Vector processing engines (VPEs) employing a tapped-delay line(s) for providing precision filter vector processing operations with reduced sample re-fetching and power consumption, and related vector processor systems and methods

An apparatus for performing a filter vector processing operation in a vector processing engine (VPE), comprising:

• means for fetching an input vector data sample set from at least one vector data file into at least one input data flow path for a filter vector processing operation;
• means for receiving the fetched input vector data sample set in the at least one input data flow path into at least one tapped-delay line provided in the at least one input data flow path between the at least one vector data file and at least one execution unit;
• and
• for each processing stage of a plurality of processing stages in the at least one execution unit, wherein a number of the plurality of processing stages equals a number of filter taps of the filter vector processing operation:
• means for shifting the input vector data sample set within the at least one tapped-delay line to a next filter tap for the filter vector processing operation in the input vector data sample set to provide a shifted input vector data sample set as the input vector data sample set, the at least one tapped-delay line configured to shift the input vector data sample set by a vector data sample width in a plurality of pipeline registers for each processing stage among a plurality of processing stages equal to a number of filter taps in the filter vector processing operation;
• means for providing the shifted input vector data sample set from the at least one tapped-delay line in the at least one input data flow path to the at least one execution unit in a current processing stage;
• means for applying a filter tap operation on the shifted input vector data sample set in the at least one execution unit in the current processing stage to generate a filter tap output vector data sample set;
• means for accumulating the filter tap output vector data sample set with a prior resultant filtered output vector data sample set in the current processing stage;
• and
• means for providing the prior resultant filtered output vector data sample set as a resultant filtered output vector data sample set in at least one output data flow path to the at least one vector data file to be stored in the at least one vector data file.

A method of performing a filter vector processing operation in a vector processing engine (VPE), comprising:

• fetching an input vector data sample set from at least one vector data file into at least one input data flow path for the filter vector processing operation;
• receiving the fetched input vector data sample set in the at least one input data flow path into at least one tapped-delay line provided in the at least one input data flow path between the at least one vector data file and at least one execution unit;
• and
• for each processing stage of a plurality of processing stages in the at least one execution unit, wherein a number of the plurality of processing stages equals a number of filter taps of the filter vector processing operation:
• shifting the input vector data sample set within the at least one tapped-delay line to a next filter tap for the filter vector processing operation in the input vector data sample set to provide a shifted input vector data sample set as the input vector data sample set, the at least one tapped-delay line configured to shift the input vector data sample set by a vector data sample width in a plurality of pipeline registers for each processing stage among a plurality of processing stages equal to a number of filter taps in the filter vector processing operation;
• providing the shifted input vector data sample set from the at least one tapped-delay line in the at least one input data flow path to the at least one execution unit in a current processing stage;
• applying a filter tap operation on the shifted input vector data sample set in the at least one execution unit in the current processing stage to generate a filter tap output vector data sample set;
• accumulating the filter tap output vector data sample set with a prior resultant filtered output vector data sample set in the current processing stage;
• providing the prior resultant filtered output vector data sample set as a resultant filtered output vector data sample set in at least one output data flow path to the at least one vector data file to be stored in the at least one vector data file.