Design Infrastructure Alley at DAC 2019

2018 marked the first year of the Design Infrastructure Alley (DIA) at DAC. It was the first time that DAC devoted floorspace to discussing the unique IT needs of the semiconductor industry.

Some of the big issues we are looking to address at DAC include:

Increased Focus on Data/IP Security
Semiconductor companies have traditionally had a very open, collegial way of working. The emphasis was on making it easy for engineers to collaborate. This was generally fine when companies created and owned virtually all of their own IP. However, with the rise of third-party IP (and the unique legal agreement for each set of IPs), it’s no longer acceptable to have “open access” to data. This is a significant IT, engineering and business challenge that will require a great deal of work to correct without wreaking havoc with design schedules.

CAD flows, which engineers have used for years, will likely face challenges in a “locked down” environment, as the new rules will surely break an underlying data access assumption embedded deep within them.

“Locking down” your IP is really just the first step. Having a data governance process and the tooling in order to give it teeth are the “long poles in the tent”. While there are several tools on the market to help with this, each company implements its own set of rules and procedures, making it difficult

The Cloud
Many industries are moving workloads to the Cloud and abandoning on-premise datacenters. Semiconductor has long been a notable hold-out. But with the growth in that sector continuing to accelerate, it is a question of when and not if the Semi industry will begin utilizing the Cloud. There are great benefits to Cloud architectures, but still some significant challenges we face in our industry.

• Data security. All of the topics listed in the first section apply in spades when it comes to the Cloud. The tools are there to make your Cloud journey safe and secure, but Cloud providers generally adhere to something similar to the AWS Shared Responsibility Model when it comes to security. Bottom line – they take care of things like physical security and patching of managed services, but everything above that is up to you to architect well.
• Data sprawl. Knowing what data to take the Cloud is, in itself, a daunting task. Years of project additions on your NFS servers means you have dependencies in people’s home directories or even in projects that ended years ago. But it’s always been there so everything has just “worked”. Finding and encapsulating those dependencies is no small task.
• Data synchronization. Once you know what you need to take, you have to get it up there. That could be just a few gigabytes or it could be a few terabytes. Do you pre-copy your data up there ahead of time, even if you aren’t using it? Or do you copy on demand? There are several approaches to them, but they all depend on your intended use model.
• Licensing. You can scale compute to huge numbers with a click of a button. Need several hundred terabytes of storage? Make an API call. However, there is no way right now to scale licensing on-demand and only pay for what you use. This will be the final hurdle which companies must solve in order to fully realize the promise of the Cloud.

Getting the Most Out of Existing Investments
Security and Cloud get a lot of attention for good reason, but the fact remains that Semiconductor companies have large investments in Compute, Storage, Networking and Software that will continue to live on-premise for the foreseeable future. It is the responsibility of every Engineering IT organization to maximize those investments. DAC is the best place for administrators and flow owners in our industry to collaborate on our unique challenges.

DIA Is For IT Professionals, CAD/Flow Owners
If you are involved in initiatives at your company regarding any of the above, DIA 2019 is going to be a great resource for you to take home practical knowledge about how to address them. The Design-On-Cloud Pavilion will have non-stop presentations focusing on solutions to these big issues from some of the most innovative suppliers in the industry. In addition, we are working on several Workshops focused on giving you practical, guided advice on how to do things like:

• Connect your on-premise Distributed Resource Manager (Grid) solution to a Grid in the Cloud.
• Create a Bill of Materials to see what NFS paths and files your flows are accessing so that you can better plan for Cloud deployments or just get a better handle on your security posture.
• Containerize applications to abstract your software away from your operating system and finally be able to upgrade to the latest versions of Linux without worrying about compatibility concerns.

2018 was a great start to the DIA. Join us from June 2-6 in Las Vegas, Nevada for the Design Infrastructure Alley at the 56th Design Automation Conference. For more information click here. Space is still available in the Design Infrastructure Alley for 2019.