PROJECT TITLE :

Two Approximate Voting Schemes for Reliable Computing - 2017

ABSTRACT:

This paper depends on the principles of inexact computing to alleviate the issues arising in static masking by voting for reliable computing within the nanoscales. Two schemes that utilize in several manners approximate voting, are proposed. The first theme is known as inexact double modular redundancy (IDMR). IDMR will not resort to triplication, so saving overhead because of modular replication. This theme is crudely adaptive in its operation, i.e., it permits a threshold to determine the validity of the module outputs. IDMR operates by initially establishing the distinction between the values of the outputs of the 2 modules; solely if the distinction is below a preset threshold, then the voter calculates the common value of the two module outputs. The second scheme (ITDMR) combines IDMR with TMR (triple modular redundancy) by using novel conditions in the comparison of the outputs of the three modules. Within an inexact framework, the bulk is established using different criteria; in ITDMR, adaptive operation is carried any than IDMR to incorporate approximate voting in a very pairwise fashion. Therefore, the validity of the three inputs is established and when solely two of the 3 inputs satisfy the brink condition, the IDMR operation is used. An extensive analysis that has the voting circuits furthermore a probabilistic framework is included. The proposed IDMR and ITDMR schemes improve the ability dissipation and tolerance to variations compared to a ancient TMR. To further validate the applicability of the proposed schemes, inexact voting has been utilized in two applications (Image Processing and FIR filtering); the simulation results show that performance is substantially improved over TMR.


Did you like this research project?

To get this research project Guidelines, Training and Code... Click Here


PROJECT TITLE : High-Performance Accurate and Approximate Multipliers for FPGA-based Hardware Accelerators ABSTRACT: In a wide variety of applications, including image and video processing and machine learning, multiplication
PROJECT TITLE : Local Kernels That Approximate Bayesian Regularization and Proximal Operators ABSTRACT: Kernel-based filtering, such as the bilateral filter and non-local means (as well as many others), is linked to broader variational
PROJECT TITLE :Low-power Implementation of Mitchell's Approximate Logarithmic Multiplication for Convolutional Neural Networks - 2018ABSTRACT:This paper proposes an occasional-power implementation of the approximate logarithmic
PROJECT TITLE :Low-Power Approximate Multipliers Using Encoded Partial Products and Approximate Compressors - 2018ABSTRACT:Approximate computing has been thought of to boost the accuracy-performance tradeoff in error-tolerant
PROJECT TITLE :Systematic Design of an Approximate Adder: The Optimized Lower Part Constant-OR Adder - 2018ABSTRACT:Exploiting the tradeoff between accuracy and hardware cost incorporates a tremendous potential to boost the efficiency

Ready to Complete Your Academic MTech Project Work In Affordable Price ?

Project Enquiry