Abstract: A fault tolerant computing system is provided comprising two or more processing sets that operate in synchronism with one another. The two processing sets are joined by a bridge, and there is a communications link for each processing set for transmitting data from the processing set to the bridge. Data transmissions are initiated in synchronism with one another from the respective processing sets to the bridge but are then subject to variable delay over the communications link. Accordingly, a buffer is included in the bridge for storing the data transmissions received from the processing sets for long enough to compensate for the variable delay. The data transmissions can then be fed out from the buffer to a comparator that verifies that the data transmissions received from the two or more processing sets properly match each other. Likewise, a buffer is included in each processing set for storing the data transmissions received from the bridge for long enough to compensate for the variable delay.

Abstract: A computing system comprises two or more processing sets, for example for fault tolerant operation. The multiple processing sets have a connection to at least one device, typically many devices. The ownership of each device is allocated to one of the two or more processing sets. When an interrupt is generated within a device, this is transmitted from the device to the processing set to which ownership of the device has been allocated, but not to the remaining processing sets. In addition, a command for a device may be generated by a processing set. However, receipt of this command by the device is disabled if the processing set that generated the command has not been allocated ownership of the device.

Abstract: A computer system comprising at least two processing sets. Each processing set includes main memory. A bridge connects the processing sets. At least a first processing set further including a dirty memory having dirty indicators for indicating dirtied blocks of the main memory of the first processing set. The bridge includes a direct memory access controller that is operable to copy blocks of the first processing set indicated in the dirty memory to the main memory of another processing set. The processors do not, therefore, need to carry out the copying, whereby the processor overhead associated therewith can be avoided, increasing the efficiency of memory reintegration. The direct memory access controller can be arranged to search the dirty memory for dirty indicators indicative of dirtied blocks. Alternatively, the dirty memory can include control logic operable to search the dirty memory for dirty indicators indicative of dirtied blocks.

Abstract: A fault tolerant computing system is provided comprising two or more processing sets that operate in synchronism with one another. The two processing sets are joined by a bridge, and there is a communications link for each processing set for transmitting data from the processing set to the bridge. Data transmissions are initiated in synchronism with one another from the respective processing sets to the bridge but are then subject to variable delay over the communications link. Accordingly, a buffer is included in the bridge for storing the data transmissions received from the processing sets for long enough to compensate for the variable delay. The data transmissions can then be fed out from the buffer to a comparator that verifies that the data transmissions received from the two or more processing sets properly match each other. Likewise, a buffer is included in each processing set for storing the data transmissions received from the bridge for long enough to compensate for the variable delay.

Abstract: A computing system comprises two or more processing sets, for example for fault tolerant operation. The multiple processing sets have a connection to at least one device, typically many devices. The ownership of each device is allocated to one of the two or more processing sets. When an interrupt is generated within a device, this is transmitted from the device to the processing set to which ownership of the device has been allocated, but not to the remaining processing sets. In addition, a command for a device may be generated by a processing set. However, receipt of this command by the device is disabled if the processing set that generated the command has not been allocated ownership of the device.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. It also comprises a bridge control mechanism configured to be operable, in an operational mode to permit access by at least one of the first and second processing sets to bridge resources and to the device bus and, in an error mode, to prevent access by the processing sets to the device bus and to permit restricted access to at least one of the processing sets to at least predetermined bridge resources. By providing restricted access to selected parameters held in the bridge during an error mode, the bridge can act as a secure repository for information which can be used by the processing sets to investigate the error and hopefully to recover therefrom, while preventing I/O devices connected to device bus from being corrupted by a faulty processing set. Storage in the bridge provides for buffering data pending resolution of the error.

Abstract: A computer system comprising at least two processing sets. Each processing set includes main memory. A bridge connects the processing sets. At least a first processing set further including a dirty memory having dirty indicators for indicating dirtied blocks of the main memory of the first processing set. The bridge includes a direct memory access controller that is operable to copy blocks of the first processing set indicated in the dirty memory to the main memory of another processing set. The processors do not, therefore, need to carry out the copying, whereby the processor overhead associated therewith can be avoided, increasing the efficiency of memory reintegration. The direct memory access controller can be arranged to search the dirty memory for dirty indicators indicative of dirtied blocks. Alternatively, the dirty memory can include control logic operable to search the dirty memory for dirty indicators indicative of dirtied blocks.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. A bridge control mechanism is operable to permit direct memory access to memory of the processing sets by a device on the device bus, to arbitrate between the first and the second processing sets for access to the bridge in a first, split, mode, and to monitor lockstep operation of the first and second processing sets in a second, combined, mode. The dirty RAM mechanism defines a dirty indicator (e.g., a bit) for each of a plurality of regions of processing set memory, a dirty indicator being set to a predetermined value when the region of memory has been written to by a DMA access.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set, and a device bus. A bridge control mechanism is configured to provide geographic addressing for devices on the device bus and to be responsive to a request from a device on the device bus for direct access to a resource of a processing set to verify that an address supplied by the device falls within a correct geographic range. A different geographic address range can allocated to each of a plurality of device slots on the device bus. A different geographic address range can also be allocated to the processor set resources (e.g., processor set memory). An address decoding mechanism maintain geographic address mappings, and verifies geographic addresses for direct memory access. The geographic address mappings can be configured in random access memory of the bridge. A slot response register is associated with each slot on the device bus.

Abstract: A bridge for a multi-processor system provides interfaces to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. A bridge control mechanism arbitrates between the first and the second processing sets for access to each others I/O bus and to the device bus in a first, split, mode, and monitors lockstep operation of the first and second processing sets in a second, combined, mode. On detecting a lockstep error in the combined mode, the bridge transfers to an error mode. The bridge control mechanism buffers write accesses in a posted write buffer in the error mode pending resolution of the error.

Abstract: A bridge for a computer system comprising at least a first processing set and a second processing set each connected to the bridge via an I/O bus. A resource control mechanism in the bridge comprises: an interface for exchanging signals with one or more resource slots of a device bus that is capable of being connected to the bridge, each of the resource slots being capable of communicating with a system resource; and a register associated with each system resource, the register having switchable indicia that indicate an operating state of the associated system resource, the control mechanism being operable in use to direct signals to and/or from respective system resources of the computer system.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. The bridge also includes a memory subsystem and a bridge control mechanism. The bridge control mechanism is operable to monitor operation of the first and second processing sets in a combined, lockstep, operating mode and to be responsive to detection of a lockstep error to cause the bridge to be operable in an error mode in which write accesses initiated by the processor sets are buffered in a bridge buffer pending resolution of the error mode. A respective buffer region is provided for each processing set. In an initial error mode, any complete device write accesses initiated by the processing sets are stored in a posted write buffer. Where data is in transit through the bridge on entry to the error mode, the data is diverted to one or more disconnect registers.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. A bridge control mechanism is operable to compare address and data phases of I/O accesses by the first and second processing sets. A direct memory access mechanism is operable to initiate a direct memory access operation to read from a corresponding location in each processor set into a respective dissimilar data register associated with each processing set. The bridge control mechanism is operable during the direct memory access operation to disregard differences in the data phase for the dissimilar data write access. As a result it is possible to transfer dissimilar data from the processors into the bridge in a combined (lockstep comparison) mode.

Abstract: A bridge for a multi-processor system includes bus interfaces for connection to an I/O bus of a first processing set, an I/O bus of a second processing set and a device bus. A bridge control mechanism is configured to compare address and data phases of I/O accesses by the first and second processing sets. At least one dissimilar data register is provided for each processing set. The bridge control mechanism is operable in response to an address phase of a dissimilar data register write access to disregard any differences in the data phase for the dissimilar data write access. Non-deterministic data (for example relating to a real time clock) can be output from the processing sets in a combined (lockstep comparison) mode. A read destination address supplied in common by the first and second processing sets for a dissimilar data read access can cause data read from a determined one of the dissimilar data registers to be supplied the first and second processing sets.