From: nedbrek on 24 Apr 2010 21:03 Hello all, "Robert Myers" <rbmyersusa(a)gmail.com> wrote in message news:i4GAn.30112$0_7.26359(a)newsfe25.iad... > nedbrek wrote: >> But, Itanium tried to record independence - turns out, determining >> dependence is much more important (see Smith's dependency chain >> processing research). > > The paper I found > > An Instruction Set and Microarchitecture for > Instruction Level Distributed Processing > Ho-Seop Kim and James E. Smith > Department of Electrical and Computer Engineering > University of Wisconsin�Madison That's the one. > advertises the ability to run at a high clock rate and also proposes > binary translation. This paper was, of course, before the Pentium 4 clock > rate debacle, before Transmeta folded, and before power consumption became > an obsession. > > That is not to say that the idea may still not have merit. On the face of > it, keeping dependent chains together has the obvious advantage of > increasing locality, so that computation can be efficiently parceled out > over threads in a core, over separate cores on a chip, or even conceivably > over multiple sockets. Yea, this is turning into the "End of Microarchitecture" thread :) Ned
From: Robert Myers on 24 Apr 2010 21:34 On Apr 24, 9:03 pm, "nedbrek" <nedb...(a)yahoo.com> wrote: > > Yea, this is turning into the "End of Microarchitecture" thread :) > Time is running out for the "We did it all fifty years ago" types, anyway. I abandoned astrophysics as a career goal to study more down-to-earth fluids because it was hard for me to see where the new data was going to come from. The search for gravitational waves, which I had been exposed to, was going nowhere and still hasn't gone anywhere, but astrophysics is now drowning in data, thanks to instruments above the earth's atmosphere. It will take something like photons or quantum mechanics to make computer architecture interesting again, and no one knows how long we will have to wait, but it will happen. Robert.
From: nmm1 on 25 Apr 2010 05:22 In article <4a90b55d-c6c3-4976-b66b-a50c189126b0(a)z11g2000yqz.googlegroups.com>, Robert Myers <rbmyersusa(a)gmail.com> wrote: >On Apr 24, 9:03=A0pm, "nedbrek" <nedb...(a)yahoo.com> wrote: > >> Yea, this is turning into the "End of Microarchitecture" thread :) > >Time is running out for the "We did it all fifty years ago" types, >anyway. You mean because innovation stopped in 1965? :-) Regards, Nick Maclaren.
From: Robert Myers on 25 Apr 2010 10:04 On Apr 25, 5:22 am, n...(a)cam.ac.uk wrote: > In article <4a90b55d-c6c3-4976-b66b-a50c18912...(a)z11g2000yqz.googlegroups..com>, > Robert Myers <rbmyers...(a)gmail.com> wrote: > > >On Apr 24, 9:03=A0pm, "nedbrek" <nedb...(a)yahoo.com> wrote: > > >> Yea, this is turning into the "End of Microarchitecture" thread :) > > >Time is running out for the "We did it all fifty years ago" types, > >anyway. > > You mean because innovation stopped in 1965? :-) I sincerely hope that computer-related disciplines get over this illness. No one dismisses the cleverness, erudition, insight, and hard work of Nineteenth Century physics and mathematics, and much of it is still in use, but both physics and mathematics have come to consider questions that would have seemed far-fetched even to the brightest of Nineteenth Century practitioners. Computer-related disciplines don't seem to have reached the point of a cataclysm like the failure of the Russell and Whitehead agenda, the widespread realization of automatic computers, special relativity, and quantum mechanics, but one assumes that the cataclysm will come. One of the reasons I have gone after the ever-bigger computer (clusters) with such energy is that it is an intellectual dead end. So long as people are convinced that there is nothing new under the sun, computer-related disciplines will be less and less like science and more like religion, where everything important was revealed in ages past and the only thing left to do is to build ever more grandiose cathedrals. Robert.
From: nmm1 on 25 Apr 2010 11:08
In article <a09f2353-bcd5-46e3-9145-97e0de98f63b(a)29g2000yqp.googlegroups.com>, Robert Myers <rbmyersusa(a)gmail.com> wrote: > >So long as people are convinced that there is nothing new under the >sun, computer-related disciplines will be less and less like science >and more like religion, where everything important was revealed in >ages past and the only thing left to do is to build ever more >grandiose cathedrals. Try rephrasing it the other way: So long as people are convinced that relabelling an old idea counts as innovation, computer-related disciplines will be less and less like science and more like religion, where everything important is revealed in this week's Revelation and the only thing left to do is to build ever more grandiose facades onto existing cathedrals. I have met almost nobody in the IT business who believes that there is nothing left to invent, though I meet a lot who claim that great god Compatibility rules, and must not be challenged. However, I have met a LOT of "computer scientists" who have claimed that their idea is new because it has been relabelled. Regards, Nick Maclaren. |