B.Sc. Thesis

Role of Approximate Computational Blocks in Implementation of Systems in Nanotechnology (thesis)

Increased power consumption is one of the main challenges in the area of digital electronics. In recent years, there has been a great interest in portable devices. The size and capacity of embedded battery cells are essential factors affecting the weight and dimension of these devices, which are influenced directly by their consumed energy. On the other hand, increasing the speed of the electronic tools and reducing the delays of the output are of great interest. The conventional digital hardware computational blocks with different structures are designed to compute the precise results of the assigned calculations. However, there are a lot of real-world applications which have the potential to accept small degrees of imprecision and uncertainty in their computations. Image processing is one of these applications. Here we propose bio-inspired imprecise computational blocks, which are designed to provide an applicable estimation of the result instead of its precise value at a lower cost. These novel structures are more efficient in terms of area, speed, and power consumption with respect to their precise rivals. We use these blocks in the hardware implementation of several image processing filters, such as Gaussian, Gradient, and Canny Edge Detector. The results show that using this method leads to higher processing speed and lower area and power consumption with a bearable effect on the precision of the output for human subjects.