Abstract: A method and system for providing an eviction protocol within a non-uniform memory access (NUMA) computer system are disclosed. A NUMA computer system includes at least two nodes coupled to an interconnect. Each of the two nodes includes a local system memory. In response to a request for evicting an entry from a sparse directory, an non-intervention writeback request is sent to a node having the modified cache line when the entry is associated with a modified cache line. After the data from the modified cache line has been written back to a local system memory of the node, the entry can then be evicted from the sparse directory. If the entry is associated with a shared line, an invalidation request is sent to all nodes that the directory entry indicates may hold a copy of the line. Once all invalidations have been acknowledged, the entry can be evicted from the sparse directory.

Abstract: A method for avoiding livelocks due to stale exclusive/modified directory entries within a non-uniform memory access (NUMA) computer system is disclosed. A NUMA computer system includes at least two nodes coupled to an interconnect. Each of the two nodes includes a local system memory. In response to an attempt by a processor of a first node to read a cache line at substantially the same time as a processor of a second node attempts to access the same cache line, wherein the cache line has been silently cast out from a cache memory within the second node even though a coherency directory within the node still indicates the cache line is held exclusively in the second node, the processor of the second node is allowed to access the cache line only if the second node is an owning node of the cache line. The processor of the first node is then allowed to access the cache line.

Abstract: A method for avoiding data loss due to cancelled transactions within a non-uniform memory access (NUMA) data processing system is disclosed. A NUMA data processing system includes a node interconnect to which at least a first node and a second node are coupled. The first and the second nodes each includes a local interconnect, a system memory coupled to the local interconnect, and a node controller interposed between the local interconnect and a node interconnect. The node controller detects certain situations which, due to the nature of a NUMA data processing system, can lead to data loss. These situations share the common feature that a node controller ends up with the only copy of a modified cache line and the original transaction that requested the modified cache line may not be issued again with the same tag or may not be issued again at all.

Abstract: A non-uniform memory access (NUMA) computer system includes at least two nodes coupled by a node interconnect, where at least one of the nodes includes a processor for servicing interrupts. The nodes are partitioned into external interrupt domains so that an external interrupt is always presented to a processor within the external interrupt domain in which the interrupt occurs. Although each external interrupt domain typically includes only a single node, interrupt channeling or interrupt funneling may be implemented to route external interrupts across node boundaries for presentation to a processor. Once presented to a processor, interrupt handling software may then execute on any processor to service the external interrupt. Servicing external interrupts is expedited by reducing the size of the interrupt handler polling chain as compared to prior art methods.

Abstract: A non-uniform memory access (NUMA) computer system includes first and second processing nodes that are each coupled to a node interconnect. The first processing node includes a system memory and first and second processors that each have a respective one of first and second cache hierarchies, which are coupled for communication by a local interconnect. The second processing node includes at least a system memory and a third processor having a third cache hierarchy. The first cache hierarchy and the third cache hierarchy are permitted to concurrently store an unmodified copy of a particular cache line in a Recent coherency state from which the copy of the particular cache line can be sourced by shared intervention.

Abstract: A data processing system is disclosed which includes a first processor having an m-byte data width, an n-byte data bus, where n is less than m, and a second processor electrically coupled to the bus which performs bus transactions utilizing n-byte packets of data. An adaptor is electrically coupled between the first processor and the bus which converts n-byte packets of data input from the bus to m-byte packets of data, and converts m-byte packets of data input from the first processor to n-byte packets of data, thereby enabling the first processor to transmit data to and receive data from the bus utilizing m-byte packets of data. In a second aspect of the present invention, a method and system are provided for arbitrating between two bus masters having disparate bus acquisition protocols. In response to a second bus master asserting a bus request when a first bus master controls the bus, control of the bus is removed from the first bus master.

Abstract: A non-uniform memory access (NUMA) data processing system includes a node interconnect to which at least a first processing node and a second processing node are coupled. The first and the second processing nodes each include a local interconnect, a processor coupled to the local interconnect, a system memory coupled to the local interconnect, and a node controller interposed between the local interconnect and the node interconnect. In order to reduce communication latency, the node controller of the first processing node speculatively transmits request transactions received from the local interconnect of the first processing node to the second processing node via the node interconnect. In one embodiment, the node controller of the first processing node subsequently transmits a status signal to the node controller of the second processing node in order to indicate how the request transaction should be processed at the second processing node.

Abstract: A computer system includes a node interconnect to which at least a first processing node and a second processing node are coupled. The first and the second processing nodes each include a local interconnect, a processor coupled to the local interconnect, a system memory coupled to the local interconnect, and a node controller interposed between the local interconnect and the node interconnect. In order to reduce communication latency, the node controller of the first processing node speculatively transmits request transactions received from the local interconnect of the first processing node to the second processing node via the node interconnect, where each such request transaction specifies an associated datum. The node controller of the second processing node handles each speculatively transmitted request transaction received in response to a directory state of its associated datum.

Abstract: A non-uniform memory access (NUMA) computer system includes an interconnect to which multiple processing nodes (including first, second, and third processing nodes) are coupled. Each of the first, second, and third processing nodes includes at least one processor and a local system memory. The NUMA computer system further includes a transaction buffer, coupled to the interconnect, that stores communication transactions transmitted on the interconnect that are both initiated by and targeted at a processing node other than the third processing node. In response to a determination that a particular communication transaction originally targeting another processing node should be processed by the third processing node, buffer control logic coupled to the transaction buffer causes the particular communication transaction to be retrieved from the transaction buffer and processed by the third processing node.

Abstract: In the system of the present invention, a time critical program operating in a window system environment is implemented. The application program containing time critical procedures is divided functionally into two or more processes. The first process contains all of the CPU time slice sensitive or time critical procedures. This process operates independently of the window system interface and communicates directly with the operating system. The second process implements all procedures which require the user input and output through the window system but not including time critical procedures. This process communicates with and operates through the window system interface. The processes exchange data and synchronize execution through the interprocess communication mechanisms such as shared memory such that the two or more processes operate and appear as a single process to the user while insulating the first process from suspension due to window system operations and blocking procedures.

Abstract: A method and apparatus accurately synchronizes a communications equipment (101) to a precise 1 PPS signal (229) when the remote GPS equipment (112) and the communications equipment (101) are separated by a cable (110) of unknown length. Accordingly, integrity and precision of the 1 PPS timing signal is maintained when synchronizing the communications system.

Abstract: A data processing system is disclosed which includes a first processor having an m-byte data width, an n-byte data bus, where n is less than m, and a second processor electrically coupled to the bus which performs bus transactions utilizing n-byte packets of data. An adaptor is electrically coupled between the first processor and the bus which converts n-byte packets of data input from the bus to m-byte packets of data, and converts m-byte packets of data input from the first processor to n-byte packets of data, thereby enabling the first processor to transmit data to and receive data from the bus utilizing m-byte packets of data. In a second aspect of the present invention, a method and system are provided for arbitrating between two bus masters having disparate bus acquisition protocols. In response to a second bus master asserting a bus request when a first bus master controls the bus, control of the bus is removed from the first bus master.

Abstract: A system and method of synchronizing data transfers between two processors having different bus transactions by providing a buffer for storing the data and a control logic for dividing a concurrent address and data bus transactions into an address bus transaction followed by a data bus transaction. During a read operation, the requesting device is forced to wait for data availability before entering the data bus transaction. During a write operation, the data bus transaction is delayed by using a storage mechanism that effectively separates the address transaction from the data transaction. The present invention also provides direct memory access fly-by operations between an input/output device and a memory device. These operations are accomplished by isolating a secondary bus from the system bus and allowing the destination device to capture the requested data as soon as it is available on the system bus.

Abstract: In the system of the present invention, a specialized form of read-ahead, write-behind buffering is provided which enables the host processing system to provide timely responses to device requests that are emulated by the host processor. Each input/output device request is identified by an address to which the device is purportedly mapped to. This address is translated to an address containing a status word for that particular device being emulated. Each status word contains a byte of information either to be sent to the microprocessor as a response during an I/O read operation request by the microprocessor, or to receive data written by the microprocessor in response to an I/O write operation request, and a plurality of status bits which identify the state of the data contained in the I/O status word.