摘要:
A pipeline is provided for processing network packets. The pipeline includes a look-ahead stage, an operation stage, an insert/remove stage, and an interleave stage. The look-ahead stage synchronizes two or more fields of a network packet. The operation stage modifies one or more of the fields of the network packet. The operation stage may modify state data and the fields of the network packet as a function of the state data and the fields. The insert/remove stage performs data insertion and removal at one or more fields of the network packet. The interleave stage ensures that the modified network packet follows rules for interleaving network packets. The look-ahead, operation, insert/remove, and interleave stages are generated from a textual language specification of the processing of the network packets by the pipeline.
摘要:
A method of partially reconfiguring an IC having programmable modules that includes the steps of reading a frame of configuration information from the configuration memory array; modifying at least part of the configuration information, thereby creating a modified frame of configuration information; and overwriting the existing frame of configuration information in the configuration memory array with the modified frame, thereby partially reconfiguring the IC.
摘要:
Method and system for generating an electronic circuit design. A first logic block is instantiated in the design in response to user input controls. The first logic block includes parameters that specify its interface requirements. Bus interface blocks, which are parameterizable to connect a logic block to a bus, are provided in a library. Bus interface blocks that connect the first logic block to the bus are instantiated in the design, and the bus interface blocks are parameterized in response to the requirements of, the first logic block. The bus interface blocks are connected to the first logic block in such a way that the first logic block is extended into a peripheral that can communicate with the bus.
摘要:
Method and apparatus for encoding configuration data is described. An integrated circuit device having a configuration interface is coupled to boot memory coupled at the configuration interface. The boot memory contains boot cores for configuring the integrated circuit device via the configuration interface. The boot cores include a configuration encoder core and an internal processor interface core. The boot cores may further include a processor core. The configuration encoder core provides a peripheral interface internal to the integrated circuit device, and the boot memory contains at least one set of instructions for encoding configuration data read from configuration memory. The encoded configuration data may be sent via the peripheral interface. Alternatively, configuration encoder core may include a configuration bitstream for instantiating an encoder in configurable resources for encoding readback configuration data.
摘要:
A method of partially reconfiguring an IC having programmable modules that includes the steps of reading a frame of configuration information from the configuration memory array; modifying at least part of the configuration information, thereby creating a modified frame of configuration information; and overwriting the existing frame of configuration information in the configuration memory array with the modified frame, thereby partially reconfiguring the IC.
摘要:
A method is provided for scheduling a network packet processor. A textual language specification is input of the processing of network packets by the network packet processor. The textual language specification includes memory read actions and modification actions. Each memory read action reads a stored value from a memory of the network packet processor. Each modification action modifies a field of the network packets. An availability is determined for each field read from the network packets for the memory read and modification actions. An availability is determined for each stored value read from the memory for the memory read actions. A look-ahead interval is determined from the availabilities. A respective storage class is determined for the fields for the memory read and modification actions. The respective storage class is one of a bus, a register, and a register with bypass.
摘要:
Embodiments of a message processing circuit are disclosed. In one embodiment, a high-level language is used to specify a broadcast channel and first and second thread circuits. The first thread circuit outputs messages to the broadcast channel, each message having units of data, and starts the second thread circuit, indicating position in a message at which the second thread circuit is to commence reading data. The broadcast channel receives messages from the first thread circuit and outputs data of each message along with a position code indicating position in the message of current output data. The second thread reads data from the broadcast channel at a specified position in a message. The high-level language specification is translated into a hardware description language (HDL) specification, and the HDL specification is used to generate configuration data for programmable logic. Programmable logic is configured to implement the thread circuits and broadcast channel.
摘要:
A method of using hardware libraries in a programmable logic device is disclosed. In particular, the method generally comprises steps of detecting a hardware library when compiling a software program for the programmable logic device; and accessing hardware module information stored in the hardware library; inserting the hardware module information of the hardware library into a reference platform.
摘要:
Method and apparatus for configuring a processor embedded in an integrated circuit for use as a logic element is described. In one example, a processing apparatus in an integrated circuit includes a point-to-point data streaming interface and arithmetic logic unit (ALU) circuitry. The ALU circuitry includes at least one input port in communication with the point-to-point data streaming interface. The processor may also include a register file and multiplexer logic. The multiplexer logic is configured to selectively couple the register file and the point-to-point streaming interface to the at least one input port of the ALU circuitry.
摘要:
Various approaches for preparing a system for multi-thread processing of messages are disclosed. In one approach, respective portions of a message accessed by a plurality of threads are determined from a high-level language programming specification of the threads. A plurality of input elements are generated and respectively coupled to the plurality of threads. Each input element is configured to select from the message received by the input element the portion of the message accessed by the respective thread and provide each selected portion to the respective thread. A plurality of output elements are generated and configured with storage for data output by a respective thread. From a definition of an output message, a concentrator element is generated and is configured to read data from the output elements and assemble the data into an output message according to the definition of the output message.