Efficient Design and Implementation of Fast-Convolution-Based Variable-Bandwidth Filters
This paper introduces an efficient design approach for a fast-convolution-based variable-bandwidth (VBW) filter. The proposed approach is based on a hybrid of frequency sampling and optimization (HFSO), that offers significant computational complexity reduction compared to existing solutions for a given performance. The paper provides a design procedure based on minimax optimization to obtain the minimum complexity of the overall filter. A design example includes a comparison of the proposed design-based VBW filter and time-domain designed VBW filters implemented in the time domain and in the frequency domain. It is shown that not only the implementation complexity can be reduced but also the design complexity by excluding any computations when the bandwidth of the filter is adjusted. Moreover, memory requirements are also decreased compared to the existing frequency-domain implementations.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A MAC-less Neural Inference Processor Supporting Compressed, Variable Precision Weights
This paper introduces two architectures for the inference of convolutional neural networks (CNNs). Both architectures exploit weight sparsity and compression to reduce computational complexity and bandwidth. The first ar…
PathfinderA low complexity and high modularity design for continuously variable bandwidth digital filters
Digital filters with variable bandwidth can be used for a variety of applications. Arbitrary change in the bandwidth of a digital Finite Impulse Response (FIR) filter can be acquired using sampling rate converters. In th…
Optimizing Memory Efficiency for Convolution Kernels on Kepler GPUs
Convolution is a fundamental operation in many applications, such as computer vision, natural language processing, image processing, etc. Recent successes of convolutional neural networks in various deep learning applica…
CNN-MERP: An FPGA-Based Memory-Efficient Reconfigurable Processor for Forward and Backward Propagation of Convolutional Neural Networks
Large-scale deep convolutional neural networks (CNNs) are widely used in machine learning applications. While CNNs involve huge complexity, VLSI (ASIC and FPGA) chips that deliver high-density integration of computationa…
Scaling up HBM Efficiency of Top-K SpMV for Approximate Embedding Similarity on FPGAs
Top-K SpMV is a key component of similarity-search on sparse embeddings. This sparse workload does not perform well on general-purpose NUMA systems that employ traditional caching strategies. Instead, modern FPGA acceler…
CPUGPU