Breaking News
News & Analysis

Big-Little, GPU-Compute Go Industrial

7/3/2013 02:20 PM EDT
13 comments
NO RATINGS
More Related Links
View Comments: Newest First | Oldest First | Threaded View
<<   <   Page 2 / 2
krisi
User Rank
Author
Re: power savings?
krisi   7/3/2013 10:59:59 PM
NO RATINGS
I saw 70% number but it just sounds too good to be true. I am curious what others think about this claim...Kris

Sanjib.A
User Rank
Author
Re: power savings?
Sanjib.A   7/3/2013 9:38:46 PM
NO RATINGS
@krisi: In the article it is mentioned as 70% energy efficient. If you take a look at the Samsung website below, it also advertises 70% energy efficient. Now 70% wih respect to which "benchmark"?...not sure.

https://www.samsung.com/global/business/semiconductor/minisite/Exynos/products5octa.html

I think two or more of these cores come in one package. For example Exynos 5 Octa processor has four Cortex-A15 cores and four Cortex-A7 cores in a package.

 

krisi
User Rank
Author
power savings?
krisi   7/3/2013 6:00:22 PM
NO RATINGS
How much power savings can be obtained using big-little concept? why not integrate the two dice into one big+ device? Kris

<<   <   Page 2 / 2
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