The major purpose of this study is to create a more efficient MAC control block-based architecture for 2D convolution. This 2D algorithm can be implemented in hardware with a smaller number …

... functional architecture of the conventional MAC unit is shown in Figure 5 The kernel uses K 2 MAC units on the image simultaneously at each clock cycle. The operands used are 8-bit …

Oct 19, 2024 · The proposed method with the help of a Stochastic number generator (SNG), MAC unit, Max pooling layer, Rectified linear unit (ReLU) and fully connected layer has build a …

This kind of operation is widely used in the field of digital image processing wherein the 2D matrix representing the image is being convolved with a 2D kernel.

A comprehensive evaluation of convolution layers shows using our proposed method when compared to the conventional MAC-based method results up to 97% and 50% reduction in …

First we define a special class of SIMD multipliers, tailored for the kind of MAC operations found in convolutional layers of CNNs (Convolutional Neural Networks). Specifically, our Double MAC …

This paper presents a new fully reconfigurable 2D convolver designed for FPGA-based image and video processors. The proposed architecture operates on image pixels coded with different bit …

Feb 8, 2023 · The 2D convolution and MAC design processes are used to perform image analysis tasks such as image blurring, softening, feature extraction, and image classification. This …

Oct 4, 2021 · This paper proposes a single-precision Floating Point MAC engine to accelerate the sliding window algorithm for the 2-D convolution of image. The engine uses a modified …

Feb 11, 2021 · A 2D image convolution process is developed by stacking and combining several MAC blocks. The developed MAC comprises a sequential multiplier, controller, and optimized …