nano plasma accelerators AND hardware optical transistors - HOTpots?
Linux - GeneralThis Linux forum is for general Linux questions and discussion.
If it is Linux Related and doesn't seem to fit in any other forum then this is the place.
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
Interesting link, but I don't share your expectations.
250 GB/S is mind boggling fast. But even piping that speed around an LSI chip would be problematic. I remember the horror among my supervisors when I designed a university student project running at 250Mhz.
The bottlenecks on processing data are less about how fast a transistor will oscillate, and more about the physics; the limitations on the bandwidth of the other components, E.g. memory, graphics and disk; The speed of peripheral devices, etc. That stuff if it gets to construction will hardly come to your everyday pc but into supercomputers and the like.
Nice points you make, but come walk (with me) down "Memory Lane" (no pun intended)...
I seem to recall in (around) 1991/2 working on a VT100 terminal connected to a PRIME mainframe computer. That was the "state of the art" then, and it was fast. I mean really FAST. However, I do also seem to remember that if a dozen or so people connected to it, simultaneously, they overloaded the 1-MB mainframe memory (yes; I meant '1-MB'). Just one too-many jobs in the queue slowed things to a snails pace, or stopped it completely to a point where everyone had to log out for the "untanglement". Thank God, in ??1993/4?? the Org allocated $1,000,000 (yes; I meant '$1-million') and upgraded the memory with another 1-MB, else we would never have got any work done (the way head-office was driving us).
Then, the next year Windows-95 came out (with good network integration capacity), along with MS-Office. Also in that year our last switch (ie the 4th!) to a brand new database on the mainframe cost $750,000. In the very same year Microsoft released the MS-Access database which could handle the same processing! It had the introductory price of $71.
Much around the same time as I recall - well a little bit after that - UNIX "became" everyday Linux. Thus, the mainframe-potential within Linux (ie "servers", and "web-servers") also changed things.
Well the rest, in terms of PC power (ie physical hardware power, but also "personal" computing power) - is history.
Just look at PCs development in only the 25 years since back then. Pretty impressive, isn't it?
So, I agree with you about the technological aspects, that is, that physical factors might have "barriers" at scaled miniaturization. However, just in the same way that the "sound barrier" was broken (and that's an interesting thought within the abovementioned concept) the barriers you speak of might not necessarily be a limitation - although they could be.
Don't be too cynical about it. The "promise" in the advancement is the thing here.
Anyway, any "jump" in performance might not end up as CPU/PC speed, as I hinted at (and really expect). For instance, a "jump" might be in the potential of the LASERed partical-beams (sic) - say, as uni-directional, temporary, hi-speed "wires" capable of delivering "something" directly (ie rather than our hi-freq, omni-directional "radio"). [No; I haven't forgotten narrow-beam microwave, but here I am talking about the "media" potential.] Who really knows?
The "technology" might deliver something completely different or unexpected, but the scientific "potential" is here, now.
[For anyone wanting to argue the actual dates, go for it. Not interested. It's just best recollection, as pretty-close approximation in the conceptualization.]
I don't know the point of the history lesson. In 1986, I was working in Amdahl who made Mainframes to compete with IBM. The models had 11 x 11 ECL chips on each of 5 - 9 compute rboards and their new model did 38 MIPS, with configurable Ram. All the chips were there, but you only connected what ram you had paid for. Their customers had at least one IBM, and several Amdahl Mainframes I take it you guys were running some budget Z80 or 68k based 'mini computer' with its 1MB of ram. Into the 1990s people in business were still using CP/M machines with only 64k of memory in pages. They were running accounts, stock, warehouse, etc on one Z80 or 8085, and as long as you left it alone while the wages went through, everything would work well.
My point was that increased CPU speed isn't the bottleneck, and I think
we agree on that. A hard disk still writes at a very finite speed, graphics cards and other peripherals have limited speed compared to your 250 gigs.
The breakthroughs that will transform computing will come in peripheral devices being faster. Optics will play a role I imagine but you're up against physics, not me. I'm merely noting facts. I felt your post was overly optimistic. But I'm not for arguing either.
I think you misread me. (That's present tense.) I was not being optimistic - although that is one possible interpretation. I was being enthusiastic.
Further, you are quite correct in that I was using "time" as a means of integrating comprehension of "technology leap", although - to me - it felt more like reminiscing rather than didacticism. So, apologies for any "lesson" you might have taken from it.
I forget that there are all "types" in forums - and not everyone is on the same page. I forget that.
The location in your tag says "Ireland", but you speak like an American. Here, in this backwater, technology - certainly in those times - was not easily come by, or was cost-prohibitive. Any details about the hardware mainframe I gave was only from comments made to me from the one "I.T. guy" running the show at the time. I was able to talk to him only on occasion, but he was a very, very dour person. Not many of my colleagues liked him. In fact, none, that I can recall! So, to be honest, I can't tell you what was really running things inside "the box". While I was honest with details I gave, the system could have actually been driven by a fat dwarf in pink tights on a hamster wheel, for all I know. However, I will add that not only was the system running payroll for several thousand people in multiple locations, but there were various (ongoing) projects each involving serious number-crunching.
However, for now let's put aside the performance of the older hardware that I mentioned, otherwise we might miss the point.
Technology advances. Technology advances mostly in steps, but sometimes in hops or skips. Occasionally, technology advances in GIANT LEAPS. I have expressed my enthusiasm about - what I perceive to be - a HUGE, GIANT, GARGGGAANTUANNN LEAP (as in the link given). I expressed it to all who might be interested.
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.