Gabe Moretti, Senior Editor
Talking to Lucio Lanza you must be open to ideas that appear strange and wrong at first sight. I had just that talk with him during DAC. I enjoy talking to Lucio because I too have strange ideas, certainly not as powerful as him, but strange enough to keep my brain flexible.
So we were talking about the industry when suddenly Lucio said: “You know the EDA industry needs to divide itself in two: design and manufacturing are different things.”
The statement does not make much sense from an historical perspective, in fact it is contrary to how EDA does business today, but you must think about it from today and future point of view. The industry was born and grew under the idea that a company would want to develop its own product totally in house, growing knowledge and experience not only of its own market, but also of semiconductor capabilities. The EDA industry provides a service that replaces what companies would otherwise have to do internally when designing and developing an IC or a PCB. The EDA industry provides all the required tools which would have otherwise been developed internally. But with the IoT as the prime factor for growth, dealing with the vagaries of optimizing a design for a given process is something most companies are either unprepared to do, or too costly given the sale price of the finished product. I think that a majority of IoT products will not be sensitive to a specific process’s characteristics.
So why not change, as Lucio forecasts. The problem is design methodology. Unfortunately, given the design flow supported today, a team is supposed to take the design through synthesis before they can analyze the design for physical characteristics. This approach is based on the assumption that the design team is actively engaged in the layout phase of the die. But product developers should not, in general, be concerned with how the die is laid out. A designer should have the tool to predict leakage, power consumption, noise, and thermal at the system level. The tools need to be accurate, but not precise. It should be possible to predict the physical behavior of the design given the characteristics of the final product and of the chosen process. Few companies producing a product that is leading edge and will sell in large volume will need to be fully involved in the post synthesis work, but the number of these companies continues to shrink in direct proportion to the cost of using the process.
EDA startups should not look at post synthesis markets. They should target system level design and verification. The EDA industry must start thinking in terms of the products its customers are developing, not the silicon used to implement them. A profound change in both the technological and business approach to our market is needed, if we want to grow. But change is difficult and new problems require not just new tools, but new thinking. Change is hard and almost always uncomfortable.
Software development and debug must be supported by a true hardware/software co-design and co-development system. At present there are co-verification tools, but true co-development is still not possible, at least not within the EDA industry.
As I have said many times before “chips don’t float” thus tier one of the new EDA must also provide packaging tools, printed circuit board (PCB) design tools, and mechanical design tools to create the product. In other words we must develop true system level design and not be so myopic to believe that our goal is Electronic System Level support. The electronic part is a partial solution that does not yield a product, just a piece of a product.
I know of a company that has already taken a business approach that is similar to what Lucio is thinking about. The company had always exhibited at DAC, but since its new business approach it was not there this year. Most customers of eSilicon do not go to DAC, they go to shows and conferences that deal with their end products’ markets. The business approach of the company, as described to me by Mike Gianfagna, VP of Marketing at eSilicon, is to partner with a customer to implement a product, not a design. eSilicon provides the EDA knowhow and the relationship with the chosen foundry, while the customer provides the knowledge of the end market. When the product is ready both companies share in the revenue following a prior agreed to formula. This apparently small change in the business model takes EDA out of the service business and into the full electronic industry opportunity. It also relives companies from the burden of understanding and working the transformation of a design into silicon.
Figure 2: Idealized eSilicon Flow (Courtesy of eSilicon)
What eSilicon offers is not what Lucio has in mind, but it comes very close in most aspects, especially in its business approach to the development of a product, not just a die.
Not surprisingly there are consortia that already provide structure to help the development of a two tiers EDA industry. The newly renamed ESDA can help define and form the new industry while its marketing agreement with SEMICO can foster a closer discourse with the IP industry. Accellera Systems Initiative, or simply Accellera, already specializes in design and verification issues, and also focuses on IP standards, thus fitting one of the two tiers perfectly. The SI2 consortium, on the other hand, focuses mostly on post synthesis and fabrication issues, providing support for the second tier. Accellera, therefore, provides standards and methodology for the first tier, SI2 for the second tier, while ESDA straddles both.
In the past using the latest process was a demonstration that a company was not only a leader in its market, but an electronics technology leader. This is no longer the case. A company can develop and sell a leading product using a 90 or 65nm process for example and still be considered a leader in its own market. Most IoT products will be price sensitive, so minimizing both development and production costs will be imperative.
Having a partner that will provide the know-how to transform the description of the electronic circuit into a layout ready to manufacture will diminish development costs since the company no longer has to employ designers that are solely dedicated to post synthesis analysis, layout and TCAD.
EDA companies that target these markets will see their market size shrink significantly but the customers’ knowledge of the requirements and technological characteristics of the tools will significantly improve.
The most significant impact will be that the EDA available revenue volume will increase since EDA companies will be able to get revenue from every unit sold of a specific product.