Breaking News
News & Analysis

IBM Turns to Semiconductor Packaging Post-Moore’s Law

1/14/2014 09:20 AM EST
12 comments
NO RATINGS
2 saves
More Related Links
View Comments: Newest First | Oldest First | Threaded View
Page 1 / 2   >   >>
Kinnar
User Rank
CEO
Re: Ignoring Information a very new approach
Kinnar   1/18/2014 11:24:45 AM
NO RATINGS
I am not sure how to do the selection process, as per today's technology and architecture it will require to process for selection as well. But since the thought has emerged in the brilliant minds some new technique will be developed for it.

DougInRB
User Rank
Manager
Re: $ per Transistor going up
DougInRB   1/16/2014 11:43:54 AM
NO RATINGS
Let's just say it will be 'more normal'.  It's all about economics.  If you are going to sell millions of chips, you will probably opt for an expensive NRE and low recurring costs.  If you are going to sell hundreds of thousands of chips, you may opt for 3D and use an older node to reduce NRE, but with higher recurring costs.  If you are only going to sell thousands of chips, you might as well figure out how to use FPGAs to accomplish your goals...

In the case of DRAM, I think the game might be a bit different, because you can charge a premium for providing higher density.  So I might expect a DRAM maker to go 3D on the latest greatest node for enterprise and HPC applications, while using that same die in 2D for PCs and cell phones...

Of course, I could be wrong about all of this :-)

 

zewde yeraswork
User Rank
Blogger
Re: $ per Transistor going up
zewde yeraswork   1/16/2014 10:46:26 AM
NO RATINGS
It seems to be just a matter of time before that kind of 3D stacking is the norm.

DougInRB
User Rank
Manager
$ per Transistor going up
DougInRB   1/15/2014 2:32:38 PM
NO RATINGS
Since wafer costs are going up faster than transistor size is going down, it will eventually make economic sense to do chip stacking.  Sources say that the $/transistor goes up when going from 28nm to 20nm - that is the first time this has ever happened.  So, going 3D may make sense despite the yield loss and the packaging costs.  You can double you density without going to the next node...

chipmonk0
User Rank
CEO
Those who can't afford to pay for a 10 B$ CMOS Fab
chipmonk0   1/15/2014 12:28:46 PM
NO RATINGS
keep harping on the demise of Moore's Law. And their numbers are growing.

But the last Fab / Foundry standing will get all the consumer electronics business as integration at a die level is still going to be cheaper than at package level - at least to integrate chips of compatible Fab technologies.

How many actual products are out there with 2.5-d or 3-d die stacking technology ( 1 for sure maybe 5 tops ? ). IBM has been talking about it for over 7 years. Do they use it for their own products ( other than building a few samples for SemTech or Micron ) ?

The real niche for integration at the package level by 2.5-d or 3-d die stacking is in heterogeneous systems using incompatible technologies. Have n't seen much action other than camera modules for mobile phones. Perhaps IoT will boost the numbers, even include RF.

But for IBM it will have to be mostly opto - electronic I/O for high speed servers or integrating chips made at various Foundries at finer nodes ( to take advantage of FinFETs ?).

IBM's volume, cost structure & strategies ( that ultimately decide the technologies they will push ) are not always relevant to mid to low end systems down to Consumer Electronics.

Also the HKMG gate first or last episode at 32 nm is still too recent to forget !

resistion
User Rank
CEO
Re: Ignoring Information a very new approach
resistion   1/15/2014 10:54:10 AM
NO RATINGS
You'd still need a processor to look at all the data for selection, and how can it be guaranteed to have error-free selection. No win.

zewde yeraswork
User Rank
Blogger
Re: Ignoring Information a very new approach
zewde yeraswork   1/15/2014 9:07:24 AM
NO RATINGS
Do people think it's best to have this approach of ignoring and selecively choosing data?

Kinnar
User Rank
CEO
Ignoring Information a very new approach
Kinnar   1/15/2014 4:14:41 AM
NO RATINGS
Yes it is rightly said that the information from all different sources are putting enormous amount for processing requirement on the silicon and the present day architecture is not designed to ignore a single bit of information, identifying and ignoring it selectively will be a beneficial approach, may be this will one a new area of research.

KB3001
User Rank
CEO
Re: Moore's Law
KB3001   1/14/2014 10:58:24 PM
NO RATINGS
New computing paradigms (perhaps biologically inspired) using different materials/technologies altogether.

daleste
User Rank
CEO
Re: Moore's Law
daleste   1/14/2014 10:46:36 PM
NO RATINGS
Chip stack packaging can help to reduce costs of components, but it is not the same as shrinking technologies.  The additional costs of complexity and defects does not give the same payback.  Are there any other ways to reduce cost?  Most packaging advancements going forward are for size, not cost.  The biggest need for our customers is to shrink the footprint for portable electronics.  Of course, cost is always an issue and needs to be addressed as best as possible.  Otherwise your competition will own the socket.

Page 1 / 2   >   >>
Flash Poll
Radio
LATEST ARCHIVED BROADCAST
EE Times editor Junko Yoshida grills two executives --Rick Walker, senior product marketing manager for IoT and home automation for CSR, and Jim Reich, CTO and co-founder at Palatehome.
Like Us on Facebook

Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
EE Times on Twitter
EE Times Twitter Feed