Method of and device for processing data using a pipeline of processing blocks
AssigneeXilinx, Inc.
InventorsMichaela Blott, Thomas B. English, Kornelis A. Vissers
Life of this patent
Estimating the term…
Abstract
A method of processing data in an integrated circuit is described. The method comprises establishing a pipeline of processing blocks, wherein each processing block has a different function; coupling a data packet having data and meta-data to an input of the pipeline of processing blocks; and processing the data of the data packet using predetermined processing blocks based upon the meta-data. A device for processing data in an integrated circuit is also described.
Claims11
A method of processing data in an integrated circuit, the method comprising:
- establishing a key-value store;
- receiving data for a transaction at an input to a pipeline of processing blocks, wherein each processing block has a different function;
- encoding state of the transaction as metadata that enables a subset of the processing blocks for processing the data;
- passing the data and the metadata through the pipeline of processing blocks as a data packet having the data and the metadata;
- and
- accessing the key-value store while processing the data in the subset of the processing blocks based upon the metadata.
A device for processing data in an integrated circuit, the device comprising:
- a network interface configured to receive data for a transaction;
- a transaction protocol parser, coupled to the network interface, configured to encode state of the transaction as metadata that enables a subset of processing blocks in a pipeline of processing blocks for processing the data and to couple the data and the metadata to the pipeline of processing blocks as a data packet having the data and the metadata;
- the pipeline of processing blocks coupled to the transaction protocol parser, wherein each processing block has a different function, and wherein the subset of the processing blocks processes the data based upon the metadata;
- a key-value store coupled to the pipeline of processing blocks, wherein the pipeline of processing blocks accesses the key-value store while processing the data based upon the metadata.
Dependencies are inferred from the claim text.