By Michael White
At DAC this past July, I had the opportunity to sit down with Phil Steinke from AMD and Keith Bendy from Google for a lunchtime chat about EDA in the cloud. Every semiconductor company is facing the same explosion in compute time and resources as Moore’s Law progresses. While acquiring and maintaining on-site resources is always a balancing act between business need and finance, the last two years have exacerbated many supply chain issues, propelling the issue to new levels of urgency in the industry.
Fortunately, there is a proven solution at hand. Leveraging the nearly infinite resource pool of the latest technology servers in the cloud enables design companies to readily and easily access the hardware resources they need to complete more design iterations per day, shortening time to tapeout and/or giving design teams time for that extra analysis/optimization to ensure they deliver the best possible design to market. And the Calibre nmPlatform has supported distributed and cloud computing for years, using the same Calibre engines and licensing and delivering the same great performance design companies know and expect.
We discussed past concerns around EDA in the cloud, such as IP security, that have now been largely resolved with new levels of security at every level. And then we got to the good stuff—talking about the many benefits EDA in the cloud can provide, including server optimization, surge computing coverage, and high performance, all of which can help design companies shorten time to tapeout while improving design quality.
If you weren’t able to be there in person, this technical paper, Google, AMD, and Siemens demonstrate the power of the cloud for EDA, sums up our discussion. If you’re considering EDA in the cloud, or want to improve your current cloud operations, it’s worth a read.