摘要:
An ordered semaphore management subsystem and method for use in an application system which includes a plurality of processors competing for shared resources each of which is controlled by a unique semaphore. The subsystem generates an ordered semaphore field (OSF) corresponding to each processor in a linked list of processors and assigns one of four statuses to the OSF depending on the position the processor occupies in the linked list of processors competing for the shared resources. The four states are (1) semaphore head (SH); (2) behind semaphore head (BSH); (3) semaphore head behind (SHB); and (4) skip (Skip). Only the SH processor is allocated the semaphore when requested. A processor not in the SH state will be denied the semaphore even if is available to assure sequential access.
摘要:
A generic method and apparatus for managing semaphores in a multi-threaded processing system has a storage area for each of the threads in the processing system. Each storage area includes a first part for storing at least one indicia for identifying at least one unique semaphore from a plurality of semaphores utilized by the multi-threaded processing system and a second part for storing an indicia for indicating a locked status for the stored semaphore. A thread requiring a semaphore sends a semaphore lock request to the semaphore manager which examines the contents of all of the storage areas to determine the status of the requested semaphore. If the requested semaphore is not locked, it is locked for the requesting thread by inserting the requested semaphore and locked status in the memory location assigned to the requesting thread.
摘要:
Processor threads in a multi-processor system can concurrently lock multiple semaphores by providing a lock command which includes the semaphore value and a semaphore number. Each processor is allocated two or more addressable semaphore stores, each of which include a multi-bit field identifying the requested semaphore and a one bit field identifying the locked status of the requested semaphore. The semaphore number determines which of the allocated semaphore stores are to be used for processing the lock command.
摘要:
A method and system for identifying a data structure associated with a packet of data. A processor internal to a packet processor may extract one or more fields in a packet header field of a received packet of data to generate a search key. The internal processor may then be configured to select which table, e.g., routing table, quality of service table, filter table, needs to be accessed using the search key in order to process the received packet of data. A determination may then be made by the internal processor as to whether a CAM or a hash table and a Patricia Tree are used to identify the data structure associated with the received packet of data. Based on table definitions in a register, the internal processor may make such a determination.
摘要:
A method and system for identifying a data structure associated with a packet of data. A processor internal to a packet processor may extract one or more fields in a packet header field of a received packet of data to generate a search key. The internal processor may then be configured to select which table, e.g., routing table, quality of service table, filter table, needs to be accessed using the search key in order to process the received packet of data. A determination may then be made by the internal processor as to whether a CAM or a hash table and a Patricia Tree are used to identify the data structure associated with the received packet of data. Based on table definitions in a register, the internal processor may make such a determination.
摘要:
A Network Processor (NP) is formed from a plurality of operatively coupled chips. The NP includes a Network Processor Complex (NPC) Chip coupled to a Data Flow Chip and Data Store Memory coupled to the Data Flow Chip. An optional Scheduler Chip is coupled to the Data Flow Chip. The named components are replicated to create a symmetric ingress and egress structure. Communications between the chips are provided by a pair of Chip to Chip Macros, one of each operatively positioned on one of the chips, and a Chip to Chip Bus Interface operatively coupling the Chip to Chip Macros.
摘要:
An interface to interconnect Network Processor and Scheduler chips in a multi-chip system includes a limited set of messages and circuit arrangements to generate the limited set of messages. The messages include FlowEnqueue.request, FlowEnqueue.response, PortEnqueue.request and PortStatus.request.
摘要:
An interface to interconnect chips in a multi-chip system includes a limited set of messages and circuit arrangements to generate the limited set of messages. The chips can be configured in different operational modes which dictates what portion of a frame is to be transmitted between selected chips of the system.
摘要:
A method, system and computer program product for eliminating memory corruption when performing multi-threaded tree operations. A network processor may receive a command to perform a tree operation on a tree on one or more of multiple threads. Upon performing the requested tree operation, the network processor may lock one or more resources during a portion of the execution of the requested tree operation using one or more semaphores. A semaphore may refer to a flag used to indicate whether to “lock” or make available the resource associated with the semaphore. Locking may refer to preventing the resource from being available to other threads. Hence, by locking one or more resources during a portion of the tree operation, memory corruption may be eliminated in a multiple thread system while preventing these resources from being used by other threads for a minimal amount of time.
摘要:
An integrated circuit having an array of programmable processing elements and a memory interface linked by an on-chip communication network. Each processing element includes a plurality of processing cores and a local memory. The memory interface block is operably coupled to external memory and to the on-chip communication network. The memory interface supports accessing the external memory in response to messages communicated from the processing elements of the array over the on-chip communication network. A portion of the local memory for a plurality of the processing elements of the array as well as a portion of the external memory are both allocated to store data shared by a plurality of processing elements of the array during execution of programmed operations distributed thereon.