Abstract: A system management module (SMM) for a host server system includes a system management processor (SMP) connected to a system management local bus. The system management local bus connects to the system PCI bus through a system management central (SMC). The SMC includes the main arbitration unit for the PCI bus and also includes the arbiter for the system management local bus. The SMM includes a video controller and/or keyboard and mouse controller connected to the system management local bus to support remote consoling of the SMM. The SMC includes logic to monitor PCI cycles and to issue error signals in the event of a system error. The SMC also isolates failed components by masking request, grant and interrupt lines for the failed device. Further, if a spare component is provided, the SMC permits dynamic switching to the spare.

Abstract: A direct media independent interface (DMII) connection for a network device including a data link circuit, a connector, a clock circuit and a crossover connection. The data link circuit includes a reconciliation circuit that transmits and receives signals according to the MII standard. The clock circuit asserts at least one MII clock signal on the crossover connection to synchronize data transfer. The crossover connection crosses MII transmit signals with MII receive signals. A grounding circuit is optionally provided to ground one or more of the MII signals that are not required for the DMII connection. The connector may be a standard MII connector, or may be implemented as a minimum or reduced profile connector for carrying only the desired MII signals. The crossover connection is performed internally within the DMII port, or externally by a crossover cable. The cable is a standard MII cable, or is implemented as a minimum or reduced profile cable.

Abstract: A multiport polling system for a network switch including a plurality of network ports, each including receive and transmit buffers. Each port includes port status logic for providing status signals indicative of whether a corresponding port has received data from a network device and whether a corresponding port has available space to receive data to transmit to a network device. The network switch further includes a switch manager for controlling data flow between the ports. The switch manager includes polling logic for periodically polling the port status logic of each port for receiving the status signals, and a memory for storing values indicative of the status signals for each port. In this manner, all of the ports are simultaneously polled in a singe query and the receive and transmit status of each port is maintained in the memory.

Abstract: A hot spare boot circuit that automatically switches from a non-operational CPU to an operational CPU for powering up the computer system. In the multiprocessor computer system, a first CPU is designated to perform power on operations. If the first CPU fails, which is determined when a dead man counter in the hot spare boot circuit times out, the hot spare circuit ensures that the first CPU is in a disabled state. Next, the hot spare boot circuit identifies an operational second CPU, reinitializing certain ID information as necessary such that the second CPU can properly perform power on operations. The hot spare boot then awakens the second CPU, using a startup interprocessor interrupt in one embodiment, or simply negating the hard reset of the second CPU in a second embodiment. The second CPU then proceeds to perform the power on functions.

Abstract: A bidirectional input/output buffer is disclosed, where the receiver includes complementary bus keeper transistors. The keeper transistors are of opposite conductivity types, and have their gates coupled to the output of a receiver inverter. The keeper transistors thus reinforce the driven data state at the input of the receiver, in CMOS latch fashion, and hold the prior data state thereon after the driving output driver is in tristate. The keeper transistors have significantly weaker drive characteristics than the other receiver transistors, and than typical output drivers, so that the keeper transistors can be easily overdriven with the next data state, if different. In addition, the source/drain resistance of the keeper transistors is also preferably quite high, so that the power dissipation on switching is relatively low. These characteristics are readily achievable by providing relatively long channel lengths for the keeper transistors, relative to other transistors in the circuit.

Abstract: A hot spare boot circuit that automatically switches from a non-operational CPU to an operational CPU for powering up the computer system. In the multiprocessor computer system, a first CPU is designated to perform power on operations. If the first CPU fails, which is determined when a dead man counter in the hot spare boot circuit times out, the hot spare circuit ensures that the first CPU is in a disabled state. Next, the hot spare boot circuit identifies an operational second CPU, reinitializing certain ID information as necessary such that the second CPU can properly perform power on operations. The hot spare boot then awakens the second CPU, using a startup interprocessor interrupt in one embodiment, or simply negating the hard reset of the second CPU in a second embodiment. The second CPU then proceeds to perform the power on functions.