Intel CoFluent Studio in Digital Imaging

Size: px
Start display at page:

Download "Intel CoFluent Studio in Digital Imaging"

Transcription

1 Intel CoFluent Studio in Digital Imaging Sensata Technologies Use Case Sensata Technologies Formerly Texas Instruments Sensors & Controls, Sensata Technologies is the world s leading designer and supplier of sensors, controls and protectors across a broad range of markets and applications, including transportation, industrial, and appliances. Today, Sensata Technologies is comprised of three major global business units with sales offices worldwide and business and manufacturing centers in 1 0 different countries. Their innovative solutions in sensors and controls improve safety, efficiency and comfort for millions of people every day. Sensata, which currently employs approximately 9,500 people, manufactures over 20,000 different highlyengineered and application-specific products. Over one billion units are shipped each year. When designing a new vision camera system aimed at automotive and security applications, Sensata utilized Intel CoFluent Studio to select and optimize its next generation image sensing architecture. The team created a model of a camera system and simulated its behavior and time properties. Architecture choices were studied and hardware/software partitioning alternatives explored. For each architecture option, local memory requirements, potential traffic bottlenecks, execution times and complexity of functions were studied and analyzed. This paper illustrates how the early design effort effectively utilized various Intel CoFluent Studio features to create, simulate, and analyze seven different architecture models in approximately four weeks.

2 Table of Contents 1 Camera System Application Modeling Application Description Behavioral Modeling Model Characterization: Time Attributes & Design Parameters Execution Platform Modeling Application Description Performance Characterization Mapping and Architecture Modeling Architecture Description Architecture Characterization Obtained Results Conclusion...1 0

3 1 Camera System Application Modeling 1.1 Application Description Sensata studied a simple camera system application. The main functions of the system are the following: - Image sensing - Image quality control - Color processing - Display handling (LCD and NTSC) - Monitoring (power control and various diagnosis) - Communication interfacing (I2C or SPI) Image sensing is handled by a dedicated hardware component, the imager, which captures 642x bit monochrome or color images at 60 frames per second. The image quality control function determines the image sensor s mode, monochrome versus color, shutter speed, and compression level. Environmental monitoring includes voltage and temperature monitoring for potential error reporting. Display handling involves reformatting the image for LCD or NTSC display. The communication interfacing includes I2C or SPI interfaces for communicating with a host controller. In its initial stage, the application model was limited to color processing while monochrome image quality control (input control, noise removal, defective pixel removal, image enhancement, output control) was reduced to a simple auto-control model. 1.2 Behavioral Modeling The camera system application is reduced to a basic color processing function. This function takes raw data frames as input and outputs frames in RGB format (8-bit Red, 8-bit Green, 8-bit Blue). A test case for the camera system simulates image sensing and display as simple video data source and sinks. The Video Source function reads test files on the simulation PC s hard disk and sends the data to the ColorProcessingfunction, while the VideoSink simply displays the received data as an image in RGB format. While actual image data is sent pixel by pixel for color processing, it is not necessary to model the camera system at the pixel level since macroscopic latency and throughput performance results are expected. For simplification, the Sensata model assumes that the ColorProcessingfunction receives a complete frame at once. ColorProcessingincludes four concurrent sub-functions that can be pipelined in a certain order: Defective PixelRemoval, White Balance, Demosaic and Sharpen. Intel CoFluent Studio message queues are used to model FIFO channels between stages of the pipeline to enable independent and asynchronous communications between stages.

4 Each pipeline function follows the same behavioral design pattern as shown below: After an initialization sequence (Initoperation), an infinite loop waits to receive a frame from stage N-1 through ChannelIn, processes the frame (Algorithm operation), and sends the result to stage N+1 through ChannelOut. A first tokenbasedsimulation without data type or data processing algorithm definitions is run to verify and analyze the complete system control and data flow. Next, C algorithms are added for each color processing pipeline function. They can be copied and pasted in the definition area of the Algorithmoperation or can be declared as external C routines, inserted to the project as external files, and called from within Algorithm. As the model of the ColorProcessingsystem is repetitive, a possible solution is to copy and paste the four sub-functions and change the code in each Initand Algorithmoperation. A more efficient way of duplicating functions is to make them reusable IP models in libraries. In this case, a single ColorProcessingStage IP is created that includes all four possible algorithms. An external parameter is defined to select which algorithm to use when reusing the IP. This mode offers the ability to test the application with different pipeline orders provided that all pipeline stages have the same input and output data formats (which is not the case for the Sensata model). A further simplification is to model the ColorProcessingfunction as a single stage function. It is defined as a vector of functions that can be instantiated from one to four times in multiple instance mode. This does not require copy-paste or multiple stage drawings, and, if applicable, has the advantage of testing the pipeline in any desired order for any number of stages (this also requires compatible input/output data formats for all stages). 1.3 Model Characterization: Time Attributes & Design Parameters Since Intel CoFluent Studio models are timed, durations of computations (operations) and communications (inputs/outputs) have to be defined. The image capture duration is defined at 1 6 ms for outputting 60 frames per second. VideoInand VideoOutmessage queues are set to 1 0 ns (nonsignificant times, as not important in the scope of this study) for send and receive times. Pipeline channels are set to complete one 1 6-bit pixel transfer in a single cycle: send time is set to a very short non-significant value (1 0 ns) and receive time to a number of cycles that correspond to the number of pixels per frame: 642 * 482 = This creates a realistic total transfer time (send time + receive time). In order to make the model independent of the frame size, a specific keyword USERDATASIZEis used. This corresponds to the value of a specific field in the model data structure set to represent the size of the data, and removes the need for the real data. To give greater flexibility to the simulation, the user-customizable data size is defined as a tunable generic parameter (a sort of simulation knob) that can be set at simulation time and called FrameLength. FrameLengthranges from 1 00 to 642x482 pixels. A number of cycles per pixel is defined for the duration of each algorithm. It is determined by existing profiling data or estimations for each color processing stage. Therefore, the duration of the Algorithmoperation corresponds to the number of cycles per pixel (specific for each algorithm) multiplied by the number of pixels per frame (FrameLength). The conversion from number of cycles to a time value is based upon the definition of the cycle period of the execution target. For example on an FPGA at 50 MHz, 1 cycle = 1 /50 us = 20 ns. In order to calculate the pipeline latency for each frame, an additional timestamp field was added to the frame data structure. The timestamp field is used to save the time when the frame enters the pipeline, enabling the latency calculation when it exits. The Intel CoFluent Studio simulation API provides access to the simulation time. In order to calculate the pipeline latency for each frame, an additional timestamp field was added to the frame data structure. The timestamp field is used to save the time when the frame enters the pipeline, enabling the latency calculation when it exits. The Intel CoFluent Studio simulation API

5 provides access to the simulation time. The simulation of the application model offers visual verification of the effectiveness of algorithms within Intel CoFluent Studio s image display tool. Results are shown below (input images on the left displayed with off-the-shelf tool, RGB output images on the right displayed within Intel CoFluent Studio). In addition, to analyze and validate the pipeline effect and its time properties, a timeline chart, or sequence diagram similar to a Gantt chart, is automatically produced during simulation. Sensata had access to real data processing algorithms. This is not always the case. If the actual data processing algorithms are unavailable, Intel CoFluent Studio can run token-based simulations with empty algorithms, using only their time characterization. For the Sensata case, profiling of algorithms execution within Intel CoFluent Studio can be used as an indication for the duration of each algorithm execution (min, max, average). This includes comparing the dynamic execution profile against simulation time or its number of executions, which is helpful in analyzing complexity

6 of functions. 2 Execution Platform Modeling 2.1 Application Description For its new vision camera system, Sensata wanted to study how two separate components from the previous design could be merged into a single system-on-chip or the proper partition between separate components. The execution platform provides various software or hardware execution resources: a DSP with its coprocessor and RAM, an FPGA, with no soft or hard core, including RAM for data buffering connected to the imager. Various pixel busses, 1 2 or 24 bits, link the different elements. 2.2 Performance Characterization Intel CoFluent Studio's platform models are created by assembling generic hardware components to provide computing, communication or storage resources. Hardware (ASIC, FPGA, co-processor, accelerator, etc.) or software (DSP, CPU, MCU) computing units are called processors. Communication links are called nodes, and can be characterized as bus, routing network or point-to-point. Storage units are called shared memories. Universal behavioral and performance attributes characterize elements of a platform model..sensata created and characterized three different platform configurations for representing potential execution structures: - Platform1: two hardware processors and a bus - Platform2: three hardware processors and a bus - Platform3: one hardware processor, one software processor, and a bus The cycle period of hardware processors is defined as a generic parameter ranging from 1 0 to 1 00 ns with a default value of 20 ns. The software processor is characterized through a relative speed ratio, which is a multiplicative factor applied to initial time values given at the application level to simulate a faster or slower processor. The transfer time of the bus was also modeled as a generic parameter with a varying value. 3 Mapping and Architecture Modeling 3.1 Architecture Description Sensata explored multiple mapping alternatives: - ConfigurationA: image quality control and color processing running on the FPGA - ConfigurationB: image quality control and color processing running on the DSP - ConfigurationC: image quality control running on the FPGA and color processing running on the DSP The display, communication and monitoring functions run on the DSP. Image sensing runs on the FPGA. Objectives Size & cost of FPGA RAM sizes Latencies (Imager > Format > Display) Bottlenecks DSP load Configuration A Configuration B Configuration C Simplified models of ConfigurationA and ConfigurationBwere completed. ConfigurationCwas found similar to ConfigurationB if using color processing at frame synchronization, but differed if using monochrome processing or row synchronization.

7 3.2 Architecture Characterization A total of seven simulation models are created for comparison: five simulation models for ConfigurationA and two for ConfigurationB. The seven models are obtained in minutes using Intel CoFluent Studio s drag-and-drop mapping feature that allows in one click of a mouse to allocate functions to processors. The resulting architecture models are automatically generated in SystemC by the tool. Memory sizes, power consumptions and cost values are defined for processors, functions, operations, and FIFO channels following certain rules. The utilization of each component at any level of the hierarchy in the model is evaluated as a load ratio (%) or in number of cycles per seconds (Cyps, KCyps, MCyps, GCyps). For example, the duration of color processing algorithms and data inputs/outputs is dependent on the image size characterized by the FrameLengthgeneric parameter. The cost attribute is used to represent the silicon area. 3.3 Obtained Results For each simulation, a table of performance results can be obtained and exported to an Excel spreadsheet, as shown below. The following useful findings are extracted from the simulation and used as system architecture guidelines. Finding the maximum lines of image to be processed in a frame timeline When FrameLength= , the image capture load is %. There is a stall in the frame sent to the camera system. The capture load reaches 1 00% when FrameLength= This shows that 49 lines of 642 pixels (642 * 49 = ) is the optimal number of lines to be processed in a frame timeline. Therefore, to meet the timing requirements, about 1 0 (= 482 / 49) stages of pipeline need be considered during each algorithm. This information is useful when the color processing algorithms are implemented in FPGA or ASIC. Finding potential bottlenecks With FrameLength= : stage 1 load = 38.59%, stage 2 load = 96.05%, stage 3 load = 57.96%, stage 4 load = 36.04%. This information illustrates that stage 2 is the potential bottleneck. Stage 2 can be analyzed and implemented as a multiplestage pipeline. Providing the utilization for each function with different pipeline numbers With FrameLength= (642 * 482 = ): stage 1 load = 96.49%, stage number = 6; stage 2 load = 93.46%, stage number = 1 7; stage 3 load = 92.64%, stage number = 1 0; stage 4 load = %, stage number = 6. Comparing dynamic memory utilization When FrameLength= and processor relative speed = 1 : memory min = Kbytes, max = Kbytes, average = Kbytes.

8 When FrameLength= and processor relative speed = 2 (2 times faster): memory min = Kbytes, max = Kbytes, average = Kbytes. This illustrates that as the processor speed increases, the memory size decreases due to less processing time and a decrease in parallel activities. Comparing dynamic power consumption When FrameLength= and processor relative speed = 1 : power min = 0 mw, max = 54 mw, average = mw. When FrameLength= and processor relative speed = 2 (2 times faster): power min = 0 mw, max = mw, average = mw. Simulation results reflect the combined effects of a reduction in power due to the decrease in algorithm execution times, and power increase related to a processor speed increase. Dynamic profiles can be obtained to do precise observations in time. Finding the minimum number of redundant algorithm processing engines for given parameters, while still meeting timing requirements When FrameLength= and number of redundant algorithm processing engines = 1 3, the resulting image capture load = 95.05%. When FrameLength= and number of redundant algorithm processing engines = 1 4, the resulting image capture load = 1 00%. When the image capture function load does not reach 1 00%, it indicates a stall in the frame sent to the camera system and causes the processing to be incomplete within one row timeline. The above results show that 1 4 is the minimum number of blocks to be processed to meet timing requirements. Optimizing the tradeoff between the number of redundant algorithm processing engines versus the memory size and the power consumption The larger the number of blocks, the more memory is required due to the increase in processing engines. This, in turn, increases the power due to the combined effects of more processing engines and less processing time. When processor speed is increases, less memory is required due to less parallel activities. This decreases the power due to the combined effects of high processing speed and less processing time. Optimizing the tradeoff between memory size, power consumption, and cost The higher the number of columns per image, the more memory is required due toincreased capacity of message queues. When processor speed is up, less memory is required because of the decrease in parallel activities. This decreases power requirements due to the combined effects of high processing speed and less processing time. Finding if a frame can be processed within a frame timeline in software A frame can be processed within a frame timeline if the color processing algorithms are implemented in software processor. The results show % total utilization for the software processor with FrameLength= The following table summarizes Sensata s findings for each of the seven simulations which serve to identify the optimal architecture by providing

9 guidelines for performance/memory/power/cost tradeoffs. From this table, Sensata deduced that: - Models 1, 4, 5A, 6, and 6A are preferred candidates compared to models 2 and 5 - Models 1, 4, 6, and 6A are hardware implementations, model 5A is a software implementation - Models 1, 6, and 6A are parallel processing implementations - Model 1 has lower power, but a small additional cost compared to models 6 and 6A - Model 6A has approximately 1 0% lower cost compared to model 1 4 Conclusion Sensata s experience with Intel CoFluent Studio was largely positive as results obtained went far beyond what could be obtained with just spreadsheets. Spreadsheetsprovide theoretical static best- and worst-case figures, whereas Intel CoFluent Studio allows observing and analyzing dynamic profiles of the system s significant properties in the context of realistic use cases. Sensata s analysis of Intel CoFluent Studio benefits were the following: - Application decomposition and application-to-platform mapping prepare efficiently for implementation - System-level modeling and graphical notations help better master complexity and improve productivity - Short design-space exploration and performance-analysis iterations allow validating architectural choices - Architectural exploration and performance analysis help optimize architectures The optimal architecture was achieved through iterating on various model configurations, mappings and characterizations. However, the research and data gathering work was key, says Qing Song, DSP Systems-On-Chip architect, Sensata Technologies. Copyright Intel Corporation. All rights reserved. Intel and Intel CoFluent are trademarks of Intel Corporation in the U.S. and/or other countries. *Othernames and brands may be claimed as the property ofothers.

Ten Reasons to Optimize a Processor

Ten Reasons to Optimize a Processor By Neil Robinson SoC designs today require application-specific logic that meets exacting design requirements, yet is flexible enough to adjust to evolving industry standards. Optimizing your processor

More information

M ICROSTAR LABORATORIES TM

M ICROSTAR LABORATORIES TM M ICROSTAR LABORATORIES TM 2265 116th Avenue N.E., Bellevue, WA 98004 Sales & Customer Support: (425) 453-2345 Finance & Administration: (425) 453-9489 Fax: (425) 453-3199 World Wide Web: http://www.mstarlabs.com/

More information

IMPROVES. Initial Investment is Low Compared to SoC Performance and Cost Benefits

IMPROVES. Initial Investment is Low Compared to SoC Performance and Cost Benefits NOC INTERCONNECT IMPROVES SOC ECONO CONOMICS Initial Investment is Low Compared to SoC Performance and Cost Benefits A s systems on chip (SoCs) have interconnect, along with its configuration, verification,

More information

Introduction to MLM. SoC FPGA. Embedded HW/SW Systems

Introduction to MLM. SoC FPGA. Embedded HW/SW Systems Introduction to MLM Embedded HW/SW Systems SoC FPGA European SystemC User s Group Meeting Barcelona September 18, 2007 rocco.le_moigne@cofluentdesign.com Agenda Methodology overview Modeling & simulation

More information

Philip Andrew Simpson. FPGA Design. Best Practices for Team-based Reuse. Second Edition

Philip Andrew Simpson. FPGA Design. Best Practices for Team-based Reuse. Second Edition FPGA Design Philip Andrew Simpson FPGA Design Best Practices for Team-based Reuse Second Edition Philip Andrew Simpson San Jose, CA, USA ISBN 978-3-319-17923-0 DOI 10.1007/978-3-319-17924-7 ISBN 978-3-319-17924-7

More information

Developing and Integrating FPGA Co-processors with the Tic6x Family of DSP Processors

Developing and Integrating FPGA Co-processors with the Tic6x Family of DSP Processors Developing and Integrating FPGA Co-processors with the Tic6x Family of DSP Processors Paul Ekas, DSP Engineering, Altera Corp. pekas@altera.com, Tel: (408) 544-8388, Fax: (408) 544-6424 Altera Corp., 101

More information

The Nios II Family of Configurable Soft-core Processors

The Nios II Family of Configurable Soft-core Processors The Nios II Family of Configurable Soft-core Processors James Ball August 16, 2005 2005 Altera Corporation Agenda Nios II Introduction Configuring your CPU FPGA vs. ASIC CPU Design Instruction Set Architecture

More information

Implementing FFT in an FPGA Co-Processor

Implementing FFT in an FPGA Co-Processor Implementing FFT in an FPGA Co-Processor Sheac Yee Lim Altera Corporation 101 Innovation Drive San Jose, CA 95134 (408) 544-7000 sylim@altera.com Andrew Crosland Altera Europe Holmers Farm Way High Wycombe,

More information

System Level Design with IBM PowerPC Models

System Level Design with IBM PowerPC Models September 2005 System Level Design with IBM PowerPC Models A view of system level design SLE-m3 The System-Level Challenges Verification escapes cost design success There is a 45% chance of committing

More information

Cadence SystemC Design and Verification. NMI FPGA Network Meeting Jan 21, 2015

Cadence SystemC Design and Verification. NMI FPGA Network Meeting Jan 21, 2015 Cadence SystemC Design and Verification NMI FPGA Network Meeting Jan 21, 2015 The High Level Synthesis Opportunity Raising Abstraction Improves Design & Verification Optimizes Power, Area and Timing for

More information

AT-501 Cortex-A5 System On Module Product Brief

AT-501 Cortex-A5 System On Module Product Brief AT-501 Cortex-A5 System On Module Product Brief 1. Scope The following document provides a brief description of the AT-501 System on Module (SOM) its features and ordering options. For more details please

More information

Verilog for High Performance

Verilog for High Performance Verilog for High Performance Course Description This course provides all necessary theoretical and practical know-how to write synthesizable HDL code through Verilog standard language. The course goes

More information

M ICROSTAR LA BORATORIE S TM

M ICROSTAR LA BORATORIE S TM M ICROSTAR LA BORATORIE S TM 2265 116th Avenue N.E., Bellevue, WA 98004 Sales & Customer Support: (425) 453-2345 Finance & Administration: (425) 453-9489 Fax: (425) 453-3199 World Wide Web: http://www.mstarlabs.com/

More information

MANAGING IMAGE DATA IN AUTOMOTIVE INFOTAINMENT APPLICATIONS USING LOW COST PLDS

MANAGING IMAGE DATA IN AUTOMOTIVE INFOTAINMENT APPLICATIONS USING LOW COST PLDS MANAGING IMAGE DATA IN AUTOMOTIVE INFOTAINMENT APPLICATIONS USING LOW COST PLDS August 2011 Lattice Semiconductor 5555 Northeast Moore Ct. Hillsboro, Oregon 97124 USA Telephone: (503) 268-8000 www.latticesemi.com

More information

With Fixed Point or Floating Point Processors!!

With Fixed Point or Floating Point Processors!! Product Information Sheet High Throughput Digital Signal Processor OVERVIEW With Fixed Point or Floating Point Processors!! Performance Up to 14.4 GIPS or 7.7 GFLOPS Peak Processing Power Continuous Input

More information

Challenges to Embedding Computer Vision J. Scott Gardner General Manager and Editor-in-Chief Embedded Vision Alliance (www.embedded-vision.

Challenges to Embedding Computer Vision J. Scott Gardner General Manager and Editor-in-Chief Embedded Vision Alliance (www.embedded-vision. Challenges to Embedding Computer Vision J. Scott Gardner General Manager and Editor-in-Chief Embedded Vision Alliance (www.embedded-vision.com) May 16, 2011 Figure 1 HAL 9000 a machine that sees. Source:

More information

TMS320C672x DSP Dual Data Movement Accelerator (dmax) Reference Guide

TMS320C672x DSP Dual Data Movement Accelerator (dmax) Reference Guide TMS320C672x DSP Dual Data Movement Accelerator (dmax) Reference Guide Literature Number: SPRU795D November 2005 Revised October 2007 2 SPRU795D November 2005 Revised October 2007 Contents Preface... 11

More information

Low-Power Server Combines Efficiency with Durable, Mobile Performance

Low-Power Server Combines Efficiency with Durable, Mobile Performance SOLUTION BRIEF Intel, XENON Systems & SenSen Networks Low-Power Server Combines Efficiency with Durable, Mobile Performance XENON* Systems developed an innovative and unique small form factor server as

More information

HotChips An innovative HD video and digital image processor for low-cost digital entertainment products. Deepu Talla.

HotChips An innovative HD video and digital image processor for low-cost digital entertainment products. Deepu Talla. HotChips 2007 An innovative HD video and digital image processor for low-cost digital entertainment products Deepu Talla Texas Instruments 1 Salient features of the SoC HD video encode and decode using

More information

Hardware Design Environments. Dr. Mahdi Abbasi Computer Engineering Department Bu-Ali Sina University

Hardware Design Environments. Dr. Mahdi Abbasi Computer Engineering Department Bu-Ali Sina University Hardware Design Environments Dr. Mahdi Abbasi Computer Engineering Department Bu-Ali Sina University Outline Welcome to COE 405 Digital System Design Design Domains and Levels of Abstractions Synthesis

More information

Platform-based Design

Platform-based Design Platform-based Design The New System Design Paradigm IEEE1394 Software Content CPU Core DSP Core Glue Logic Memory Hardware BlueTooth I/O Block-Based Design Memory Orthogonalization of concerns: the separation

More information

VHDL for Synthesis. Course Description. Course Duration. Goals

VHDL for Synthesis. Course Description. Course Duration. Goals VHDL for Synthesis Course Description This course provides all necessary theoretical and practical know how to write an efficient synthesizable HDL code through VHDL standard language. The course goes

More information

Five Ways to Build Flexibility into Industrial Applications with FPGAs

Five Ways to Build Flexibility into Industrial Applications with FPGAs GM/M/A\ANNETTE\2015\06\wp-01154- flexible-industrial.docx Five Ways to Build Flexibility into Industrial Applications with FPGAs by Jason Chiang and Stefano Zammattio, Altera Corporation WP-01154-2.0 White

More information

CONSIDERATIONS FOR THE DESIGN OF A REUSABLE SOC HARDWARE/SOFTWARE

CONSIDERATIONS FOR THE DESIGN OF A REUSABLE SOC HARDWARE/SOFTWARE 1 2 3 CONSIDERATIONS FOR THE DESIGN OF A REUSABLE SOC HARDWARE/SOFTWARE DEVELOPMENT BOARD Authors: Jonah Probell and Andy Young, design engineers, Lexra, Inc. 4 5 6 7 8 9 A Hardware/Software Development

More information

Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances

Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances Technology Brief Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances Intel PRO/1000 PT and PF Quad Port Bypass Server Adapters for In-line Server Appliances The world

More information

Supra-linear Packet Processing Performance with Intel Multi-core Processors

Supra-linear Packet Processing Performance with Intel Multi-core Processors White Paper Dual-Core Intel Xeon Processor LV 2.0 GHz Communications and Networking Applications Supra-linear Packet Processing Performance with Intel Multi-core Processors 1 Executive Summary Advances

More information

MEMORY/RESOURCE MANAGEMENT IN MULTICORE SYSTEMS

MEMORY/RESOURCE MANAGEMENT IN MULTICORE SYSTEMS MEMORY/RESOURCE MANAGEMENT IN MULTICORE SYSTEMS INSTRUCTOR: Dr. MUHAMMAD SHAABAN PRESENTED BY: MOHIT SATHAWANE AKSHAY YEMBARWAR WHAT IS MULTICORE SYSTEMS? Multi-core processor architecture means placing

More information

Hardware/Software Co-design

Hardware/Software Co-design Hardware/Software Co-design Zebo Peng, Department of Computer and Information Science (IDA) Linköping University Course page: http://www.ida.liu.se/~petel/codesign/ 1 of 52 Lecture 1/2: Outline : an Introduction

More information

Functional Safety and Safety Standards: Challenges and Comparison of Solutions AA309

Functional Safety and Safety Standards: Challenges and Comparison of Solutions AA309 June 25th, 2007 Functional Safety and Safety Standards: Challenges and Comparison of Solutions AA309 Christopher Temple Automotive Systems Technology Manager Overview Functional Safety Basics Functional

More information

FEATURES. APPLICATIONS Machine Vision Embedded Instrumentation Motion Control Traffic Monitoring Security

FEATURES. APPLICATIONS Machine Vision Embedded Instrumentation Motion Control Traffic Monitoring Security FEATURES High-performance CMOSIS sensors - Sensitivity: 5.56 V/lux.s - Dynamic range: 60 db - Dark Noise: 8.6 e - - High speed: 95* fps - 8M Pixel: 3360(H) x 2496(V) - Monochrome / Color - Global Shutter

More information

Overview of Microcontroller and Embedded Systems

Overview of Microcontroller and Embedded Systems UNIT-III Overview of Microcontroller and Embedded Systems Embedded Hardware and Various Building Blocks: The basic hardware components of an embedded system shown in a block diagram in below figure. These

More information

Bosch Rexroth* Innovates Sercos SoftMaster* for the Industrial PC Platform with the Intel Ethernet Controller I210

Bosch Rexroth* Innovates Sercos SoftMaster* for the Industrial PC Platform with the Intel Ethernet Controller I210 Solution brief Bosch Rexroth* Innovates Sercos SoftMaster* for the Industrial PC Platform with the Intel Ethernet Controller I210 TenAsys* INtime* real-time software enables the solution on a standard,

More information

Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models. Jason Andrews

Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models. Jason Andrews Performance Optimization for an ARM Cortex-A53 System Using Software Workloads and Cycle Accurate Models Jason Andrews Agenda System Performance Analysis IP Configuration System Creation Methodology: Create,

More information

GigE Vision, Sony ICX625 CCD sensor, auto-iris, 15 fps

GigE Vision, Sony ICX625 CCD sensor, auto-iris, 15 fps Prosilica GC 2450 Sony ICX625 CCD sensor 15 fps at full resolution Rugged housing Video-type auto iris GigE Vision, Sony ICX625 CCD sensor, auto-iris, 15 fps Prosilica GC2450 is a 5.0 Megapixel camera

More information

COE 561 Digital System Design & Synthesis Introduction

COE 561 Digital System Design & Synthesis Introduction 1 COE 561 Digital System Design & Synthesis Introduction Dr. Aiman H. El-Maleh Computer Engineering Department King Fahd University of Petroleum & Minerals Outline Course Topics Microelectronics Design

More information

The Challenges of System Design. Raising Performance and Reducing Power Consumption

The Challenges of System Design. Raising Performance and Reducing Power Consumption The Challenges of System Design Raising Performance and Reducing Power Consumption 1 Agenda The key challenges Visibility for software optimisation Efficiency for improved PPA 2 Product Challenge - Software

More information

EMBEDDED VISION AND 3D SENSORS: WHAT IT MEANS TO BE SMART

EMBEDDED VISION AND 3D SENSORS: WHAT IT MEANS TO BE SMART EMBEDDED VISION AND 3D SENSORS: WHAT IT MEANS TO BE SMART INTRODUCTION Adding embedded processing to simple sensors can make them smart but that is just the beginning of the story. Fixed Sensor Design

More information

ASYNCHRONOUS SHADERS WHITE PAPER 0

ASYNCHRONOUS SHADERS WHITE PAPER 0 ASYNCHRONOUS SHADERS WHITE PAPER 0 INTRODUCTION GPU technology is constantly evolving to deliver more performance with lower cost and lower power consumption. Transistor scaling and Moore s Law have helped

More information

Parallel Programming Multicore systems

Parallel Programming Multicore systems FYS3240 PC-based instrumentation and microcontrollers Parallel Programming Multicore systems Spring 2011 Lecture #9 Bekkeng, 4.4.2011 Introduction Until recently, innovations in processor technology have

More information

Network Embedded Systems Sensor Networks Fall Hardware. Marcus Chang,

Network Embedded Systems Sensor Networks Fall Hardware. Marcus Chang, Network Embedded Systems Sensor Networks Fall 2013 Hardware Marcus Chang, mchang@cs.jhu.edu 1 Embedded Systems Designed to do one or a few dedicated and/or specific functions Embedded as part of a complete

More information

Lab Report 6. Chris Dobson EEL4713

Lab Report 6. Chris Dobson EEL4713 Lab Report 6 Chris Dobson EEL4713 Section 1: Book Problems The Blue non-revised 4th edition was used 6.3.1) b) 13.1992 ms 6.3.2) *minimum assumes the case where there is no seek time or rotational delay.

More information

White Paper The Need for a High-Bandwidth Memory Architecture in Programmable Logic Devices

White Paper The Need for a High-Bandwidth Memory Architecture in Programmable Logic Devices Introduction White Paper The Need for a High-Bandwidth Memory Architecture in Programmable Logic Devices One of the challenges faced by engineers designing communications equipment is that memory devices

More information

COT 4600 Operating Systems Fall Dan C. Marinescu Office: HEC 439 B Office hours: Tu-Th 3:00-4:00 PM

COT 4600 Operating Systems Fall Dan C. Marinescu Office: HEC 439 B Office hours: Tu-Th 3:00-4:00 PM COT 4600 Operating Systems Fall 2009 Dan C. Marinescu Office: HEC 439 B Office hours: Tu-Th 3:00-4:00 PM Lecture 23 Attention: project phase 4 due Tuesday November 24 Final exam Thursday December 10 4-6:50

More information

Moore s Law. Computer architect goal Software developer assumption

Moore s Law. Computer architect goal Software developer assumption Moore s Law The number of transistors that can be placed inexpensively on an integrated circuit will double approximately every 18 months. Self-fulfilling prophecy Computer architect goal Software developer

More information

Cache Justification for Digital Signal Processors

Cache Justification for Digital Signal Processors Cache Justification for Digital Signal Processors by Michael J. Lee December 3, 1999 Cache Justification for Digital Signal Processors By Michael J. Lee Abstract Caches are commonly used on general-purpose

More information

ArduCAM-M-5MP Camera Shield

ArduCAM-M-5MP Camera Shield ArduCAM-M-5MP Camera Shield 5MP SPI Camera User Guide Rev 1.0, Mar 2015 Table of Contents 1 Introduction... 2 2 Application... 2 3 Features... 3 4 Key Specifications... 3 5 Pin Definition... 3 6 Block

More information

DesignWare IP for IoT SoC Designs

DesignWare IP for IoT SoC Designs DesignWare IP for IoT SoC Designs The Internet of Things (IoT) is connecting billions of intelligent things at our fingertips. The ability to sense countless amounts of information that communicates to

More information

The Embedded System Design Process. Wolf Text - Chapter 1.3

The Embedded System Design Process. Wolf Text - Chapter 1.3 The Embedded System Design Process Wolf Text - Chapter 1.3 Design methodologies A procedure for designing a system. Understanding your methodology helps you ensure you didn t skip anything. Compilers,

More information

Computer and Hardware Architecture I. Benny Thörnberg Associate Professor in Electronics

Computer and Hardware Architecture I. Benny Thörnberg Associate Professor in Electronics Computer and Hardware Architecture I Benny Thörnberg Associate Professor in Electronics Hardware architecture Computer architecture The functionality of a modern computer is so complex that no human can

More information

SAP HANA. Jake Klein/ SVP SAP HANA June, 2013

SAP HANA. Jake Klein/ SVP SAP HANA June, 2013 SAP HANA Jake Klein/ SVP SAP HANA June, 2013 SAP 3 YEARS AGO Middleware BI / Analytics Core ERP + Suite 2013 WHERE ARE WE NOW? Cloud Mobile Applications SAP HANA Analytics D&T Changed Reality Disruptive

More information

SDACCEL DEVELOPMENT ENVIRONMENT. The Xilinx SDAccel Development Environment. Bringing The Best Performance/Watt to the Data Center

SDACCEL DEVELOPMENT ENVIRONMENT. The Xilinx SDAccel Development Environment. Bringing The Best Performance/Watt to the Data Center SDAccel Environment The Xilinx SDAccel Development Environment Bringing The Best Performance/Watt to the Data Center Introduction Data center operators constantly seek more server performance. Currently

More information

Intel Solid State Drive Data Center Family for PCIe* in Baidu s Data Center Environment

Intel Solid State Drive Data Center Family for PCIe* in Baidu s Data Center Environment Intel Solid State Drive Data Center Family for PCIe* in Baidu s Data Center Environment Case Study Order Number: 334534-002US Ordering Information Contact your local Intel sales representative for ordering

More information

Datacenter replication solution with quasardb

Datacenter replication solution with quasardb Datacenter replication solution with quasardb Technical positioning paper April 2017 Release v1.3 www.quasardb.net Contact: sales@quasardb.net Quasardb A datacenter survival guide quasardb INTRODUCTION

More information

The S6000 Family of Processors

The S6000 Family of Processors The S6000 Family of Processors Today s Design Challenges The advent of software configurable processors In recent years, the widespread adoption of digital technologies has revolutionized the way in which

More information

NI Smart Cameras PRODUCT FLYER CONTENTS. Have a question? Contact Us.

NI Smart Cameras PRODUCT FLYER CONTENTS. Have a question? Contact Us. Have a question? Contact Us. PRODUCT FLYER NI Smart Cameras CONTENTS NI Smart Cameras Detailed View of ISC-178x Key Features Vision Software Hardware Services Page 1 ni.com NI Smart Cameras NI Smart Cameras

More information

Introduction. Definition. What is an embedded system? What are embedded systems? Challenges in embedded computing system design. Design methodologies.

Introduction. Definition. What is an embedded system? What are embedded systems? Challenges in embedded computing system design. Design methodologies. Introduction What are embedded systems? Challenges in embedded computing system design. Design methodologies. What is an embedded system? Communication Avionics Automobile Consumer Electronics Office Equipment

More information

Course Introduction. Purpose: Objectives: Content: Learning Time:

Course Introduction. Purpose: Objectives: Content: Learning Time: Course Introduction Purpose: This course provides an overview of the Renesas SuperH series of 32-bit RISC processors, especially the microcontrollers in the SH-2 and SH-2A series Objectives: Learn the

More information

Your Company Logo Here. Flying High-Performance FPGAs on Satellites: Two Case Studies

Your Company Logo Here. Flying High-Performance FPGAs on Satellites: Two Case Studies Your Company Logo Here Flying High-Performance FPGAs on Satellites: Two Case Studies Introduction Often when considering flying a FPGA or other high-performance device the first thoughts might be how will

More information

Media Instructions, Coprocessors, and Hardware Accelerators. Overview

Media Instructions, Coprocessors, and Hardware Accelerators. Overview Media Instructions, Coprocessors, and Hardware Accelerators Steven P. Smith SoC Design EE382V Fall 2009 EE382 System-on-Chip Design Coprocessors, etc. SPS-1 University of Texas at Austin Overview SoCs

More information

FPGA design with National Instuments

FPGA design with National Instuments FPGA design with National Instuments Rémi DA SILVA Systems Engineer - Embedded and Data Acquisition Systems - MED Region ni.com The NI Approach to Flexible Hardware Processor Real-time OS Application software

More information

Flexible & Scalable 48V Solutions Powering Tomorrow s Data Centers. Sean Gold Maxim Integrated 3/9/2017

Flexible & Scalable 48V Solutions Powering Tomorrow s Data Centers. Sean Gold Maxim Integrated 3/9/2017 Flexible & Scalable 48V Solutions Powering Tomorrow s Data Centers Sean Gold Maxim Integrated 3/9/2017 Rack Architectures are Changing from 12V to 48V Why a New Rack Power Architecture is Needed Data Centers

More information

CEC 450 Real-Time Systems

CEC 450 Real-Time Systems CEC 450 Real-Time Systems Lecture 6 Accounting for I/O Latency September 28, 2015 Sam Siewert A Service Release and Response C i WCET Input/Output Latency Interference Time Response Time = Time Actuation

More information

QLogic 16Gb Gen 5 Fibre Channel for Database and Business Analytics

QLogic 16Gb Gen 5 Fibre Channel for Database and Business Analytics QLogic 16Gb Gen 5 Fibre Channel for Database Assessment for Database and Business Analytics Using the information from databases and business analytics helps business-line managers to understand their

More information

Apple ProRes RAW. White Paper April 2018

Apple ProRes RAW. White Paper April 2018 Apple ProRes RAW White Paper April 2018 Contents Introduction 3 About Raw Video 4 Data Rate 6 Performance 8 Using ProRes RAW in Final Cut Pro 12 Using Log Conversion with Built-in Camera LUTs 13 Using

More information

COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. 5 th. Edition. Chapter 1. Computer Abstractions and Technology

COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface. 5 th. Edition. Chapter 1. Computer Abstractions and Technology COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface 5 th Edition Chapter 1 Computer Abstractions and Technology The Computer Revolution Progress in computer technology Underpinned by Moore

More information

EEM870 Embedded System and Experiment Lecture 4: SoC Design Flow and Tools

EEM870 Embedded System and Experiment Lecture 4: SoC Design Flow and Tools EEM870 Embedded System and Experiment Lecture 4: SoC Design Flow and Tools Wen-Yen Lin, Ph.D. Department of Electrical Engineering Chang Gung University Email: wylin@mail.cgu.edu.tw March 2013 Agenda Introduction

More information

Multimedia Systems 2011/2012

Multimedia Systems 2011/2012 Multimedia Systems 2011/2012 System Architecture Prof. Dr. Paul Müller University of Kaiserslautern Department of Computer Science Integrated Communication Systems ICSY http://www.icsy.de Sitemap 2 Hardware

More information

Addressing the Memory Wall

Addressing the Memory Wall Lecture 26: Addressing the Memory Wall Parallel Computer Architecture and Programming CMU 15-418/15-618, Spring 2015 Tunes Cage the Elephant Back Against the Wall (Cage the Elephant) This song is for the

More information

New System Solutions for Laser Printer Applications by Oreste Emanuele Zagano STMicroelectronics

New System Solutions for Laser Printer Applications by Oreste Emanuele Zagano STMicroelectronics New System Solutions for Laser Printer Applications by Oreste Emanuele Zagano STMicroelectronics Introduction Recently, the laser printer market has started to move away from custom OEM-designed 1 formatter

More information

Memory Systems IRAM. Principle of IRAM

Memory Systems IRAM. Principle of IRAM Memory Systems 165 other devices of the module will be in the Standby state (which is the primary state of all RDRAM devices) or another state with low-power consumption. The RDRAM devices provide several

More information

Execution architecture concepts

Execution architecture concepts by Gerrit Muller Buskerud University College e-mail: gaudisite@gmail.com www.gaudisite.nl Abstract The execution architecture determines largely the realtime and performance behavior of a system. Hard

More information

PowerPlay Early Power Estimator User Guide for Cyclone III FPGAs

PowerPlay Early Power Estimator User Guide for Cyclone III FPGAs PowerPlay Early Power Estimator User Guide for Cyclone III FPGAs 101 Innovation Drive San Jose, CA 95134 www.altera.com Software Version: QII v9.0 SP2 Document Version: 2.0 Document Date: June 2009 UG-01013-2.0

More information

White Paper. Major Performance Tuning Considerations for Weblogic Server

White Paper. Major Performance Tuning Considerations for Weblogic Server White Paper Major Performance Tuning Considerations for Weblogic Server Table of Contents Introduction and Background Information... 2 Understanding the Performance Objectives... 3 Measuring your Performance

More information

The Use Of Virtual Platforms In MP-SoC Design. Eshel Haritan, VP Engineering CoWare Inc. MPSoC 2006

The Use Of Virtual Platforms In MP-SoC Design. Eshel Haritan, VP Engineering CoWare Inc. MPSoC 2006 The Use Of Virtual Platforms In MP-SoC Design Eshel Haritan, VP Engineering CoWare Inc. MPSoC 2006 1 MPSoC Is MP SoC design happening? Why? Consumer Electronics Complexity Cost of ASIC Increased SW Content

More information

The Computer Revolution. Classes of Computers. Chapter 1

The Computer Revolution. Classes of Computers. Chapter 1 COMPUTER ORGANIZATION AND DESIGN The Hardware/Software Interface 5 th Edition 1 Chapter 1 Computer Abstractions and Technology 1 The Computer Revolution Progress in computer technology Underpinned by Moore

More information

Prosilica GC 1380H. GigE Vision, Sony ICX285 EXview CCD sensor, auto-iris, 30 fps. Benefits and features: Options:

Prosilica GC 1380H. GigE Vision, Sony ICX285 EXview CCD sensor, auto-iris, 30 fps. Benefits and features: Options: Prosilica GC 1380H Sony ICX285 CCD sensor 30 fps at full resolution Rugged housing Video-type auto iris GigE Vision, Sony ICX285 EXview CCD sensor, auto-iris, 30 fps Prosilica GC1380H is a 1.4 Megapixel

More information

THE GROWING USE OF PROGRAMMABLE LOGIC DEVICES IN MOBILE HANDSETS

THE GROWING USE OF PROGRAMMABLE LOGIC DEVICES IN MOBILE HANDSETS THE GROWING USE OF PROGRAMMABLE LOGIC DEVICES IN MOBILE HANDSETS June 2012 Lattice Semiconductor 5555 Northeast Moore Ct. Hillsboro, Oregon 97124 USA Telephone: (503) 268-8000 www.latticesemi.com 1 The

More information

FPGA Implementation of a Single Pass Real-Time Blob Analysis Using Run Length Encoding

FPGA Implementation of a Single Pass Real-Time Blob Analysis Using Run Length Encoding FPGA Implementation of a Single Pass Real-Time J. Trein *, A. Th. Schwarzbacher + and B. Hoppe * Department of Electronic and Computer Science, Hochschule Darmstadt, Germany *+ School of Electronic and

More information

FPGA Provides Speedy Data Compression for Hyperspectral Imagery

FPGA Provides Speedy Data Compression for Hyperspectral Imagery FPGA Provides Speedy Data Compression for Hyperspectral Imagery Engineers implement the Fast Lossless compression algorithm on a Virtex-5 FPGA; this implementation provides the ability to keep up with

More information

Most real programs operate somewhere between task and data parallelism. Our solution also lies in this set.

Most real programs operate somewhere between task and data parallelism. Our solution also lies in this set. for Windows Azure and HPC Cluster 1. Introduction In parallel computing systems computations are executed simultaneously, wholly or in part. This approach is based on the partitioning of a big task into

More information

ni.com Best Practices for Architecting Embedded Applications in LabVIEW

ni.com Best Practices for Architecting Embedded Applications in LabVIEW Best Practices for Architecting Embedded Applications in LabVIEW Overview of NI RIO Architecture PC Real Time Controller FPGA 2 Where to Start? 3 Requirements Before you start to design your system, you

More information

GAUSS OBC ABACUS 2017

GAUSS OBC ABACUS 2017 [] Table of contents Table of contents... 1 1. Introduction... 3 1.1. ABACUS Features... 3 1.2. Block Diagram... 6 2. Pinouts... 7 3. Inertial Measurement Unit Details... 10 3.1. Orientation of Axes...

More information

The Design of MCU's Communication Interface

The Design of MCU's Communication Interface X International Symposium on Industrial Electronics INDEL 2014, Banja Luka, November 0608, 2014 The Design of MCU's Communication Interface Borisav Jovanović, Dejan Mirković and Milunka Damnjanović University

More information

Intel Atom Processor Based Platform Technologies. Intelligent Systems Group Intel Corporation

Intel Atom Processor Based Platform Technologies. Intelligent Systems Group Intel Corporation Intel Atom Processor Based Platform Technologies Intelligent Systems Group Intel Corporation Legal Disclaimer INFORMATION IN THIS DOCUMENT IS PROVIDED IN CONNECTION WITH INTEL PRODUCTS. NO LICENSE, EXPRESS

More information

Applying the Benefits of Network on a Chip Architecture to FPGA System Design

Applying the Benefits of Network on a Chip Architecture to FPGA System Design white paper Intel FPGA Applying the Benefits of on a Chip Architecture to FPGA System Design Authors Kent Orthner Senior Manager, Software and IP Intel Corporation Table of Contents Abstract...1 Introduction...1

More information

Monitor Qlik Sense sites. Qlik Sense Copyright QlikTech International AB. All rights reserved.

Monitor Qlik Sense sites. Qlik Sense Copyright QlikTech International AB. All rights reserved. Monitor Qlik Sense sites Qlik Sense 2.1.2 Copyright 1993-2015 QlikTech International AB. All rights reserved. Copyright 1993-2015 QlikTech International AB. All rights reserved. Qlik, QlikTech, Qlik Sense,

More information

Chronos Latency - Pole Position Performance

Chronos Latency - Pole Position Performance WHITE PAPER Chronos Latency - Pole Position Performance By G. Rinaldi and M. T. Moreira, Chronos Tech 1 Introduction Modern SoC performance is often limited by the capability to exchange information at

More information

Fujitsu Semiconductor Releases New System Controller LSI with High-Performance Graphics for Automotive Applications

Fujitsu Semiconductor Releases New System Controller LSI with High-Performance Graphics for Automotive Applications Fujitsu Semiconductor Releases New System Controller LSI with High-Performance Graphics for Automotive Applications Yokohama, Japan, July 26, 2010 - today announced the forthcoming release of six products

More information

PowerPC on NetFPGA CSE 237B. Erik Rubow

PowerPC on NetFPGA CSE 237B. Erik Rubow PowerPC on NetFPGA CSE 237B Erik Rubow NetFPGA PCI card + FPGA + 4 GbE ports FPGA (Virtex II Pro) has 2 PowerPC hard cores Untapped resource within NetFPGA community Goals Evaluate performance of on chip

More information

Increasing Performance for PowerCenter Sessions that Use Partitions

Increasing Performance for PowerCenter Sessions that Use Partitions Increasing Performance for PowerCenter Sessions that Use Partitions 1993-2015 Informatica LLC. No part of this document may be reproduced or transmitted in any form, by any means (electronic, photocopying,

More information

INTRODUCTION TO CATAPULT C

INTRODUCTION TO CATAPULT C INTRODUCTION TO CATAPULT C Vijay Madisetti, Mohanned Sinnokrot Georgia Institute of Technology School of Electrical and Computer Engineering with adaptations and updates by: Dongwook Lee, Andreas Gerstlauer

More information

Hardware-Software Codesign. 1. Introduction

Hardware-Software Codesign. 1. Introduction Hardware-Software Codesign 1. Introduction Lothar Thiele 1-1 Contents What is an Embedded System? Levels of Abstraction in Electronic System Design Typical Design Flow of Hardware-Software Systems 1-2

More information

Intel Parallel Studio 2011

Intel Parallel Studio 2011 THE ULTIMATE ALL-IN-ONE PERFORMANCE TOOLKIT Studio 2011 Product Brief Studio 2011 Accelerate Development of Reliable, High-Performance Serial and Threaded Applications for Multicore Studio 2011 is a comprehensive

More information

Tutorial: Analyzing MPI Applications. Intel Trace Analyzer and Collector Intel VTune Amplifier XE

Tutorial: Analyzing MPI Applications. Intel Trace Analyzer and Collector Intel VTune Amplifier XE Tutorial: Analyzing MPI Applications Intel Trace Analyzer and Collector Intel VTune Amplifier XE Contents Legal Information... 3 1. Overview... 4 1.1. Prerequisites... 5 1.1.1. Required Software... 5 1.1.2.

More information

MIPS Technologies MIPS32 M4K Synthesizable Processor Core By the staff of

MIPS Technologies MIPS32 M4K Synthesizable Processor Core By the staff of An Independent Analysis of the: MIPS Technologies MIPS32 M4K Synthesizable Processor Core By the staff of Berkeley Design Technology, Inc. OVERVIEW MIPS Technologies, Inc. is an Intellectual Property (IP)

More information

Higher Level Programming Abstractions for FPGAs using OpenCL

Higher Level Programming Abstractions for FPGAs using OpenCL Higher Level Programming Abstractions for FPGAs using OpenCL Desh Singh Supervising Principal Engineer Altera Corporation Toronto Technology Center ! Technology scaling favors programmability CPUs."#/0$*12'$-*

More information

QPP Proprietary Profile Guide

QPP Proprietary Profile Guide Rev. 04 April 2018 Application note Document information Info Content Keywords Proprietary Profile, Server, Client Abstract The Proprietary Profile is used to transfer the raw data between BLE devices.

More information

Hardware-Software Codesign. 1. Introduction

Hardware-Software Codesign. 1. Introduction Hardware-Software Codesign 1. Introduction Lothar Thiele 1-1 Contents What is an Embedded System? Levels of Abstraction in Electronic System Design Typical Design Flow of Hardware-Software Systems 1-2

More information

[Sub Track 1-3] FPGA/ASIC 을타겟으로한알고리즘의효율적인생성방법및신기능소개

[Sub Track 1-3] FPGA/ASIC 을타겟으로한알고리즘의효율적인생성방법및신기능소개 [Sub Track 1-3] FPGA/ASIC 을타겟으로한알고리즘의효율적인생성방법및신기능소개 정승혁과장 Senior Application Engineer MathWorks Korea 2015 The MathWorks, Inc. 1 Outline When FPGA, ASIC, or System-on-Chip (SoC) hardware is needed Hardware

More information