Breaking News
News & Analysis

Multicore CPUs face slow road in comms

3/20/2009 06:00 PM EDT
2 comments
NO RATINGS
More Related Links
View Comments: Newest First | Oldest First | Threaded View
rick merritt
User Rank
Author
re: Multicore CPUs face slow road in comms
rick merritt   5/18/2009 10:05:28 PM
NO RATINGS
I'm looking foir embedded developers on the bleeding edge of multicore work for a story. Have any prospects contact me at rmerritt@techinsights.com Thanks Rick

TechnoMarketeer
User Rank
Author
re: Multicore CPUs face slow road in comms
TechnoMarketeer   3/25/2009 11:27:23 AM
NO RATINGS
Yay! Another voice of common sense rises up in the multicore hype arena. "The barriers are high, especially in software" - have to agree with this. The core problem all along is that multicore does not work as a silicon solution, its only half a solution. And the silicon vendors, Intel included even, have gone far to fast for the software ecosystem to keep up. I also agree that the solutions are highly fragmented at the moment, and will remain so, until some sanity arises as to where multicore truly offers value in embedded, and as the market definition narrows, the software ecosystem will get a chance to focus and then we'll start to see complete solutions, hardware+software in harmony.

Most Recent Comments
michigan0
 
SteveHarris0
 
realjjj
 
SteveHarris0
 
SteveHarris0
 
VicVat
 
Les_Slater
 
SSDWEM
 
witeken
Most Recent Messages
9/25/2016
4:48:30 PM
michigan0 Sang Kim First, 28nm bulk is in volume manufacturing for several years by the major semiconductor companies but not 28nm FDSOI today yet. Why not? Simply because unlike 28nm bulk the LDD(Lightly Doped Drain) to minimize hot carrier generation can't be implemented in 28nm FDSOI. Furthermore, hot carrier reliability becomes worse with scaling, That is the major reason why 28nm FDSOI is not manufacturable today and will not be. Second, how can you suppress the leakage currents from such ultra short 7nm due to the short channel effects? How thin SOI thickness is required to prevent punch-through of un-dopped 7nm FDSOI? Possibly less than 4nm. Depositing such an ultra thin film less then 4nm filum uniformly and reliably over 12" wafers at the manufacturing line is extremely difficult or not even manufacturable. If not manufacturable, the 7nm FDSOI debate is over!Third, what happens when hot carriers are generated near the drain at normal operation of 7nm FDSOI? Electrons go to the positively biased drain with no harm but where the holes to go? The holes can't go to the substrate because of the thin BOX layer. Some holes may become trapped at the BOX layer causing Vt shift. However, the vast majority of holes drift through the the un-dopped SOI channel toward the N+Source,...

Datasheets.com Parts Search

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