Breaking News
News & Analysis

Brocade's Chairman on the Future of Engineering, Communications

7/1/2013 07:10 AM EDT
5 comments
NO RATINGS
Page 1 / 3 Next >
More Related Links
View Comments: Oldest First | Newest First | Threaded View
Allthingstech
User Rank
Author
Blurred Lines
Allthingstech   7/1/2013 9:34:35 AM
NO RATINGS
I was just remarking on this last week. When I last worked in an engineering department (before going F/T writer/editor), there were two distinct teams: HW and SW. And a fair amount of suspicion between the two as to which group did more work...

rick merritt
User Rank
Author
Soft vs Hard; Ether vs. FC
rick merritt   7/1/2013 11:57:50 AM
NO RATINGS
I'd love to hear more stories about the state of play between software and hardware engineering...and/or the tussle in storage networking between Ethernet and Fibre Channel.

DaveHouse
User Rank
Author
Re: Soft vs Hard; Ether vs. FC
DaveHouse   7/1/2013 6:39:36 PM
NO RATINGS
On the tussle between Ethernet and Fibre Channel, both technologies have a strong role to play in storage networking.  Fibre channel continues to find adoption and loyalty among customers who value the six 9's of uptime fibre channel can uniquely deliver for the most mission critical applications and data.  It is perhaps one of the stickiest technologies I have seen in my career because of its unmatched reliability and deterministic performance.  Ethernet is ideal for IP-based storage.  The industry has recognized the need for purpose-built Ethernet technology, such as Ethernet fabrics, for the data center and in support of newer technologies like scale-out NAS and distributed file systems that have become popular with applications such as Big Data analytics.

garydpdx
User Rank
Author
Re: Soft vs Hard; Ether vs. FC
garydpdx   7/1/2013 6:59:56 PM
NO RATINGS
Rick - at Space Codesign, we have an ESL EDA tool for hardware/software co-design of SoC embedded systems.  It's a Montreal-based university tech transfer startup and our key technology allows you to use the same C/C++/SystemC model and retarget it for either hardware or software implementation - without recoding.  It's targeted at system architects but also enables software designers and hardware engineers to work with them as a team.


Here's our recent listing from Embedded World 2013 in Nuremberg, Germany:

 

http://www.ask-embedded-world.de/?Action=showCompany&id=28056


 

rick merritt
User Rank
Author
Re: Soft vs Hard; Ether vs. FC
rick merritt   7/1/2013 7:45:08 PM
NO RATINGS
Thanks for chiming in Dave!

I wrote recently about standards efforts to drive new ultra low latencies into Ethernet that will have these folks nipping at FC's heels in the future. Two Broadcom engineers are among the leaders of the efforts.

See http://www.eetimes.com/document.asp?doc_id=1280906

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