High Level Synthesis. Tasks of the Designer/Manager These ideas apply to the design itself, must be reproduced in the chip.

Slides:



Advertisements
Similar presentations
ECE 667 Synthesis and Verification of Digital Circuits
Advertisements

Linear Programming Sensitivity Analysis How will a change in a coefficient of the objective function affect the optimal solution? How will a change in.
Presenter MaxAcademy Lecture Series – V1.0, September 2011 Stream Scheduling.
Courseware Integer Linear Programming approach to Scheduling Sune Fallgaard Nielsen Informatics and Mathematical Modelling Technical University of Denmark.
Introduction to Data Flow Graphs and their Scheduling Sources: Gang Quan.
Winter 2005ICS 252-Intro to Computer Design ICS 252 Introduction to Computer Design Lecture 5-Scheudling Algorithms Winter 2005 Eli Bozorgzadeh Computer.
Reconfigurable Computing S. Reda, Brown University Reconfigurable Computing (EN2911X, Fall07) Lecture 10: RC Principles: Software (3/4) Prof. Sherief Reda.
Interactive System for Pulverized Coal Combustion Visualization with Fluid Simulator Marek Gayer, Pavel Slavík and František Hrdlička Department of Computer.
Performance Visualizations using XML Representations Presented by Kristof Beyls Yijun Yu Erik H. D’Hollander.
Courseware High-Level Synthesis an introduction Prof. Jan Madsen Informatics and Mathematical Modelling Technical University of Denmark Richard Petersens.
Simulated-Annealing-Based Solution By Gonzalo Zea s Shih-Fu Liu s
Courseware Force-Directed Scheduling Sune Fallgaard Nielsen Informatics and Mathematical Modelling Technical University of Denmark Richard Petersens Plads,
ICS 252 Introduction to Computer Design
ECE Synthesis & Verification - LP Scheduling 1 ECE 667 ECE 667 Synthesis and Verification of Digital Circuits Scheduling Algorithms Analytical approach.
Threshold Voltage Assignment to Supply Voltage Islands in Core- based System-on-a-Chip Designs Project Proposal: Gall Gotfried Steven Beigelmacher 02/09/05.
Center for Embedded Computer Systems University of California, Irvine and San Diego SPARK: A Parallelizing High-Level Synthesis.
Introduction to Data Flow Graphs and their Scheduling Sources: Gang Quan.
Linear Inequalities in one variable Inequality with one variable to the first power. for example: 2x-3
Universität Dortmund  P. Marwedel, Univ. Dortmund, Informatik 12, 2003 Hardware/software partitioning  Functionality to be implemented in software.
Graph an equation in standard form
7.1 SOLVING SYSTEMS BY GRAPHING The students will be able to: Identify solutions of linear equations in two variables. Solve systems of linear equations.
Course Outline DayContents Day 1 Introduction Motivation, definitions, properties of embedded systems, outline of the current course How to specify embedded.
Section 6-3: Standard Form of a Linear Equation SPI 22C: select the graph that represents a given linear function Objective: Graph and write linear equations.
Linear Equations, Inequalities, and Absolute Value
CAD Techniques for IP-Based and System-On-Chip Designs Allen C.-H. Wu Department of Computer Science Tsing Hua University Hsinchu, Taiwan, R.O.C {
Software Pipelining for Stream Programs on Resource Constrained Multi-core Architectures IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEM 2012 Authors:
Thinking Mathematically Algebra: Graphs, Functions and Linear Systems 7.1 Graphing and Functions.
High Performance Scalable Base-4 Fast Fourier Transform Mapping Greg Nash Centar 2003 High Performance Embedded Computing Workshop
13.6 MATRIX SOLUTION OF A LINEAR SYSTEM.  Examine the matrix equation below.  How would you solve for X?  In order to solve this type of equation,
1 Towards Optimal Custom Instruction Processors Wayne Luk Kubilay Atasu, Rob Dimond and Oskar Mencer Department of Computing Imperial College London HOT.
Introduction to Algorithms (2 nd edition) by Cormen, Leiserson, Rivest & Stein Chapter 1: The Role of Algorithms in Computing (slides by N. Adlai A. DePano)
L11: Lower Power High Level Synthesis(2) 성균관대학교 조 준 동 교수
UNIT 1 Introduction. 1-2 OutlineOutline n Course Topics n Microelectronics n Design Styles n Design Domains and Levels of Abstractions n Digital System.
- 1 - EE898_HW/SW Partitioning Hardware/software partitioning  Functionality to be implemented in software or in hardware? No need to consider special.
Learning Task/Big Idea: Students will learn how to find roots(x-intercepts) of a quadratic function and use the roots to graph the parabola.
Solve each equation for y. 1. 3x + y = 52. y – 2x = x – y = x + 4y = 85. 9y + 3x = 16. 5y – 2x = 4 Clear each equation of decimals x.
Chapter 21 Exact Differential Equation Chapter 2 Exact Differential Equation.
3.6 Solving Absolute Value Equations and Inequalities
Modeling and Visualization of Combustion Using Fluid Simulator and Particle Systems Ing. Marek Gayer (supervised by prof. Pavel Slavík) Computer Graphics.
Hough transform and geometric transform
Differential Equations Linear Equations with Variable Coefficients.
Graphing Linear Equations 4.2 Objective 1 – Graph a linear equation using a table or a list of values Objective 2 – Graph horizontal or vertical lines.
Entry Task 1.Evaluate 2xy + 3(x + y) when x = 4 and y = 7 Evaluate when a = -3 and b = ab 3. 12a + (b - a - 4)
Dynamic visualisation of the combustion processes in boilers Marek Gayer Computer Graphics Group Department of Computer Science and.
Algebra 1 Section 5.6 Write linear equations in standard form Recall: Forms of linear equations Standard Slope-intercept Point-slope Graph 4x – 3y = 6.
S5.40. Module Structure 30% practical tests / 70% written exam 3h lectures / week (except reading week) 3 x 2h of computer labs (solving problems practicing.
3.3 – Solving Systems of Inequalities by Graphing
Rational Functions (Algebraic Fractions)
Notes Over 4.2 Is a Solution Verifying Solutions of an Equation
Solve a system of linear equation in two variables
Solve System by Linear Combination / Addition Method
Notes Over 11.8 Cross Multiplying
STUDY AND IMPLEMENTATION
Physics-based simulation for visual computing applications
Transformations.
Graphing Linear Equations
Standard Form Examples 3x + y = 5 -2x + y = 10 x – y = 6
What is the x-intercept?
Writing Linear Equations in Standard Form
HIGH LEVEL SYNTHESIS.
5.1 Solving Systems of Equations by Graphing
Systems of Equations Solve by Graphing.
Jeopardy Final Jeopardy Solving Equations Solving Inequalities
5-3 Standard Form Hubarth Algebra.
Example 2B: Solving Linear Systems by Elimination
Review Plot (3,5) (-4,3) (0,4) (-2,0) Identify the coordinate.
Solving a System of Linear Equations
Intercepts of a Line Intercepts are the points at which the graph intersects the x-axis or the y-axis. Since an intercept intersects the x-axis or the.
A Visual Way to the World of Parallel Computations
Reconfigurable Computing (EN2911X, Fall07)
Presentation transcript:

High Level Synthesis

Tasks of the Designer/Manager These ideas apply to the design itself, must be reproduced in the chip

Aspects of Pipelining

A view at the synthesis and design You may optimize on focus of an aspect at one time

The most important aspect of design is how you deal with time

Dealing with space is the result of dealing with time

Parameters of design

Floorplanning

Fighting complexity

Example: Partial Differential Equation

2 ALU/* 1 ALU 2 * Earliest Deadline (ASAP) ALU/* * *

Another ALU

Hardware Solution number 3 Slow and cheap 1 ALU and 1 multiplier 7 time steps + <

ALAP ALU/* * ALU 2 ALU/* 2 * 1 ALU

There are free Integer Linear Programming Packages on the internet, you can buy one at PSU bookstore

Harmony and Balance in Design

The Kung Systolic Array as an example of high-level structural synthesis, universal protype CAD tools: Simulation and visual simulation Code generation, Array design Optimization

Spatial Computing

Conclusion: Steps lead to design This year project is on Hough Transform

Problems for students to think about. Recall and discuss examples of pipelining. Ford’s pipelining and other metaphores from social life or industry that may be used in high level and system design. (how many workers to speed-up mowing the lawn). How to implement a long convolution – think about all possible methods. Discuss how you can solve scheduling and allocation using graphs and moving their nodes vertically and horizontally. Use first the differential equation example, next generalize to new graphs. Relation of floor-planning and high level synthesis – a new perspective. Computing in space – one, two and three directions. Discuss ray-tracing and other similar applications in which the computer mimicks physics in space.