Breaking News
News & Analysis

ARM Stressed in Server Bid

8/20/2014 06:00 AM EDT
4 comments
NO RATINGS
Page 1 / 2 Next >
More Related Links
View Comments: Threaded | Newest First | Oldest First
rick merritt
User Rank
Author
Software for ARM servers
rick merritt   8/20/2014 11:03:24 AM
NO RATINGS
Anyone seen signs of Windows Server on ARM? What other software milestones are still ahead?

Some Guy
User Rank
Author
Re: Software for ARM servers
Some Guy   8/20/2014 12:45:05 PM
NO RATINGS
A couple of other big challenges: Middleware, Virtualization, Server Management, KVM. It is a chicken and egg problem. I expect that Linux / Open Source will lead it and it will take a long time to get enough volume to interest Microsoft. Especially with Intel two years ahead with microserver product and now willing to customize Xeon.

Wilco1
User Rank
Author
Re: Software for ARM servers
Wilco1   8/21/2014 6:45:55 PM
NO RATINGS
ARM & Microsoft have stated a long time ago they are working on a 64-bit port of Windows. Once you've got the OS kernel working on 64-bit ARM, it becomes a relatively simple recompile as everything already works on 64-bit x86 CPUs (just like RT runs the traditional desktop without a glitch).

As for milestones ahead, I think the main one is TSMC 16FF as that's what many of the ARM server companies are aiming for. As for ARM being stressed, they have already been paid for their licenses (server chips, even if highly successful, will never add much to ARM's bottom line compared to the billions of $1 ARM chips). So with money in the bank, I can't see much stress there...

DrFPGA
User Rank
Author
Intel ARMs Up?
DrFPGA   8/21/2014 6:19:23 PM
NO RATINGS
Intel probably adds FPGA-like programmability to their chips well before we ever see them shift to an ARM-based architecture.

Intel needs to do something innovative however to deliver something to customers other than just code compatibility (IMHO)...

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