editor's blog
Subscribe Now

An Almost-Cloudy San Diego Day

Not long ago we looked at how EDA is shaping up in the cloud, including work that Synopsys has been doing to make VCS available for bursty relief usage. I was fortunate enough to attend a demo session to show how what has heretofore been an interesting theoretical discussion could be made concrete.

Synopsys spent a lot of effort on cloud computing at DAC this year, including a cloud partners booth. Various names, both obvious and some not so, were in the booth: Amazon, NetAp, Cisco, CloudPassage, Univa, Platform Computing, Xuropa, and EVE. Most of these guys provide a variety of services to bolster the Infrastructure as a service (IaaS), Platform as a service (PaaS), or Software as a service (SaaS) layers of any EDA offering. They appear to have very specific EDA (not just Synopsys) messaging.

In the demo session itself, we saw a bit more of Synopsys’s VCS specifics. As mentioned before, their setup involves a master node and multiple work nodes. Each cloud-computing instance (CCI) node consists of an 8-core Nehalem machine with 23 GB of memory for the 8 cores, along with a single VCS license. You can then requisition clusters consisting of multiples of 8 nodes, sizing up to hundreds of nodes (although they want advance notice on really large requests for now so they can set that up with Amazon; they don’t currently have them lying around because that costs money and there’s not that much demand yet).

They showed the scripts used to get things set up. The bring-up process lasts about a half an hour (they didn’t try to run that live), which might sound like a long time until you realize that, in that time, you’ve gone from nothing to, potentially, a multi-hundred-server compute farm.

I’d like to report on how they then went into the cloud and ran an example OpenSPARC simulation. That was the plan. But the unthinkable happened. And I totally felt for the guy running the demo. I mean, it’s the nightmare scenario for any of you (and me) who have done demos: you go to where the files are all ready to be uploaded and run… and… they’re gone. Completely gone. Like, the folder isn’t even there.

Turns out that a hard drive died on the Synopsys campus. The drive housing the project they were going to demonstrate. File it under “W” for “WT…” well, you know how that one ends. Yeah, crazy. So there wasn’t time to reconstruct it on another drive and start again. So we’ll have to report later when we see things actually happening in the cloud.

Leave a Reply

featured blogs
Dec 13, 2019
Long gone are the days of simply selling a selling a part, pins in plastic if you will. Between environmental standards, qualification testing, UL ratings, and thermal models; customers have come to expect information about the products they purchase as well. Thermal modeling...
Dec 13, 2019
I'm a firm believer that you can'€™t have too many LEDs; "Show me a flashing LED, and I'll show you a man drooling!"...
Dec 13, 2019
[From the last episode: We summarized the last several weeks of computing posts.] We'€™ve talked about processors and we'€™ve talked about several kinds of memories. Today we'€™re going to focus in on the memory used when a program is running. We'€™re not talking abou...
Dec 13, 2019
Do you know what known good die are? Do you know what wafer sort is? Final test? Wafer Sort After a wafer has been manufactured in the fab, it usually (but not always) goes through wafer sort. This... [[ Click on the title to access the full blog on the Cadence Community sit...