摘要:
A method for maintaining cache coherency for a multi-node system using a specialized bridge which allows for fewer forward progress dependencies. A local node makes a determination whether a request is a local or system request. If the request is a local request, a look-up of a directory in the local node is performed. If an entry in the directory of the local node indicates that data in the request does not have a remote owner and that the request does not have a remote destination, the coherency of the data is resolved on the local node, and a transfer of the data specified in the request is performed if required and if the request is a local request. If the entry indicates that the data has a remote owner or that the request has a remote destination, the request is forwarded to all remote nodes in the multi-node system.
摘要:
A method for maintaining cache coherency for a multi-node system using a specialized bridge which allows for fewer forward progress dependencies. A look-up of a local node directory is performed if a request received at a multi-node bridge of the local node is a system request. If a directory entry indicates that data specified in the request has a local owner or local destination, the request is forwarded to the local node. If the local node determines that the request is a local request, a look-up of the local node directory is performed. If the directory entry indicates that data specified in the request has a local owner and local destination, the coherency of the data on the local node is resolved and a transfer of the request data is performed if required. Otherwise, the request is forwarded to all remote nodes in the multi-node system.
摘要:
A method for maintaining cache coherency for a multi-node system using a specialized bridge which allows for fewer forward progress dependencies. A local node makes a determination whether a request is a local or system request. If the request is a local request, a look-up of a directory in the local node is performed. If an entry in the directory of the local node indicates that data in the request does not have a remote owner and that the request does not have a remote destination, the coherency of the data is resolved on the local node, and a transfer of the data specified in the request is performed if required and if the request is a local request. If the entry indicates that the data has a remote owner or that the request has a remote destination, the request is forwarded to all remote nodes in the multi-node system.
摘要:
A method for maintaining cache coherency for a multi-node system using a specialized bridge which allows for fewer forward progress dependencies. A look-up of a local node directory is performed if a request received at a multi-node bridge of the local node is a system request. If a directory entry indicates that data specified in the request has a local owner or local destination, the request is forwarded to the local node. If the local node determines that the request is a local request, a look-up of the local node directory is performed. If the directory entry indicates that data specified in the request has a local owner and local destination, the coherency of the data on the local node is resolved and a transfer of the request data is performed if required. Otherwise, the request is forwarded to all remote nodes in the multi-node system.
摘要:
In a first aspect, a first method of reducing command processing latency while maintaining memory coherence is provided. The first method includes the steps of (1) providing a memory map including memory addresses available to a system; and (2) arranging the memory addresses into a plurality of groups. At least one of the groups does not require the system, in response to a command that requires access to a memory address in the group from a bus unit, to get permission from all remaining bus units included in the system to maintain memory coherence. Numerous other aspects are provided.
摘要:
The present invention provides for an integrated circuit (IC) bus system. A local IC is coupled to a remote IC through a bus interface. A local memory is coupled to the local IC. A bus interface controller is employable to track data transfer requests from the remote IC for data address that are contained within at least one segment of the first partitioned memory range. The bus interface controller is further employable to stop the forwarding of a data transfer request generated within the local IC to the remote IC, if the memory segment count corresponding to the data address of the locally generated data transfer request equals zero.
摘要:
A fair hierarchical arbiter comprises a number of arbitration mechanisms, each arbitration mechanism forwarding winning requests from requestors in round robin order by requestor. In addition to the winning requests, each arbitration mechanism forwards valid request bits, the valid request bits providing information about which requestor originated a current winning request, and, in some embodiments, about how many separate requesters are arbitrated by that particular arbitration mechanism. The fair hierarchical arbiter outputs requests from the total set of separate requestors in a round robin order.
摘要:
According to the present invention, a pipelined SRAM structure and clocking method is disclosed. The SRAM interface and clocking method are specifically intended for use with Level 2 and Level 3 cache SRAM memory devices. In the present invention, the oscillator that generates the clock signal for the CPU is also used to generate the clock signals for all of the other components that interface with the SRAM. Each of the generated clock signals are dependant on the same clock event, allowing the clock speed to be decreased for testing or debugging while maintaining higher speed clock edge relationships. The various clock signals that are generated from the oscillator are used to cycle-steal time from multiple cycles. This technique allows sub-5 nanosecond (nS) access to Level 2 and Level 3 cache memory devices that have access times greater than 5 nS.
摘要:
A method and apparatus for loading a ring of non-scan latches for a logic built-in self-test. A logic built-in self-test value is loaded into a scannable latch from the logic built-in self-test. An override control signal is asserted in response to loading the logic built-in self-test value into the scannable latch. A non-scan latch is forced to load the logic built-in self-test value from the scannable latch in response to asserting the override control signal. Logic paths in the ring of non-scan latches are exercised. The non-scan latch is part of the logical paths. The test results are captured from the logic paths and the test results are compared against expected test results to determine if the logic paths within the ring of non-scan latches are functioning properly.
摘要:
A shared bus non-sequential data ordering method and apparatus are provided. A maximum bus width value and a minimum transfer value are identified. A minimum number of sub-transfers is identified responsive to the identified maximum bus width value and the minimum transfer value. A bus unit having a maximum number of chips to receive and/or send data receives data in a predefined order during multiple sub-transfers. During each data sub-transfer, a corresponding predefined word is transferred to each chip of the bus unit.