Towards the Design of Heterogeneous Real-Time Multicore System m5151117 Yumiko Kimezawa February 1, 20131MT2012.

Slides:



Advertisements
Similar presentations
Bus Specification Embedded Systems Design and Implementation Witawas Srisa-an.
Advertisements

Maciej Gołaszewski Tutor: Tadeusz Sondej, PhD Design and implementation of softcore dual processor system on single chip FPGA Design and implementation.
Nios II Processor-Based Self- Adaptive QRS Detection System Institution: Indian Institute of Technology, Kharagpur Participants: Sai Prashanth, Prashant.
MotoHawk Training Model-Based Design of Embedded Systems.
Week 1- Fall 2009 Dr. Kimberly E. Newman University of Colorado.
1 Performed By: Khaskin Luba Einhorn Raziel Einhorn Raziel Instructor: Rivkin Ina Spring 2004 Spring 2004 Virtex II-Pro Dynamical Test Application Part.
A.R. Hertneky J.W. O’Brien J.T. Shin C.S. Wessels Laser Controller One (LC1)
Department of Electrical and Computer Engineering Texas A&M University College Station, TX Abstract 4-Level Elevator Controller Lessons Learned.
Define Embedded Systems Small (?) Application Specific Computer Systems.
Configurable System-on-Chip: Xilinx EDK
Technion – Israel Institute of Technology Department of Electrical Engineering High Speed Digital Systems Lab Project performed by: Naor Huri Idan Shmuel.
ECE Department: University of Massachusetts, Amherst Lab 1: Introduction to NIOS II Hardware Development.
Ethernet Bomber Ethernet Packet Generator for network analysis Oren Novitzky & Rony Setter Advisor: Mony Orbach Started: Spring 2008 Part A final Presentation.
Processor Frequency Setting for Energy Minimization of Streaming Multimedia Application by A. Acquaviva, L. Benini, and B. Riccò, in Proc. 9th Internation.
Ethernet Bomber Ethernet Packet Generator for network analysis Oren Novitzky & Rony Setter Advisor: Mony Orbach Spring 2008 – Winter 2009 Midterm Presentation.
ABACUS: A Hardware-Based Software Profiler for Modern Processors Eric Matthews Lesley Shannon School of Engineering Science Sergey Blagodurov Sergey Zhuravlev.
Classification of Electrocardiogram (ECG) Waveforms for the Detection of Cardiac Problems By Enda Moloney.
PCI-Express Network Sniffer Characterization Presentation Project Period : 2 semesters Students: Neria Wodage Aviel Tubul Advisor: Mony Orbach 17/12/2007.
Engineering 1040: Mechanisms & Electric Circuits Fall 2011 Introduction to Embedded Systems.
Digital Communication Techniques
GallagherP188/MAPLD20041 Accelerating DSP Algorithms Using FPGAs Sean Gallagher DSP Specialist Xilinx Inc.
GPGPU platforms GP - General Purpose computation using GPU
Out-of-Order OpenRISC 2 semesters project Semester A: Implementation of OpenRISC on XUPV5 board Final A Presentation By: Vova Menis-Lurie Sonia Gershkovich.
An FPGA implementation of real-time QRS detection H.K.Chatterjee Dept. of ECE Camellia School of Engineering & Technology Kolkata India R.Gupta, J.N.Bera,
The 6713 DSP Starter Kit (DSK) is a low-cost platform which lets customers evaluate and develop applications for the Texas Instruments C67X DSP family.
EKT303/4 PRINCIPLES OF PRINCIPLES OF COMPUTER ARCHITECTURE (PoCA)
Technion – Israel Institute of Technology Department of Electrical Engineering High Speed Digital Systems Lab Spring 2009.
Optimization of System Performance using OpenMP m Yumiko Kimezawa May 25, 20111RPS.
1.  Project Goals.  Project System Overview.  System Architecture.  Data Flow.  System Inputs.  System Outputs.  Rates.  Real Time Performance.
NetBurner MOD 5282 Network Development Kit MCF 5282 Integrated ColdFire 32 bit Microcontoller 2 DB-9 connectors for serial I/O supports: RS-232, RS-485,
Out-of-Order OpenRISC 2 semesters project Semester A: Implementation of OpenRISC on XUPV5 board Midterm Presentation By: Vova Menis-Lurie Sonia Gershkovich.
Lecture 18 Lecture 18: Case Study of SoC Design ECE 412: Microcomputer Laboratory.
Research Summary and Schedule m Yumiko Kimezawa August 1, 20121RPS.
OS Implementation On SOPC Midterm Presentation Performed by: Ariel Morali Nadav Malki Supervised by: Ina Rivkin.
Adding the TSE component to BANSMOM system and Software Development m Yumiko Kimezawa October 4, 20121RPS.
Project Goals 1.Get to know Quartus SoPC builder environment 2.Stream 2.Stream Video 3.Build 3.Build foundation for part B - Tracking system.
By: Oleg Schtofenmaher Maxim Fudim Supervisor: Walter Isaschar Characterization presentation for project Winter 2007 ( Part A)
ECE Department: University of Massachusetts, Amherst Using Altera CAD tools for NIOS Development.
1 3-General Purpose Processors: Altera Nios II 2 Altera Nios II processor A 32-bit soft core processor from Altera Comes in three cores: Fast, Standard,
1 Nios II Processor Architecture and Programming CEG 4131 Computer Architecture III Miodrag Bolic.
Microcontroller Presented by Hasnain Heickal (07), Sabbir Ahmed(08) and Zakia Afroze Abedin(19)
© 2005 Altera Corporation SOPC Builder: a Design Tool for Rapid System Prototyping on FPGAs Kerry Veenstra Workshop on Architecture Research using FPGA.
Research on Reconfigurable Computing Using Impulse C Carmen Li Shen Mentor: Dr. Russell Duren February 1, 2008.
Advanced SW/HW Optimization Techniques for Application Specific MCSoC m Yumiko Kimezawa Supervised by Prof. Ben Abderazek Graduate School of Computer.
Using Cycle Efficiency as a System Designer Metric to Characterize an Embedded DSP and Compare Hard Core vs. Soft Core Advisor Dr. Vishwani D. Agrawal.
© 2010 Altera Corporation—Public Easily Build Designs Using Altera’s Video and Image Processing Framework 2010 Technology Roadshow.
NIOS II Ethernet Communication Final Presentation
Towards the Design of Heterogeneous Real-Time Multicore System Adaptive Systems Laboratory, Master of Computer Science and Engineering in the Graduate.
Electrocardiogram (ECG) application operation – Part B Performed By: Ran Geler Mor Levy Instructor:Moshe Porian Project Duration: 2 Semesters Spring 2012.
1 Introduction CEG 4131 Computer Architecture III Miodrag Bolic.
This course will help you understand the latest technologies & how they work. You will lean how to develop computer programs to solve problems.
Electrocardiogram (ECG) application operation – Part A Performed By: Ran Geler Mor Levy Instructor:Moshe Porian Project Duration: 2 Semesters Spring 2012.
25 April 2000 SEESCOASEESCOA STWW - Programma Evaluation of on-chip debugging techniques Deliverable D5.1 Michiel Ronsse.
Modes of transfer in computer
Network On Chip Platform
Architecture of Microprocessor
Research Progress Seminar
Additional Hardware Optimization m Yumiko Kimezawa October 25, 20121RPS.
Advanced Hardware/Software Optimization Techniques for Application Specific MCSoC m Yumiko Kimezawa Supervised by Prof. Ben Abderazek Adapted Systems.
Ethernet Bomber Ethernet Packet Generator for network analysis
S Yumiko Kimezawa A design of the ECG prototype system for two leads November 5, 20101Preliminary presentation.
1 Level 1 Pre Processor and Interface L1PPI Guido Haefeli L1 Review 14. June 2002.
Advanced SW/HW Optimization Techniques for Application Specific MCSoC m Yumiko Kimezawa Supervised by Prof. Ben Abderazek Graduate School of Computer.
Team 6. Guitar Audio Amplifier Audio Codec DSP Wireless Adapter Motor Array PC LCD Display LED Arrays Pushbutton or RPG Input Device
Investigation of BANSMOM System m Yumiko Kimezawa February 3, 20121RPS.
System on a Programmable Chip (System on a Reprogrammable Chip)
January 21, 2011GT20101 Multicore SoC Architecture and Prototyping for Parallel ECG Processing s Yumiko Kimezawa Supervised by Prof. Abderazek Ben.
February 1, 2011GT20101 Multicore SoC Architecture and Prototyping for Parallel ECG Processing s Yumiko Kimezawa Supervised by Prof. Abderazek Ben.
Lab 1: Using NIOS II processor for code execution on FPGA
Avalon Switch Fabric.
Presentation transcript:

Towards the Design of Heterogeneous Real-Time Multicore System m Yumiko Kimezawa February 1, 20131MT2012

Background (1/5) Electrocardiography (ECG) is a well known method for heart diagnosis -Used as one of major diagnosis for conventional health monitoring Main challenges of processing ECG arise from: -High computational demand for processing huge amount of data under:  Strict time constraints  Relatively high sampling frequency  Life critical conditions February 1, 2013MT20122

February 1, 2013MT20123 Most ECG systems use Pan-Tompkins approach based on QRS complex o Usage of R-peak as a reference point o Accurate detection of R-peak is a must  R-peak detection might be inaccurate Traditional techniques may fail in detecting serious heart problems Background (2/5)

February 1, 2013MT20124 Most ECG systems use Pan-Tompkins approach based on QRS complex o Usage of R-peak as a reference point o Accurate detection of R-peak is a must  R-peak detection might be inaccurate Traditional techniques may fail in detecting serious heart problems Background (2/5)

February 1, 2013MT20125 Most ECG systems use Pan-Tompkins approach based on QRS complex o Usage of R-peak as a reference point o Accurate detection of R-peak is a must  R-peak detection might be inaccurate Traditional techniques may fail in detecting serious heart problems Background (2/5)

Background(3/5): BANSMOM System February 1, 2013MT20126 System Architecture of BANSMOM System Stratix III Real-time monitoring interface Verification R y : Autocorrelation function y[n]: The filtered ECG signal L: Lags of the calculations to get the period PPD algorithm -Autocorrelation

Background (4/5) February 1, 2013MT20127 Graphic LCD Controller Master CPU Memory Master CPU Memory Master CPU Timer Graphic LCD Graphic LCD LED JTAG UART JTAG UART PPD Module Master Module LED Controller LED Controller Avalon Bus FIR Filter Timer Slave CPU Memory Slave CPU External Memory External Memory Shared Memory Shared Memory ECG Data Rom : Data flow : Control signal : Data flow : Control signal Master module -Controlling the whole systems such as reading date from shared memory, etc PPD module -Detection of following information using PPD algorithm  Intervals and their position  Position and voltage of each peak (P, Q, R, S, T and U) Figure: Block diagram of 3-lead system

8 Period detection Peaks detection Reading data Derivation Autocorrelation Find interval Extraction of max point Store results Discrimination Based on autocorrelation approach Background (5/5) : PPD Algorithm February 1, 2013MT2012

Problems Requiring a large amount of hardware resources -Logic utilization shows a linear increase for each additional PPD modules PPD Algorithm runs on single processor  may miss Real-Time deadlines The need for connecting to database server in order to monitor data efficiently in real-time February 1, 2013MT20129

Research Goals 1.Software Optimization  Parallelize PPD algorithm to boost performance and meet real-time deadlines 2.Hardware Optimization  Optimize system hardware (Sharing, DMA and Ethernet cores) 3.System Integration ▪Integrate and evaluate the new optimized system with a Real-Time Monitoring Interface (being Developed by Achraf) February 1, 2013MT201210

Graphic LCD Controller Master CPU Memory Master CPU Timer Graphic LCD LED JTAG UART PPD Module Master Module LED Controller Avalon Bus FIR Filter Timer Slave CPU Memory Slave CPU Filtered Data Memory Shared Memory ECG Data Rom : Data flow : Control signal DMA Controller Ethernet Module Ethernet PHY TSE MAC TX SGDMA Descriptor Memory The Block Diagram of improved system February 1, MT2012

The Broad layout of N-lead System February 1, 2013MT PPD module 1-lead 2-lead 3-lead N-lead Ethernet PHY Master module, Ethernet module Graphic LCD Input Output

Evaluation methodology Language: Verilog HDL Tools: Quartus II, SOPC Builder, and NIOS II IDE Target device: Stratix III DSP Board (EP3SL150F1152C2) Target data: 10 sample data -From MIT-BIH Normal Sinus Rhythm Database Evaluation approach -Hardware complexity -Execution time February 1, MT2012

Hardware Complexity February 1, 2013MT System model Logic utilization Block memory bits Fmax (MHz) Power (mW) Combinational ALUTs Memory ALUTs Dedicated Logic registers Total 1-lead12, ,33618%1,368,920(24%) lead20, ,23131%1,971,992(35%) lead28, ,15343%2,575,064(46%) lead36, ,02455%3,178,584(56%) lead44,161054,27867%3,783,066(67%) lead52,060064,06679%4,386,330(78%) lead66,496082,356104%4,972,866(88%)N/A

Execution Time February 1, 2013MT The following table shows the average execution time 10 kinds of sample data is used to calculate that time Comparing the execution time of improved system including the feature of DMA transfer to execution time of previous system Architecture Improved SystemPrevious System 1-lead 2-lead 3-lead 4-lead

Conclusion Optimizing hardware part by adding DMA feature to previous system Optimizing software to boost performance and meet real-time deadlines (not yet) Processing time is decreased by (not yet) -XXX % in improved system February 1, 2013MT201216

Future Work Integrating and evaluating the new improved system with a Real-Time Monitoring Interface February 1, 2013MT201217

Thank you for listening February 1, 2013MT201218

19 Period detection Peaks detection Reading data Derivation Autocorrelation Find interval Extraction of max point Store results Discrimination Based on autocorrelation approach Background (3/5) : PPD Algorithm February 1, 2013MT2012

Research Schedule February 1, 2013MT TaskDateStatus Investigating DMA transfer ○ Investigating how to transfer data using Ethernet ○ Minor modification of software November, 2012 ○ Adding DMA controller ~ December, 2012 × Adding Ethernet module ~December, 2012 × Modification of software ~ January, 2012 × Performance evaluation ~ January, 2012 × Writing thesis ~ January, 2013 ×