Why so little parallelism?
|
From: BDH on 12 Nov 2006 08:02 > This is getting boring. If you can provide evidence for the above claims, > please do so. Until then, I don't believe that you can, and few other > experienced people will, either. These are problems that have been > extensively worked over, there is a lot of money available for a much > better solution, and nobody has been able to provide one in 30+ years. So unless I've made a mistake somewhere I have something new? I coulda sworn this is all in literature somewhere.
From: Nick Maclaren on 12 Nov 2006 08:48 In article <1163336548.916143.53010(a)m7g2000cwm.googlegroups.com>, "BDH" <bhauth(a)gmail.com> writes: |> |> So unless I've made a mistake somewhere I have something new? I coulda |> sworn this is all in literature somewhere. Yes. It could well be. One of the reasons that so many of the 'known facts of computer science' are complete claptrap is that they use a completely unrealistic model or, in extreme cases, an inconsistent one. As every competent engineer knows, you can design the most incredible products if you are allowed to assume an unrealistic model. And as every competent mathematician knows, you can prove anything using an inconsistent model. In the case of sorting, if you have come across the old, bogus argument that 'proves' that radix sort is always O(N) and comparison sorting is always O(N log N), I am not surprised that you have got confused. The same 'logic' can be applied to FFTs, too, to show that they can be done a lot faster. Regards, Nick Maclaren.
From: BDH on 12 Nov 2006 09:14 So...you suspect I have something new but useless because it uses an unrealistic model? I thought things were the other way around.
From: BDH on 12 Nov 2006 10:22 > In the case of sorting, if you have come across the old, bogus argument > that 'proves' that radix sort is always O(N) and comparison sorting is > always O(N log N), I am not surprised that you have got confused. The > same 'logic' can be applied to FFTs, too, to show that they can be done > a lot faster. Your wording is confusing, but anyway I'm pretty sure I'm not making any mistakes THAT dumb.
From: Jan Vorbrüggen on 12 Nov 2006 11:37
> Tape is a way to increase the ratio of memory to read/write speed. When > that ratio is already very high, why bother? You bother if you're > recording something continuously on the small chance that you will want > to rewind to some known point and see what happens, so surveillance and > backup and that's about it. Survelliance is now all on harddisks - digital video recorders. Jan |