EDACafe: Agnisys Automation Review

Agnisys Automation Review

Posts Tagged ‘SemiEDA’

Teaching the Computers to Teach Themselves – Why Machine Learning Matters

Monday, June 11th, 2018

why-machine-Learning-matters Machine learning (or “ML” for short) may have begun life as something of a buzzword, but it has long since proven itself to be anything but. At its core, the term itself describes a situation where computer scientists use statistical techniques to essentially “learn” with data, without being specifically programmed to do so. In essence, you build a system to complete a specific task. The more data you feed into the system, the better it gets at that task – all without requiring human beings to make those improvements on their own.

This seemingly straightforward concept has led to a massive disruption in the field of electronic design, especially over the last few years. It has already led to the creation of a brand new class of embedded systems that use both machine learning and deep learning, otherwise known as ML/DL systems.

The Power of Machine Learning: Breaking It Down

Although it’s still a relatively new concept in the modern context, machine learning is already having a massive impact on just about every industry. Businesses regularly use machine learning systems powered by customer data to help improve satisfaction whenever possible. If you can power a machine learning system to analyze user activity in real-time, you’re therefore in a better position to identify the conditions for a potential account closure before it happens. You can then proactively reach out to that customer and save the account before they head off into the arms of a competitor. Or, a financial services company might use machine learning to better respond to changes and fluctuations in the local market as they happen. The system itself can quickly identify trends and patterns that would have otherwise went unnoticed, alerting humans to the idea that something is about to happen so that they can react in the most appropriate way.

For the rest of this blog article, please visit Agnisys.com.

Tags: IDS NextGen, machine learning, SemiEDA
No Comments »

The Intersection of Functional Safety and Electronic Design – How Safe is Your Ride?

Sunday, May 27th, 2018

The Intersection of Functional Safety and Electronic Design

In an industry that has gone through an incredibly rapid transformation over the past few years alone, auto manufacturers all over the world have had to rethink nearly every aspect of their own processes within the context of the 21st century. Because of this, an almost incredible emphasis has been placed on what concepts like “functional safety” even mean in 2018 (or 2019, or 2020 and beyond). This is especially true as vehicles incorporate more and more electronics with each passing day.

Autonomous vehicles have elevated this concern to the next level because as the level of control that a driver has over their car goes down, the liability of that car’s manufacturer shoots sky high. Many studies have shown that when automated systems are introduced into an industry, there is often a significant increase in the rate of “adverse” events as a result. This is the point that we have currently reached in terms of self-driving cars and functional safety.

In an effort to mitigate this risk as much as possible, functional safety is necessary – but in a way that also addresses the needs of what is already a high-volume, cost-sensitive industry. Luckily, the tools to address this problem sooner rather than later are already here. They just require us to keep a few key things in mind.

Functional Safety in Automotive Electronics: Breaking It Down

One of the most important elements of functional safety as it relates to the embedded systems that are now present in modern day vehicles has to do with fault detection. Simply put, regardless of where a particular fault comes from, the system’s ability to both A) identify it, and B) resolve it in the minimum time span possible is and will always be the goal.

In a lot of ways, this requires functional safety to take a more proactive approach to its own objective than ever before. Especially in an era of self-driving and autonomous vehicles where drivers are relinquishing more control all the time, the system itself must become aware of that fault and, if possible, recover from it, all without either endangering the passengers or requiring any intervention on their behalf, to begin with.

For the rest of this article, please visit Agnisys.com.

Tags: DO-254, functional safety, IDesignSpec, SemiEDA
No Comments »

Shift Left: Verification and Validation are two sides of the same coin

Friday, April 27th, 2018

Verification and Validation are two sides of the same coin

In 2011, Intel discovered a design flaw in its Sandy Bridge combination graphics-microprocessor chip that led to not only a major production delay but that ultimately cost more than $1 billion in replacement costs and lost revenue. If you’re searching for a clear-cut example as to why finding bugs early in the development process is always a top priority, look no farther than that. A product recall can be a terrible experience for everyone involved, but the costs associated with that recall alone are the stuff that nightmares are made of.

Yet at the same time, the complexity of the modern SoC environment has made things difficult in this regard to say the least. Getting SoC to market (and doing so with quality) is such an enormous task that teams are always looking for newer and more innovative ways to shorten the development time. The situation has also raised the requirement to incorporate verification and validation as a one-step process to catch bugs from an early design stage. Bringing the enormous tasks of verification and validation closer together is great news for the entire semiconductor industry.

This, however, is where the concept of “shift left” enters the conversation. As its name suggests, “shift left” is a series of activities and processes that better position design teams to anticipate and address downstream issues upfront, thus fixing a small problem now before it becomes a much bigger (and more expensive one) tomorrow. It’s the heart of the idea that you should “test early and often.” It also does so in a way that has proven to shorten development times so that no time is wasted late in the process where every second counts.

Why This Matters

But before we can focus on the importance of “shift left,” we must first address the early stages of this process in general. Verification and Validation are two critical steps in the creation of electronic systems, but over the last few years, in particular, their roles (and how those roles relate to one another) has changed.

In the modern era, there is an urgent need to enable users to describe the programming and test sequences of a device in a way that automatically generates sequences ready to use from an early design and verification stage, all the way up through post-silicon validation.