensure that the node controller may stream data to the memory subsystem, the bus is not reparked towards the memory subsystem until a configurable number of cycles after the data bus has been granted to the node controller.
摘要:
A novel crossbar switching matrix that improves the transmission of variable length broadcast packets by greatly reducing transmission latency time. Unicast traffic is halted in the middle of packet transmission operations and the broadcast packet is transmitted. Once the broadcast packet has finished transmission, unicast packet transmission resumes without any loss of data. A unicast buffer is used to store the unicast packet while the broadcast packet is being transmitted. A broadcast buffer is used to buffer the broadcast packet as it egresses from the switch matrix. In this fashion, the broadcast information is given high priority and passes quickly through the switch without the large delays associated with the prior art switch matrixes. The crossbar switch matrix of the present invention is applicable to any switching matrix adapted to switch variable length data units.
摘要:
The interface circuit serves for connecting two apparatus by way of a bidirectional bus which comprises a data lead for transmitting data and a cycle lead for transmitting a cycle signal. The interface circuit consists of a circuit arrangement provided at each apparatus, which comprises a separating means for separating the data signal on the data lead and the cylce signal on the cycle lead in each case into a transmitting and a receiving branch, and which furthermore comprises in each case for the data lead and the cylce lead a bus driver having a differential transmitter and receiver. The data signals and cylce signals between the apparatus are transmitted via differential leads.
摘要:
A computer system includes a host processor, a first PCI bus, a second PCI bus and a PCI-to-PCI bridge. The first PCI bus is coupled with the host processor. The PCI-to-PCI bridge interconnects the first and second PCI buses. The PCI-to-PCI bridge includes a first portion and a second portion. The first portion includes a first configuration register and the second portion includes a second configuration register. A method is also taught.
摘要:
One embodiment of the present invention provides an apparatus that selectively encodes bus grant lines to reduce I/O pin requirements. This apparatus includes a semiconductor chip with bus arbitration circuit. A number of grant lines emanate from the bus arbitration circuit. An encoder circuit encodes the grant lines into a smaller number of encoded grant lines. A selector circuit selects outputs from between the encoded grant lines and a first subset of grant lines. These outputs pass through output pins off of the semiconductor chip. During a first mode of operation, the first subset of grant lines is driven through the plurality of output pins. During a second mode of operation, the encoded grant lines are driven through the output pins. A variation on the above embodiment includes a number of bus request lines, which are divided into a first subset and a second subset. The first subset of request lines feeds through a number of input pins into the bus arbitration circuit. During the first mode of operation, the second subset of request lines feeds from off of the semiconductor chip through a number of I/O pins and bi-directional buffers into the bus arbitration circuit. During the second mode of operation, the second subset of grant lines feeds from the bus arbitration circuit, through the bi-directional buffers and I/O pins and off of the semiconductor chip.
摘要:
One embodiment of the present invention provides a method for selectively encoding bus grant lines to reduce I/O pin requirements. The method includes receiving a number of grant lines emanating from a bus arbitration circuit and encoding the grant lines into a smaller number of encoded grant lines. The method selects outputs from between the encoded grant lines and a first subset of the grant lines. These outputs are driven off of a semiconductor chip through a number of output pins. During a first mode of operation, the first subset of grant lines is selected to be driven through the output pins. During a second mode of operation, the encoded grant lines are selected to driven through the output pins. In a variation on the above embodiment, the method additionally receives a number of bus request lines. These request lines are divided into a first subset and a second subset. The first subset of request lines is received through a number of input pins from off of the semiconductor chip. During the first mode of operation, the second subset of request lines is received from off of the semiconductor chip through a number of I/O pins and bi-directional buffers into the bus arbitration circuit. This first mode of operation allows more request lines to be used in conjunction with the plurality of encoded grant lines. During the second mode of operation, the second subset of bus grant lines feeds from the bus arbitration circuit through the bi-directional buffers and I/O pins and off of the semiconductor chip. This second mode of operation allows more pins to be used for grant lines when grant lines are not encoded.
摘要:
A memory controller for a dynamic random access memory which pre-charges active banks in a particular chip select when an eight quadword access is made to another bank within that same chip select. When the memory controller detects an eight quadword access which is a page hit or page miss within the same chip select, the memory controller will look for any other active banks on that chip select. If there is another active bank other than the bank being accessed by the eight quadword access, the memory controller will attempt to transmit a pre-charge operation to that bank in the clock cycle immediately following the acceptance of the eight quadword access.
摘要:
An apparatus for reusing arbitration signals to frame data transfers between hub agents is disclosed. The apparatus includes an arbitration signal output circuit to output a first request signal to indicate a data transfer. The apparatus further includes a data path input/output unit to output data to a data path during a period indicated by the arbitration signal.
摘要:
A bus bridge is defined to provide an interface between two AHB buses. These busses normally have separate requirements but both must provide high performance. The first is for transfer of data from CPU to memory and peripherals. The second is to support the transfer of a large amount of data by a single peripheral to local memory or other local peripherals. The AHB-to-HTB bus bridge provides a means for the interfacing these two separate AHB buses allowing communication between them and securing data integrity. The bus bridge of this invention is defined to be an AHB memory bus slave but a high performance data transfer bus master.
摘要:
A dual-edge FIFO interface having a host FIFO interface operative to receive data from a host module on a single edge of a host clock, and determine situations when valid read data is present in a read data FIFO or when the read data FIFO is full, a target FIFO interface operative to receive read data from a target core module, transfer data out, and determine when the read data FIFO is full, and a register block in communication with the host FIFO and the target FIFO, wherein the dual-edge FIFO interface is operative to interconnect internal modules at a core logic level, a block level, or a chip level.