Abstract: Embodiments herein provide for avoiding address collisions in a memory device. In one embodiment, a memory controller includes a command scheduler operable to process a read-modify-write I/O command to a location in memory, to detect another I/O command to the same memory location while the read-modify-write I/O command is accessing the memory location, and to stall the other I/O command until the read-modify-write I/O command is complete while allowing a third I/O command to access the memory.

Abstract: Embodiments herein provide for avoiding ID collisions in a memory device. In one embodiment, a memory device includes slave logic operable to receive I/O commands from a plurality of master components and a memory controller operable to process the I/O commands from the master components to operate on data in the memory. Each I/O command comprises an ID assigned by its originating master component. The slave logic is further operable to determine the ID of a first I/O command from a first of the master components, to receive a second I/O command from a second of the master components having a same ID as the first I/O command while the first I/O command is being processed by the memory controller, and to stall the second I/O command until the first I/O command is complete while allowing other I/O commands with other IDs to access the memory.

Abstract: Embodiments herein provide for avoiding address collisions in a memory device. In one embodiment, a memory controller includes a command scheduler operable to process a read-modify-write I/O command to a location in memory, to detect another I/O command to the same memory location while the read-modify-write I/O command is accessing the memory location, and to stall the other I/O command until the read-modify-write I/O command is complete while allowing a third I/O command to access the memory.

Abstract: Disclosed is a system and method for monitoring PCIe packets between clock domains. An interrupt is set to a root complex or external hardware based on the detection of malformed, and illegal, packets.

Abstract: Disclosed is a system and method for monitoring PCIe packets between clock domains. An interrupt is set to a root complex or external hardware based on the detection of malformed, and illegal, packets.

Abstract: Methods and structure for accounting are provided for enhancing communications via a PCIE bridge. The bridge comprises a host interface that manages communications with a host device, and a PCIE interface that provides Memory Read Requests (MRds) to a PCIE device and receives Memory Read Completions (MRCs) from the PCIE device. The bridge also comprises a control unit that inserts tag information into the MRds. The control unit detects a reset of the host interface and revises the tag information inserted into the MRds responsive to detecting the reset. Additionally, the control unit analyzes tag information of received MRCs to determine whether it is the revised tag information or is old tag information, returns completion data from MRCs having the revised tag information to the host device, and discards completion data from received MRCs having the old tag information.

Abstract: Methods and structure for accounting are provided for enhancing communications via a PCIE bridge. The bridge comprises a host interface that manages communications with a host device, and a PCIE interface that provides Memory Read Requests (MRds) to a PCIE device and receives Memory Read Completions (MRCs) from the PCIE device. The bridge also comprises a control unit that inserts tag information into the MRds. The control unit detects a reset of the host interface and revises the tag information inserted into the MRds responsive to detecting the reset. Additionally, the control unit analyzes tag information of received MRCs to determine whether it is the revised tag information or is old tag information, returns completion data from MRCs having the revised tag information to the host device, and discards completion data from received MRCs having the old tag information.

Abstract: Methods and apparatus to provide a high throughput pipelined data path are described. In one embodiment, an apparatus may include three stages to process inbound data packets, e.g., to align one or more bits of data. Other embodiments are also described.

Abstract: A packet alignment system for pre-processing/aligning incoming packets may comprise one or more registers for receiving control signals and data signals. An aligner may cyclically shift said data signals to form a plurality of shifted data words. A plurality of pipe registers may collect and generate an adjusted control signal for each one of the plurality of shifted data words. A filtering logic may identify one of the plurality of shifted data words as a desired aligned data word. The filter logic may also be configured for registering header data, payload data and ECRC data contained in the desired aligned data word in a header register, a payload register and an ECRC register, respectively. An output interface may generate an outgoing signal and provide data from at least one of the header register, the payload register and the ECRC register.

Abstract: A packet alignment system for pre-processing/aligning incoming packets may comprise one or more registers for receiving control signals and data signals. An aligner may cyclically shift said data signals to form a plurality of shifted data words. A plurality of pipe registers may collect and generate an adjusted control signal for each one of the plurality of shifted data words. A filtering logic may identify one of the plurality of shifted data words as a desired aligned data word. The filter logic may also be configured for registering header data, payload data and ECRC data contained in the desired aligned data word in a header register, a payload register and an ECRC register, respectively. An output interface may generate an outgoing signal and provide data from at least one of the header register, the payload register and the ECRC register.

Abstract: Methods and apparatus to provide a high throughput pipelined data path are described. In one embodiment, an apparatus may include three stages to process inbound data packets, e.g., to align one or more bits of data. Other embodiments are also described.

Abstract: An arbitration elimination scheme for a bus. In a preferred embodiment, a programmable counter determines when a SCSI bus idle condition is reached and when a portion of an arbitration window for the bus has passed without participants. If there are no participants for arbitration, the SCSI initiator eliminates arbitration by asserting SEL and issuing initiator/target IDS. If any other device attempts to arbitrate at this time, the device sees SEL asserted and does not attempt to participate in arbitration.

Abstract: A silent mirroring protocol is provided, which eliminates the arbitration/selection times associated with all nexuses after the first nexus. During the initial SCSI bus negotiation, the initiator determines the transfer mode capability of all targets. The initiator establishes a group identification. Participants of the group recognize the group and look for an individual identification within the group. The initiator performs arbitration/selection with attention to the leader of the group. The initiator uses a message out phase with a vendor command to select a participant for a data block transfer. Each participant snoops the bus and recognizes when it is the target. If the initiator has more data to mirror, the process is repeated. When the last data block is transferred, the initiator sends a message out to the last participant, which is interpreted by the target leader as a command to release the bus. Each participant reselects the nexus initiator and returns a status.

Abstract: An innovative circuit is disclosed that enhances performance on a SCSI bus by pipelining nexuses in order to associate all nexus attributes on a per nexus basis. For example, a pipeline of nexuses is created so as to associate all of the nexus attributes from different connections involved. A plurality of load stages is provided whereby each load stage can latch all nexus attributes received at that stage. The latched nexus attributes can be loaded and stored at that stage or shifted to the next stage. As a result of the loading and shifting operations, a pipeline of nexuses is created that associates all of the nexus attributes received from the different connections on a per nexus basis. Therefore, all types of data traffic can be processed concurrently on a SCSI bus, which enhances data throughput and bus performance.

Abstract: An interface system capable of providing pre-emptive arbitration among multiple agents comprises an interface including at least a first agent and a second agent which share the interface for transferring data, the second agent having priority over the first agent for access to the interface. A pre-emptive arbiter provides arbitration between the first agent and the second agent when at least one of a first transfer request signal is asserted by the first agent for requesting access to the interface by the first agent and a second transfer request signal is asserted by the second agent for requesting access to the interface by the second agent. The pre-emptive arbiter is capable of synthesizing a transfer completion signal on the interface for preempting access of the first agent to the interface so that access may be granted to the second agent.

Abstract: A method and apparatus for traversing a queue of commands through part or all of the queue by selecting only the commands that need to be reissued. Commands to be reissued are labeled or designated as valid. The method may be practiced by setting a next valid address pointer in all queue entries. Queue traversal may be forward, backward, or bi-directional.

Abstract: A method and apparatus for generating a delay in the timing of a bus or other logic circuit such that changes may be made to timing parameters without undue hardware design changes is disclosed. A counter is used to count a number of clock cycles to time the delay. The number of clock cycles is pre-loaded into the counter from a memory. This eliminates the need for costly hardware design changes when timing parameters change, since all that must be changed is the number of clock cycles to be counted, which can be modified by replacing or reprogramming the memory.

Abstract: An arbitration elimination scheme for a bus. In a preferred embodiment, a programmable counter determines when a SCSI bus idle condition is reached and when a portion of an arbitration window for the bus has passed without participants. If there are no participants for arbitration, the SCSI initiator eliminates arbitration by asserting SEL and issuing initiator/target IDS. If any other device attempts to arbitrate at this time, the device sees SEL asserted and does not attempt to participate in arbitration.

Abstract: A method and apparatus for traversing a queue of commands through part or all of the queue by selecting only the commands that need to be reissued. Commands to be reissued are labeled or designated as valid. The method may be practiced by setting a next valid address pointer in all queue entries. Queue traversal may be forward, backward, or bi-directional.

Abstract: An interface system capable of providing pre-emptive arbitration among multiple agents comprises an interface including at least a first agent and a second agent which share the interface for transferring data, the second agent having priority over the first agent for access to the interface. A pre-emptive arbiter provides arbitration between the first agent and the second agent when at least one of a first transfer request signal is asserted by the first agent for requesting access to the interface by the first agent and a second transfer request signal is asserted by the second agent for requesting access to the interface by the second agent. The pre-emptive arbiter is capable of synthesizing a transfer completion signal on the interface for preempting access of the first agent to the interface so that access may be granted to the second agent.