Abstract:
A method of communications at an encapsulating bridge includes receiving a packet having an unencapsulated-DA (destination address) and an associated encapsulation identifier. The unencapsulated-DA and the associated encapsulation identifier are used to determine a TxPort-unencapsulated network (unencapsulated network side transmit port) or an encapsulated-DA for the packet. This method reduces latency of processing by reducing lookups, thereby also increasing transmission bandwidth of the communications network. The invention also facilitates embodiments with reduced memory and processing requirements, as compared to conventional implementations. This method is particularly useful for MAC-in-MAC encapsulation.
Abstract:
A device includes multiple registers, multiple hardware-implemented Privilege Level Indicators (PLIs), and one or more circuits. The registers are to store respective values. The PLIs are to specify privilege levels for accessing the respective registers. The one or more circuits are to perform a secure memory dump operation including (i) checking the PLIs of one or more of the registers and (ii) outputting the values of the registers that are permitted for outputting according to the respective PLIs.
Abstract:
A system includes a communication bus, a controller device, and a target device. The controller device and the target device may transition between different communication protocols in association with transferring data over the communication bus. The target device may receive a transaction command including a slave address. Based on the slave address, the target device may determine a communication protocol associated with transferring data in association with the transaction command. A first communication protocol may include a message protocol, and the message protocol may be associated with an I2C communication protocol or an I3C communication protocol. The second communication protocol may include a bus protocol, and the bus protocol may be associated with the I2C communication protocol.
Abstract:
A relay device is provided that may identify a quantity of empty data byte locations in a data buffer of the relay device. The relay device may receive an indicator associated with transmitting data packets. The relay device may pause or enable a lossless flow of data between the relay device, a host device, and a peer device based on the quantity of empty data byte locations, the indicator, or both. The relay device may include a first data interface coupled with a peer device, a second data interface coupled with a host device, a data buffer configured to store data packets received from the host device, and a state machine that enables a lossless transmission of data between the host device and peer device. The state machine may transmit a pause frame to the host device based on a data buffer utilization reaching a data storage capacity.
Abstract:
A network adapter includes a port and one or more circuits. The port is to send packets to a network in accordance with a Remote Direct Memory Access over Converged Ethernet (RoCE) protocol. The one or more circuits are to decide whether a packet is permitted to undergo Adaptive Routing (AR) in being routed through the network, to mark the packet with an indication of whether the packet is permitted to undergo AR, and to send the marked packet to the network via the port.
Abstract:
A relay device is provided that may identify a quantity of empty data byte locations in a data buffer of the relay device. The relay device may receive an indicator associated with transmitting data packets. The relay device may pause or enable a lossless flow of data between the relay device, a host device, and a peer device based on the quantity of empty data byte locations, the indicator, or both. The relay device may include a first data interface coupled with a peer device, a second data interface coupled with a host device, a data buffer configured to store data packets received from the host device, and a state machine that enables a lossless transmission of data between the host device and peer device. The state machine may transmit a pause frame to the host device based on a data buffer utilization reaching a data storage capacity.
Abstract:
An apparatus includes a processor and split-read control circuitry (SRCC). The processor is to issue a set of one or more split-read requests for loading one or more data values to one or more respective local registers of the processor. The SRCC is to receive the set of one or more split-read requests, to read the one or more data values on behalf of the processor, and to write the data values into the one or more respective local registers. The processor and the SRCC are to coordinate a status of the split-read requests via a split-read-status indication.
Abstract:
A method for communication includes storing packets received from a sending node over a communication link in a receive buffer of a receiving node. The receive buffer includes one or more blocks having a first block size. A first credit count, corresponding to a number of available blocks in the receive buffer, is derived. The first credit count is converted to a second credit count so as to represent an available space in the receive buffer in accordance with a second block size, which is different from the first block size. A transmission rate of the sending node is controlled by publishing the second credit count to the sending node over the communication link.
Abstract:
An apparatus includes multiple data sources and arbitration circuitry. The data sources are configured to send to a common destination data items and respective arbitration requests, such that the data items are sent to the destination regardless of receiving any indication that the data items were served to the destination in response to the respective arbitration requests. The arbitration circuitry is configured to receive and buffer the data items, to perform arbitration on the buffered data items responsively to the arbitration requests, and to serve the buffered data items to the destination in accordance with the arbitration.
Abstract:
A communication network includes multiple nodes, which are arranged in groups such that the nodes in each group are interconnected in a bipartite topology and the groups are interconnected in a mesh topology. The nodes are configured to convey traffic between source hosts and respective destination hosts by routing packets among the nodes on paths that do not traverse any intermediate hosts other than the source and destination hosts.