Advertisement

Blog

New Design Opportunities as Semiconductor Boundaries Blur

Danny Biran, senior vice president of marketing at {complink 265|Altera Corp.}, sees opportunities where others may see intractable challenges in the evolution of the semiconductor market. In a presentation at the recent Semico summit, Biran agreed that the lines between the different semiconductor logic devices are blurring but noted this development is creating opportunities for IC vendors to offer even better and more compelling products to customers.

According to Biran, the boundaries among FPGAs, ASICS, ASSPS, and CPUs (MPUs, MCUs, and DSPs) have, until recently, been extremely well defined. FPGAs (field programmable gate array) were customer programmable standard products; programming was developed for and owned by the customer, hence the name. FPGAs can be programmed by the customer and customized as necessary after manufacturing.

ASICs (application-specific integrated circuits), on the other hand, used a standard cell design methodology. The design is owned by the customer, and the ASICs go into specific applications. ASSPs (application-specific standard parts) were standard high-volume products developed by the semiconductor vendor for sale to multiple customers. MPUs, MCUs, and DSPs were standard products, but the software needed to implement an application was developed by the customer. Now, the boundaries between those categories are fading.

Various semiconductor vendors are offering FPGAs with an on-board MPU, ASICs that include an FPGA block, or ASSPs with multiple processing cores. Altera's Stratix V FPGA is an example of this trend. It combines high-speed transceivers, hard IP, soft IP, logic blocks, memory arrays, and advanced DSP blocks on one IC.

There are several factors driving this trend, including increasing levels of integration, the high cost of developing leading edge ASICs, and the availability of IP (Intellectual Property). Another factor is the availability of integration tools, such as Altera's Qsys system integration tool.

But there is more to the blurring of boundaries between device types than just the availability of advanced ICs. There is a wide variety of system integration tools, intellectual property blocks, floating point IP libraries, and other tools available to today’s design engineer. This requires a fundamental change in the way that system engineers approach their tasks.

Biran made the point that system companies should not be trapped into thinking about design solutions in terms of IC categories: FPGAs, ASICs, ASSPs, or processors. Instead, they should think about the combination of technologies that will provide the best solution. This may require reorganization or the acquisition of new skills. For example, the emphasis might shift from standard cell design skills to programming skills.

The optimum solution for a part of the design might be an FPGA. The optimum solution for another part of the design might be an MPU or a DSP. The significant change is that both of these, the FPGA and the processor, or other device types, can now be integrated onto one IC.

This requires another change in thinking. In the past, a system company might begin coordinating with vendors relatively late in the design cycle. Now, with the boundaries blurring, a system company can achieve a better solution by consulting with a vendor from the very beginning of the design cycle.

As we all know, the number of transistors per IC is increasing, in accordance with Moore's law. This is making it possible to combine several functionalities on one IC. In fact, according to Biran, the record for the number of transistors on an IC is held by an FPGA, not a microprocessor. This can lead to better design solutions, but only if system companies recognize the trend and alter their design concepts to take advantage of the possibilities.

8 comments on “New Design Opportunities as Semiconductor Boundaries Blur

  1. tioluwa
    May 26, 2011

    This is very interesting, and like all technological innovations, it opens doors to greater possiblities for designers.

    Like you observed, it helps with the issue of cost and design considerations extensively if more than one programmable device can be found on a single chip.

    I haven't had the opportunity of using any of such chips but will the entire IC be programmed using a single language?

    You have observed that an MCU, MPU, FPGA, ASIC are programmed differently, using different concepts and rules. If an MPU and ASIC are designed on a single IC, how will it be programmed?

    I'm sure these guys have it all worked out, but i would like to know, as a designer.

  2. Daniel
    May 27, 2011

       Morry, you are right. 5 years back in my company there are separate wings for ASIC and FPGA. When new software and tools are coming, there is no need for any specialized peoples. Both the same can be done by a single person, that means the border line is reducing.  Inter operability is possible and now a day’s many engineers are doing multi tasking.

  3. FLYINGSCOT
    May 27, 2011

    Most of the programmable IC companies offer free tools and IP to help designers use their products.  Having used several of these tools I wish there was better documentation, canned examples and product support to enable the user to gain familiarity much more quickly.  The common way to develop solutions is to use VHDL or Verilog or a mixture of the two.  Most freebie tools support both languages but only some offer mixed VHDL/Verilog support.

  4. FLYINGSCOT
    May 27, 2011

    If anyone wants to know which IC devices contain the most transistors…….look here:

     

    http://en.wikipedia.org/wiki/Transistor_count

  5. tioluwa
    May 27, 2011

    Well Jacob answered my question, 

    However, i'm still wondering, does it really payoff to have engineers go cross-platform in design consideration.

     

    I think they are great, ideas, however, the need for separate platforms will still remain in areas where the advanced functionality of the combined platforms will not be necessary.

    I identify with FLYINGSCOT's view on documentations, there can be a real problem.

    I'm a newbie to FPGAs and ASIC. can VHDL be used to program them all? especially those they say have MPUs on board as well.

  6. SunitaT
    May 28, 2011

    “For example, the emphasis might shift from standard cell design skills to programming skills.”

    Morry,

     Thanks for interesting article. I agree with your point  that ” the FPGA and the processor, or other device types, can now be integrated onto one IC”.  But  why do you think this will have an impact on the standard cell design because we can never integrate ASIC libraries in single ICs.

  7. Taimoor Zubar
    May 30, 2011

    I think technology is effectively replacing the role of humans here. With the tools getting more and more sophisticated, engineers are not required to have much technical skills in terms of programming. They need to be more skilled with the use of software tools that program the chips. Similarly, the cross-platform factor is also being taken care of by the software tools. All of this is making the tasks for users much easier.

  8. Backorder
    May 30, 2011

    Its often that I hear designers talk about analog technologies disappearing from the board and digital and embedded replacing them. They have to be reminded of the analog sockets around the gorilla chips which still account for tens of billions of market across the globe. But, it is a truth that semicon boundaries have blurred to the extent that even traditionally analog business units are borrowing controller technlogy and we are never sure if the device in consideration belongs to the digital or the analog domain.

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.