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!
This topic probably requires its own thread, but I’ll take a quick stab. Note I’m still ‘jury out’ on this approach.
Air gapped networks are still a thing for various purposes; those air gaps definitely struggle for cost effectiveness for total available compute resources. Likewise, if you...
Hats off (again) to the engineers behind all of this tech. Imagine sending this back in time and showing to Gordon Moore in 1965, or Shockley in 1949.
On the video I think it’s reasonable as it’s intended for investors and the public. “This technology is a work of art, Intel is first to use...
FWIW - Apple’s iPhone business in 2022/2023 dropped from $66B in revenue to $51B from calendar Q4 to Q1, a drop of roughly 23%. Some prior years have been steeper, though many similar (source: Statista).
It looks like TSMC’s revenue drop for N3 is probably just that as (I believe) it’s the...
Tell me a little more if you don't mind.
I thought they had some layoffs in engineering a year or two ago. Also some pay reductions that may have bled some talent. They are also splitting into two companies and competing in more segments than before. And CPUs are getting more complex (with...
Power is just really another “knob”; they may have decided that they needed the throughput more and were OK with the power budget this time.
Voltage going up with a frequency rise of almost 70% seems reasonable.
My take on this is they probably looked at their limited engineering pool and decided to use it for getting the next gen product after Falcon Shores out in as good of shape as possible.
They’ve made a lot of similar decisions lately - Extending Raptor Lake an extra year because it’s “good...
Jensen is shrewd -- he's going to take the best fab deal with the most advanced technology that he can get.
He fell out with TSMC but had no problem going back to them when Samsung failed to keep up with his needs.
For 18A, the target segment is HPC (noteably ‘not mobile’). Is it possible that the density estimate vs competition is correct for that segment? High performance libraries for comparison instead of high density?
Apologies - I really had it in my head they showed LNL as 20A but searching around I can’t find proof :(. (I can’t find anything saying it’s exclusively N3 either, but..)
Agreed and makes sense — but is that worth the extra time and cost of adding those extra dummy dies over millions of products? That’s where I’m a little skeptical.
(It may be worth it to Intel - but just thinking that’s extra packaging steps, more time = less volume, more cost).