Day 1 Tuesday, June 7th, 2016 Click on the class name to see the abstract. | ||
---|---|---|
Time | Room | Agenda |
10:15 - 11:05 | 13AB | Keynote Address: Pragmatic approach to making the Internet of Things real today with Joyce Mullen, Vice President and General Manager, Dell OEM Solutions |
11:10 - 12:00 | 13AB | Choosing an OS for your IoT device with Bob Zeidman, Founder and President, Zeidman Technologies, Inc. |
14 | The Heterogeneous System Architecture – A foundation for the next generation of heterogeneous computing with Paul Blinzer, Fellow, AMD | |
1:00 - 1:55 | 13AB | The pros and cons of using Agile for embedded and IoT systems with Niall Cooling, CEO, Feabhas Ltd. |
14 | GPU compute in medical and print imaging with Amey Deosthali, Director of Embedded Imaging, AMD | |
2:00 - 2:25 | 13AB | Pre-silicon OS porting, bring up and driver development with Simon Davidmann, Founder and CEO, Imperas Software Ltd. |
2:00 - 2:55 | 14 | The embedded acceleration API maze: Options and tradeoffs with Neil Trevett, President of the Khronos Group and Vice President of Mobile Ecosystem at NVIDIA |
2:30 - 2:55 | 13AB | Accelerating ARM software development, debug, and test with Simon Davidmann, Founder and CEO, Imperas Software Ltd. |
3:00 - 3:30 | 13AB | EXPERT PANEL – Heterogeneous Systems Architectures: Power, performance, and programming for the future with Paul Blinzer (AMD), Amey Deosthali (AMD), Neil Trevett (Khronos Group), and Brandon Lewis (Moderator) |
3:35 - 5:35 | 13AB | Shortening your embedded design cycle: Hands-on lab with Renesas Synergy Starter Kit with Gary Jacobson, Principal Engineer, General Purpose Products Unit, Renesas Electronics America Inc. |
Day 2 Wednesday, June 8th, 2016 Click on the class name to see the abstract. | ||
---|---|---|
Time | Room | Agenda |
10:15 - 11:05 | 13AB | Keynote Address: Just how much is enough security? with Rhonda Dirvin, Director, IoT Verticals, ARM |
11:10 - 12:00 | 13AB | Securing the Internet of Things begins with high-quality code with Jared Fry, Field Applications Engineer, LDRA |
14 | Designing systems for multi-node Big Analog Data acquisition with Matthew Bollom, Product Manager for NI InsightCM, National Instruments | |
1:00 - 1:55 | 13AB | Develop new products, services, and business models with cloud-based cognitive computing with Arnaud Mathieu, Program Director, Watson IoT Platform Development, IBM |
14 | Industrial motion control: Why software Is better, faster, and cheaper than hardware with Dipesh Mukerji, VP Marketing & Strategy, KINGSTAR and Jerry Leitz, Director of Field Engineering, IntervalZero | |
2:00 - 2:55 | 13AB | Transforming IoT data with machine learning and artificial intelligence with Usman Shuja, VP of Business Development, SparkCognition |
14 | Technologies emerging at the Edge with John Milios, CEO, Sendyne | |
3:00 - 3:55 | 13AB | Software virtualization lessons for extreme IoT portability and scale with Vincent Perrier, Chief Marketing Officer, MicroEJ |
14 | The merits of digital power for embedded and industrial IoT designs with Chance Dunlap, Director of Infrastructure Power, Intersil | |
4:00 - 5:30 | 13AB | Ethernet-enabled imaging and motor control with industrial-grade SoC FPGAs with Mark Nagel, Field Applications Engineer/Senior Technical Contributor, Microsemi |
The Renesas Synergy™ SK-S7G2 Starter Kit is an extremely low-cost way to access the entire Synergy Platform enabling full development using the vast majority of all Synergy Software Package (SSP) functions. Secure connectivity over Ethernet, USB, CAN, plus wireless connectivity to mobile Internet devices via BLE 4.1 can be exercised and tailored to your needs. Color graphics, audio, and capacitive touch user interface features of SSP are operative with the ability to exercise the SSP's Application Framework to balance simultaneous connectivity and user interface activities all managed by the ThreadX® RTOS. Within minutes you can experience the capabilities of the S7 Series S7G2 MCU and all the ingredients of the Synergy Platform. Expansion of the SK-S7G2 board is available via Arduino and Pmod™ connection points enabling you to add your own functionality to the baseline.
The Industrial Internet of Things still feels like the wild, wild west. Things have improved, but
there’s still a long way to go. To achieve success, manufacturers need to understand how the IIoT
can create real value for their customers and their company, and then set up the team for success.
In this Keynote Address, Joyce Mullen, Vice President and General Manager of Dell OEM Solutions,
will share Dell’s pragmatic approach towards making the Internet of Things a reality today. Using
case studies, Joyce will share insights on architecting for analytics, the need to put security
first, and importance of choice and flexibility.
In today’s highly connected world your solutions need to keep up. And you can maintain your competitive advantage by leveraging Dell OEM’s cloud, mobility, big data, security and Internet of Things experience to stay on the cutting edge.
This workshop explores the different operating system options available to developers working with
Internet of Things systems-on-chip (SoCs). The three basic options are 1) to purchase an
off-the-shelf RTOS, 2) write your own RTOS, or 3) use a software synthesis tool to automatically
generate an RTOS. If you purchase one, what is available and what are the tradeoffs? If you write
your own, which issues do you need to take into account? If you synthesize one, what tools are
available and how do they work? And, all of this must be considered within the resource constraints
of device-class MCUs and SoCs.
Zeidman Technologies develops hardware/software codesign tools for embedded system development that promise to change the way these systems are designed, simulated, and implemented. The company is an outgrowth of Zeidman Consulting, a research and development contract firm, specializing in digital hardware and software design.
The pace of today's embedded and Internet of Things device deployments (and lifecycles) demands a
new approach to software development that is leaner, meaner, and can meet the challenges of
continuous integration. Enter Agile development practices, but what does that mean, really? Since
the Agile Manifesto was released in 2001, Agile development has been influenced by processes ranging
from XP and SCRUM to Lean and Kanban, but none to date have effectively aligned Agile with the
requirements of embedded/IoT development. In this technical presentation from Niall Cooling, CEO of
Feabhas Limited, learn about the pros, cons, and intricate complexities of using Agile practices in
embedded design.
Feabhas is a specialist in real time embedded software development, providing assessment, training and consulting to clients in a wide range of industry sectors. The Feabhas mission is to improve the quality of the embedded software development process and thus reduce software development times and costs. Based in the UK, Feabhas was formed in 1995 and has trained over 15,000 engineers worldwide to date.
Just because you get to the prompt doesn’t mean your OS is working. Virtual platforms can help you
get to the prompt and beyond, by helping to port and bring up Linux or a real time operating system
(RTOS) without silicon, or even an emulation platform or FPGA prototype, being available. Virtual
platforms with OS-aware tools non-instrusively enable detailed debug. These tools also allow for
peripheral-driver, hardware-software co-debug. Case studies of both Linux and RTOS bring up will be
presented.
Imperas is revolutionizing embedded software development! Our innovative approach to virtual platforms combines open source modeling and infrastructure for easy open platform creation, a powerful embedded software development environment, industrial strength simulation technology and advanced development tooling. Results: Imperas software development, debug and test tools improve code quality, engineering productivity, and accelerate time to market.
Of course you’re using an ARM-based SoC in your embedded system. So how to accelerate software
development and achieve higher code quality? Virtual platforms can do both. This session uses a
Cortex-A72 based platform as an example to show how open source modeling enables easy virtual
platform creation, and how tools on top of the virtual platform can provide the controllability and
visibility needed to achieve a more robust and comprehensive software development environment.
Imperas is revolutionizing embedded software development! Our innovative approach to virtual platforms combines open source modeling and infrastructure for easy open platform creation, a powerful embedded software development environment, industrial strength simulation technology and advanced development tooling. Results: Imperas software development, debug and test tools improve code quality, engineering productivity, and accelerate time to market.
If your system needs to connect, whether it’s via Ethernet, USB, CAN, or a wireless medium such as
Bluetooth Low Energy, the Renesas Synergy SK-S7G2 Starter Kit offers a great head start. Couple that
with two hours of expert instruction, and you’re well on your way to learning how to save time when
designing your embedded system. In this hands-on workshop, you’ll receive the SK-S7G2 Starter Kit,
which is yours to keep after the class, as well as the training required to design a system with
color graphics and touch user interface. Using the Renesas Synergy Software Platform, which
encompasses application frameworks and the ThreadX real-time operating system, the instructor will
show you how to connect your board to a mobile phone as a simple example that will guide you down
the right path to your own embedded design.
Renesas Electronics, the #1 global microcontroller company, has taken its leadership and expertise into developing the Renesas Synergy™ Platform, a complete and qualified platform that accelerates IoT embedded development, in addition to being a premier supplier of advanced semiconductor solutions, including microcontrollers, SoC solutions and analog and power devices. http://www.renesas.com
Heterogeneous computing for compute intensive tasks has been established in a wide variety of
platforms, from IoT to smartphones and PCs to cloud data centers, using accelerators like DSPs,
CPUs, GPUs, and FPGAs. Applications range from machine learning, data mining, and environmental
cognition to enabling a better user experience at lower power points.
But using heterogeneous compute in these applications requires a great deal of specialized knowledge and tools, and maintenance of different implementations using APIs like OpenCL, custom vendor libraries, and proprietary APIs like CUDA, with little to no portability in programming model and between accelerators and vendors.
The Heterogeneous System Architecture (HSA) Foundation, a not-for-profit open consortium of SOC and SOC IP vendors, OEMs, academia, OSVs and ISVs, is designing a consistent heterogeneous platform architecture to make it dramatically easier to program heterogeneous parallel devices.
HSA addresses many of the current shortcomings at a system architecture and programming model level while providing a great foundation for existing software programming models.
In addition to GPU compute support, HSA allows for easily extending the architecture to other domain specific processors, fixed function or reprogrammable logic accelerators, and lays an efficient and versatile foundation for development of heterogeneous computing into the future. HSA provides platform requirements, and supports common toolchains like LLVM and GNU tools and many other high-level and domain specific languages. Various software frameworks have already been ported, and others are being ported to the infrastructure at an ever advancing rate.
The presentation gives the audience a high-level understanding of the goals of HSA, the HSA system architecture properties, and its use models by system software, tools and applications.
The following areas will be covered:
The HSA Foundation was founded June 2012 to enable the industry specification, advancement, and promotion of the Heterogeneous Systems Architecture (HSA) and help bring HSA-enabled platform and software solutions to the market, from mobile and embedded all the way up to HPC and cloud computing. The HSA Foundation is an open foundation with broad industry support for driving the next generation in compute and innovation.
GPU compute has leveraged discrete GPUs for a fairly limited set of academic and supercomputing
system workloads until recently. With the increase in performance of integrated GPU inside an
Accelerated Processing Unit (APU), introduction of Heterogeneous System Architecture (HSA) devices,
and proliferation of programming tools, we are seeing GPU compute make its way into mainstream
applications. In this discussion we will cover GPU compute and HSA, focusing on the application of
GPU compute in the Medical and Print Imaging segments. Examples of performance data will be reviewed
and the case made for how GPU compute can deliver tangible benefits.
For more than 45 years, AMD has driven innovation in high-performance computing, graphics, and visualization technologies -- the building blocks for gaming, immersive platforms, and the datacenter. Hundreds of millions of consumers, leading Fortune 500 businesses, and cutting-edge scientific research facilities around the world rely on AMD technology daily to improve how they live, work, and play. AMD employees around the world are focused on building great products that push the boundaries of what is possible.
It’s been a busy year in the world of hardware acceleration APIs. Many industry-standard APIs, such
as OpenCL and OpenVX, have been upgraded, and the industry has begun to adopt the new generation of
low-level, explicit GPU APIs, such as Vulkan, that tightly integrate graphics and compute. Some of
these APIs, like OpenVX and OpenCV, are vision-specific, while others, like OpenCL and Vulkan, are
general-purpose. Some, like CUDA and RenderScript, are supplier-specific, while others are open
standards that any supplier can adopt. Which ones should you use for your project? In this
presentation, Neil Trevett, President of the Khronos Group standards organization, updates the
landscape of APIs for embedded parallel processing and vision acceleration APIs and highlights where
these APIs overlap and where they complement each other.
The Khronos Group is a not for profit, member-funded consortium focused on the creation of royalty-free open standards for parallel computing, graphics and dynamic media on a wide variety of platforms and devices. All Khronos members are able to contribute to the development of Khronos API specifications, are empowered to vote at various stages before public deployment, and are able to accelerate the delivery of their cutting-edge 3D platforms and applications through early access to specification drafts and conformance tests.
Moderated by Brandon Lewis, Technology Editor, Embedded Computing Design, this panel comprised of development, debug, and test experts from AMD, Khronos Group, and the HSA Foundation investigates the current state of heterogeneous computing architectures, the power and performance benefits they afford embedded systems designers, and the programming hurdles that must be overcome to make HSA architectures more accessible in next-generation devices. Audience participation is encouraged.
HSA Panelist: Mr. Paul Blinzer works on wide variety of Platform System Software architecture projects and specifically on the Heterogeneous System Architecture (HSA) System Software at Advanced Micro Devices, Inc. (AMD) as a Fellow in the System Software group. Living in the Seattle, WA area, during his career he has worked in various roles on system level driver development, system software development, graphics architecture, graphics & compute acceleration since the early '90s. Paul is the chairperson of the ""System Architecture Workgroup"" of the HSA Foundation. He has a degree in Electrical Engineering (Dipl.-Ing) from TU Braunschweig, Germany.
AMD Panelist: Amey Deosthali is Director of Embedded Imaging at AMD, where he is responsible for P&L management, business development, and technical marketing efforts. Prior to joining AMD, Amey worked at Texas Instruments, contributing to his several years of business and engineering management experience in the embedded and mobile communications industries. Amey holds a MSEE from The University of Texas at Austin and MBA from University of California, Irvine.
Khronos Group Panelist: Neil Trevett was elected President of the Khronos Group in 2001, where he created and chaired the OpenGL ES working group, which has defined a standard for 3D graphics on embedded devices. Trevett also chairs the OpenCL working group at Khronos defining an open standard for heterogeneous computing. In July 2005 he became Vice President, Mobile Ecosystem at Nvidia where he is responsible for enabling and encouraging visual computing applications on non-PC platforms, including mobile phones.
MODERATOR: Brandon is responsible for Embedded Computing Design’s IoT Design, Industrial Embedded Systems, and Automotive Embedded Systems brands, where he drives content strategy, positioning, and community engagement. He is also Embedded Computing Design’s IoT Insider columnist, and enjoys covering topics that range from development kits and tools to cyber security and technology business models. Brandon received a BA in English Literature from Arizona State University, where he graduated cum laude.
Embedded Computing Design is the go-to trusted property for information regarding embedded design and development. We cultivate the largest global community of embedded designers through our content leadership channels, including blogs, design articles, videos, news, and product information. Coverage comes in the form of digital (websites, webinars, interactive magazines, newsletters, online education, apps, and traditional social media), print magazines, and live events. Applications covered include: IoT, Automotive, Medical, Industrial, DIY, Consumer, Digital Signage, and more.
For one reason or another, data acquisition within the Internet of Things are often overlooked. Most
Industrial IoT deployments consist of capturing data from multiple analog sensors at the system or
gateway level, and simultaneously fuse that data in real-time to provide precision metrics on the
performance of jet engines, electric power turbines, the smart grid, and other critical systems. Any
latency or data loss in these contexts can make the information useless, or worse, limit the ability
of operators to take preventative actions against system failure.
In this workshop presented by Roberto Piacentini of National Instruments, learn how to design a multi-node data acquisition equipped with the horsepower to perform instantaneous analytics on Big Analog Data. In addition, discover how LabVIEW tools can help abstract the complexities of FPGA programming in C or VHDL to help get your systems to market almost as quickly as they can provide metrics.
For nearly 40 years, NI has worked with engineers and scientists to provide answers to the most challenging questions. Through these pursuits, NI customers have brought hundreds of thousands of products to market, overcome innumerable technological roadblocks, and engineered a better life for us all. If you can turn it on, connect it, drive it, or launch it, chances are NI technology helped make it happen.
The traditional model of building motion controllers using DSP-based hardware solutions connected to
your PC is now outdated: it's expensive, cumbersome, slow, and inefficient. Software, long
considered inferior to hardware for motion control, solves these challenges and more, providing
equal or better performance at a significantly lower cost. In this session, you'll see the software
approach to motion control in action, including:
KINGSTAR combines more than three decades of embedded software innovation into open and standards-based real-time software that enables engineers to design, develop, and integrate motion and vision control applications. The company's global customer base includes OEMs and end users in industrial automation, robotics, semiconductors, manufacturing, textiles, packaging, medical systems, and other industries.
New scientific programming methods with low computational power and high speeds of execution are
coming to the forefront as IoT is pushing computations closer to the Edge. For example, dtSolve, a
scientific model solver that can do the job of a large mathematical package within an embedded
environment, uses physical models for real-time prediction and control that makes sophisticated
computing possible at the Edge, thereby enabling a new paradigm of IoT applications. In this class,
John Milios, CEO of Sendyne, will review these emerging technologies, including dtSolve, and discuss
their potential impact on the IoT.
Sendyne, focused on technologies for sensing, modeling and control, develops novel and effective approaches for solving many of the issues associated with large-scale storage, enabling cost reductions and superior performance in terms of pack utilization, enhanced cycle life, and accurate capacity prediction. Many of the technologies developed for this purpose are equally useful for other applications, such as model-based predictive control and distributed computing.
With the increasing complexity of embedded systems, adding more features and capabilities, the one
area that has not kept pace in meeting the design challenges of functionality in a small space has
been the power supplies. With digital content increasing through use of modern FPGAs and ASICs, the
number of power rails required has also increased. As a percentage of the board space, power
supplies have been increasingly area intensive. With the introduction of digital control to power
electronics, a new opportunity has arisen to reduce the size impact while enabling advanced features
for improving control and reliability. Coupled with new semiconductor packaging techniques, digital
power provides a path forward to enabling advanced embedded designs.
Intersil's customers build the products and applications of the future in the industrial, infrastructure, mobile computing, automotive and aerospace markets. Our advances in power management help them improve efficiency, power density and battery life.
The question that keeps management up at night is how much security is enough? One tradeoff has to
do with cost versus the importance of the data to be secured. Since there are several stages where
attacks can compromise sensitive data, building a security architecture into your device to protect
that data is critical – secure by design. There are different approaches to providing built-in
security measures, but ARM TrustZone technology protects against threats with a combination of
methodologies to help deliver the right amount of protection needed by the system and the user. This
talk will explore some of the key details on how ARM can be the start of a secure solution.
ARM is the world’s leading semiconductor IP company, developing and licensing technology that is at the heart of many of the digital electronics devices sold each year, from smartphones and tablets to sensors and servers.
With the massive proliferation of devices in the Internet of Things (IoT), security has become a
primary concern across nearly every vertical market segment. Medical devices, industrial control
equipment, unmanned systems, and automobiles can all be remotely controlled and monitored, providing
new high-value capabilities – as well as opportunities for security breaches. Even if devices aren’t
considered safety-critical, the impact of their data being hacked can be devastating for the user
and the manufacturer. But all the security measures designed to enforce encryption, authentication,
and protection aren’t enough if the underlying software isn’t developed securely. In fact, common
software defects are the leading cause of security vulnerabilities in the IoT.
In this presentation, we’ll describe tools and techniques for mitigating software vulnerability risks. We’ll discuss how recent high-visibility IoT security breaches were introduced through failures in software quality, and we’ll cover specific processes that will show you how to:
By employing proven software quality technologies, developers will learn how to make IoT devices more dependable, trustworthy, and secure.
LDRA develops software that automates code analysis and software testing for safety-, mission-, security-, and business-critical markets. Working with clients to achieve early error identification and full compliance with industry standards, LDRA traces requirements through static and dynamic analysis to unit testing and verification for a wide variety of hardware and software platforms.
The Internet of Things promises the ability to fuse data from multiple, perhaps unrelated sources to
paint a synergistic picture of technology and business performance that was previously unavailable
to organizations. The use cases range from combining vehicle performance information with weather
conditions to ensure safe operation and reduce accidents, or leveraging industrial machine vision to
examine products on a manufacturing line and determine whether a specific component in a factory is
malfunctioning. The possibilities are as limitless as the amount of data one can acquire, but making
sense of it all requires analytics technology that can scale as sensor inputs are added to the
IoT.
This workshop presented by Arnaud Mathieu, Program Director, Internet of Things Development, IBM Analytics, IBM, will introduce you to Watson IoT, a cloud-based cognitive computing platform now exposed to developers through a set of APIs. Access the platform in this interactive tutorial and find out how to combine tools from IBM, third-party providers, and your own data with machine learning capabilities to create new products, services, and businesses capped only by what data you can acquire.
Watson IoT is a set of capabilities that learn from, and infuse intelligence into, the physical world. The Internet of Things-generated data is growing twice as fast as social and computer-generated data, and it is extremely varied, noisy, time-sensitive and often confidential. Complexity grows as billions of devices interact in a moving world. This presents a growing challenge that will test the limits of programmable computing. Cognitive IoT is our best opportunity to fully exploit this resource.
The diversity of systems on the Internet of Things presents serious limitations for developers seeking to deploy applications to the largest number of platforms, while the economics of IoT make producing hardware-dependent software an archaic notion. In addition, as more devices get connected and demand for IoT solutions grows, a software development ecosystem will be required that has a much larger size and scope than that currently available through the traditional embedded programming workforce. It’s time for a new approach.
Software virtualization provides a solution to these challenges, as it abstracts underlying hardware and makes IoT device software development accessible to the largest community of programmers in the world using the Java language. Although historically too cumbersome for use in resource-constrained devices based on microcontrollers, discover how a Java platform can be compacted to RTOS-level footprints to bring massive portability and scale to your IoT development efforts.
MicroEJ is an independent software vendor of cost-driven solutions for the smart digital world. MicroEJ is focused on providing turnkey software products to solve the embedded world’s major business challenges and to enable application-driven uses and services in the IoT world commensurate with the cost and resource constraints of that world. MicroEJ helps OEMs create flexible and future-proof smart devices, brings rich user experiences, and enables additional sources of revenue across the whole value chain, from sensor data collection to cloud-based services.
The Internet of Things, Industrial Internet, and Industry 4.0 are built on a foundation of data.
That much we can all agree on. But how useful that data can become once acquired is still largely a
matter of conjecture, as, pragmatically speaking, the Big Data swell created by IoT devices will
overwhelm the small community of data analysts and scientists tasked with harnessing
transformational insights from it.
Enter machine learning and artificial intelligence, which are now being leveraged to assist with Big Data analytics for applications ranging from preventative maintenance to cybersecurity. In this technical session by Usman Shuja of SparkCognition, learn how cognitive algorithms can be put to use in your real-world IoT deployment to support root cause analysis, business intelligence, SIEM, and almost any other system or process that you (or it) can think of.
SparkCognition, Inc. is the world's first Cognitive Security Analytics company. Its MindFabric platform and Cognitive Fingerprinting technology model physical and virtual assets, continuously learn from data, and derive intelligent insights to secure and protect assets round the clock.
Industrial solutions require connectivity today more than ever. This presentation explores the details of deploying motor control, imaging/video, and Ethernet in a variety of real-world settings using development kits based on the Microsemi SmartFusion2 SoCs as a baseline for development with various software and developer APIs, including OpenGL.
More information coming soon!