Re: Algorithm design: computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!)

From	Bernd Paysan <bernd.paysan@gmx.de>
Newsgroups	comp.lang.forth
Subject	Re: Algorithm design: computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!)
Date	2013-04-08 19:54 +0200
Organization	1&1 Internet AG
Message-ID	<kjv09k$nuq$1@online.de> (permalink)
References	(2 earlier) <98eb98de-b24c-47bd-9480-37f6bde941d8@googlegroups.com> <ki967o$kc7$1@speranza.aioe.org> <51485eee$0$6095$e4fe514c@dreader36.news.xs4all.nl> <kjn7fa$agu$1@dont-email.me> <23f53cc8-cc60-4347-90d0-a03230674141@googlegroups.com>

Show all headers | View raw

Brad Eckert wrote:
> FWIW, an 8" processed wafer costs $2000. The GA144 looks to be about 1300
> chips per wafer (generous dicing streets) or maybe 1500 otherwise. I would
> be skeptical about the million chips, unless they included a lot of tiny
> processors like the GA4.

Nah, they are counting "computers".  A GA144 is 144 "computers", according 
to Chuck, a "computer" is something with a processor, RAM and ROM.  
Everybody else calls these things "cores".  I think Chuck spent too much 
time together with a Patent Troll(tm) and got confused over terminology.

Multiply 144 with 1500, and you need 5 wafers for a million.  The usual run 
on TSMC for prototypes are 6 wafers, they don't do less (but you can let 
them hold 3 before metal).  That's where the "one million computers" figure 
comes from.  If you do a redesign, you run another 6 wafers.  Another 
million "computers" in Chuck's term.

-- 
Bernd Paysan
"If you want it done right, you have to do it yourself"
http://bernd-paysan.de/

Back to comp.lang.forth | Previous | Next — Previous in thread | Next in thread | Find similar

Thread

Re: Algorithm design:  computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!) rickman <gnuarm@gmail.com> - 2013-04-05 10:30 -0400
  Re: Algorithm design:  computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!) Brad Eckert <hwfwguy@gmail.com> - 2013-04-08 09:32 -0700
    Re: Algorithm design:  computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!) Bernd Paysan <bernd.paysan@gmx.de> - 2013-04-08 19:54 +0200
    Re: Algorithm design:  computational cost of ordinary stack operations (dup, rot, over, swap, etc.) vs. cost of fetch (@) and store (!) rickman <gnuarm@gmail.com> - 2013-04-09 09:58 -0400

csiph-web