Advantages of Reconfigurable System Architectures

Slides:



Advertisements
Similar presentations
Reconfigurable Computing After a Decade: A New Perspective and Challenges For Hardware-Software Co-Design and Development Tirumale K Ramesh, Ph.D. Boeing.
Advertisements

Nios Multi Processor Ethernet Embedded Platform Final Presentation
Using Virtual Platforms for Firmware Verification James Pangburn Jason Andrews.
A reconfigurable system featuring dynamically extensible embedded microprocessor, FPGA, and customizable I/O Borgatti, M. Lertora, F. Foret, B. Cali, L.
MotoHawk Training Model-Based Design of Embedded Systems.
Graduate Computer Architecture I Lecture 15: Intro to Reconfigurable Devices.
ECE 699: Lecture 1 Introduction to Zynq.
Some Thoughts on Technology and Strategies for Petaflops.
Configurable System-on-Chip: Xilinx EDK
6/30/2015HY220: Ιάκωβος Μαυροειδής1 Moore’s Law Gordon Moore (co-founder of Intel) predicted in 1965 that the transistor density of semiconductor chips.
XUP Virtex-5 Development System January XUP Virtex52 Introducing XUPV5-LX110T A powerful and versatile platform packaged and priced for Academia!
Implementation of DSP Algorithm on SoC. Mid-Semester Presentation Student : Einat Tevel Supervisor : Isaschar Walter Accompaning engineer : Emilia Burlak.
Intel ® Research mote Ralph Kling Intel Corporation Research Santa Clara, CA.
Introduction to FPGA and DSPs Joe College, Chris Doyle, Ann Marie Rynning.
Zynq-7000 EPP Introduction Where ARM Processors Meet HW Programmability May 2012.
Using FPGAs with Embedded Processors for Complete Hardware and Software Systems Jonah Weber May 2, 2006.
Building an Application Server for Home Network based on Android Platform Yi-hsien Liao Supervised by : Dr. Chao-huang Wei Department of Electrical Engineering.
EE587 SoC Design & Test School of EECS Washington State University
General Purpose FIFO on Virtex-6 FPGA ML605 board midterm presentation
Programmable Logic- How do they do that? 1/16/2015 Warren Miller Class 5: Software Tools and More 1.
- 1 - A Powerful Dual-mode IP core for a/b Wireless LANs.
Role of Standards in TLM driven D&V Methodology
UCT Software-Defined Radio Research Group
© Copyright 2009 Xilinx Copyright 2012 Xilinx August 2012 Zynq-7000 All Programmable SoC Product Overview The SW, HW and IO Programmable Platform.
Introducing Zynq-7000 EPP The First Extensible Processing Platform Family March 2011.
Xilinx at Work in Hot New Technologies ® Spartan-II 64- and 32-bit PCI Solutions Below ASSP Prices January
EKT303/4 PRINCIPLES OF PRINCIPLES OF COMPUTER ARCHITECTURE (PoCA)
RSC Williams MAPLD 2005/BOF-S1 A Linux-based Software Environment for the Reconfigurable Scalable Computing Project John A. Williams 1
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,
A Company Selling Technology and not just a Product.
Department of Electrical Engineering Electronics Computers Communications Technion Israel Institute of Technology High Speed Digital Systems Lab. High.
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,
Silicon Building Blocks for Blade Server Designs accelerate your Innovation.
J. Christiansen, CERN - EP/MIC
® SPARTAN Series High Volume System Solution. ® Spartan/XL Estimated design size (system gates) 30K 5K180K XC4000XL/A XC4000XV Virtex S05/XL.
Computer Organization CT213 – Computing Systems Organization.
STMIK Jakarta STI&K, Jakarta - September Designing Image Processing Component using FPGA Device By : Sunny Arief Sudiro.
DIPARTIMENTO DI ELETTRONICA E INFORMAZIONE Novel, Emerging Computing System Technologies Smart Technologies for Effective Reconfiguration: The FASTER approach.
Development of Programmable Architecture for Base-Band Processing S. Leung, A. Postula, Univ. of Queensland, Australia A. Hemani, Royal Institute of Tech.,
Copyright  2005 SRC Computers, Inc. ALL RIGHTS RESERVED Overview.
VLSI Algorithmic Design Automation Lab. THE TI OMAP PLATFORM APPROACH TO SOC.
SOC Virtual Prototyping: An Approach towards fast System- On-Chip Solution Date – 09 th April 2012 Mamta CHALANA Tech Leader ST Microelectronics Pvt. Ltd,
Performed By: Itamar Niddam and Lior Motorin Instructor: Inna Rivkin Bi-Semesterial. Winter 2012/2013 3/12/2012.
Embedded Systems Design with Qsys and Altera Monitor Program
Final Presentation Hardware DLL Real Time Partial Reconfiguration Management of FPGA by OS Submitters:Alon ReznikAnton Vainer Supervisors:Ina RivkinOz.
Design with Vivado IP Integrator
Aditya Dayal M. Tech, VLSI Design ITM University, Gwalior.
Zynq-7000 All Programmable SoC for Smarter Vision
System on a Programmable Chip (System on a Reprogrammable Chip)
April 15, 2013 Atul Kwatra Principal Engineer Intel Corporation Hardware/Software Co-design using SystemC/TLM – Challenges & Opportunities ISCUG ’13.
© Copyright 2013 Xilinx. Zynq Development Flow to Accelerate C Code.
Voice Controlled Robot by Cell Phone with Android App
Programmable Logic Devices
PICK N PLACE ROBOTIC ARM AND MOVEMENT CONTROLLED BY ANDROID WIRELESSLY
ARM Embedded Systems
Hands On SoC FPGA Design
Hands On SoC FPGA Design
Using FPGAs with Processors in YOUR Designs
Introduction to Programmable Logic
How to Quick Start Virtual Platform Development
System On Chip.
Andes Technology Innovate SOC ProcessorsTM
Texas Instruments TDA2x and Vision SDK
ENG3050 Embedded Reconfigurable Computing Systems
Overview of Embedded SoC Systems
Using FPGAs with Processors in YOUR Designs
Programmable Logic- How do they do that?
PICK N PLACE ROBOTIC ARM AND MOVEMENT CONTROLLED BY ANDROID WIRELESSLY
The performance requirements for DSP applications continue to grow and the traditional solutions do not adequately address this new challenge Paradigm.
System View Inc..
Presentation transcript:

Advantages of Reconfigurable System Architectures Vidhumouli H Xilinx

Advances in Reconfigurable Platforms Challenges and How Latest Innovations Address Processing Platform Offerings Focus on Hard Processing with Configurability Considerations: How to best evaluate your design needs New Advances in Reconfigurable Processing Platforms Key advantages of each and limitations

Embedded Designers are Asking For More More than a processor delivers… More than an ASIC or ASSP delivers… More than an FPGA delivers… The programmable imperative is great, but the challenge in an FPGA for volume applications is to deliver the capacity at the power and cost of the ASIC and ASSP.

Embedded Processing Needs and Limitations The Need Higher Performance Lower Cost Lower Power Smaller Form Factor Greater Flexibility The Limitations Microprocessors have insufficient signal processing Multiple chip implementations are too expensive Multiple chip implementations burn too much power Multiple chip implementations take up too much room ASICs/ASSPs cannot adapt to rapid changes in requirements and provide completive differentiation PowerPC was the right choice at the time…

ASIC Starts Continued Drop Fueling the Programmable Imperative

Increasing Demand for Processing in Reconfigurable Platforms

PROCESSOR CORE TRENDS

Increasing Design Costs

Embedded Processing Design Considerations

Embedded Design Considerations Architect Architecture and Processor selection HW and SW Partitioning Software Developer Waiting for HW Before SW Development Tools support Code Optimization HW/SW Co-debug HW Designer Processing System Development Hand-crafting RTL for Parallel DSP Acceleration IP Availability and Integration from Multiple Sources Cross-domain development / debug

What’s Needed in Embedded Processing Systems Key Requirements Higher Performance with Lower System Power More Integration with Reduced System Cost Increased Scalability IP Inter-operability Design Re-use Ease of Programming Extensive Ecosystem Improved Products Increased Productivity Need full range of embedded product line – not just processors in high end chips Need unified architecture – across device families so make it easy to migrate both SW and HW across diff levels of product Need to raise design abstraction – like LabView offering from NI, ESL, other Need to free designers from having to reinvent what is already proven to go beyond that

Extensible Processing Platform Examples

Smart Fusion from Mircosemi FPGA +ARM Cortex-M3 Analog and Digital Mixed signal FPGA. Secure flash IP Kiel + IAR Systems and GNU Micrium

More than a Microcontroller

Tools Flow with Processing Configurator and IP Embedded Design: Softconsole Eclipse based IDE FPGA design : Libero IDE Analog Design: MSS configurator Grapical based configuration

Intel Atom E600 Series paired with FPGA Arria GX2 FPGA Provide gate count and features..

Intel Atom with FPGA Fabric

Intel Atom E600 Series with FPGA Fabric

Intel Platform Solution

SPEAr 1310 –One Time Programmable ASSP Dual _ARM

Current Selections Equal Compromise ASIC ASSP 2 Chip Solution Performance + . Power - Unit Cost TCO Risk TTM Flexibility Scalability + = positive, - = negative, . = neutral Conflicting Demands Not Served

New Class of Product Extensible Processing Platform Additional Peripherals Extensible Processing Platform High Performance, Reconfigurable, Application Optimized Accelerators Programmable Logic for Extensions Rapid Differentiation High Performance, Scalable Programmed by Processor ARM® Dual Cortex™-A9MPCore Complex Memory Interfaces Common Peripherals Off the- Shelf Custom Processing System Hardwired SoC High Performance Low Power, Low Cost Boots OS at Reset High-Bandwidth AMBA-AXI Interfaces ARM Dual Cortex-A9 MPCore

Zynq-7000 EPP Family Highlights Complete ARM Processing System Dual ARM® Cortex™-A9 Integrated Memory Controllers & Peripherals Tightly integrated Programmable Logic Extends Processing System Scalable density and performance Over 3000 Internal Interconnects Flexible array of I/O Wide Range of external Multi Standard I/O High Performance integrated serial tranceivers Analog-to-Digital Converter inputs 7 Series Programmable Logic Common Peripherals Custom Peripherals Common Accelerators Custom Accelerators Common Processing System Memory Interfaces ARM® Dual Cortex-A9 MPCore™ Software & Hardware Programmable

Emulation of an Extensible Processing Platform

Zynq-7000 EPP Device Portfolio Summary Zynq-7000 EPP Devices Z-7010 Z-7020 Z-7030 Z-7040 Processing System Processor Core Dual ARM® Cortex™-A9 MPCore™ Processor Extensions NEON™ & Single / Double Precision Floating Point Max Frequency 800MHz Memory L1 Cache 32KB I / D, L2 Cache 512KB, on-chip Memory 256KB External Memory Support DDR2, DDR3, LPDDR2, 2x QSPI, NAND, NOR Peripherals 2x USB 2.0 (OTG), 2x Tri-mode Gigabit Ethernet, 2x SD/SDIO, 2x UART, 2x CAN 2.0B, 2x I2C, 2x SPI, 32b GPIO   Programmable Logic Approximate ASIC Gates ~430K (30k LC) 1.3M (85k LC) 1.9M (125k LC) 3.5M (235k LC) Extensible Block RAM 245KB 573KB 1,085KB 1,904KB Peak DSP Performance (Symmetric FIR) 58 GMACS 158 GMACS 480 GMACS 912 GMACS PCI Express® (Root Complex or Endpoint) - 1x Gen2 x4 1x Gen2 x8 Analog to Digital Converters (ADC) Dual 12bit 1Msps A/D Converter I/O Processor System IO 130 Multi Standards 3.3V IO 100 200 Multi Standards High Performance 1.8V IO 150 Multi Gigabit Transceivers 4 12

Application Mapping Table

Zynq-7000 EPP Platform Offering Applications OS Kernel High Level and Low Level Drivers Processing System Programmable Logic OS BSP’s Silicon Custom Libraries & APIs Reference Design & Board Partners Xilinx Simulators SW Development Tools SW & HW IP IDS More than just Silicon: A Comprehensive Platform Offering

Embedded Design Flow Using Zynq-7000 EPP Programming Integrate IP Test Debug Design Xilinx IP Partner IP Custom IP Software Developer Hardware Designer System Architect Industry-Leading Tools Xilinx SDK ARM Ecosystem Many Sources of SW IP Xilinx, ARM libraries 3rd Parties Industry-Leading Tools C-Gates / AutoESL System Generator VHDL/Verilog Many Sources of HW IP Standardized around AXI 3rd Parties Unified architecure. Accelerates Application Development and TTM

Zynq-7000 EPP SW Development Environment Widely used ARM development environment Easily migrate code already developed for ARM-based systems ARM ecosystem support ARM Xilinx Software Development Kit other 3rd Parties Vast off-the-shelf SW and Libraries Open source Commercially available Applications OS Kernel High Level and Low Level Drivers Processing System Programmable Logic OS BSP’s Silicon Custom Libraries & APIs

Zynq-7000 EPP HW Design Environment Xilinx ISE Development Suite Embedded Edition AutoESL HLS Support Plug & Play IP Portfolio AXI Enabled Hardware abstraction layer Simplifies interface between Cortex-A9 and custom accelerators/peripherals Drivers and APIs Provided for a common set of accelerators for key applications Applications OS Kernel High Level and Low Level Drivers Processing System Programmable Logic OS BSP’s Silicon Custom Libraries & APIs

Image Processing Example – System Validation Android 2.2 based multi channel video processing Image enhancement with ARM Dual Cortex-A9 System interoperability w/ AMBA AXI IP & FMC display Emulation Platform Camera Link Interfaces iVeia FMC Daughter Card Touch Screen 3.5” LCD 640x480

Significant Head Start Emulation Platform: Alpha Participants First systems delivered ~ 6 months ago Customers & Partners already completed development of SW, HW IP own daughter cards Customer and Partner Efforts Android Handheld Driver Assistance OS port w/ CAN and GigE Real Time Linux applications Custom AXI IP blocks 3rd party GNU & Debugging tools and more…

Conclusion

Zynq-7000 EPP Value Proposition ASIC ASSP 2 Chip Solution Zynq-7000 Performance + . Power - Unit Cost TCO Risk TTM Flexibility Scalability + = positive, - = negative, . = neutral Conflicting Demands Now Served by Zynq-7000 EPP

What’s Needed in Embedded Processing Systems Key Requirements Higher Performance with Lower System Power More Integration with Reduced System Cost Increased Scalability IP Inter-operability Design Re-use Ease of Programming Extensive Ecosystem Improved Products Increased Productivity Need full range of embedded product line – not just processors in high end chips Need unified architecture – across device families so make it easy to migrate both SW and HW across diff levels of product Need to raise design abstraction – like LabView offering from NI, ESL, other Need to free designers from having to reinvent what is already proven to go beyond that

Zynq-7000 ARM Processing System High BW Memory Interfaces Internal L1 Cache – 32KB/32KB L2 Cache – 512KB Unified On-Chip Memory of 256KB Integrated Memory Controllers (DDR2, DDR3, LPDDR2, 2xQSPI, NOR, NAND Flash) Processor Core Complex Dual ARM® Cortex™-A9 MPCore™ with NEON™ extensions Single / Double Precision Floating Point support Up to 800 MHz Operation Open Standard Interconnect Enabled by AXI High Bandwidth Interconnect between Processing System and Programmable Logic ACP port for enhanced Hardware Acceleration and cache coherency for additional Soft processors Integrated Memory Mapped Peripherals 8 DMA Channels 2x USB 2.0 (OTG) w/DMA 2x Tri-mode Gigabit Ethernet w/DMA 2x SD/SDIO w/DMA, 2x UART, 2x CAN 2.0B, 2x I2C, 2x SPI, 32b GPIO Processing System Ready to Program

Tightly Integrated Programmable Logic Built with State-of-the-art 7 Series Programmable Logic 28K-235K logic cells 430K – 3.5M equivalent ASIC gates Over 3000 internal Interconnects Up to 100Gb of BW Memory-mapped interface Integrated ADCs Dual 12-bit A/D converter Up to 1Msps Enables Massive Parallel Processing Up to 760 DSP blocks delivering over 910 GMACs Scalable Density and Performance

Flexible External I/O Flexible Memory Interfaces 32 bit DDR2 / DDR3 / LPDDR2 Memory Interfaces 54 Processor I/O Supports integrated peripherals Static Memory (NAND, NOR, QSPI) High Performance Integrated Serial Tranceivers Up to 12 Transceivers Operates at up to 10.3Gbs Supports popular protocols … Integrated PCIe Gen2 block in the 2 Largest devices 350 Multi-standard and High Performance I/O Up to 200 3.3V capable Multi-standard I/O Up to 150 High Performance I/O Up to 17 ADC Inputs Flexibility Beyond Any Standard Processing Offering