摘要:
A method of and apparatus for associating units of data with threads of a multi-threaded processor for processing, and enabling each thread to perform processing for at least two of the data units during a thread execution period. The thread execution period is divided among phases, and each of the data units processed by a thread is processed by a different one of the phases.
摘要:
A mechanism to process units of data associated with a dependent data stream using different threads of execution and a common data structure in memory. Accessing the common data structure in memory for the processing uses a single read operation and a single write operation. The folding of multiple read-modify-write memory operations in such a manner for multiple multi-threaded stages of processing includes controlling a first stage, which operates on the same data unit as a second stage to pass context state information to the second stage for coherency.
摘要:
A parallel hardware-based multithreaded processor is described. The processor includes a general purpose processor that coordinates system functions and a plurality of microengines that support multiple program threads. The processor also includes a memory control system that has a first memory controller that sorts memory references based on whether the memory references are directed to an even bank or an odd bank of memory and a second memory controller that optimizes memory references based upon whether the memory references are read references or write references. A program thread communication scheme for packet processing is also described.
摘要:
A parallel hardware-based multithreaded processor is described. The processor includes a general purpose processor that coordinates system functions and a plurality of microengines that support multiple program threads. The processor also includes a memory control system that has a first memory controller that sorts memory references based on whether the memory references are directed than even bank or an odd bank of memory and a second memory controller that optimizes memory references based upon whether the memory references are read references or write references. A program thread communication scheme for packet processing is also described.
摘要:
A method of operating a processor includes concatenating a first word and a second word to produce an intermediate result, shifting the intermediate result by a specified shift amount and storing the shifted intermediate result in a third word, to create an address.
摘要:
In general, in one aspect, the disclosure describes a system to process packets received over a network. The system includes a receive process of at least one thread of a network processor to receive data of packets belonging to different flows. The system also includes a transmit process of at least one thread to transmit packets received by the receive process. A scheduler process of at least one thread populates at least one schedule of flow service based, at least in part, on quality of service characteristics associated with the different flows. The schedule identifies different flow candidates for service. The system also includes a shaper process of at least one thread to select from the candidate flows for service from the at least one schedule.
摘要:
A method and apparatus for meeting a given content throughput using at least one memory channel is generally described. In accordance with one example embodiment of the invention, a method to meet a given content throughput using at least one memory channel comprising, comparing the size of at least a portion of received content to a capacity of a single contiguous location within at least one memory channel to meet a given throughput and determining whether to distribute the at least portion of received content across the at least one memory channel, based at least in part, on the comparison.
摘要:
A scheduling mechanism to control transmission of data units, such as variable size packets or fixed size cells, to ports of a network device such as a switching fabric system. The scheduling mechanism maintains scheduling data structures, including an array storing information for available queues of ports and circular buffers representing nonempty port queues of the available port queues according to classes of service. The scheduling mechanism uses the data structures to make scheduling decisions concerning the scheduling of data units in the nonempty port queues for transmission to the ports.
摘要:
A method of processing network data in a network processor includes using three or more threads to process a beginning portion, a middle portion, and an end portion of data packet. The first thread processes the beginning portion; one or more middle threads process the middle portion, and a last thread processes the end portion. First information is indirectly passed from the first thread to the last thread via a first buffer with the middle threads progressively updating the first information. Second information is directly passed from the first thread to the last thread via a second buffer.
摘要:
In general, in one aspect, the disclosure describes a method of tracking a network statistic stored within a collection of bits. The method includes storing the collection of bits storing the network statistic as at least a first portion and a second portion. The first portion includes a set of least-significant bits and the second portion includes a set of more significant bits. The method also includes incrementing the first portion based on a packet and=determining if the incrementing of the first portion caused a designated bit of the first portion to be set. If it is determined that the incrementing of the first portion caused the designated bit to be set, the method increments the value stored by the second portion and resets the designated bit within the first portion.