Lsi Corporation

Agere Systems Inc.

Intel Corporation

Steven J Pollock

William G Burroughs

Deepak Mital

James T Clee

Jerry Pirog

Te Khac Ma

David Allen Brown

David Sonnier

Ephrem C Wu

Ting Zhou

Richard Joseph Byrne

Narender R Vangati

Joseph R Hasting

Michael R Betker

Hakan I Pekcan

David S Masters

Larry Stephen King

Described embodiments classify packets received by a network processor. A processing module of the network processor generates tasks corresponding to each received packet. A scheduler generates contexts corresponding to tasks received by the packet classification processor from corresponding processing modules, each context corresponding to a given flow, and stores each context in a corresponding per-flow first-in, first-out buffer of the scheduler. A packet modifier generates a modified packet based on threads of instructions, each thread of instructions corresponding to a context received from the scheduler. The modified packet is generated before queuing the packet for transmission as an output packet of the network processor, and the packet modifier processes instructions for generating the modified packet in the order in which the contexts were generated for each flow, without head-of-line blocking between flows. The modified packets are queued for transmission as an output packet of the network processor.

Modifying data streams without reordering in a multi-thread, multi-flow network processor

Described embodiments provide a method of updating configuration data of a network processor having one or more processing modules and a shared memory. A control processor of the network processor writes updated configuration data to the shared memory and sends a configuration update request to a configuration manager. The configuration update request corresponds to the updated configuration data. The configuration manager determines whether the configuration update request corresponds to settings of a given one of the processing modules. If the configuration update request corresponds to settings of a given one of the one or more processing modules, the configuration manager, sends one or more configuration operations to a destination one of the processing modules corresponding to the configuration update request and updated configuration data. The destination processing module updates one or more register values corresponding to configuration settings of the processing module with the corresponding updated configuration data.

Dynamic configuration of processing modules in a network communications processor architecture

Described embodiments classify packets received by a network processor. A processing module of the network processor generates tasks corresponding to each received packet. A packet classification processor determines, independent of a flow identifier of the received task, control data corresponding to each task. A multi-thread instruction engine processes threads of instructions corresponding to received tasks, each task corresponding to a packet flow of the network processor and maintains a thread status table and a sequence counter for each flow. Active threads are tracked by the thread status table, and each status entry includes a sequence value and a flow value identifying the flow. Each sequence counter generates a sequence value for each thread by incrementing the sequence counter each time processing of a thread for the associated flow is started, and decrementing the sequence counter each time a thread for the associated flow is completed.

Changing a flow identifier of a packet in a multi-thread, multi-flow network processor

Described embodiments provide a network processor having a plurality of processing modules coupled to a system cache and a shared memory. A memory manager allocates blocks of the shared memory to a requesting one of the processing modules. The allocated blocks store data corresponding to packets received by the network processor. The memory manager maintains a reference count for each allocated memory block indicating a number of processing modules accessing the block. One of the processing modules reads the data stored in the allocated memory blocks, stores the read data to corresponding entries of the system cache and operates on the data stored in the system cache. Upon completion of operation on the data, the processing module requests to decrement the reference count of each memory block. Based on the reference count, the memory manager invalidates the entries of the system cache and deallocates the memory blocks.

Memory manager for a network communications processor architecture

Described embodiments provide address translation for data stored in at least one shared memory of a network processor. A processing module of the network processor generates tasks corresponding to each of a plurality of received packets. A packet classifier generates contexts for each task, each context associated with a thread of instructions to apply to the corresponding packet. A first subset of instructions is stored in a tree memory within the at least one shared memory. A second subset of instructions is stored in a cache within a multi-thread engine of the packet classifier. The multi-thread engine maintains status indicators corresponding to the first and second subsets of instructions within the cache and the tree memory and, based on the status indicators, accesses a lookup table while processing a thread to translate between an instruction number and a physical address of the instruction in the first and second subset of instructions.

Reducing data read latency in a network communications processor architecture

Described embodiments provide a system having a bridge for connecting two different processor buses. A process monitor within the bridge allows for measuring latency of commands issued on a first bus, passing through the bridge, and executed by clients coupled to the second bus. By using identification fields associated with the command, measuring the latency of each command begins with matching the identification field of the command to an integer. As the bridge passes acknowledgements back to the first bus, the monitoring of the command is stopped when an identification field associated with an acknowledgement matches the identification field of the command being monitored. Data collected include the minimum, maximum, total latency, and the number of commands monitored. From this data, the average latency can be easily calculated.

Transaction performance monitoring in a processor bus bridge

Described embodiments provide for transfer of data between data modules. At least two crossbar switches are employed, where input nodes and output nodes of each crossbar switch are coupled to corresponding data modules. The ith crossbar switch has an N-input by M-output switch fabric, wherein Nand Mare positive integers greater than one. Each crossbar switch includes an input buffer at each input node, a crosspoint buffer at each crosspoint of the switch fabric, and an output buffer at each output node. The input buffer has an arbiter that reads data packets from the input buffer according to a first scheduling algorithm. An arbiter reads data packets from a crosspoint buffer queue according to a second scheduling algorithm. The output node receives segments of data packets provided from one or more corresponding crosspoint buffers.

Buffered crossbar switch system

The invention includes a method and apparatus for synchronizing a first processor with a second processor. The method includes storing in a register parallel bits of data from the first processor, wherein at least one bit of data is a logic ONE. An output signal is formed from the one bit of data in the register. The output signal is sent as an interrupt signal to an interrupt terminal of the second processor for synchronizing the first processor with the second processor. The method may be used with a memory mapped register or an off-core register. The first and second processors may each be a digital signal processor (DSP) or any other type of processor.

Inter-DSP signaling in a multiple DSP environment

A programmable delay circuit includes a plurality of delay blocks, a plurality of corresponding tri-state drivers and at least one decoder. The delay blocks are connected together so as to form a series chain. Each of the tri-state drivers includes an input connected to an output of a corresponding one of the delay blocks, and a control input adapted to receive one of multiple control signals. The tri-state driver is operative in one of at least a first mode and a second mode as a function of a corresponding one of the control signals. In the first mode, an output signal generated at an output of the tri-state driver is a function of a voltage level at the input of the tri-state driver, and in the second mode the output of the tri-state driver is in a high-impedance state. The output of each of the tri-state drivers is coupled together and forms an output of the programmable delay circuit. The decoder is connected to the plurality of tri-state drivers. The decoder includes at least one control input for receiving at least a second signal and is operative to generate the control signals for activating a corresponding one of the tri-state drivers as a function of the second signal.

Programmable delay circuit having reduced insertion delay

An inter-processor data exchange system is provided in a multiple processor environment. The system includes a first message unit and a second message unit. The first message unit stores first data from a first processor and transfers the stored first data to the second message unit. The second message unit stores the first data from the first message unit and responsively provides the first data to a second processor. The second message unit also stores second data from the second processor and transfers the stored second data to the first message unit, and the first message unit stores the second data from the second message unit and responsively provides the second data to the first processor. Each message unit also provides an interrupt signal to the other processor for informing the other processor that the data is available for reading. In addition, each message unit provides a first flag signal for informing its own processor that the other processor has read the data.

Growing community of inventors

Allentown, PA, United States of America

Steven J Pollock