Abstract: A system and device for expanding accessible memory of a processor is provided. An interposer is coupled to the processor and a memory module. The interposer is coupled to a first connection and a second connection. The interposer includes a memory controller circuit. The memory controller circuit receives signals from the processor, using the first connection, and transmits the received signals to the memory module, using the second connection. The interposer expands memory access without an unnecessary second processor.

Abstract: A system and device for expanding accessible memory of a processor is provided. An interposer is coupled to the processor and a memory module. The interposer is coupled to a first connection and a second connection. The interposer includes a memory controller circuit. The memory controller circuit receives signals from the processor, using the first connection, and transmits the received signals to the memory module, using the second connection. The interposer expands memory access without an unnecessary second processor.

Abstract: A system and method for providing efficient communication between a processor and a device. An interposer is provided to send signals from the processor to the device. The interposer includes a printed circuit board, a first interconnection port communicating with the processor, and a second interconnection port communicating with the device. A retimer/redriver circuit is coupled to the first interconnection port and the second interconnection port, and the retimer/redriver circuit routes signals from the first interconnection port to the second interconnection port.

Abstract: A system and method for generating a control bifurcation signal in accordance with the Open Compute Project (OCP) Specification. An OCP device is provided that has a bifurcation function with an input to activate a bus bifurcation function. An input/output control circuit having an output coupled to a bifurcation control line coupled to the OCP device is provided. The input/output control circuit is operable to provide a bifurcation control signal to the OCP device over the bifurcation control line during an auxiliary power phase transition period of powering-on the OCP device.

Abstract: A system for sharing input/output using universal sleds includes a first universal sled that includes a first switch and a first universal node, and a second universal sled that includes a second switch and a second universal node, where the first universal sled and second universal sled have interchangeable physical dimensions. The midplane board includes a management processor and a midplane switch. The system further includes an input/output sled and a bus that connects the first universal sled, the second universal sled, the midplane board, and the input/output sled.

Abstract: Embodiments generally relate to a universal debug design which involves integrating a debug controller and a debug card with display together into a single debug design. Debug codes, such as power-on self-test (POST) codes and other error codes, are generated by various subsystems of a server-related system. The codes are transmitted to a controller, which stores the codes in memory. In some embodiments, a multiplexer outputs one debug code from the multitude of received codes, based on a user or event selecting which desired debug code should be displayed. In some embodiments, a decoder converts and sends the LED display signals to a debug card, which displays the debug code on a 7-segment LED display.

Abstract: A device, such as a baseboard management controller, monitors a physical-layer device in a server and at least one network connector/cable connected to the physical-layer device, determines a status of the physical-layer device or a status of the at least one network connector/cable indicates at least one of a warning or a failure, and transmits an alert corresponding to the at least one of the warning or the failure to a rack management controller.

Abstract: A component carrier with a housing and a converter board disposed within the housing. The converter board including a U.2 connector, an M.2 connector configured to receive an M.2 solid state drive having a cache memory, and a capacitor. The capacitor provides backup power for a power loss protection system allowing flush cache storage. The housing configured to receive one or more M.2 solid state drives coupled with the converter board.

Abstract: A method for automatic clock configurations is performed by a system having a host and a peripheral device. The host indicates on a first general-purpose input/output (GPIO) of a peripheral interface connecting the host and the peripheral device, whether the host supports a first clock configuration. The peripheral device receives from the first GPIO whether the host supports the first clock configuration. The peripheral device selects, in response to the host supporting the first clock configuration, use of a local clock of the peripheral device. The peripheral device selects, in response to the host not supporting the first clock configuration, use of a common clock of the host.

Abstract: A controller in a server system can determine whether to share a network connection of the server system. In response to determining to share the network connection, the controller can disable a dedicated network connection between the controller and a network interface controller (NIC) in the server system, enable a first shared network connection between the controller and a computing module in the server system, and enable a second shared network connection between the computing module and the NIC. In response to determining not to share the network connection, the controller can enable the dedicated network connection between the controller and the NIC.

Abstract: Embodiments generally relate to thermal management in a multi-node computing device. The present technology discloses techniques that can receive multiple control signals from multiple computing nodes, each of the control signals being associated with a fan duty request, which is a request for a fan duty needed to keep a related computing node operating within a predetermined temperature range. The logic controller can rank the received control signals and select a control signal that requests a highest fan duty; lastly, the logic controller can cause multiple cooling fans to operate at the selected highest fan duty.

Abstract: A component carrier with a housing and a converter board disposed within the housing. The converter board including a U.2 connector, an M.2 connector configured to receive an M.2 solid state drive having a cache memory, and a capacitor. The capacitor provides backup power for a power loss protection system allowing flush cache storage. The housing configured to receive one or more M.2 solid state drives coupled with the converter board.

Abstract: A method for automatic clock configurations is performed by a system having a host and a peripheral device. The host indicates on a first general-purpose input/output (GPIO) of a peripheral interface connecting the host and the peripheral device, whether the host supports a first clock configuration. The peripheral device receives from the first GPIO whether the host supports the first clock configuration. The peripheral device selects, in response to the host supporting the first clock configuration, use of a local clock of the peripheral device. The peripheral device selects, in response to the host not supporting the first clock configuration, use of a common clock of the host.

Abstract: A device, such as a baseboard management controller, monitors a physical-layer device in a server and at least one network connector/cable connected to the physical-layer device, determines a status of the physical-layer device or a status of the at least one network connector/cable indicates at least one of a warning or a failure, and transmits an alert corresponding to the at least one of the warning or the failure to a rack management controller.

Abstract: A system for sharing input/output using universal sleds includes a first universal sled that includes a first switch and a first universal node, and a second universal sled that includes a second switch and a second universal node, where the first universal sled and second universal sled have interchangeable physical dimensions. The midplane board includes a management processor and a midplane switch. The system further includes an input/output sled and a bus that connects the first universal sled, the second universal sled, the midplane board, and the input/output sled.

Abstract: Embodiments generally relate to power loss protection in a computing system. The present technology discloses techniques that enable a graceful removal of power using a microcontroller controller in communication with a backup power supply. By utilizing a relative inexpensive microcontroller, the present technology can achieve data protection for a large number of storage devices at a low cost.

Abstract: Embodiments generally relate to a universal debug design which involves integrating a debug controller and a debug card with display together into a single debug design. Debug codes, such as power-on self-test (POST) codes and other error codes, are generated by various subsystems of a server-related system. The codes are transmitted to a controller, which stores the codes in memory. In some embodiments, a multiplexer outputs one debug code from the multitude of received codes, based on a user or event selecting which desired debug code should be displayed. In some embodiments, a decoder converts and sends the LED display signals to a debug card, which displays the debug code on a 7-segment LED display.

Abstract: A controller in a server system can determine whether to share a network connection of the server system. In response to determining to share the network connection, the controller can disable a dedicated network connection between the controller and a network interface controller (NIC) in the server system, enable a first shared network connection between the controller and a computing module in the server system, and enable a second shared network connection between the computing module and the NIC. In response to determining not to share the network connection, the controller can enable the dedicated network connection between the controller and the NIC.

Abstract: Embodiments generally relate to thermal management in a multi-node computing device. The present technology discloses techniques that can receive multiple control signals from multiple computing nodes, each of the control signals being associated with a fan duty request, which is a request for a fan duty needed to keep a related computing node operating within a predetermined temperature range. The logic controller can rank the received control signals and select a control signal that requests a highest fan duty; lastly, the logic controller can cause multiple cooling fans to operate at the selected highest fan duty.

Abstract: A server cluster including a network switch and multiple server nodes is provided. The network switch is connected to an external network. Each server node performs an operation system and respectively includes a network port, a network chip and a south bridge chip. The network port is connected to the network switch via a cable. The network chip outputs a power-off signal according to a received power-off packet after the network switch is started. The south bridge chip outputs a shutdown signal to shut down the server node according to the power-off signal when the server node is turned on and the operation system is working normally.