Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 30 Aug 1995 12:48:44 +0930 (CST)
From:      Michael Smith <msmith@atrad.adelaide.edu.au>
To:        rgrimes@gndrsh.aac.dev.com (Rodney W. Grimes)
Cc:        hardware@freebsd.org
Subject:   Re: S.O.S -2.1Stable and ASUSP54TP4
Message-ID:  <199508300318.MAA27585@genesis.atrad.adelaide.edu.au>
In-Reply-To: <199508300302.UAA05696@gndrsh.aac.dev.com> from "Rodney W. Grimes" at Aug 29, 95 08:02:01 pm

next in thread | previous in thread | raw e-mail | index | archive | help
Rodney W. Grimes stands accused of saying:
> I would have agreed with this 3 years ago, but I suggest you go study
> some of the current technology in use.

I'd love to - you try getting that sort of data on this side of the planet 8)

> First alpha particle disturbance in DRAM is gone, it was pretty much killed
> 4 years ago with the advent of certain epoxy materials used to coat the
> die with before plastic encapsolation.  At todays DRAM scales a single

Neat - I knew they were using plastic because they could control the 
isotope content more closely, I wasn't aware they'd gone to those 
lengths.

> Static memories are suspetable to alpha particule disturbance, it just
> takes a heck of a lot more to do it, and given ceramic is out of the
> picture it won't occur anyway.  In a cmos static memory you have to have
> enough disturbance to perturb the gate voltage of one side of the latch
> to cause a bit flip, about 10 micro rinkens will do it, but it usually
> sends the device into latchup at the same time :-).

Exactly; and to get that sort of flux, unless you're direct-beaming the 
device, you're going to poach anyone standing nearby 8)

> The more prevelent cause today in single bit errors in both DRAM and SRAM
> is cause by VCC noise and or ION contamination caused by moisture
> absorbition into plastic packages before surface mount vapor phase soldering.

Is that what the bother about mositure absorption is?  I thought it had to
do with sweating during soldering - we get lots of SMD parts coming through
in moisture-proof packaging, but never got an answer out of the 
manufacturers as to why...

> Current FIT per bit are in the 0.0002 to 0.0004 range, that is measure in
> billions of power on hours.  Today MTBF in a 2MB x 16 bit DRAM subsystem
> is 30 to 35 years... I'd say I can live with that given that my disk
> is going to go belly up in 57 years anyway :-) :-) :-)

*chuckle* You're not taking vibration into account there - I'd love to
see some numbers on accelerated failure due to bond wire stress from
fan and disk spindle vibration Especially given the MTBBF 
(mean time between bearing failure 8) for modern taiwanese CPU fans is
about, oh, six weeks ...

> Sources of information for this and more details are in many vendors
> data books, Mircon's 1995 has a few good tech notes about it, as does
> Intels memory products books.

Almost impossible to get over here 8(  The agents for either of those two
want to talk MOQ 1000+ before they'll even think about giving you data.

> Rod Grimes                                      rgrimes@gndrsh.aac.dev.com

(note the new cc:)

-- 
]] Mike Smith, Software Engineer        msmith@atrad.adelaide.edu.au    [[
]] Genesis Software                     genesis@atrad.adelaide.edu.au   [[
]] High-speed data acquisition and                                      [[
]] realtime instrument control          (ph/fax) +61-8-267-3039         [[
]] My car has "demand start" -Terry Lambert  UNIX: live FreeBSD or die! [[



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199508300318.MAA27585>