01OC2000 Slide 1 © 2000 General Motors Corporation James B. Kolhoff Real Time Scheduling Issues in Powertrain Controls James B. Kolhoff.

Slides:



Advertisements
Similar presentations
Developed by Reneta Barneva, SUNY Fredonia
Advertisements

1 Chapter 1 Why Parallel Computing? An Introduction to Parallel Programming Peter Pacheco.
Leveraging Success Through Effective Project Management Tools and Processes Charlie Schloff Manager, C3P Project Office Ford Motor Company File: MPUG 2000.
OBP Research Oy for simpler creation of embedded systems.
CHAPTER 1 THE 8051 MICROCONTROLLERS. Microcontroller vs. General- Purpose Microprocessor General-purpose microprocessors have ◦ No RAM ◦ No ROM ◦ No I/O.
Optimizations for a Simulator Construction System Supporting Reusable Components David A. Penry and David I. August The Liberty Architecture Research Group.
Chapter 10 Schedule Your Schedule. Copyright 2004 by Pearson Education, Inc. Identifying And Scheduling Tasks The schedule from the Software Development.
MotoHawk Training Model-Based Design of Embedded Systems.
Chapter 13 Embedded Systems
Technical Architectures
Vertically Integrated Analysis and Transformation for Embedded Software John Regehr University of Utah.
Behavioral Design Outline –Design Specification –Behavioral Design –Behavioral Specification –Hardware Description Languages –Behavioral Simulation –Behavioral.
Analysis of power dissipation in embedded systems using real-time operating systems Dick, R.P. Lakshminarayana, G. Raghunathan, A. Jha, N.K. Dept. of Electr.
CS350/550 Software Engineering Lecture 1. Class Work The main part of the class is a practical software engineering project, in teams of 3-5 people There.
1 SOFTWARE QUALITY ASSURANCE Basic Principles. 2 Requirements System Design Detailed Design Implementation Installation & Testing Maintenance SW Quality:
SOFTWARE ENGINEERING for REAL-TIME SYSTEMS (© J.E.Cooling 2003) Introduction to real-time systems - slide 1 Software engineering for real-time systems.
1 Embedded Computer System Laboratory RTOS Modeling in Electronic System Level Design.
Approaches to ---Testing Software Some of us “hope” that our software works as opposed to “ensuring” that our software works? Why? Just foolish Lazy Believe.
H-1 Network Management Network management is the process of controlling a complex data network to maximize its efficiency and productivity The overall.
Digital Signal Processors for Real-Time Embedded Systems By Jeremy Kohel.
© VESP International Pty Limited To Contents Slide CLICK to advance slides/ bullet points within slides Integrated Master Planner An Overview.
Supporting tools in an IT Project & Portfolio Management environment Ann Van Belle -
Overview of EASE results 2009 Prof. Per Runeson – Director.
SAMANVITHA RAMAYANAM 18 TH FEBRUARY 2010 CPE 691 LAYERED APPLICATION.
MathCore Engineering AB Experts in Modeling & Simulation WTC.
1 Powering Financial Markets © Copyright 2011 Path Solutions All Rights Reserved i SHRAQ*Invest.
Role-Based Guide to the RUP Architect. 2 Mission of an Architect A software architect leads and coordinates technical activities and artifacts throughout.
Design Verification An Overview. Powerful HDL Verification Solutions for the Industry’s Highest Density Devices  What is driving the FPGA Verification.
1 Developing Custom Modeling Tools at GM with embedded Validation James A. Bullard General Motors.
SOFTWARE DESIGN (SWD) Instructor: Dr. Hany H. Ammar
University of Virginia Software Development Processes (CS340 John Knight 2005) 1 Software Development Processes.
Xilinx Programmable Logic Design Solutions Version 2.1i Designing the Industry’s First 2 Million Gate FPGA Drop-In 64 Bit / 66 MHz PCI Design.
Plant Modeling for Powertrain Control Design Modelica Automotive Workshop Dearborn, MI November 19, 2002 Dr. Larry Michaels GM Powertrain Controls Engineering.
1 ENERGY 211 / CME 211 Lecture 26 November 19, 2008.
Software Dynamics: A New Method of Evaluating Real-Time Performance of Distributed Systems Janusz Zalewski Computer Science Florida Gulf Coast University.
Real-Time Operating Systems for Embedded Computing 李姿宜 R ,06,10.
Chapter 101 Multiprocessor and Real- Time Scheduling Chapter 10.
MERCURY BUSINESS PROCESS TESTING. AGENDA  Objective  What is Business Process Testing  Business Components  Defining Requirements  Creation of Business.
Ethics of Software Testing Thomas LaToza CS 210 Final Presentation 12 / 2 / 2002.
© 2012 xtUML.org Bill Chown – Mentor Graphics Model Driven Engineering.
Robotics & Engineering Design Projective Management Chin-Sung Lin Eleanor Roosevelt High School.
Encapsule Systems Reducing Software Development Costs.
Accessing I/O Devices Processor Memory BUS I/O Device 1 I/O Device 2.
BridgePoint Integration John Wolfe / Robert Day Accelerated Technology.
CSC480 Software Engineering Lecture 10 September 25, 2002.
CS 484 Designing Parallel Algorithms Designing a parallel algorithm is not easy. There is no recipe or magical ingredient Except creativity We can benefit.
EGR 115 Introduction to Computing for Engineers Introduction to Computer Programming Wednesday 27 Aug 2014 EGR 115 Introduction to Computing for Engineers.
CASE (Computer-Aided Software Engineering) Tools Software that is used to support software process activities. Provides software process support by:- –
CSCI1600: Embedded and Real Time Software Lecture 33: Worst Case Execution Time Steven Reiss, Fall 2015.
Integrating DAQ, IMAQ, and Motion Joe Hays Applications Engineer Thu 11:30a, 2:00p and 4:45p Red River (4B) Joe Hays Applications Engineer.
CSC 480 Software Engineering Test Planning. Test Cases and Test Plans A test case is an explicit set of instructions designed to detect a particular class.
What is a Microprocessor ? A microprocessor consists of an ALU to perform arithmetic and logic manipulations, registers, and a control unit Its has some.
CSCI1600: Embedded and Real Time Software Lecture 23: Real Time Scheduling I Steven Reiss, Fall 2015.
Real-Time Systems, Events, Triggers. Real-Time Systems A system that has operational deadlines from event to system response A system whose correctness.
03/30/031 ECE Digital System Design & Synthesis Lecture Design Partitioning for Synthesis Strategies  Partition for design reuse  Keep related.
1/50 University of Turkish Aeronautical Association Computer Engineering Department Ceng 541 Introduction to Parallel Computing Dr. Tansel Dökeroğlu
1 Chapter 2 SW Process Models. 2 Objectives  Understand various process models  Understand the pros and cons of each model  Evaluate the applicability.
7 November 2006Program Management Basics Purdue FIRST Programs Slide 1 Program Management Basics Purdue FIRST Programs Chris Fultz Rolls-Royce Corporation.
Embedded Systems. What is Embedded Systems?  Embedded reflects the facts that they are an integral.
Parallel Objects: Virtualization & In-Process Components
The University of Adelaide, School of Computer Science
Chapter 1: The 8051 Microcontrollers
CPSC 531: System Modeling and Simulation
CSCI1600: Embedded and Real Time Software
SAMANVITHA RAMAYANAM 18TH FEBRUARY 2010 CPE 691
Computer Evolution and Performance
AIMS Equipment & Automation monitoring solution
Mark McKelvin EE249 Embedded System Design December 03, 2002
CHAPTER 1 THE 8051 MICROCONTROLLERS
CSCI1600: Embedded and Real Time Software
Presentation transcript:

01OC2000 Slide 1 © 2000 General Motors Corporation James B. Kolhoff Real Time Scheduling Issues in Powertrain Controls James B. Kolhoff Engineering Group Manager Front Wheel Drive Controller Team General Motors Powertrain

01OC2000 Slide 2 © 2000 General Motors Corporation James B. Kolhoff Overview of Presentation n GMPT Electronics Integration & SW - Group & Product n Scheduling Requirements and Problem n Solution n Distributed architecture n Next step

01OC2000 Slide 3 © 2000 General Motors Corporation James B. Kolhoff Group and Product Background Group GMPT is a division of General Motors, responsible for engine, transmission, powertrain controls engineering and manufacture Electronics Integration & Software (EI&S) is a product engineering team responsible for the electronics and software for powertrain controls Product EI&S end product is an embedded microprocessor control module(s) that controls and diagnoses engine, transmission, and vehicle functions. n Multiple end products (ECM, TCM, PCM) with different feature content (internal GM and external customers) n Multiple controller and compiler suppliers n Other vehicle module interfaces n Development and production tool interfaces n Controller: 32bit uc, 1Mb ROM, 150+ pins

01OC2000 Slide 4 © 2000 General Motors Corporation James B. Kolhoff Scheduling requirements n Two categories of task - time synchronous, engine event synchronous u Time: 3.125ms, 6.25, 12.5, 25, 100 ms u Engine: crankshaft synchronous, cam synchronous n The engine event tasks cause the processing power to be consumed in direct proportion to engine speed n Engine event synchronous tasks have harder deadlines and higher priorities than time based tasks u 8 cylinder engine engine, event sw task execution time 1ms u 600 rpm: 25ms event rate, 4% available processor thruput u 7000 rpm: 2.1ms event rate, 48% available processor thruput

01OC2000 Slide 5 © 2000 General Motors Corporation James B. Kolhoff Task scheduling

01OC2000 Slide 6 © 2000 General Motors Corporation James B. Kolhoff Scheduling Problems n Most critical scheduling problem was task deadlines missed at higher engine speeds n Basic root cause: Limited processing power u Using low cost microprocessor u Low clock speed for EMC performance u Too late in program to make processor change n ROM limited so we can’t do ROM tradeoffs for thruput n Fixed point math operations u Library not optimized for performance n Requirement of ANSI-C for code portability u Not designed for performance n SW Design and Coding Standards u Designed for reuse and readability, not performance

01OC2000 Slide 7 © 2000 General Motors Corporation James B. Kolhoff Solutions applied n Re-design software for improved efficiency u Significant work effort, potential loss of function, repeat verification n Optimize libraries to take advantage of processor specifics u Significant work effort, reduces reuse, increases verification requirements n Revise coding standards to maximize efficiency u At the expense of portability and reuse u Rework and revalidation across large number of engineers n Biggest bang for the buck - dynamic scheduling u Can localize redesign at areas of maximum benefit u Time tasks slower than 25ms rates are insignificant to the problem

01OC2000 Slide 8 © 2000 General Motors Corporation James B. Kolhoff Dynamic scheduling n Objective: Reduce execution requirements at higher engine speeds u Difficult to individually disable or redesign functions n Developed engine speed zones approach u Different function level in each zone u Simplifies coordination of scheduling change n In middle engine speed range, divide function across multiple engine events u Balance load across multiple cylinder events n At highest engine speeds, significantly simplify some functions u Engine states don’t change every cylinder

01OC2000 Slide 9 © 2000 General Motors Corporation James B. Kolhoff Effect of Dynamic Scheduling

01OC2000 Slide 10 © 2000 General Motors Corporation James B. Kolhoff Controller System Topologies PCM Vehicle Electrical System Engine Electrical System Transmission Electrical System ECM TCM Vehicle Electrical System Engine Electrical System Transmission Electrical System Legend Electrical System Control Module Electrical Interface Powertrain Control ModuleEngine/Transmission Control Modules

01OC2000 Slide 11 © 2000 General Motors Corporation James B. Kolhoff Distributed architecture n Controller systems architecture for GMPT is changing to separate engine controller / transmission controller u For reasons of powertrain portfolio management n This architecture reduces the computing power needed in any single controller n Scheduling and thruput still needed to be carefully managed u System partitioning plays a key role u Inter-module Communications uses some of the freed up thruput

01OC2000 Slide 12 © 2000 General Motors Corporation James B. Kolhoff Future n Microprocessor power has grown dramatically over the past 5 years n At the same time, costs have fallen dramatically for this power n With the microprocessors available for the projects planned, thruput will not be the significant problem it has been in the past n Simulation and schedule/thruput budgets are the next steps