Filter parallelization for high data throughput

摘要

A filter can include a first channel and a second channel. The first channel can be configured to process a first term and a second term of an input vector using a first coefficient and a second coefficient of the filter. The first channel can be configured to generate a first term of an output vector. The second channel can be configured to process the first term and the second term of the input vector using the first coefficient and the second coefficient of the filter. The second channel can be configured to generate a second term of the output vector. The first and second channels can be configured to operate in parallel.

主权项

1. A method of processing a data stream using a filter, the method comprising:
generating a first product and a second product by multiplying each of a first term and a second term of an input vector respectively by a first coefficient of the filter using a first multiplier circuit and a second multiplier circuit of the filter; delaying the first product and the second product to generate a delayed first product and a delayed second product; delaying each of the first term and a second term of a prior input vector to generate a delayed first term and a delayed second term of the prior input vector; generating a third product as the delayed second term of the prior input vector multiplied by a second coefficient of the filter using a third multiplier circuit of the filter, and generating a fourth product as the delayed first term of the input vector multiplied by the second coefficient of the filter using a fourth multiplier circuit of the filter; and generating, using the filter, an output vector comprising a first output term as a sum of the third product and the delayed first product and a second output term as a sum of the fourth product and the delayed second product.