Breaking News
News & Analysis

Tensilica DSP core does 100 GMACs at 1W

8/19/2011 01:15 PM EDT
5 comments
NO RATINGS
More Related Links
View Comments: Newest First | Oldest First | Threaded View
MAHESH.SHUKLA
User Rank
Author
re: Tensilica DSP core does 100 GMACs at 1W
MAHESH.SHUKLA   8/23/2011 5:24:08 AM
NO RATINGS
Instead of quoting "100 GMACs at 1W", it would be more interesting to see figures (perf & power) from usecase pov -- audio/speech algos (which are less data-hungry) and video/imaging algos (which are more data hungry). Then only we can understand how viable is the chip from product pov.

Kinnar
User Rank
Author
re: Tensilica DSP core does 100 GMACs at 1W
Kinnar   8/21/2011 11:52:39 AM
NO RATINGS
Hot Chips have really gone a very hot event as most of the recent news are from the Hot Chips event.

rick merritt
User Rank
Author
re: Tensilica DSP core does 100 GMACs at 1W
rick merritt   8/19/2011 9:28:15 PM
NO RATINGS
Fixed. Thx R

mrahman
User Rank
Author
re: Tensilica DSP core does 100 GMACs at 1W
mrahman   8/19/2011 3:47:27 PM
NO RATINGS
Rick misquoted what I said to him. I said 160GFLOPS ( not 125MFLOPS) which is also publicly available info.

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