Why so little parallelism?
|
From: BDH on 3 Nov 2006 04:31 > Del is pretty sharp. He and I may not always disagree, but > we do agree here. von Neumann was not always right: he was somewhat > wrong about Fortran and things like word processing (another waste), > but he is not shrugged lightly. He was one of the smartest > mathematicians who ever lived. He would never have bothered with > something lik Usenet. So if I was smart enough to handle the position I want, I wouldn't be on Usenet? Ouch!
From: Terje Mathisen on 3 Nov 2006 04:28 Eugene Miya wrote: > In article <ch2q14-1d1.ln1(a)osl016lin.hda.hydro.com>, > Terje Mathisen <terje.mathisen(a)hda.hydro.com> wrote: >> Feynman was a "wizard of the highest order". Even after he had figured >> something out and explained it, there was no way for mere mortals to see >> how they could ever have done the same. > > Oh that was you who said that. > > Hmmmm what can I say? > Caltech collects geniuses like Feynman. He was clearly unique, but so > are and were a fair number of other people who went to, worked at, or > were part of Tech. I could never have gotten in. I am not smart enough. Right. Pull another one. There's a Churchill quote: ?Mr. Attlee is a very modest man. Indeed he has a lot to be modest about.? Don't try to impersonate Mr Attlee! BTW, my younger brother Knut got his PhD (in industrial chemistry) at Caltech, at the same time I was working for Novell in Utah. According to him it was a nice place. > They may have also passed their their prime (friends hope not). > I took a class from a JPL co-worker (hard to use that word as he was so > much more advanced that I was: Blinn). Most of you will have never > heard Jim because this isn't comp.graphics. He had a hobby of > collecting Pythagorean theorem proofs (he's got over 100). > He's also a master of 4x4 matrix multiplication. > > That says nothing of non-computational fields. > You should visit Tech for half a day the next time you come to > California Terje. OK, I'll try to if I can figure out an excuse to travel so far south. My last US trip was a 3 day in&out to Seattle a couple of weeks ago, with no time for sightseeing. :-( Terje -- - <Terje.Mathisen(a)hda.hydro.com> "almost all programming can be viewed as an exercise in caching"
From: BDH on 3 Nov 2006 04:42 > >Golomb rulers are already found with massively parallel computation. I > >guess I'm not sure what you mean. > > Not very far. Not many. The parallelism is quite bounded. They're found by exhaustive searching of a reduced search space. It's easy to partition that for massive parallelism. > >Some people definitely have a higher opinion of him than I do though. > > Well few of us will ever a book like his game theory book, some of his > papers, his work at the Manhattan Project and on the H-bomb, etc. Hey, I have time... ....or maybe I don't. Probably don't. =( > >But its influence died off too. Why? > > APL or the Star? > > The Star probably died most because it was a system which lacked balance. > Its vector pipeline could not compensate for the poor scalar performance. > It took too long to learn how to use at the compiler level, and > its software came too late that it destroyed the careers and psyches of > people assigned to work with it during the Cold War. And that's an over > simple way of saying that. I never had to use the machine. I know and > have interviewed people who did. I was thinking of APL, but thanks for that. Thinking Machines went under too, but we still have Microsoft. I suspect that in another 10 years people will still be assuming incorrect things about compilers. > >> Part of the problem which kills simple languages like these are the > >> kinds of numeric applications which have volumetric and border (edges, > >> faces, vertices, and hyper-structures (4D and higher Ds) which are > >> exception cases which then go to irregular geometries, etc. > > > >That can be turned into arrays too. > > Oh, they are arrays, no question, but few outside certain communities > can appreciate good gather-scatter hardware and operations. I guess my question was, is there something about APL that is incompatible with either someone educated a certain way or inherently incompatible with the majority of programmers, or was it just happenstance of history? > Anyways. I'm outta here. Bye.
From: BDH on 3 Nov 2006 04:50 > The Star probably died most because it was a system which lacked balance. > Its vector pipeline could not compensate for the poor scalar performance. > It took too long to learn how to use at the compiler level, and > its software came too late that it destroyed the careers and psyches of > people assigned to work with it during the Cold War. And that's an over > simple way of saying that. I never had to use the machine. I know and > have interviewed people who did. CDC, I guess it was run in a smart way. But some kinds of useful smart need tempering to keep them away from insanity. I guess maybe they were missing that. Of course, usually companies get much less intelligent insanity.
From: Eugene Miya on 3 Nov 2006 10:38
In article <amer14-vlb.ln1(a)osl016lin.hda.hydro.com>, Terje Mathisen <terje.mathisen(a)hda.hydro.com> wrote: >>> Feynman was a "wizard of the highest order". >> Caltech collects geniuses like Feynman. He was clearly unique, but so > >Right. Pull another one. Well my friend who married Pauling daughter (as well as Pauling) are 2. Many Divisions have world famous people. I have no idea what some of my friends who teach and do research there are noted for. We just recreate together, have common friends. >There's a Churchill quote:... >Don't try to impersonate Mr Attlee! > >BTW, my younger brother Knut got his PhD (in industrial chemistry) at >Caltech, at the same time I was working for Novell in Utah. According to >him it was a nice place. It's an intense place. Depends on the person and the field. If you have been there, no need to visit. It's where the Einstein photo of him on the bike is taken. >> You should visit Tech for half a day the next time you come to >> California Terje. > >OK, I'll try to if I can figure out an excuse to travel so far south. Naw if you visited your bro, you have seen enough. >My last US trip was a 3 day in&out to Seattle a couple of weeks ago, >with no time for sightseeing. :-( Yeah I hate those in and out trips. Travel is a thread over in alt.folklore.computers right now. -- |