Abstract: A bus interface is partitionable into at least two slices. Each slice interfaces a respective subset of data from a computer device to a system bus. Each slice also receives a corresponding subset of control information and a complete set of address information from the computer device. Moreover, each slice may be implemented on a single integrated circuit chip, which thus handles both data and control functions.

Abstract: A bus interface is partitionable into at least two slices. Each slice interfaces a respective subset of data from a computer device to a system bus. Each slice also receives a corresponding subset of control information and a complete set of address information from the computer device. Moreover, each slice may be implemented on a single integrated circuit chip, which thus handles both data and control functions.

Abstract: The present invention is directed to a method of managing a cache upon detection of an address TAG parity error, The cache includes a plurality of entries for storage of data, with each entry having a corresponding address TAG entry. The method includes the steps of performing a TAG parity check for each access to the cache, and upon detection of a parity error in an address TAG, disabling allocation of TAG entries for storage of new address TAGs. A signal indicating the TAG parity error is transmitted to an error correction mechanism.

Abstract: A data processing system includes a plurality of nodes connected to a shared data path, one of said plurality of nodes being a commander node to initiate a transaction on said shared data path, and one of said plurality of nodes being a responder node. The system also includes means for providing, by said responder node, a response to said commander node indicating unavailability of said responder node and for providing an acknowledgement of said transaction over said shared data path; and means, directly responsive to said response indicating that said responder node is unavailable to respond to said transaction, for retrying said transaction. In this manner, a retry mechanism can be implemented on a bus which does not directly support a retry signal.

Abstract: A read buffering system employs FIFOs to hold sequential read data for a number of data streams being fetched by a computer. When the system sees a read command from the CPU, it stores an incremented value of the address of the read command in a history buffer and marks the entry as valid. The system detects a stream when a subsequent read command specifies an address that matches the address value stored in the history buffer. Upon detecting a stream, the system fetches data from DRAMs at addresses that follow the address of the subsequent read command, and stores it in a FIFO. However, to reduce unnecessary prefetching, the system looks for a read X, write X, read X+1 (where X and X+1 designate addresses) succession of commands so as to prevent them from creating a stream. This succession occurs often and qualifies as a stream, but is seldom followed by other reads that maintain the stream.

Abstract: The present invention is directed to a method for arbitrating for control of a bus in a multiprocessor system. The multiprocessor system comprises a plurality of processors and a main memory coupled to one another by the bus, each processor including a cache memory accessible by the corresponding processor and in connection with transactions on the bus. The method includes the steps of generating requests for control of the bus and granting control of the bus in respect of one of the requests. The bus is monitored for preselected transaction activity on the bus; and an idle cycle is inserted on the bus upon monitoring the preselected transaction activity.

Abstract: The present invention is directed to a method and apparatus for performing exchange transactions between caches and a main memory of a computer system, the caches and main memory being coupled to one another by a bus. The method includes the steps of providing caches of different sizes with a cache having a smallest size, and with each cache having an index fixed as a function of the size of the cache. For each exchange transaction, the number of bits of an index used to address a selected cache location are determined, and the upper bits of a memory address from a tag store location corresponding to the selected cache location are retrieved, where the retrieved upper address bits form an exchange address. In the event that the index of the selected cache location comprises more bits than the index of the cache having the fewest addressable locations, the excess bits of the index of the selected cache location are appended to the exchange address.

Abstract: A memory system has a stream buffer with several performance-enhancing features. Two distinct sets of latches receive data from the memory array. One set feeds the stream buffer, while the other holds memory data that is destined for a system bus. The dual-latch configuration allows stream buffer fills to proceed even if system bus stalls prevent the memory data latch from being timely emptied. The memory controller prefetches a number of data blocks depending on the interleave factor of the memory system, as well as in response to control information from the CPU that can override the interleave-based number in some system configurations. The stream buffer employs a history buffer containing the addresses of recently-read memory locations in order to declare a new stream. The addresses of memory reads are normally entered into the history buffer on a round-robin basis.

Abstract: A read buffering system employs a bank of FIFOs to hold sequential read data for a number of data streams being fetched by a computer. The FIFOs are located in the memory controller, so the system bus is not used in memory accesses used to fill the stream buffer. The system stores addresses used for read requests made by a CPU, and if a next sequential address is then detected in a subsequent read request, this is designated to be a stream (i.e., sequential reads). When a stream is thus detected, data is fetched from DRAM memory for addresses following the sequential address, and this prefetched data is stored in one of the FIFOs. The system also prevents the unnecessary prefetching of data by preventing certain CPU requests from being used to detect streams. A FIFO is selected using a least-recently-used algorithm. When the CPU subsequently makes a read request for data in a FIFO, this data can be returned without making a memory access.

Abstract: The present invention is directed to a control flow logic device for handling data received from a bus by a bus interface, in response to a bus read transaction, and transferred to a processor. The control flow logic includes an error checker to check data received from the bus for hard errors and parity errors and an ECC generator to generate an ECC for the received data, the ECC being forced to a bad ECC when a hard error is detected by the error checker and to a good ECC in the absence of a hard error. An error signal generator is utilized to generate and transmit an error signal to the processor when there is a hard error or a parity error in the received data and a data mover transmits the received data and the ECC to the processor.

Abstract: A processor apparatus for use in a multiprocessor computer system having a main memory storing a plurality of data items and being coupled to a bus operating according of a SNOOPY protocol. The processor apparatus includes a processor, a primary cache, a backup cache and a bus interface. The backup cache memory a first TAG store comprising a plurality of VALID indicators, one VALID indicator for each of the data items currently contained in the backup cache memory. The primary cache memory includes a second TAG store comprising a plurality of address indicators and a plurality of VALID indicators, one address indicator and one VALID indicator for each of the data items currently contained in the primary cache memory. The interface includes a duplicate TAG store coupled to the primary cache memory, the duplicate TAG store consisting of a copy of the address indicators of the second TAG store. The bus interface is coupled to the processor, the backup cache memory and to the bus.

Abstract: A method and apparatus for polling a status register selectively delays the returning of status data in the status register. Prior to polling, a match register is loaded via a system bus with a desired status. Status data is presented to the system bus when the status data is the same as the desired status. The features of the invention also permit the masking of selective bits of the status register during the comparison of the status data with the desired status. A mode register selectively inhibits the delayed presentation, and a timer ensures that status data is presented to the system bus within a predetermined interval even if the status data is not the same as the desired status.

Abstract: A N-stage synchronizer for synchronizing asynchronous signals in a destination system's time domain. The synchronizer has N-stages with each stage having a series connected logic gate and flip-flop, and each of the N-stages are connected in series. Each logic gate has the output of the previous stage input thereto along with an ABORT signal. The ABORT signal when asserted blocks the synchronization of the asynchronous signal. The synchronizer permits a reduction in the latency associated with the synchronization process while not affecting reliability.

Abstract: A N-stage synchronizer for generating a synchronous signal that is derived from multiple sources. The synchronizer has an edge detector and N-1 stages for each asynchronous source signal. The outputs of the N-1 the synchronizer stages are processed according to an OR function. After the OR function, the merged asynchronous source signals are input to the shared last synchronizer stage. The output of the last synchronizer stage is the synchronous signal. The N-stage synchronizer reduces capacitance associated with the synchronizer and, therefore, lessens the time to assert or de-assert the synchronous signal, and reduces the time necessary to generate the synchronous signal.