In my previous article, Improving chip yield rates with cognitive manufacturing, I highlighted the costs associated with semiconductor manufacturing, and how cognitive methods can yield benefits in both design and manufacture. In this article, I show how software license utilization and management can further effect costs and time-to-results and where dramatic improvements can be realized.
The compute farms and private clouds required to run the necessary semiconductor simulations and verifications can be pretty substantial, with the largest companies deploying hundreds of thousands of compute cores. Frequently, the applications used in chip design are primarily sequential and only utilize one core at a time. In many cases, the runtime is quite short which means potentially millions of simulations/verifications per day. These factors make the ability to efficiently and intelligently schedule such volumes of work well beyond manual capabilities.
Unlike other industries, most EDA applications are licensed from independent software vendors (ISVs) with prices ranging from a few thousand dollars to hundreds of thousands of dollars per instance per year. Large design companies can end up paying tens millions of dollars per year in licensing fees.
With expenditures like that, you need to ensure that you are not only getting high license utilization but that you are also ensuring the right license is being used for the right person on the right project.
For example, if you are paying $20 million dollars a year in license fees and only getting 50 percent-effective utilization — that is a lot of wasted money. If you could drive it closer to 100 percent, you could potentially get the same work done, in the same time, with only half the licenses – a savings of $10 million dollars.
But more importantly, keeping the same number of licenses, you could cut the time needed in half. In many cases it is a lack of application license capacity rather than compute capacity that is the limiting factor on time-to-results. Or you could take the same time, but run more simulations and verifications — resulting in a better product. Or finally, you could pick the optimum combination these characteristics for your business.
Workload managers with license schedulers that automate sharing between local or global project teams are one way to increase license utilization. Using flexible policies, they can ensure that license availability is prioritized by workload, user and project, and that licenses are optimally used instead of simply throttling jobs based on license. Without any form of managed scheduling and allocation, the system is a free-for-all — whoever requests the license first gets it and keeps it.
Figure 1 shows a typical trace of license usage. The workload scheduler allocates licenses to jobs, and at some point the job actually makes use of it – hopefully. There may be cases where it doesn’t use that license at all, or uses an entirely different license. Other licenses are being reserved so urgent work can start as soon as possible – the net result is that utilization suffers, lots of licenses are reserved or allocated, but unused. That results in a lot of wasted money.
In figure 1 we can see there are always a certain number of licenses reserved (the red area). A simple improvement would be to enable over-allocation – to tell the scheduler that there are more licenses available than there really are (purple) – and in figure 2 we see that this can make a noticeable difference.
However, we’re still losing 15-20 percent efficiency as the “reserved” amount is not constant.
Solutions like IBM Spectrum LSF License Scheduler can apply cognitive techniques to enable the system to learn how licenses are really being reserved, allocated and consumed, then dynamically adjust the buffer (purple) in response to changes in reservations (red), thus driving actual license utilization (green) very close to 100 percent.
By taking advantage of these techniques in conjunction with detailed license usage reporting, organizations understand the real usage of application licenses. They can also remix their existing license portfolio within their existing budget and realize significant cost and time to market benefits.
Furthermore, it becomes much easier to justify the investment in additional licenses when you can prove to the CFO that you are using everything you already have effectively.
IBM Spectrum LSF License Scheduler provides the functionality needed to maximize license utilization while minimizing license costs. We’ve now made it easier than ever to try IBM Spectrum LSF. Learn more about IBM Spectrum LSF evaluations here.