1 DSP handling of Video sources and Etherenet data flow Supervisor: Moni Orbach Students: Reuven Yogev Raviv Zehurai Technion – Israel Institute of Technology.

Slides:



Advertisements
Similar presentations
Computer-System Structures Er.Harsimran Singh
Advertisements

Bus Specification Embedded Systems Design and Implementation Witawas Srisa-an.
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.
System Integration and Performance
MICROPROCESSORS TWO TYPES OF MODELS ARE USED :  PROGRAMMER’S MODEL :- THIS MODEL SHOWS FEATURES, SUCH AS INTERNAL REGISTERS, ADDRESS,DATA & CONTROL BUSES.
Internal Logic Analyzer Final presentation-part B
Internal Logic Analyzer Final presentation-part A
Processor System Architecture
Interrupts (contd..) Multiple I/O devices may be connected to the processor and the memory via a bus. Some or all of these devices may be capable of generating.
Super Fast Camera System Performed by: Tokman Niv Levenbroun Guy Supervised by: Leonid Boudniak.
Network based System on Chip Final Presentation Part B Performed by: Medvedev Alexey Supervisor: Walter Isaschar (Zigmond) Winter-Spring 2006.
© 2004 Xilinx, Inc. All Rights Reserved Implemented by : Alon Ben Shalom Yoni Landau Project supervised by: Mony Orbach High speed digital systems laboratory.
Silberschatz, Galvin and Gagne  Operating System Concepts Chapter 2: Computer-System Structures Computer System Operation I/O Structure Storage.
t Popularity of the Internet t Provides universal interconnection between individual groups that use different hardware suited for their needs t Based.
I/O Hardware n Incredible variety of I/O devices n Common concepts: – Port – connection point to the computer – Bus (daisy chain or shared direct access)
Chapter 7 Interupts DMA Channels Context Switching.
WXES2106 Network Technology Semester /2005 Chapter 8 Intermediate TCP CCNA2: Module 10.
INPUT-OUTPUT ORGANIZATION
Multicore Navigator: Queue Manager Subsystem (QMSS)
Chapter 7 Input/Output Luisa Botero Santiago Del Portillo Ivan Vega.
Chapter 8 Input/Output. Busses l Group of electrical conductors suitable for carrying computer signals from one location to another l Each conductor in.
Introduction to Computer Networks Introduction to Computer Networks.
Chapter 10: Input / Output Devices Dr Mohamed Menacer Taibah University
© Janice Regan, CMPT 300, May CMPT 300 Introduction to Operating Systems Principles of I/0 hardware.
2: Computer-System Structures
Top Level View of Computer Function and Interconnection.
Computer Architecture Lecture10: Input/output devices Piotr Bilski.
EE 445S Real-Time Digital Signal Processing Lab Fall 2011 Lab #2 Generating a Sine Wave Using the Hardware & Software Tools for the TI TMS320C6713 DSP.
8279 KEYBOARD AND DISPLAY INTERFACING
Electrocardiogram (ECG) application operation – Part B Performed By: Ran Geler Mor Levy Instructor:Moshe Porian Project Duration: 2 Semesters Spring 2012.
LZRW3 Data Compression Core Dual semester project April 2013 Project part A final presentation Shahar Zuta Netanel Yamin Advisor: Moshe porian.
Electrocardiogram (ECG) application operation – Part A Performed By: Ran Geler Mor Levy Instructor:Moshe Porian Project Duration: 2 Semesters Spring 2012.
Performed by:Yulia Turovski Lior Bar Lev Instructor: Mony Orbach המעבדה למערכות ספרתיות מהירות High speed digital systems laboratory הטכניון - מכון טכנולוגי.
Chapter 4 MARIE: An Introduction to a Simple Computer.
Embedded Network Interface (ENI). What is ENI? Embedded Network Interface Originally called DPO (Digital Product Option) card Printer without network.
VLSI Algorithmic Design Automation Lab. THE TI OMAP PLATFORM APPROACH TO SOC.
1 CS.217 Operating System By Ajarn..Sutapart Sappajak,METC,MSIT Chapter 2 Computer-System Structures Slide 1 Chapter 2 Computer-System Structures.
Lecture 25 PC System Architecture PCIe Interconnect
Silberschatz, Galvin and Gagne  2002 Modified for CSCI 399, Royden, Operating System Concepts Operating Systems Lecture 4 Computer Systems Review.
Silberschatz, Galvin and Gagne  Applied Operating System Concepts Chapter 2: Computer-System Structures Computer System Architecture and Operation.
8279 KEYBOARD AND DISPLAY INTERFACING
Programmable Interrupt Controller (PIC)
Input/Output Problems Wide variety of peripherals —Delivering different amounts of data —At different speeds —In different formats All slower than CPU.
IT3002 Computer Architecture
Performed by: Yarovoy Boris Dubossarsky Maxim Instructor: Michael Itzkovitz המעבדה למערכות ספרתיות מהירות High speed digital systems laboratory הטכניון.
Different Microprocessors Tamanna Haque Nipa Lecturer Dept. of Computer Science Stamford University Bangladesh.
DDRIII BASED GENERAL PURPOSE FIFO ON VIRTEX-6 FPGA ML605 BOARD PART B PRESENTATION STUDENTS: OLEG KORENEV EUGENE REZNIK SUPERVISOR: ROLF HILGENDORF 1 Semester:
Time Management.  Time management is concerned with OS facilities and services which measure real time.  These services include:  Keeping track of.
KeyStone SoC Training SRIO Demo: Board-to-Board Multicore Application Team.
EE 345S Real-Time Digital Signal Processing Lab Fall 2008 Lab #3 Generating a Sine Wave Using the Hardware & Software Tools for the TI TMS320C6713 DSP.
1 load [2], [9] Transfer contents of memory location 9 to memory location 2. Illegal instruction.
Introduction An interrupt is an event which informs the CPU that its service (action) is needed. Sources of interrupts: Internal fault (e.g.. divide by.
EE 107 Fall 2017 Lecture 7 Serial Buses – I2C Direct Memory Access
CS 286 Computer Organization and Architecture
Chapter III Desktop Imaging Systems & Issues
IRQ, DMA and I/O Ports - Introduction -
EE 445S Real-Time Digital Signal Processing Lab Spring 2017
Overview Peripheral Devices Input-Output Interface
Module 2: Computer-System Structures
EE 445S Real-Time Digital Signal Processing Lab Fall 2013
Module 2: Computer-System Structures
Chapter 13: I/O Systems I/O Hardware Application I/O Interface
Module 2: Computer-System Structures
Module 2: Computer-System Structures
Chapter 13: I/O Systems.
Virtual Memory 1 1.
Presentation transcript:

1 DSP handling of Video sources and Etherenet data flow Supervisor: Moni Orbach Students: Reuven Yogev Raviv Zehurai Technion – Israel Institute of Technology High speed Digital Lab Project D1722 Final Presentation

2 System Structure BridgingCard FIFO DSP Memories EthernetController Evaluation Board Video Sources

3 Hardware Integration – step A The first stage was to connect the video camera to the bridging card, in order to examine the camera’s operation and our abilities to initialize it.

4 Hardware Integration – step A We received the information from the video camera through connector C2 along with the relevant control signals (as programmed in VHDL). We used Logic Analyzer to view the signals. This information is later on inserted to the FIFO on the evaluation board.

5 Hardware Integration – step B 0xFFFF0000 0x x0000FFFF0xFFFFFFFF FIFO The second step was to connect the bridging card to the evaluation board. We disconnected the camera video from the bridging card and it injected Test Pattern to the FIFO, accompanied by appropriate control signals.

6 Hardware Integration – step B The DSP was unable to read the FIFO, because it was burned, therefore we were instructed to move on. We reduced the signal to a third of its value on the entrance to the FIFO.

7 The C6416 DSP System block diagram

8 The main components of the DSP The main core of the system – CPU L1 Program memory – 16KB L1 Data memory – 16KB The Enhanced DMA L2 memory / cache – 1MB EMIF A (64 bit) and EMIF B (16 bit) McBSPTimers

9 The EDMA Architecture The EDMA controls access to resources and arbitrates between concurrent transfers. The EDMA includes 64 channels with programmable priority, and has the ability to link and chain data transfers. Transfer requests originate from many requestors: the sixty-four programmable EDMA channels, the level 2 (L2) memory controller, and other master peripherals.

10 SUBMITTING TRANSFER REQUEST The transfer request chain

11 Assuming each makes a submission on the same cycle, the requestor closest to the TC arrives first, and the farthest arrives last. Once a request is within the request chain, it has priority over new submissions, such that the requests at the end of the chain (HPI/PCI) do not get starved for servicing. Once a transfer request reaches the end of the request chain, it is sent to the transfer crossbar (TC). Within TC, the transfer request shifts into one of the transfer request queues to await processing. Once the transfer request reaches the head of its queue, it is submitted to the address generation/transfer logic for processing. The address generation/transfer logic only services one transfer request from each queue. In order to maximize the data transfer bandwidth in a system, we should utilize all queues.

12 The EDMA Controller Architecture The EDMA controller block diagram

13 The EDMA controller comprises: Event and interrupt processing registers Event encoder Parameter RAM (PaRAM) Address generation hardware

14 The Mechanism of Data Transfer The event register captures EDMA events. An event is a synchronization signal that triggers an EDMA channel to start a transfer. If events occur The event register captures EDMA events. An event is a synchronization signal that triggers an EDMA channel to start a transfer. If events occur simultaneously, the event encoder resolves them. The transfer parameters corresponding to this event are stored in the EDMA parameter RAM, and are passed onto the address generation hardware, which address the EMIF and/or peripherals to perform the necessary read and write transactions. simultaneously, the event encoder resolves them. The transfer parameters corresponding to this event are stored in the EDMA parameter RAM, and are passed onto the address generation hardware, which address the EMIF and/or peripherals to perform the necessary read and write transactions.

15 The Parameter Ram (PaRAM) The table is a 2K-byte block of internal parameter RAM. The PaRAM table consists of six-word parameter entries of 24 bytes each, for a total of 85 entries. The contents of the 2K-byte PaRAM include 64 transfer parameter entries for the 64 EDMA events. Remaining parameter entries (21 entries) serve as additional parameter sets used for linking transfers. Once an event is captured, its parameter entries are read from one of the top 64 entries in the PaRAM. These parameter entries are then sent to the address generation hardware.

16 The Structure of EDMA channel parameter entry Each parameter entry of an EDMA event is organized into six 32-bit words or 24 bytes

17 EDMA Channel Options Parameter (OPT) EDMA Channel Source Address Parameter (SRC)

18 EDMA Channel Transfer Count Parameter (CNT) EDMA Channel Destination Address Parameter (DST)

19 EDMA Channel Index Parameter (IDX) EDMA Channel Count Reload/Link Address Parameter (RLD)

20 The Link Feature An important capability of the EDMA is that of linking. By providing a link address and setting LINK = 1 in the transfer options, an EDMA channel loads a new entry from PaRAM and begins performing the new transfer. The linked list is traversed until LINK = 0. An important capability of the EDMA is that of linking. By providing a link address and setting LINK = 1 in the transfer options, an EDMA channel loads a new entry from PaRAM and begins performing the new transfer. The linked list is traversed until LINK = 0.

21 The NDKC64x - Network Development Kit for C64x The main Hardware features of the NDKC64x are: 10/100 Mb/s Fast Ethernet controller 10/100 Mb/s Fast Ethernet controller IEEE 802.3u compliant MAC/PHY 128 KB of on-board memory

22 The Client Project We use the client project as a platform which allow us to send the image we built through the Ethernet. We use the client project as a platform which allow us to send the image we built through the Ethernet. This client project give us this capability by: This client project give us this capability by: Creating a socket Creating a socket Configuring the Tx and Rx timeout Configuring the Tx and Rx timeout Connecting the socket to an address Connecting the socket to an address Allocate a buffer which will be sent through the Ethernet. In this case, the buffer is our image. Allocate a buffer which will be sent through the Ethernet. In this case, the buffer is our image. Send the buffer and receive it back.