🚀 go-pugleaf

On 01/11/2012 08:26 PM, krw@att.bizzzzzzzzzzzz wrote:
> On Wed, 11 Jan 2012 14:22:11 -0500, Phil Hobbs
> <pcdhSpamMeSenseless@electrooptical.net>  wrote:
>
>> On 01/11/2012 01:43 PM, John Larkin wrote:
>>> On Tue, 10 Jan 2012 18:02:50 -0800 (PST), Bill Sloman
>>> <bill.sloman@gmail.com>   wrote:
>>>
>>>> On Jan 10, 4:55 pm, John Devereux<j...@devereux.me.uk>   wrote:
>>>>> Robert Macy<robert.a.m...@gmail.com>   writes:
>>>>>> On Jan 10, 2:28 am,BillSloman<bill.slo...@ieee.org>   wrote:
>>>>>>> On Jan 10, 7:47 am, "David L. Jones"<altz...@gmail.com>   wrote:
>>>>>
>>>>>>>> Just thought some might be interested in hearing our recent guest on
>>>>>>>> our Amp Hour radio show, Dr Howard Johnson of "Handbook of Black
>>>>>>>> Magic" fame:http://www.theamphour.com/2012/01/10/the-amp-hour-77-winsome-waveform...
>>>>>
>>>>>>>> Lots of history of the book, signal integrity, Gigabit Ethernet
>>>>>>>> development, 90 degree PCB bends, audiophoolery, and a whole bunch of
>>>>>>>> other talk over almost 1 1/12 hours.
>>>>>
>>>>>>> "Black Magic" is more notorious than famous. I own both it and it's
>>>>>>> follow-up, and both have got some useful content but they are badly
>>>>>>> organised and what useful content they do contain is hard to find.
>>>>>
>>>>>>> The field is still waiting for a decent textbook on high speed circuit
>>>>>>> design and layout.
>>>>>
>>>>>>> This is one of the few matters on which John Larkin and I seem to
>>>>>>> agree.
>>>>>
>>>>>>> --
>>>>>>> BillSloman, Nijmegen
>>>>>
>>>>>> Perhaps, it is time for the first ever 'conference' book written by a
>>>>>> consortium of engineers/scientists.
>>>>>
>>>>>> Put my name in for proffreading.  :)
>>>>>
>>>>> Great idea. Perhaps John Larkin, Jim Thompson and Bill Sloman could
>>>>> collaborate on it.
>>>>>
>>>>> Sure that will work out well... :)
>>>>
>>>> I'm not sure what Jim Thompson might contribute. I've seen papers that
>>>> worry about the characteristic impedance of connections on the silicon
>>>> (or whatever) inside integrated circuits, but I don't have the feeling
>>>> that Jim designs stuff that's big enough and fast enough for him to
>>>> need to know much about it.
>>>
>>> I get the impression that most interconnects inside ICs are primarily
>>> distributed R-C things, not real transmission lines at all.
>>> Propagation speed of interconnects is a big deal in routing fast logic
>>> chips, but the speed of light isn't the issue.
>>>
>>>>
>>>> Motorola's ECL applications notes on board layout were rather useful,
>>>
>>> Just don't trust their microstrip equation!
>>>
>>> John
>>>
>>
>> Yup, all RC transmission lines with repeaters, speed roughly c/10.
>
> The routing delay scales roughly with the square of the length (not at all
> linear).  Yes, it's often faster to buffer the middle of a long line.  In the
> PPC970/G5, there were several nets with three and four repeaters.  Even
> numbers work better, though.  ;-)

In the limit of long lines, that's true.  However, you can't build chips 
in that limit, because the bandwidth goes down quadratically with length 
as well.  To maintain speed, you have to use repeaters, and maintaining 
2-3 GHz clock rates with reasonable jitter requires spacing them at 
something like 1 mm intervals on long lines.  In an optimized layout, 
that turns out to produce a roughly constant propagation speed of c/10 
or so.

Cheers

Phil "Former on-chip optical interconnect person" Hobbs

-- 
Dr Philip C D Hobbs
Principal Consultant
ElectroOptical Innovations LLC
Optics, Electro-optics, Photonics, Analog Electronics

160 North State Road #203
Briarcliff Manor NY 10510
845-480-2058

hobbs at electrooptical dot net
http://electrooptical.net