DOC PREVIEW
MIT 6 111 - Floating-Point Unit for Numerical Calculations

This preview shows page 1 out of 3 pages.

Save
View full document
View full document
Premium Document
Do you want full access? Go Premium and unlock all 3 pages.
Access to all documents
Download any document
Ad free experience
Premium Document
Do you want full access? Go Premium and unlock all 3 pages.
Access to all documents
Download any document
Ad free experience

Unformatted text preview:

file:///C:/Documents%20and%20Settings/cjt/Desktop/jwalden/6111-presentation/index.htmlA Floating-Point Unit for Numerical CalculationsJeff Walden6.111 Fall 2006Final Project PresentationThe GoalA partially IEEE 754-compatible FPUAddition/subtraction, multiplication, exceptions, and comparisons“Enough” functionalityHardware-based speedupThe goal of my project is to partially implement a floating-point unit, by which I mean ahardware device capable of performing a set of basic mathematical operations onnumbers which can contain fractional parts. The intent is that the final product be usablewithin the context of some other project — a device which must manipulate floating-pointnumbers, such as a CPU or a GPU, could use the unit to handle many commonfloating-point calculations.Time and complexity limitations restrict the functionality which will be implemented toaddition, subtraction, multiplication, comparison values, and support for IEEE exceptions;floating-point arithmetic is a surprisingly complex topic. The goal is “enough”functionality to do most of what you might want to do with floating-point numbers inmost situations — with the speedup afforded by implementation in hardware as amotivation.A Brief DiversionAn IEEE 754 floating-point number (Wikipedia)IEEE 754Floating-points, +/-0, +/-Infinity, NaNExceptions: invalid operation, divide by zero, overflow/underflow, inexactfile:///C:/Documents%20and%20Settings/cjt/Desktop/jwalden/6111-presentation/index.htmlFloating-point exactness and roundingFPU OverviewTest, adder, multiplier, comparison modulesUser InterfaceInputs: buttons and state machine used to modify input floating-pointsevaluating other interfaces for use after initial mockupOutputs: sign bit, exponent, and significand on labkit LEDsTime-permitting, hope to implement a VGA-based displayThe MultiplierThe Adderfile:///C:/Documents%20and%20Settings/cjt/Desktop/jwalden/6111-presentation/index.htmlImplementation StepsMultiplier module1.Concurrently:FPU container module (partial functionality)User interface, first mockup2.Concurrently:Improved user interfaceAdder module3.Other FPU operations (division,


View Full Document

MIT 6 111 - Floating-Point Unit for Numerical Calculations

Documents in this Course
Verilog

Verilog

21 pages

Video

Video

28 pages

Bass Hero

Bass Hero

17 pages

Deep 3D

Deep 3D

12 pages

SERPENT

SERPENT

8 pages

Vertex

Vertex

92 pages

Vertex

Vertex

4 pages

Snapshot

Snapshot

15 pages

Memories

Memories

42 pages

Deep3D

Deep3D

60 pages

Design

Design

2 pages

Frogger

Frogger

11 pages

SkiFree

SkiFree

81 pages

Vertex

Vertex

10 pages

EXPRESS

EXPRESS

2 pages

Labyrinth

Labyrinth

81 pages

Load more
Download Floating-Point Unit for Numerical Calculations
Our administrator received your request to download this document. We will send you the file to your email shortly.
Loading Unlocking...
Login

Join to view Floating-Point Unit for Numerical Calculations and access 3M+ class-specific study document.

or
We will never post anything without your permission.
Don't have an account?
Sign Up

Join to view Floating-Point Unit for Numerical Calculations 2 2 and access 3M+ class-specific study document.

or

By creating an account you agree to our Privacy Policy and Terms Of Use

Already a member?