Technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen1 B.D. Theelen Architecture Design of a Scalable Single-Chip Multi-Processor.

Slides:



Advertisements
Similar presentations
VHDL Design of Multifunctional RISC Processor on FPGA
Advertisements

Technische universiteit eindhoven 1 Problem 16: Design-space Exploration Jeroen Voeten, Bart Theelen Eindhoven University of Technology Embedded Systems.
Technische universiteit eindhoven 20 October 2001www.ics.ele.tue.nl/~btheelen1 Performance Modeling in the Large: A Case Study B.D. Theelen.
Simulation of Feedback Scheduling Dan Henriksson, Anton Cervin and Karl-Erik Årzén Department of Automatic Control.
Nios Multi Processor Ethernet Embedded Platform Final Presentation
Computer Architecture and Organization
Evaluation of On-Chip Interconnect Architectures for Multi-Core DSP Students : Haim Assor, Horesh Ben Shitrit 2. Shared Bus 3. Fabric 4. Network on Chip.
1 Operating Systems Input/Output Management. 2 What is the I/O System A collection of devices that different sub- systems of a computer use to communicate.
Technische universiteit eindhoven PROGRESS 11 December 2002www.ics.ele.tue.nl/~btheelen1 Performance Modelling of Complex Hardware/Software Systems B.D.
© 2003 Xilinx, Inc. All Rights Reserved Course Wrap Up DSP Design Flow.
Technische universiteit eindhoven November 2000Ad Verschueren and Bart Theelen1 The Multi Micro Processor Eindhoven.
Mikael Collin Mälardalen University 1 SoCrates -A Multiprocessor SoC in 40 days Mikael Collin Co-authors: Raimo Haukilahti, Mladen Nikitovic, Joakim Adomat.
1 Scaleable Architecture for Real-Time Applications, SARA Lennart Lindh, Tommy Klevin and Johan Furunäs, Department of Computer Engineering (IDT), Mälardalens.
A Sample RTOS Presentation 4 Group A4: Sean Hudson, Manasi Kapadia Syeda Taib.
Slides Prepared from the CI-Tutor Courses at NCSA By S. Masoud Sadjadi School of Computing and Information Sciences Florida.
Real-Time Library: RTX
1/1/ / faculty of Electrical Engineering eindhoven university of technology Architectures of Digital Information Systems Part 1: Interrupts and DMA dr.ir.
1/1/ / faculty of Electrical Engineering eindhoven university of technology Processor support devices Part 1:Interrupts and shared memory dr.ir. A.C. Verschueren.
1/1/ /e/e eindhoven university of technology Microprocessor Design Course 5Z008 Dr.ir. A.C. (Ad) Verschueren Eindhoven University of Technology Section.
An introduction to: The uRT51 Microprocessor and Real-Time Programming Suite.
- the new generation realtime operating system For embedded and fault tolerant applications.
1/1/ / faculty of Electrical Engineering eindhoven university of technology Introduction Part 3: Input/output and co-processors dr.ir. A.C. Verschueren.
Computer Systems/Operating Systems - Class 8
International Workshop on Satellite Based Traffic Measurement Berlin, Germany September 9th and 10th 2002 TECHNISCHE UNIVERSITÄT DRESDEN Onboard Computer.
Processor history / DX/SX SX/DX Pentium 1997 Pentium MMX
© ABB Group Jun-15 Evaluation of Real-Time Operating Systems for Xilinx MicroBlaze CPU Anders Rönnholm.
DISTRIBUTED CONSISTENCY MANAGEMENT IN A SINGLE ADDRESS SPACE DISTRIBUTED OPERATING SYSTEM Sombrero.
INTRODUCTION OS/2 was initially designed to extend the capabilities of DOS by IBM and Microsoft Corporations. To create a single industry-standard operating.
Configurable System-on-Chip: Xilinx EDK
Chapter 13 Embedded Systems
University College Cork IRELAND Hardware Concepts An understanding of computer hardware is a vital prerequisite for the study of operating systems.
Figure 1.1 Interaction between applications and the operating system.
Operating Systems CS208. What is Operating System? It is a program. It is the first piece of software to run after the system boots. It coordinates the.
A. Frank - P. Weisberg Operating Systems Introduction to Tasks/Threads.
1 Chapter 13 Embedded Systems Embedded Systems Characteristics of Embedded Operating Systems.
HARDWARE SUPPORT FOR REAL TIME OPERATING SYSTEMS A presentation by: Jake Swart.
Chapter 18 Multicore Computers
CHAPTER 3 TOP LEVEL VIEW OF COMPUTER FUNCTION AND INTERCONNECTION
Real-Time Operating Systems for Embedded Computing 李姿宜 R ,06,10.
Operating Systems. Definition An operating system is a collection of programs that manage the resources of the system, and provides a interface between.
FPGA (Field Programmable Gate Array): CLBs, Slices, and LUTs Each configurable logic block (CLB) in Spartan-6 FPGAs consists of two slices, arranged side-by-side.
I/O Computer Organization II 1 Interconnecting Components Need interconnections between – CPU, memory, I/O controllers Bus: shared communication channel.
EEE440 Computer Architecture
An Architecture and Prototype Implementation for TCP/IP Hardware Support Mirko Benz Dresden University of Technology, Germany TERENA 2001.
ECEG-3202 Computer Architecture and Organization Chapter 3 Top Level View of Computer Function and Interconnection.
Development of Programmable Architecture for Base-Band Processing S. Leung, A. Postula, Univ. of Queensland, Australia A. Hemani, Royal Institute of Tech.,
RTX - 51 Objectives  Resources needed  Architecture  Components of RTX-51 - Task - Memory pools - Mail box - Signals.
Different Microprocessors Tamanna Haque Nipa Lecturer Dept. of Computer Science Stamford University Bangladesh.
1 Hardware/Software Co-Design Final Project Emulation on Distributed Simulation Co-Verification System 陳少傑 教授 R 黃鼎鈞 R 尤建智 R 林語亭.
Chapter 13 – I/O Systems (Pgs ). Devices  Two conflicting properties A. Growing uniformity in interfaces (both h/w and s/w): e.g., USB, TWAIN.
Computer Organization Instruction Set Architecture (ISA) Instruction Set Architecture (ISA), or simply Architecture, of a computer is the.
Different Microprocessors Tamanna Haque Nipa Lecturer Dept. of Computer Science Stamford University Bangladesh.
Chapter 3 System Buses.  Hardwired systems are inflexible  General purpose hardware can do different tasks, given correct control signals  Instead.
1 Device Controller I/O units typically consist of A mechanical component: the device itself An electronic component: the device controller or adapter.
Internal Logic Analyzer Characterization presentation By: Moran Katz and Zvika Pery Mentor: Moshe Porian Dual-semester project Spring 2012.
Unit - I Real Time Operating System. Content : Operating System Concepts Real-Time Tasks Real-Time Systems Types of Real-Time Tasks Real-Time Operating.
Outlines  Introduction  Kernel Structure  Porting.
Configuring pacemaker while 2kms away. Person is travelling in driverless car.
Programmable Logic Devices
Architectures of Digital Information Systems Part 1: Interrupts and DMA dr.ir. A.C. Verschueren Eindhoven University of Technology Section of Digital.
UNIT – Microcontroller.
System On Chip.
Derek Chiou The University of Texas at Austin
Course Agenda DSP Design Flow.
Multiprocessor Introduction and Characteristics of Multiprocessor
Multithreaded Programming
Operating System Introduction.
ADSP 21065L.
Presentation transcript:

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen1 B.D. Theelen Architecture Design of a Scalable Single-Chip Multi-Processor

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen2 Overview Introduction MµP Features System Architecture Hardware RTOS Example Configuration Experimental Results Conclusions

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen3 Introduction Architecture Platforms for Real-Time Embedded Systems Scalable, Customisable, Reusable Parallel Execution of Various Tasks Configurable Set of Application-Dedicated Processor Cores Customisability + Parallel + Scalable + Reusable  Configurable Set of Application-Dedicated Processor Cores (Scalable Number of Identical) General-Purpose Processor Core(s) Flexibility + (Parallel + Scalable) + Reusable  (Scalable Number of Identical) General-Purpose Processor Core(s) SoC technology enables embedding both on Single-Chip flexiblescalable Involves flexible and scalable Interconnects and Memory Architecture Examples: TriMedia, SpaceCake

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen4 Real-Time Environment Architecture Platforms for Real-Time Embedded Systems Deadlines, Task Priorities, Impact of Overhead fast dealing with task priorities Involves fast Interconnects and Memory Architecture capable of dealing with task priorities Multi-Micro Processor (MμP) Scalable Number of Identical General-Purpose Master ProcessorsConfigurable Set of Shared Application-Dedicated Co- processors Combines Scalable Number of Identical General-Purpose Master Processors with Configurable Set of Shared Application-Dedicated Co- processors and Hardware RTOS Kernel a Hardware RTOS Kernel to reduce task switching overhead Software RTOS KernelMµP Hardware RTOS Kernel 100+ clocks16 clocks

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen5 MµP Features True parallel execution of tasks independently –Master Processors execute tasks independently extendable –Instruction Set is extendable Only 1/16 th of instruction space is executed by Master Processors Remainder is split over up to 15 different Co-processor types Co-processor type determines actual use of instruction space scalable –Number of Co-processors of certain type is scalable On-chip RTOS Kernel –Transparent priority-based multi-tasking –Transparent priority-based multi-tasking over Master Processors fast –Hardware support for fast task switches –Communication and synchronisation –Communication and synchronisation between (local and remote) tasks (Counting) semaphores, mailboxes, pipes –Extended event handling –Extended event handling mechanism instead of interrupts Uses counting semaphores

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen6 System Architecture Master Processors n n Shared Co- Processors m.y FPU m.y FPU 2.x LSU 2.x LSU m.1 FPU m.1 FPU 1 TCU 1 TCU 2.1 LSU 2.1 LSU Function Switch Result Switch Task Assignment Event Inputs Chip Boundary L1 I$ L2 I$ Arbiter Memory M  P Network MultiPort D$ Register D$ Task Control Unit Hardware RTOS Kernel

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen7 Design Issues On-Chip Interconnects –Cyclic path of instructions and results non-blockingInterconnects are non-blocking accept resultsscoreboardingMaster processors accept results at all times and implement scoreboarding –Function Switch routes on co-processor type number high/low priorityFair arbitration with high/low priority based on task priority and request age –Result Switch routes on task number FCFS arbitration without priorities one clock –Perform routing functionality in one clock Memory Architecture –Separated instruction and data path Two-level instruction cache architecture with round-robin arbitration multi port data cacheShared multi port data cache = data cache with statistically multiplexed banks Round-robin arbitration between accesses for different paths No real cache coherency problems

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen8 Hardware RTOS TCU Core Executive Function Switch Function Rx Result Switch Result Tx Master Processors Task Scheduler Task Scheduler Sorted Task List Sorted Task List Control Space Event Inputs Event Detect Timers TCU Network Management Link Network Switch MultiPort D$ Arbiter Task Admin Resource Admin Resource Data

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen9 Design Issues Task Management creating, terminating, delaying, suspending restarting changing priority –Commands for creating, terminating, delaying, suspending and restarting tasks and for changing priority –Tasks of equal priority time share master processors available to them –Task switching accelerated by specialised cache storing volatile contexts Transparent Communication activating, deactivating, reading writing –Commands for activating, deactivating, reading and writing resources –Counting semaphores, mailboxes and pipes in hardware –Network Manager shields tasks from MµP network –Tasks can access any resource in the MµP network Extended Event Handling activatingdeactivating –Commands for activating and deactivating event inputs –Event inputs are coupled to counting semaphores –Involved semaphore might not be in same MµP where the task resides

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen10 Example Configuration (Mini MµP) By V.R. Suárez Two 8048 ISA compatible Master Processors 8048 compatible I/O and Timers in Co-Processors 1 clock Function Switch and Result Switch On-chip 2kB Instruction ROM and 1kB Data RAM 1 clock Register D$ enabling Task Switches in 1 clock TCU Co-Processor -15 user-definable tasks -32 binary semaphores -Timers and Interrupts supported as events for predefined tasks 1 clock -all commands executed in 1 clock

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen11 Experimental Results (Mini MµP) IDaSSMini MµP designed using IDaSS –Interactive Design and Simulation System –Automatic generation of synthesisable VHDL or Verilog Mini MµP implemented in Xilinx Spartan-II 200 FPGA –Uses 42% of memory area and 83% of gate area –Total gate count of 141k –Runs at 25 Mhz (expect over 30Mhz for optimised version) –Critical path is 14 gates (in Master Processor core) –Next critical path in TCU Co-Processor

technische universiteit eindhoven 4 September 2002www.ics.ele.tue.nl/~btheelen12 Conclusions Multi Micro Processor (MµP) Architecture –Scalable Single-Chip Multi-Processor –Intended for Real-Time Embedded Systems –On-chip RTOS Kernel with hardware support for fast Task Switches Design issues –On-chip Interconnects –Memory Architecture –Hardware RTOS Task Management Transparent Communication Extended Event Handling Results –Mini version of MµP with two 8048 ISA compatible Master Processors