Polyphase Recursive Frame Filters for High-Throughput Signal Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional filters with recursive transfer functions process data serially, leading to slow throughput and potential bottlenecks in systems handling high rates of input samples, causing samples to be dropped and increasing power consumption.
Innovation Solution
Implementing a parallel filter processing method using polyphase decomposition to process frames of multiple samples simultaneously, allowing for faster filtering and reduced power consumption by distributing processing across multiple cores or logic elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional serial filtering is used, then implementation simplicity is maintained, but throughput is slow and samples may be dropped
Solution Approach 1:
The patent divides the recursive filter operation into multiple independent parallel filter operations through polyphase decomposition. The transfer function H(z) is decomposed into N polyphase components H_k(z), where each component processes a different phase of the input signal. This segmentation allows the filter to process N samples simultaneously in parallel, dramatically increasing throughput while maintaining implementation feasibility through modular structure.
2Use of energy by moving object
If serial processing is used, then power consumption is high due to bottleneck processing, but parallel processing requires complex decomposition
Solution Approach 1:
The filter is segmented into N independent parallel processing paths through polyphase decomposition. Each path processes a different phase of the input signal independently, allowing simultaneous execution across multiple processing elements. This parallelization eliminates the serial bottleneck, distributing the computational load and reducing power consumption per processing element while maintaining overall processing capability.
Solution Approach 2:
The patent creates a universal parallel filter structure that can process multiple phases of input signals simultaneously using the same decomposed transfer function components. The polyphase decomposition produces N filter operations that can be executed in parallel, making the system multi-functional in handling N different signal phases concurrently, thereby improving power efficiency through load distribution.
3Productivity
If parallel processing is implemented, then throughput increases and power consumption decreases, but implementation complexity increases
Solution Approach 1:
The recursive filter is segmented into N independent polyphase components through mathematical decomposition of the transfer function. Each component H_k(z) represents a separate filter operation that can be implemented independently. This segmentation transforms a single complex serial operation into multiple simpler parallel operations, making the overall system easier to manufacture through standardized modular components while achieving high throughput.
Data Source
AI summary
The exemplary embodiments provide a parallel implementation of filters with recursive transfer functions. This can enable a filter to act as a frame filter that may process a frame of multiple samples of data in parallel rather than being limited to processing a single sample of data at a time. Each frame contains plural input samples of data values. The input samples are from a common source and have a time dependency. The exemplary embodiments are suitable for implementing various types of filters in parallel, such as cascaded integrator comb filters, biquad filters and other types of infinite impulse response (IIR) filters. The exemplary embodiments may use polyphase decomposition to decompose a filter with a recursive transfer function into multiple polyphase component filters. The polyphase component filters may be applied to respective samples of data in a parallel pipelined configuration to produce filtered output for the samples of data in parallel.