Breaking News
Blog

The Mill: Ivan Godard Explains a Revolutionary New CPU

NO RATINGS
Page 1 / 2 Next >
View Comments: Newest First | Oldest First | Threaded View
garydpdx
User Rank
Author
Re: Design Creation for FPGA
garydpdx   11/24/2013 5:48:56 PM
NO RATINGS
To create parallel multicore systems, many FPGA tools fall short because they are design assembly and implementation infrastructure, lacking in analysis.  At Space Codesign, one of the ways that our SpaceStudio ESL hardware/software codesign tool can be used, is as a design creation front end for FPGA tool infrastructures like Xilinx Vivado (and likely others).  We published a position paper on this topic on this site a few weeks ago ...

 

http://www.eetimes.com/author.asp?section_id=36&doc_id=1319640&

 

The key to supercomputer performance is that your architecture is optimized for an application, or family of applications.  Knowing the internal details of a processor core or FPGA device (there are architecture diagrams available, after all!) but it is the system level performance that comes into play, at the end of the day.

betajet
User Rank
Author
Re: More details also in comp.arc
betajet   11/21/2013 7:28:05 PM
NO RATINGS
Peter Kogge has an interesting article called Next-Generation Supercomputing (IEEE Spectrum, January 2011).  In it he states that the bottleneck with next-generation supercomputing is not the speed of floating-point processors.  The problem is that the power needed to transfer data to and from those processors is much higher than the power used by the processors themselves.  So a conventional computer memory hierarchy with caches and main memory becomes impractical.

A possible solution?  How about FPGAs as I mentioned above -- you arrange the FPGA logic implementing your problem so that each result is pumped to adjacent or at least nearby processing elements, not bothering with register files and caches.  However, it's not practical to do this because of... FPGA tools, as I just described.  JMO/YMMV

betajet
User Rank
Author
Re: More details also in comp.arc
betajet   11/21/2013 7:11:41 PM
NO RATINGS
An FPGA-based reconfigurable computing engine has the potential to be a superb high-performance supercomputer.  Unfortunately, FPGA tools are not up to the task as discussed in this 2007 article.  It has to be as easy to design parallel hardware data paths as it is to write code for general-purpose CPUs, and that's not the case with current FPGA design languages and tools.  FPGA tool research has always been stymied by the fact that no major FPGA manufacturer publishes their internal architecture so that the research community can develop efficient design tools for reconfigurable computing.  It would be like Intel refusing to publish the X86 instruction set and requiring everyone to program in PL/M using a compiler provided by Intel.  I believe this is the primary reason CPU makers sell billions and FPGA makers have stayed small.  JMO/YMMV



Caleb Kraft
User Rank
Author
Re: More details also in comp.arc
Caleb Kraft   11/21/2013 1:59:52 PM
NO RATINGS
Do you feel like there never will be any new ideas?

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