Each year, DesignCon offers training boot camps covering various core topics essential to the skills toolbox of hardware design engineers. For 2019, we have assembled some of the most respected instructors in their field to hold three all-day, hands-on boot camps covering signal integrity, power integrity, and machine learning.

DesignCon's 2019 boot camps run 9:00 am to 4:30 pm on Tuesday, January 29, with a mid-day break for the keynote and lunch. If you need to brush up your basics or get up to speed fast, these boot camps are for you! Since these are all hands-on, space is very limited.

Power Integrity Hands-On Simulation & Measurement

Tuesday, January 29, 9 a.m. - 4:30 p.m.

See how the gigabit SI world of IoT, automotive, cloud server products, etc. with the demand for lower power and multiple power rails is driving new paradigms for flat impedance and not just a maximum target Z. Led by DesignCon legends Heidi Barnes, Applications Engineer at Keysight Technologies, and Steve Sandler, Founder of Picotest, attendees at this boot camp will learn how to use impedance vs. frequency data to create measured models, estimate decoupling capacitance, and debug noise ripple on a power rail. Step through optimizing the decoupling for a DDR4 example and then run the PI eco-system simulation with AC and Harmonic balance to look at small signal and large signal responses.

Attendees should be familiar with power rail simulations (SPICE type), AC simulations with S-Parameter and Z-Parameters, PCB technology, capacitors, inductors, switch mode power supply basics, and low impedance 2-port shunt VNA measurements. (Bode plots are not a prerequisite.)

Every attendee will have access to a hands-on simulation tool using 1 of 40 supplied laptops or access to a cloud based version using an attendee's personal laptop. Smaller break out groups will be rotated through hands-on measurements with a network analyzer and oscilloscope for creating measure based models and exploring simulation to measurement correlation.

Get your pass.

The Bootcamp will be broken down into the following 5 sections:

  1. Set the stage – Evolutionary Changes in Power Integrity for High Speed Digital Designs. Cover the basics of target impedance and how multiple peaks can still lead to rogue waves even if they are all below the target Z. Flat Z not just Max Z is what is needed for minimum ripple, and lower EMI.
  2. Simulate and measure passive C, L, and R components to obtain accurate measured models with parasitics for use in SPICE like simulations, and without PCB mounting parasitics for use with EM models.
  3. Explore the basic types of DC-DC converters to see how the selection of the VRM can impact the cost and performance of the PDN and decoupling. Simulate the impact of component tolerances on current mode vs. voltage mode converters.
  4. Step through VNA and Oscilloscope measurements needed to create an accurate measure based model of the DC-DC converter. Learn how to use state based average voltage regulator model for fast Harmonic Balance and AC simulations to get both small signal steady state impedances and large signal switching transients.
  5. Utilize all the skills learned to design a flat impedance network for a DDR4 design example. Step through the process of estimating the required decoupling capacitance for Flat Z and then selecting commercially available values for final optimization.

The Art of Signal Integrity Analysis

Tuesday, January 29, 9 a.m. - 4:30 p.m.

Are you intrigued by the advanced signal integrity topics covered at DesignCon but feel you need a bit more information to get up to speed? Then The Art of Signal Integrity Analysis Boot Camp is for you. Led by Davi Correia, Signal Integrity Engineer at Carlisle IT, this boot camp is designed to give engineers the knowledge they need about signal integrity and to introduce new engineers to the concept.

At the end of this course, attendees will be able to identify the key components in a high-speed channel, understand how they can be simulated, and know how they impact the overall performance. Both the source code and the compiled version of the software used in the course will be made available to the students.

Get your pass.

This course focuses on fundamental aspects of signal integrity.

  1. We will start by characterizing common passive components of a system (vias, connectors, cables) using measurement and simulation.
  2. Then, the channel will be evaluated both in frequency and time domains. Students will be shown how to isolate measured components from test fixtures using de-embedding techniques.
  3. We will correlate the measurement and simulation results using cascaded s-parameters.
  4. Finally, an eye-pattern of the entire equalized channel will be generated.
  5. At the end, attendees should be able to see the relationship between each individual component of a channel and the final channel performance.

Machine Learning & Artificial Intelligence for Hardware & Electronics Design

Tuesday, January 29, 9 a.m. - 4:30 p.m.

Machine learning can enable fast, accurate design and verification of microelectronic circuits and systems by creating algorithms to derive models for electronics and system design automation. Unlike traditional programming approaches that have knowledge embedded in complex algorithms and mathematical models, machine-learning uses simple algorithms and models, but with numerous parameters that are intensively trained with complex data sets. 

Led by long-time ML enthusiast Chris Cheng, Distinguished Technologist at HP Enterprise, along with others, this ML boot camp will provide a day long introduction for beginners who are interested in learning the basics of machine learning (ML) and artificial intelligence (AI) and their applications in hardware and electronics design. Participants will have hands-on opportunity to measure and train dynamic neural networks to illustrate its usefulness for complex equalizer modelling.

We will provide an introduction to ML and AI, and continue with information on linear and logistic regression, Bayesian surrogate models, artificial neural networks, regularization and gradient descent, recurrent neural networks, and advance topics in ML and AI (PCA and self-correcting models). There will be a live demo of how to use test instruments as ML tools.

Get your pass.

The boot camp will go through the following topics

  1. We will start the day with a brief introduction to generative vs. discriminative models and their differences. From these models, we can consider examples where deploying machine learning/AI techniques can have big advantages and cases where they may not help.
  2. Linear & logistic regression: Start with the basic concept of statistical linear & logistic regression of multivariable. Participants will begin to learn how to use collection of input and output samples to implement generative models.
  3. Bayesian surrogate models: Participants will be introduced to the important concept of Bayesian surrogate models to effectively model analog generative models
  4. Artificial neural networks: We will move into the area of artificial neural networks. This is one of the most popular artificial intelligence engine. Concepts of input, output and hidden layer will be discussed. Activation functions and the overall operation of the ANN will also be discussed.
  5. Regularization and gradient descent: Method to converge to optimal solutions for ANN through back propagation and gradient descent will be discussed. Undesirable results such as over/underfitting and their mitigation through regularization will be covered.
  6. Recurrent neural networks: More advance neural network structures such as recurrent neural network will be discussed including their application in time series analysis for SI.
  7. Advance topics in machine learning and AI (PCA and self-correcting models): We will briefly touch on some advance topics and their application in hardware design. Examples will be using Principal component analysis for channel performance optimization, causal and structural inference for complex deep state space models such as hidden Markov and recurrent neural networks
  8. Live demo of using test instruments as machine learning tools: The course will end with a hands on demo of using recurrent neural network to create a complex equalizing receiver model with test instruments. Measurements results will be compared with original IBIS-AMI models, any mismatch will be corrected through retraining of the recurrent neural network model (i.e. self-correcting model) without needing to know the IBIS or the receiver IP.