You are currently viewing SemiWiki as a guest which gives you limited access to the site. To view blog comments and experience other SemiWiki features you must be a registered member. Registration is fast, simple, and absolutely free so please, join our community today!
Small foundries are a thing, most of them specialized. Why don't you do some research on a few of them? Here's a couple of names to get started:
Tower/Jazz
Skywater
Those are both pure-play foundries. A lot of smaller, specialized foundries are attached to companies like Texas Instruments, NXP...
Shrinking from something previous to 28nm or 16nm probably means a switch from single- to double-patterning. Combine that with the shrink and you've more than doubled your tooling costs for the production run. The EDA for double patterning is more expensive, too, which will be trouble for the...
Yeah, Samsung is like a supernova: however big you think they are, they're bigger.
They have weapons divisions! If Apple really wants to rival Samsung, how'd you like to see the iRifle or iMortar? Come to think of it, from what I hear about how military gadgets work, the troops could really use...
My guess, based on the information that the chip is being designed by a team in the Azure division, is that MS is aiming for Graviton binary compatibility, the better to compete with AWS. Imagine the marketing about a no-mess-no-fuss transfer from AWS to Azure. They probably also have hopes for...
Decades ago, people predicted a dark future in which something like 1 to 5 massive foundries made all the world's chips, and our response was to do little to nothing about it. Now we live in that dark future, so it's our own fault, really.
The only bright spot I can see is, assuming scaling...
Hi. Sorry to fall silent like that; just updated my notification preferences.
Assuming you're talking about my beef with file formats, well, I suppose that's more of an analog thing. Digital design already has these standardized file formats their baseline IP goes into: VHDL and Verilog. What...
I don't know enough about hardware emulation to comment on (2), but I have comments to make on (1) and (3).
I like your point about peak usage. I've had the experience of working in startups where, when all on-site and remote engineers were working, there was an "odd man out" who would have to...
I find the whole thing both awesome and annoying at the same time. Here's the deal:
The process is an older 130nm process, which is perfect for big-A/little-D work.
The emphasis seems to be on logic chips.
Now, this is kind of understandable, really. The whole idea is to get open source tool...
I think DNA technologies or some kind of molecular machine approach will get scaling going again in approximately 10 years. Feel free to round that up to 100 if you like.
As for microfabricated optics, certainly, it could do a lot to improve networking speeds, but it won't help with increasing...