Closing the Gap Between Data & Usable Info

There is a lot of industry buzz these days about big data and the ways it can be leveraged to improve a company's overall business intelligence processes. While the industry consensus is that big data is a foregone conclusion in the supply chain and the semiconductor industry, what is not so clear is how this big data can and should be used.

Semiconductor manufacturing test is a prime example, where enormous amounts of data are being generated from multiple steps in manufacturing operations such as wafer sort, final test, and system-level test. These test operations are essential to ensure that defective parts are not being shipped to end-customers. This test data is also used for other types of downstream analysis, but as the amount of parametric data generated continues to grow, and device volumes increase, the ability of companies to effectively mine their data becomes a significant challenge.

For companies with high-volume products, the amount of data generated each month can easily run into the tens of terabytes. There is amazing value in that data, but if you cannot make clear, timely decisions based on that data, all it is doing is sitting around and taking up storage space.

Driving improved data analysis is critical to the forward-looking semiconductor marketplace. End-market customers are demanding more and faster “everything” from their semiconductor providers. One example as to how truly usable data can drive real value is with escape prevention. If you have a part that tests “good” but is at the margin of what is defined as a good part, what do you do? Do you ship it or hold it back?

The ability to rapidly analyze the entire DNA history of a specific device to drive an informed decision for how best to position that part for a given end-customer is a powerful way to provide greater value and differentiation against your competitors. Moving forward, having the capability to mine data across all aspects of manufacturing  to proactively control the quality and performance of the products that are shipped will be become the norm, not the exception for the semiconductor industry.

Most methods to manage test data are based on legacy, proprietary solutions. In order to successfully address the demands of the end-markets they serve, semiconductor companies will need to look “outside the box” and explore new, commercially developed manufacturing intelligence solutions in lieu of existing, internally developed ones.

Commercial solutions bring together three key components that are not typically found in proprietary solutions: a comprehensive data infrastructure that can collect and validate manufacturing data from any point in the semiconductor supply chain; a powerful and automated data analysis engine that can rapidly mine the data for relevant information; and, finally, the means to perform cross-operational analytics that can leverage input from multiple data sources to make highly informed decisions at all stages of manufacturing operations.

Forward-looking companies are already using commercial solutions in place of their internally developed ones to leverage their global data sources to drive significant improvements in operations, product planning, and distribution. They see big data, not as a looming problem for their IT departments, but as a never-ending source of employable data that can fuel their success in the marketplace.

11 comments on “Closing the Gap Between Data & Usable Info

  1. davidpark
    April 21, 2014

    @Rich Krajewski, thanks for your comments. No question, data integrity is a big challenge, but so are the manufacturing operations of global semiconductor companies. They don't have devices that come from just one factory, but many factories. The issue with in-house solutions is that they are typically done ad-hoc and the way data is collected at different factories or subcons/OSATs is not always consistent which makes it difficult if not impossible to extract manufacturing intelligence from their data. 

    The benefit of a commercial-solution that understands the global, heterogeneous nature of manufacturing data, is that you can collect data from different vendors, with different test equipment, at multiple stages in the manufacturing process (wafer sort, final test etc.) with excellent data integrity and consistency and in near real-time (within minutes).

    I can't speak for other companies involved in manufacturing BI&A, but we processs parametric data from over 1 billion parts per month and deliver that information safely and securely to the biggest IDMs and fabless companies in the industry. One of the many benefits of our solution is the ability to provide highly accurate and reliable data so that critical business decision can be made 24/7.

  2. Hailey Lynne McKeefry
    April 21, 2014

    The security piece of big data is always going to be critical. Worse, when you bring several disparate streams of data together it can become even more valuable to hackers. Worse, many organizations haven't yet learned how to manage let alone use the stacks fo data sitting around. I suspect there will be some cautionary tales in the media (read huge data snafus) before we get this completely nailed down.

  3. SunitaT
    April 22, 2014

    I think with the recent advancements in the field of IOT, the boundary between Data and Usable Info is getting blurrier by the minute. There is simply too much confidential data in many company's hands to track and we as the end user cannot do anything but hope for the best and pray such that nobody uses the data in a bad way.

  4. SunitaT
    April 22, 2014

    @Rich: Truly said. Higher streams of data mean higher storage complexity. But with the recent advancements in cloud storage, it is now possible to store Exabyte of data in the cloud, and this only requires little cost. Cloud systems can be managed easily with virtual servers throughout the world.

  5. Himanshugupta
    April 22, 2014

    Like any other manufacturing industry, i think that semiconductor industry has become so mature that there is little or no unstructured data as far as big data is concerned. Most of the processes are mature and the semiconductor hardwares are tested based on random sampling. 

    I think i missed the point on semiconductor industry a fargone case for big data. Most of the semiconductor companies use data extensively to optimize the procedures and processes. Though i agree that they do not use big data as such because more of the data is dependent so need not to be analyzed in great details.

  6. davidpark
    April 23, 2014

    @ Himanshugupta, yes the semiconductor industry is maturing, but there is still much that can be learned, and optimized, by data analysis on the manufacturing side. While semiconductor data is not “big data” if you compare it to things like Google or healthcare records, it is still quite large. We are seeing 30+ TBs of parametric data generated every month by our customers. Even this amount of data is very challenging to identify actionable data in a timely fashion.

    It is one thing to find a problem, but there is an even bigger challenge to find that problem soon enough to take corrective action that is meaningful for your business. Even for a relatively-mature business like semiconductors, there are still many ways where manufacturing data can be rapidly transformed into intelligent information that can significantly improve many facets of a company's business.

    Outlier detection, escape prevention and RMA management are three areas where data analytics are now being used to a much greater extent to drive higher quality and reliability metrics for semiconductor devices. As device complexity continues to rise with smaller process geometries and the adoption of multi-chip packages, the amount of manufacturing data that is generated will continue to grow. Companies that develop core competencies in being able to create “manufacturing intelligence” of out of their “big data” will have a signficant advantage over their competitors. 

  7. Himanshugupta
    April 23, 2014

    Thanks David for your insight. Actually i am looking for ways to improve the semiconductor process by using the data that FAB produces. I think specific teams (such as characterization) closely monitor the data to keep yields on acceptable limits but i can imagine that there are many areas where intelligent analysis can be done and problems can be identifies before they actually occur. However, management do not seem to bother to invest in such softwares or algorithms and it is to the discretion of individual employee to improve the system.

    Can semicondutor industry learn from other manufacturing units or the problems of semiconductor industry uniques? Also can you please elaborate what big data techniques are actually available to solve semiconductor problems.


  8. Himanshugupta
    April 23, 2014

    @Rich, the problems about big data that you have described are actually true. Most of the organizations do not know what to do with their data and most of all there is little understanding on how to deal with big data. However, there are some companies which have used the power of data to understand the problems and increase the revenues. This is still an evolving field and it will take years before the fields gets more formalized.

  9. davidpark
    April 23, 2014

    @Rich, I don't want to turn this discussion into a promotional pitch for my company. I would be very happy to discuss this in more detail with you and @Himanshugupta in more detail at your convenience. You can reach me at .

  10. davidpark
    April 23, 2014

    @Himanshugupta, great questions that you are posing. I will try to answer them as best I can.

    We are also seeing that management sometimes is not interested in investing in new data analysis applications, but that is generally because they have little exposure to the benefits of what truly global data-mining can provide, especially for semiconductor manufacturing and test. Like many big ideas that involve change, it takes a while for people to embrace it, especially when they think that what they have in place is “pretty good”.

    It does take time to educate and inform people about what is possible to improve in such a mature area as semiconductor manufacturing. But it is happening, slowly but surely. We come up against NIH (not invented here) everyday with manufacturing organizations, but when you can demonstrate real ROI, and show very clear and specific actionable information that can enable manufacturing operations to significantly improve yield, quality and throughput, people start to listen.

    Most of what is done in data analytics is valuable across multiple industries, the part that is specific is the type of data that is collected and the rules that identify the problem and a course of action.  One of the easiest ways that big data analytics can help semiconductor manufacturing is to quickly identify trends. For example, if you have a test site that was yielding at 95% but all of a sudden in the last hour it is only yielding 85%, you know something is wrong and needs to be addressed. Fixing this as soon as possible can significantly improve recoverable yield. If you cannot detect this for hours or days, you have lost real yield. If you can find it in minutes you are now helping to improve your company's revenue.

    On the quality side, one common issue is a tester freeze (for various reasons), now you can be passing off parts as “good” when they haven't been actually tested at all. This can introduce a lot of suspect parts into your supply chain. Again, being able to mine your global manufacturing data in real-time can help you see this problem as soon as possible so that you can fix the problem and avoid having quality issues with your end customers. 

    In both cases, the source of the data and the “rules” that find both of these examples are industry-specific. However, the underlying data collection, normalization, validation and data analysis that is done is industry-neutral.

    For the specific challenges that you are dealing with, we can apply generic big data analytics to help address some specific issues. One thing that is looked at during NPI is scan chain failures.  There are many yield analysis tools/companies out there, but one of their challenges is finding real failure data to analyze. They are looking for a needle in a haystack. One application of data analytics is to monitor bad bins. If the bad bin associated with scan failures reaches a certain threshold, you can create “rules” that direct an automatic retest of those parts to capture full scan chain diagnostics, and ten automatically pass that information off to the yield engineers to diagnose. So now those people are getting real information they can troubleshoot. They can spend their time fixing problems not looking for them. This is just one example for how companies can turn their data into actionable information and create a source of manufacturing intelligence that can help many different parts of their company.

    Sorry for the long reply…

  11. Himanshugupta
    April 24, 2014

    Thanks David for the elaborate reply. I have seen Engineers using statistical softwares such as SAS or JMP or R to build pedictive and forecasting models but i think still the predictive models can be much improved taking clues from other industries such as oil and gas, energy, automotive etc. 

    I also agree that testing and diagnosting chips is a real challenge and if this can be done in real time then we can take corrective course of action to save the whole batch going bad. Most of the time, it is very time consuming to find the bad patterns or burried layers responsible for the failure of the chip. 

    The semiconductor data is real big data and i think industry will warm up to the potential of the big data techniques and invest in the resources.

Leave a Reply

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