Breaking News
Comments
Newest First | Oldest First | Threaded View
zeewee
User Rank
Author
re: Big.little test results show promise, ARM reports
zeewee   11/20/2012 4:37:05 AM
NO RATINGS
I think it's more efficient to improve its power saving mode such as Intel's CPU's C-state.

help.fulguy
User Rank
Author
re: Big.little test results show promise, ARM reports
help.fulguy   11/10/2012 7:15:19 PM
NO RATINGS
@ Rick, a Dual core A15 @ 2GHz in our lab is consuming 4W. Mind you, this is just the CPU Cores. When we add the Graphics, Video and IOs, you are looking at around 6-7W. ARM is in big trouble. This big.Little is just a hog-wash. Unless we see this from a 3rd party, I cant believe 50% improvement. ARM CEO can say Power this and power that, but his ARM Cores are getting worse by day.

danny1024
User Rank
Author
re: Big.little test results show promise, ARM reports
danny1024   11/6/2012 4:49:38 PM
NO RATINGS
I'll ask around but I can tell you that many of the A15 licensees are greatly disappointed with its perf/watt and associated manufacturability issues.

rick merritt
User Rank
Author
re: Big.little test results show promise, ARM reports
rick merritt   11/5/2012 9:06:04 PM
NO RATINGS
Can any share some performance per watt data they have seen on an A15?

danny1024
User Rank
Author
re: Big.little test results show promise, ARM reports
danny1024   11/5/2012 8:15:23 PM
NO RATINGS
There have been many research projects that have looked at combining Atom and "big cores" e.g. Ivy Bridge and Haswell as well as ARM processors to handle low-level OS functions and some applications while the bigger cores are sleeping. In fact, I think Dell had a laptop that had both "ARM & Intel Inside" to do roughly the same thing. The A15 is a hot, complex chip that's not particularly performant for the power nor does it yield particularly well. That A7 companion chip and the entire Big.Little concept is a tacit admission of that regrettable reality.

glennthera
User Rank
Author
re: Big.little test results show promise, ARM reports
glennthera   11/5/2012 4:53:28 PM
NO RATINGS
Thanks 4 d update Rick, been waiting on some news frm ARM n Samsung 4 a long, long time! big.Little is d future of processors, not jst SOC designs!

rick merritt
User Rank
Author
re: Big.little test results show promise, ARM reports
rick merritt   11/5/2012 3:15:19 PM
NO RATINGS
The Samsung Exynos 5 uses two A15 cores which are pretty power hungry. In the A7/A15 big.little approach, the A7 does most of the work and the A15 just powers up a minority of the time to blast through intense jobs. That should cut power by 150% or more, ARM estimates. Now I wonder, will Intel adopt this concept in mobile?

wsw1982
User Rank
Author
re: Big.little test results show promise, ARM reports
wsw1982   11/5/2012 10:15:12 AM
NO RATINGS
That's different form what observed from Samsung Chromebook and Nexus 10. The Exynos 5 is power hungry.



Datasheets.com Parts Search

185 million searchable parts
(please enter a part number or hit search to begin)
Radio
LATEST ARCHIVED BROADCAST

What are the engineering and design challenges in creating successful IoT devices? These devices are usually small, resource-constrained electronics designed to sense, collect, send, and/or interpret data. Some of the devices need to be smart enough to act upon data in real time, 24/7. Specifically the guests will discuss sensors, security, and lessons from IoT deployments.

Brought to you by:

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,...
Like Us on Facebook
Special Video Section
Once the base layer of a design has been taped out, making ...
In this short video we show an LED light demo to ...
The LTC2380-24 is a versatile 24-bit SAR ADC that combines ...
In this short video we show an LED light demo to ...
02:46
Wireless Power enables applications where it is difficult ...
07:41
LEDs are being used in current luxury model automotive ...
With design sizes expected to increase by 5X through 2020, ...
01:48
Linear Technology’s LT8330 and LT8331, two Low Quiescent ...
The quality and reliability of Mill-Max's two-piece ...
LED lighting is an important feature in today’s and future ...
05:27
The LT8602 has two high voltage buck regulators with an ...
05:18
Silego Technology’s highly versatile Mixed-signal GreenPAK ...
The quality and reliability of Mill-Max's two-piece ...
01:34
Why the multicopter? It has every thing in it. 58 of ...
Security is important in all parts of the IoT chain, ...
Infineon explains their philosophy and why the multicopter ...
The LTC4282 Hot SwapTM controller allows a board to be ...
This video highlights the Zynq® UltraScale+™ MPSoC, and sho...
Homeowners may soon be able to store the energy generated ...
The LTC®6363 is a low power, low noise, fully differential ...