Abstract: Methods and arrangements for parallel parity checking for content addressable memory and ternary content addressable memory during compare cycles are disclosed. Further, methods and arrangements for remedying storage bit corruption are also disclosed.

Abstract: A method for remedying data corruption in a first circuit, which may be a CAM or a TCAM. The method includes providing a RAM circuit external to the first circuit, the RAM circuit being configured for storing error detection information for data stored in the first circuit. The method also includes scrubbing the data stored in the first circuit during scrubbing cycles of the first circuit. The scrubbing corrects stored bit patterns read from the first circuit that fail an error detection test using error detection information corresponding to individual ones of the stored bit patterns. In an embodiment, ECC may be employed for the error detection test and also to correct any single bit error found.

Abstract: Methods and apparatus for performing, using smaller, more efficient shared logic circuitry, the parity checking function and the compare function in a mutually exclusive manner in different cycles of a ternary content addressable memory are disclosed.

Abstract: Systems, methods, and devices are disclosed that provide packet protection for header modification. One method includes receiving a packet to a computing device. The method includes apply error checking techniques independently to different portions of the packet.

Abstract: Systems, methods, and devices are provided for moving packets on a network device. One method includes receiving packets to a number of network chips, the number of network chips having a conduit port which can be selectively chosen to exchange packets with a processor responsible for processing packets. The method includes adding data for additional functionality to certain packets. Adding data includes encapsulating the certain packets to maintain an appearance of a certain packet format.

Abstract: In an embodiment of the invention, a method of providing redundancy in a ternary content addressable memory (TCAM) includes: detecting a defective entry in a ternary content addressable memory (TCAM); marking the defective entry so that the defective entry is visible to a software; and avoiding in using the defective entry. For data that normally would have been written into the defective entry, the data is written into an entry that is subsequent to the defective entry. In another embodiment, the redundancy is provided in a CAM instead of a TCAM.

Abstract: Methods, systems, and circuits are provided for signals crossing multiple clock domains. One circuit includes a number of different clock domains located on different portions of the ASIC. A number of input/output (I/O) ports are provided to couple signals to and from the ASIC. The circuit includes means for moving internal signals from a subset of the number of different clock domains of multiple frequencies to a different clock domain for monitoring, observation, counting, and debug.

Abstract: Network devices and methods are provided for device monitoring. One embodiment includes a network device having a processor, a high speed interconnect and a number of network chips. The number of network chips are coupled to one another through the high speed interconnect. The number of network chips have a conduit port which can be selectively chosen to exchange packets, received to any network chip, with the processor.

Abstract: Methods, systems, and circuits are provided for monitoring multiple clock domains. One method for monitoring multiple clock domains includes pipelining different sets of signals from different clock domains on an application specific integrated circuit (ASIC) to a particular input/output (I/O) port on the ASIC using an associated clock from each different clock domain, and selecting a particular set of signals from among the different sets of signals to send out of the particular I/O port.

Abstract: Network devices and methods are provided involving a support chip in association with network chips. One embodiment includes a network device having a processor, a high speed interconnect, and a number of network chips coupled to one another through the high speed interconnect. The number of network chips include a conduit port which can be selectively chosen to exchange packets, received to the number of network chips, with the processor. The support chip is coupled to the number of network chips in association with selecting a conduit port on one of the number of network chips to exchange packets with the processor.

Abstract: Application specific integrated circuits (ASICs) and methods are provided which allow for internal testing of an ASIC. One ASIC embodiment includes a processor on the ASIC. A memory is coupled to the processor. A test circuit is integrated on the ASIC and coupled to the processor to perform testing internal to the ASIC, the test circuit having an input to receive signals from the processor. The processor can read an output of the test circuit to determine a performance speed of the ASIC.

Abstract: A semaphore mechanism in a multiport cache memory system allows concurrent accesses to the cache memory. When there is no contention for the same cache line, multiple requesters may access the cache memory concurrently. A status bit in each cache line indicates whether that particular cache line is in use, and is used to arbitrate among various requesters for the same cache line. When at least two requests for the same cache line is received, a cache arbiter examines the status bit to determine if the requested cache line is in use. If the cache line is not already in use, the cache arbiter selects, and sends a signal granting the request to, the requesters one at a time to allow access to the contested cache line, while allowing concurrent access to the cache memory to other requesters requesting different cache lines. The semaphore mechanism allows exchanges of signals between the cache arbiter and the requesters to provide an orderly arbitration of multiple requests for the same cache line.

Abstract: A performance adder for providing a running total of performance values within an integrated circuit chip. The performance adder is triggered by various performance events as determined through multiplexer logic for detecting occurrence of a particular performance event. The multiplexer logic can also trigger the performance adder through atomic, edge, toggle, or on/off signals related to the performance events or through a logical function of a combination of performance events. The performance adders can be used to compute average latency of a component in the circuit.

Abstract: A performance adder for providing a running total of performance values within an integrated circuit chip. The performance adder is triggered by various performance events as determined through multiplexer logic for detecting occurrence of a particular performance event. The multiplexer logic can also trigger the performance adder through atomic, edge, toggle, or on/off signals related to the performance events or through a logical function of a combination of performance events. The performance adders can be used to compute average latency of a component in the circuit.

Abstract: Test circuitry is incorporated on a chip die together with a circuit to be tested, such as an ASIC or microprocessor, to provide external access to signals that are internal to an integrated circuit chip package. A test device includes a state machine responsive to (i) an arm command for transitioning from a standby state to an armed state, (ii) a final trigger event for transitioning from the armed state to a triggered state, and (iii) a post trigger count event for transitioning from the triggered state to the standby state. A controller provides the arm command and issues appropriate configuration controls to collect signal samples. In particular, a network responds to these commands from the controller to selectively provide signal samples from a device under test. A trigger event generator responds to logic or other characteristics of the signal samples to provide trigger events.

Abstract: A data processing system includes a memory storing data to be retrieved and an I/O controller configured to request data stored in the memory at a plurality of addresses. The I/O may be responsive to an internal or external device requesting such data. A fetch machine provides or initiates retrieval of data stored at the requested address, while a prefetch machine predicts future requests and keeps track of memory requests already initiated and queued. Thus, the prefetch machine is responsive to the plurality addresses to predict others of the addresses and provide or initiate retrieval of data stored thereat. To avoid prefetching information already requested and in a fetch queue, the prefetch machine includes a memory storing a last one of the addresses subject to prefetching. Finally, to avoid conflicts between currently requested data and prefetch operation, an arbiter resolves memory accesses or data requests initiated by the fetch and prefetch machines.

Abstract: Test circuitry is incorporated on a chip die together with a circuit to be tested, such as an ASIC or microprocessor, to provide external access to signals that are internal to an integrated circuit chip package. A test device includes a state machine responsive to (i) an arm command for transitioning from a standby state to an armed state, (ii) a final trigger event for transitioning from the armed state to a triggered state, and (iii) a post trigger count event for transitioning from the triggered state to the standby state. A controller provides the arm command and issues appropriate configuration controls to collect signal samples. In particular, a network responds to these commands from the controller to selectively provide signal samples from a device under test. A trigger event generator responds to logic or other characteristics of the signal samples to provide trigger events.

Abstract: A timeout mechanism that can accommodate an improved accuracy in determining the timeout of a pending transaction while conserving the amount of processing circuitry is herein disclosed. A fetch state machine is associated with each cache line. When the cache line is fetched from memory, the fetch state machine tracks the number of timeout periods that lapse before the cache line is retrieved. If a predetermined number of timeout periods lapses before the cache line is retrieved, a timeout occurs and processed accordingly.

Abstract: A shared memory provides data access to a plurality of agents (e.g., processor, cells of processors, I/O controllers, etc.) and includes a memory and a memory controller. The memory controller selectively provides memory access to the agents in both coherent and read current modes of operation. In the coherent mode, the memory controller ensures that the data stored in system memory is accurately and precisely mirrored in all subservient copies of that data as might typically be stored in agent cache memories. Using, for example, a MESI type protocol, the memory controller limits access to memory so that only an “owner” or a particular portion or line of memory has write access and that, during the extension of these write privileges, no other agent has a valid copy of the data subject to being updated. Thus, the memory controller implements a first set of rule in the coherent mode of operation to insure that all copies of data stored by the agents are coherent with data stored in the memory.

Abstract: A snapshot mechanism that includes an apparatus and method for tracking DMA read requests for cacheable data that can be altered before the data is returned to a requesting I/O device is herein disclosed. Attributes that uniquely identify the original I/O device and DMA read request are stored in a cache tag unit. A read lock is set when a request is made to obtain the requested data when it is not resident in a local cache. When the cache line containing the requested data is snooped out and the read lock is set, then the cache line is set in a snapshot state. The snapshot state assures that only the original I/O device receives the read data when it has been altered subsequent to the time the original DMA read request was made. Once the data is returned to the original I/O device, the cache line is invalidated in order to prevent another I/O device from reading the stale data. Prefetched data is marked as such and cannot be marked as snapshot data.