From rc1.vub.ac.be!idefix.CS.kuleuven.ac.be!ub4b!EU.net!sun4nl!cs.vu.nl!germans Mon Oct  3 13:35:39 1994
Newsgroups: comp.sys.ibm.pc.demos
Path: rc1.vub.ac.be!idefix.CS.kuleuven.ac.be!ub4b!EU.net!sun4nl!cs.vu.nl!germans
From: germans@cs.vu.nl (Germans DM)
Subject: Re: ARM writes about his WAVES
Message-ID: <Cx37DH.9Aq@cs.vu.nl>
Sender: news@cs.vu.nl
Organization: Fac. Wiskunde & Informatica, VU, Amsterdam
References: <Cww38J.825@dit.upm.es>
Date: Mon, 3 Oct 1994 07:56:04 GMT
Lines: 23

: ; When at/h =  last term vanishes, giving:
: ;                      1   
: ;        u(t+1) =   1 0 1 u - u(t-1)
: ;                      1   
: ;
: ; This needs only 4 ADD/SUB and one SAR operation per mesh point!

Tough shit!

I never thought of that. Hmm. So you don't keep a speed array at all! That should
speed up my routine considerably. I did my stuff in machine language this
weekend and was already stunned by the result... But, it was over 40 instructions
per mesh point

Thanx for posting this.
--
          _  |_  __ |_   _  _   _  |_
         (_| |_) _) |_, |  (_| (_, |_,  _   _   _   _   _   _  |_  __
                                       (_, (_) | | (_, (-, |_) |_, _)
                                                           |
                      A DVision Software Group division
====== Simm (germans@cs.vu.nl) - Coder / Musician / Graphician / etc. ======
          "Whatever you do, continue to F5" - Space Manbow / Konami

