Design of Power-Efficient Posit Multiplier

Also Available Domains Arithmetic Core|Xilinx Vivado

Project Code :TVPGTO375

Objective

The major contribution of this work is to implement a power-efficient posit multiplier architecture which divides the mantissa multiplier into small portions. Thus the proposed method is suitable to be used in any low power posit arithmetic unit designs

Abstract

In this project, an efficient scheme is presented to correct limited magnitude errors on multilevel cell memories. The proposed scheme combines the use of a low redundancy SECDAEC code in the two lowest bits of the cell with IP bits to correct up to magnitude-3 symmetric errors. The SEC-DAEC code is used to locate the cell in error and correct errors on some bits.

The IP is used to identify the error pattern on the remaining bits. The proposed IP-DAEC scheme provides a simple implementation that achieves a low delay with a reduced number of parity bits.

The proposed scheme has been compared to existing schemes that have similar capability showing an advantage of memory redundancy, as well as a lower encoder/decoder overhead in most cases. The synthesis and simulation results are carried out using Xilinx ISE 14.7

Keywords: Error Correction Codes, Multilevel cell memories, limited magnitude errors, SEC-DAEC codes

NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.

Block Diagram

Specifications

Software Requirements:

Xilinx ISE 14.7
HDL: Verilog

Hardware Requirements:

Microsoft® Windows XP
Intel® Pentium® 4 processor or Pentium 4 equivalent with SSE support
512 MB RAM
100 MB of available disk space

Learning Outcomes

Basics of Digital Electronics
FPGA design Flow
Introduction to Verilog Coding.
Different modeling styles in Verilog

Data Flow modeling
Structural modeling
Behavioral modeling
Mixed level modeling

Introduction to Posit Multiplier
Knowledge on floating point arithmetic
Basics of Leading one detector circuit
Knowledge on Leading zero detector
Knowledge on Comparators
Knowledge on carry propagation adder
Concept of Rounding technique
How to achieve high speed, Low power and Area efficiency?
Scope of approximation concept in today’s world
Applications in real time
Xilinx ISE 14.7 for design and simulation
Generation of Netlist
Solution providing for real time problems
Project Development Skills:

Problem Analysis Skills
Problem Solving Skills
Logical Skills
Designing Skills
Testing Skills
Debugging Skills
Presentation Skills
Thesis Writing Skills

Demo Video

Request Video

Front End Domains

DSP Core
Communications and Crypto Core
Design for Testability
Arithmetic Core
Nano Technology

Back End Domains

Nano Technology
Core Memories
Transistor Logic
Low Power VLSI

Tools

Cadence EDA
Xilinx Vivado
Xilinx ISE
Tanner EDA
FPGA

Others

Matlab Interfacing