Farhan Mohamed Ali W21 Jigar Vora W22 Sonali Kapoor W23 Avni Jhunjhunwala W24 - PowerPoint PPT Presentation

About This Presentation
Title:

Farhan Mohamed Ali W21 Jigar Vora W22 Sonali Kapoor W23 Avni Jhunjhunwala W24

Description:

Bit slicing the adder in the layout. 9. 9. Adder Schematic. 10. 10. Adder Schematic Simulation ... Adder Bit Slice Layout. 12. 12. 0.13. 475p. 500. 100 ... – PowerPoint PPT presentation

Number of Views:81
Avg rating:3.0/5.0
Slides: 19
Provided by: avn2
Category:

less

Transcript and Presenter's Notes

Title: Farhan Mohamed Ali W21 Jigar Vora W22 Sonali Kapoor W23 Avni Jhunjhunwala W24


1
Presentation 8 MAD MAC 525
Farhan Mohamed Ali (W2-1)Jigar Vora
(W2-2)Sonali Kapoor (W2-3) Avni Jhunjhunwala
(W2-4)
W2
Design Manager Zack Menegakis
22nd March, 2006 Functional Block and Simulations
Project Objective Design a crucial part of a GPU
called the Multiply Accumulate Unit (MAC) which
will revolutionize graphics.
2
MAD MAC 525 Status
  • Project chosen
  • Specifications defined
  • Architecture
  • Design
  • Behavioral Verilog
  • Testbenches
  • Verilog Gate Level Design
  • Floor plan
  • Schematics and Analog Verifications
  • Layout of basic gates and small blocks
  • Large block layouts, extractions, LVS,
    simulations (in progress)
  • Spring Break ?
  • To be done
  • Full chip layout and simulation

3
Block Diagram
Input
Input
Input
16
16
16
5
RegArray A
RegArray B
RegArray C
10
10
10
5
5
Multiplier
Exp Calc
Align
1
5
14
22
35
Control Logic Sign Dtrmin
Leading 0 Anticipator
Adder/Subtractor
36
4
Normalize
14
5
1
Round
Reg Y
10
5
Output
16
15
1
1
Ovf Checker
4
Design Decisions
  • Pipelining Stages Add another stage in
    multiplier since adder is very fast.
  • Projected speed is at least 400 MHz
  • Exceeds the design goal of 300MHz ?

5
Pipelining Stages
Reg C
Multiplier
Reg A
Exp Calc
Reg B
Pipeline Reg
Pipeline Reg
Pipeline Reg
Align C
Pipeline Reg
Pipeline Reg
Adder
Ld Zero
Pipeline Reg
Round
Normalize
Overflow checker

Reg Y
6
Timing Diagram
7
New Floorplan
8
Design Decisions
  • Pipelining Stages Add another stage in
    multiplier since adder is very fast.
  • Projected speed is at least 400 MHz
  • Exceeds the design goal of 300MHz ?
  • Optimized adder design which implements carry
    look ahead architecture
  • Propagation delay of around 800ps (1250MHz)
  • Bit slicing the adder in the layout

9
Adder Schematic
10
Adder Schematic Simulation
11
Adder Bit Slice Layout
12
(No Transcript)
13
Optimized Round Schematic
14
Normalize Layout
15
Align Layout
16
Align Simulation
17
Exponents progress
18
Questions??
Write a Comment
User Comments (0)
About PowerShow.com