Moores Law will hold true for a while yet

Discussion in 'NZ Computing' started by Shane, Feb 26, 2006.

  1. Shane

    Shane Guest

    1. Advertising

  2. "Shane" <-a-geek.net> wrote in message
    news:dtrqrd$1it$...
    > http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >


    but, has moores law held true for the last 3 years?

    3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    Looking around today, I should be able to find a pc with the equivalent
    power of a 12ghz processor.

    I bet there aren't any pc's that could encode video 3 times faster than my
    machine.

    Multi core technology doesn't count either. It should be the output from a
    single processor that counts, (to compare apples with apples)
     
    news.xtra.co.nz, Feb 26, 2006
    #2
    1. Advertising

  3. Shane

    Shane Guest

    news.xtra.co.nz wrote:

    >
    > "Shane" <-a-geek.net> wrote in message
    > news:dtrqrd$1it$...
    >>

    http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>

    >
    > but, has moores law held true for the last 3 years?
    >
    > 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    > Looking around today, I should be able to find a pc with the equivalent
    > power of a 12ghz processor.
    >
    > I bet there aren't any pc's that could encode video 3 times faster than my
    > machine.
    >
    > Multi core technology doesn't count either. It should be the output from a
    > single processor that counts, (to compare apples with apples)



    Multicore tech does count, moores observation was concerned with the number
    of transistors on a chip, its only a consequence of those transistors that
    has led to clock speeds.

    A possible anology
    A one horse cart with the horse getting progressively
    bigger/stronger/faster, followed by a two horse cart, with two string
    horses, speeds the same but capable of carrying heavier loads

    AMD has shown that clock speed alone is a poor measurement of a chip, and
    like I always say, its not the size that counts, but its what you can do
    with it that matters
     
    Shane, Feb 26, 2006
    #3
  4. "Shane" <-a-geek.net> wrote in message
    news:dtt2hg$b33$...
    > news.xtra.co.nz wrote:
    >
    >>
    >> "Shane" <-a-geek.net> wrote in message
    >> news:dtrqrd$1it$...
    >>>

    > http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>

    >>
    >> but, has moores law held true for the last 3 years?
    >>
    >> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >> Looking around today, I should be able to find a pc with the equivalent
    >> power of a 12ghz processor.
    >>
    >> I bet there aren't any pc's that could encode video 3 times faster than
    >> my
    >> machine.
    >>
    >> Multi core technology doesn't count either. It should be the output from
    >> a
    >> single processor that counts, (to compare apples with apples)

    >
    >
    > Multicore tech does count, moores observation was concerned with the
    > number
    > of transistors on a chip, its only a consequence of those transistors that
    > has led to clock speeds.
    >
    > A possible anology
    > A one horse cart with the horse getting progressively
    > bigger/stronger/faster, followed by a two horse cart, with two string
    > horses, speeds the same but capable of carrying heavier loads
    >
    > AMD has shown that clock speed alone is a poor measurement of a chip, and
    > like I always say, its not the size that counts, but its what you can do
    > with it that matters



    Basically, they are not speeding up the processing for a 'single thread'
    applications. They are improving chips multitasking abilities, rather than
    making it absolutely faster.

    My analogy is of a racing car. The 'moores' law applies to the absolute
    top speed of the racing car. Then, each year, the racing car should be twice
    as fast. ie, this year, the top speed is 100kph. In 18 months, they will
    build one that can go 200kph, and so on.

    In my opinion. the 'single thread' execution speed is what counts the most.
    Actually, I am not exactly sure the definition of moores law but I thought
    it related to speed, rather than power.
     
    news.xtra.co.nz, Feb 26, 2006
    #4
  5. Shane

    Andrew Guest

    news.xtra.co.nz wrote:
    > "Shane" <-a-geek.net> wrote in message
    > news:dtt2hg$b33$...
    >> news.xtra.co.nz wrote:
    >>
    >>> "Shane" <-a-geek.net> wrote in message
    >>> news:dtrqrd$1it$...

    >> http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>> but, has moores law held true for the last 3 years?
    >>>
    >>> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >>> Looking around today, I should be able to find a pc with the equivalent
    >>> power of a 12ghz processor.
    >>>
    >>> I bet there aren't any pc's that could encode video 3 times faster than
    >>> my
    >>> machine.
    >>>
    >>> Multi core technology doesn't count either. It should be the output from
    >>> a
    >>> single processor that counts, (to compare apples with apples)

    >>
    >> Multicore tech does count, moores observation was concerned with the
    >> number
    >> of transistors on a chip, its only a consequence of those transistors that
    >> has led to clock speeds.
    >>
    >> A possible anology
    >> A one horse cart with the horse getting progressively
    >> bigger/stronger/faster, followed by a two horse cart, with two string
    >> horses, speeds the same but capable of carrying heavier loads
    >>
    >> AMD has shown that clock speed alone is a poor measurement of a chip, and
    >> like I always say, its not the size that counts, but its what you can do
    >> with it that matters

    >
    >
    > Basically, they are not speeding up the processing for a 'single thread'
    > applications. They are improving chips multitasking abilities, rather than
    > making it absolutely faster.
    >
    > My analogy is of a racing car. The 'moores' law applies to the absolute
    > top speed of the racing car. Then, each year, the racing car should be twice
    > as fast. ie, this year, the top speed is 100kph. In 18 months, they will
    > build one that can go 200kph, and so on.
    >
    > In my opinion. the 'single thread' execution speed is what counts the most.
    > Actually, I am not exactly sure the definition of moores law but I thought
    > it related to speed, rather than power.
    >
    >
    >

    Multi threaded in terma of the racing car analogy... that car that can
    travel 200kph could probably only travel at 100kph up a hill, So if it
    was multithreaded it would have more power and be able to travel up the
    hill at 200kph
     
    Andrew, Feb 26, 2006
    #5
  6. Shane

    Shane Guest

    news.xtra.co.nz wrote:

    >
    > "Shane" <-a-geek.net> wrote in message
    > news:dtt2hg$b33$...
    >> news.xtra.co.nz wrote:
    >>
    >>>
    >>> "Shane" <-a-geek.net> wrote in message
    >>> news:dtrqrd$1it$...
    >>>>

    >>

    http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>>
    >>>
    >>> but, has moores law held true for the last 3 years?
    >>>
    >>> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >>> Looking around today, I should be able to find a pc with the equivalent
    >>> power of a 12ghz processor.
    >>>
    >>> I bet there aren't any pc's that could encode video 3 times faster than
    >>> my
    >>> machine.
    >>>
    >>> Multi core technology doesn't count either. It should be the output from
    >>> a
    >>> single processor that counts, (to compare apples with apples)

    >>
    >>
    >> Multicore tech does count, moores observation was concerned with the
    >> number
    >> of transistors on a chip, its only a consequence of those transistors
    >> that has led to clock speeds.
    >>
    >> A possible anology
    >> A one horse cart with the horse getting progressively
    >> bigger/stronger/faster, followed by a two horse cart, with two string
    >> horses, speeds the same but capable of carrying heavier loads
    >>
    >> AMD has shown that clock speed alone is a poor measurement of a chip, and
    >> like I always say, its not the size that counts, but its what you can do
    >> with it that matters

    >
    >
    > Basically, they are not speeding up the processing for a 'single thread'
    > applications. They are improving chips multitasking abilities, rather
    > than making it absolutely faster.
    >


    This is correct, unfortunately this means its up to the software designers
    to take full advantage of that power, so older programs will not have any
    noticeable change.

    > My analogy is of a racing car. The 'moores' law applies to the absolute
    > top speed of the racing car. Then, each year, the racing car should be
    > twice
    > as fast. ie, this year, the top speed is 100kph. In 18 months, they will
    > build one that can go 200kph, and so on.
    >
    > In my opinion. the 'single thread' execution speed is what counts the
    > most. Actually, I am not exactly sure the definition of moores law but I
    > thought it related to speed, rather than power.


    From the ubiquitous wikipedia
    http://en.wikipedia.org/wiki/Moores_Law
    Moores original statement on the phenomenon (try and spell that without a
    spellcheka)
    The complexity for minimum component costs has increased at a rate of
    roughly a factor of two per year ... Certainly over the short term this
    rate can be expected to continue, if not to increase. Over the longer term,
    the rate of increase is a bit more uncertain, although there is no reason
    to believe it will not remain nearly constant for at least 10 years. That
    means by 1975, the number of components per integrated circuit for minimum
    cost will be 65,000. I believe that such a large circuit can be built on a
    single wafer.
     
    Shane, Feb 26, 2006
    #6
  7. "Shane" <-a-geek.net> wrote in message
    news:dtt86k$b33$...
    > news.xtra.co.nz wrote:
    >
    >>
    >> "Shane" <-a-geek.net> wrote in message
    >> news:dtt2hg$b33$...
    >>> news.xtra.co.nz wrote:
    >>>
    >>>>
    >>>> "Shane" <-a-geek.net> wrote in message
    >>>> news:dtrqrd$1it$...
    >>>>>
    >>>

    > http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>>>
    >>>>
    >>>> but, has moores law held true for the last 3 years?
    >>>>
    >>>> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >>>> Looking around today, I should be able to find a pc with the equivalent
    >>>> power of a 12ghz processor.
    >>>>
    >>>> I bet there aren't any pc's that could encode video 3 times faster than
    >>>> my
    >>>> machine.
    >>>>
    >>>> Multi core technology doesn't count either. It should be the output
    >>>> from
    >>>> a
    >>>> single processor that counts, (to compare apples with apples)
    >>>
    >>>
    >>> Multicore tech does count, moores observation was concerned with the
    >>> number
    >>> of transistors on a chip, its only a consequence of those transistors
    >>> that has led to clock speeds.
    >>>
    >>> A possible anology
    >>> A one horse cart with the horse getting progressively
    >>> bigger/stronger/faster, followed by a two horse cart, with two string
    >>> horses, speeds the same but capable of carrying heavier loads
    >>>
    >>> AMD has shown that clock speed alone is a poor measurement of a chip,
    >>> and
    >>> like I always say, its not the size that counts, but its what you can do
    >>> with it that matters

    >>
    >>
    >> Basically, they are not speeding up the processing for a 'single thread'
    >> applications. They are improving chips multitasking abilities, rather
    >> than making it absolutely faster.
    >>

    >
    > This is correct, unfortunately this means its up to the software designers
    > to take full advantage of that power, so older programs will not have any
    > noticeable change.
    >
    >> My analogy is of a racing car. The 'moores' law applies to the absolute
    >> top speed of the racing car. Then, each year, the racing car should be
    >> twice
    >> as fast. ie, this year, the top speed is 100kph. In 18 months, they will
    >> build one that can go 200kph, and so on.
    >>
    >> In my opinion. the 'single thread' execution speed is what counts the
    >> most. Actually, I am not exactly sure the definition of moores law but I
    >> thought it related to speed, rather than power.

    >
    > From the ubiquitous wikipedia
    > http://en.wikipedia.org/wiki/Moores_Law
    > Moores original statement on the phenomenon (try and spell that without a
    > spellcheka)
    > The complexity for minimum component costs has increased at a rate of
    > roughly a factor of two per year ... Certainly over the short term this
    > rate can be expected to continue, if not to increase. Over the longer
    > term,
    > the rate of increase is a bit more uncertain, although there is no reason
    > to believe it will not remain nearly constant for at least 10 years. That
    > means by 1975, the number of components per integrated circuit for minimum
    > cost will be 65,000. I believe that such a large circuit can be built on a
    > single wafer.
    >
    >


    yes, so, it is the number of components on a 'single' wafer. If they can
    continue putting extra cores onto a wafer then it seems moores law is
    upheld.

    I just like the idea, of being able to encode an mp3 in 1/2 the time in
    18months time. But, it seems under the existing definition this is not
    predicted.
     
    news.xtra.co.nz, Feb 26, 2006
    #7
  8. Shane

    -=rjh=- Guest

    news.xtra.co.nz wrote:

    > In my opinion. the 'single thread' execution speed is what counts the most.
    > Actually, I am not exactly sure the definition of moores law but I thought
    > it related to speed, rather than power.


    Neither, it related to the number of components that could be built into
    an integrated circuit for the same basic cost - Moore didn't specify the
    function of the circuit. Bear in mind that he was thinking that
    transistor counts of up to 65,000 should be possible.

    At the time that Moore first made his observation, (which others later
    called Moore's Law) the microprocessor didn't exist, and even when Moore
    was working at Intel later, Intel was focusing on memory production, not
    microprocessors.

    Fortunately Japan thought memory was more important at that time and
    made a huge government backed push to control that industry, while Intel
    practically stumbled into processor production; the results of this
    split in production are still evident today.

    "Inside Intel" is probably at your local library, it is a very
    interesting read.

    http://www.amazon.com/gp/product/0452276438/
     
    -=rjh=-, Feb 26, 2006
    #8
  9. On Mon, 27 Feb 2006 10:25:44 +1300, news.xtra.co.nz wrote:

    > In my opinion. the 'single thread' execution speed is what counts the
    > most. Actually, I am not exactly sure the definition of moores law but I
    > thought it related to speed, rather than power.


    Moore's law relates to the density of transistors located on an
    intergrated circut.


    Have A Nice Cup of Tea

    --
    Buffer-overflow vulnerabilities are simply programming errors; they occur when
    coders fail to deploy proper memory-management techniques.
     
    Have A Nice Cup of Tea, Feb 26, 2006
    #9
  10. Shane

    Jerry Guest

    news.xtra.co.nz wrote:
    > "Shane" <-a-geek.net> wrote in message
    > news:dtrqrd$1it$...
    >
    >>http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>

    >
    >
    > but, has moores law held true for the last 3 years?
    >
    > 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    > Looking around today, I should be able to find a pc with the equivalent
    > power of a 12ghz processor.
    >
    > I bet there aren't any pc's that could encode video 3 times faster than my
    > machine.
    >
    > Multi core technology doesn't count either. It should be the output from a
    > single processor that counts, (to compare apples with apples)
    >
    >

    Moore's law has to do with the number of transisters per given area of a
    chip.

    at http://www.webopedia.com/TERM/M/Moores_Law.html it gives a
    definition, but it appears the page is a few years old. Multi core
    would count for sure, it increases the number of transistors on a given
    sized chip.

    (môrz lâ) (n.) The observation made in 1965 by Gordon Moore,
    co-founder of Intel, that the number of transistors per square inch on
    integrated circuits had doubled every year since the integrated circuit
    was invented. Moore predicted that this trend would continue for the
    foreseeable future. In subsequent years, the pace slowed down a bit, but
    data density has doubled approximately every 18 months, and this is the
    current definition of Moore's Law, which Moore himself has blessed. Most
    experts, including Moore himself, expect Moore's Law to hold for at
    least another two decades.
     
    Jerry, Feb 27, 2006
    #10
  11. Shane

    Rob Guest

    They will be releasing a lot of faster chips once Vista comes out. Basically
    Microsoft appears to have slowed it down, by not releasing a new version of
    windows for many years.


    "news.xtra.co.nz" <> wrote in message
    news:qWnMf.154638$...
    >
    > "Shane" <-a-geek.net> wrote in message
    > news:dtrqrd$1it$...
    >> http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>

    >
    > but, has moores law held true for the last 3 years?
    >
    > 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    > Looking around today, I should be able to find a pc with the equivalent
    > power of a 12ghz processor.
    >
    > I bet there aren't any pc's that could encode video 3 times faster than my
    > machine.
    >
    > Multi core technology doesn't count either. It should be the output from a
    > single processor that counts, (to compare apples with apples)
    >
     
    Rob, Feb 28, 2006
    #11
  12. Shane

    Nik Coughlin Guest

    Rob wrote:
    > "news.xtra.co.nz" <> wrote in message
    > news:qWnMf.154638$...
    >>
    >> "Shane" <-a-geek.net> wrote in message
    >> news:dtrqrd$1it$...
    >>> http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>

    >>
    >> but, has moores law held true for the last 3 years?
    >>
    >> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >> Looking around today, I should be able to find a pc with the
    >> equivalent power of a 12ghz processor.
    >>
    >> I bet there aren't any pc's that could encode video 3 times faster
    >> than my machine.
    >>
    >> Multi core technology doesn't count either. It should be the output
    >> from a single processor that counts, (to compare apples with apples)

    >
    > They will be releasing a lot of faster chips once Vista comes out.
    > Basically Microsoft appears to have slowed it down, by not releasing
    > a new version of windows for many years.


    That makes very little sense.
     
    Nik Coughlin, Feb 28, 2006
    #12
  13. Shane

    Mercury Guest

    > Moore's law relates to the density of transistors located on an
    > intergrated circut.


    ..... and

    clock speed (~= performance for a particular architecture)
    and heat dissipation
    and power consumption (== heat)
    and ? forget.


    "Moore's Law" isn't a law by any means at all to start off with **. It is
    more an observation that it is possible to achieve the "doubling" of
    "performance" over a time interval as a means to an end: and that end is
    the ability of the chip industry to make marketable chips with a self
    perpetuation sales cycle.

    Improving on any of the key factors above is adherence with the "law".
    Halving the chip size and preserving performance, or halving heat
    dissipation and preserving size and performance, or doubling performance and
    preserving heat dissipation levels all individually qualify (read the
    original article).

    Going dual core is dubious just as doubling cache size is dubious since the
    change has to translate into usable benefit. Adding 8MB cache onto a single
    core chip that previously had 1 MB probably represents a very substantial
    increase in logic gates (towards 9 times as many if ignoring the gates in
    the CPU core), but how much benefit is there? While increasing cache size,
    the chip size is also increasing negating the benefit - if the chip size
    were preserved then there is benefit.

    I have always regarded Moore's "Law" in a light similar to Moore himself in
    that
    1. he did not coin the term,
    2. he did not claim that it was perpetual
    3. he merely published (extremely well) a set of observations that should
    have put a big smile on the faces of investors, engineers, and consumers
    that said basically "we are in for a very interesting time". It was only
    recently that Moore (forget his first name) even gave the word "Law" any
    credence & it was a bit odd that he did.

    The "Law" has not held true for Intel (no comment for AMD - they have
    reduced heat dissipation and added x64 as major achievements) for some
    time - following the principals o the "Law" we should have either 30+ GHZ
    single core systems or systems with 3GHz grunt using less than 1 watt or
    power or 3GHz systems in absolutely tiny chips, or all flavours of variants
    across the board from 3 to 30GHz and about 1 (or less) to 100 watts for the
    highest spec low cost chips. This has not happened because Intel stuffed up
    and has chosen to concentrate on heat dissipation.

    Intel could have stuck with it (Moore's "Law") if they had wished and not
    stuffed up. They stuffed up and tried to produce high clock P4 family chips
    when there were heat dissipation issues clearly acting as a limiting factor.
    Instead of addressing this factor they have copped out and taken the easy
    way out and gone multi core. There is no guarantee at all that there will
    ever be sufficient uptake in the consumer market of multithreaded
    applications or multiple concurrent app usage to ever benefit the consumer
    to become a worthwhile upgrade - do not be surprised to see the GHz race
    come back at a later date when someone redesigns the chips to do more per
    clock cycle, drop the clock cycles down substantially (Itanium's are under
    2GHz still and apparently have stunning performance) and the start producing
    a new product family with 2, 3, 4, 5, 6 GHZ cores that leave current systems
    in the dust.

    x64 has been another distraction on this front. In a way it is just another
    architecture and only that even though it is only an extension of the
    existing architecture. Most users won't see great performance benefits to ma
    it worth while by its self. How fast can you type or click?

    So, I describe Moore's "Law" as a marketing plan (not a Law) - a business
    driver which if a CPU manufacturer sticks to (with eyes open) results in a
    set a rules that tells the company what to do to produce a set of products
    that will sell themselves as they will be 100% faster and / or leaner or
    cooler or lower in power consumption every 18 months to 2 years.

    Frankly I have been astonished that Intel has give away such a large chunk
    of its business to AMD so quickly. But then it could be part of their
    business plans - desk top machines are on the way out. Mobile is the hot
    thing, that still needs fast cool, low power consumption chips IE centrino /
    Pentium M - Intel's only success in recent years and other architectures.

    Thankfully at the end of the day we now have a new variant of Moore's "Law".
    rather than having the disgusting high heat dissipation P4 Prescott chips
    with howling coolers we will benefit from quiet easier to build and maintain
    systems with vastly lower heat dissipation / power consumption - this is
    getting back to Moore's "Law" as a halving of heat dissipation is a very
    sellable thing by its self.

    ** if it were a law then how could you possibly stuff it up? How fast were
    the processors cave men used?
     
    Mercury, Mar 1, 2006
    #13
  14. Shane

    Mercury Guest

    Doubt it.

    So no one wants a faster sytem just cos there are no new OS?

    One of the really big new things is Media Centre type apps. I would like to
    be able to biff the 4GB files arounf a *lot* faster than I can currently - I
    am sure everyone else working with VOB's and DIVx and whatever else would
    like to too. Thats only 1 application, but its a biggy and growing quickly.

    One can spend days sorting out video files due to current performance limits
    and not evn have much o a video library.





    "Rob" <> wrote in message
    news:1141097307.167219@ftpsrv1...
    > They will be releasing a lot of faster chips once Vista comes out.
    > Basically Microsoft appears to have slowed it down, by not releasing a new
    > version of windows for many years.
    >
    >
    > "news.xtra.co.nz" <> wrote in message
    > news:qWnMf.154638$...
    >>
    >> "Shane" <-a-geek.net> wrote in message
    >> news:dtrqrd$1it$...
    >>> http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>

    >>
    >> but, has moores law held true for the last 3 years?
    >>
    >> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >> Looking around today, I should be able to find a pc with the equivalent
    >> power of a 12ghz processor.
    >>
    >> I bet there aren't any pc's that could encode video 3 times faster than
    >> my machine.
    >>
    >> Multi core technology doesn't count either. It should be the output from
    >> a single processor that counts, (to compare apples with apples)
    >>

    >
    >
     
    Mercury, Mar 1, 2006
    #14
  15. Shane

    Rob Guest

    "Mercury" <> wrote in message
    news:du2t6p$lh4$...
    > Doubt it.
    >
    > So no one wants a faster sytem just cos there are no new OS?
    >
    > One of the really big new things is Media Centre type apps. I would like
    > to be able to biff the 4GB files arounf a *lot* faster than I can
    > currently - I am sure everyone else working with VOB's and DIVx and
    > whatever else would like to too. Thats only 1 application, but its a biggy
    > and growing quickly.
    >
    > One can spend days sorting out video files due to current performance
    > limits and not evn have much o a video library.
    >
    >
    >
    >
    >
    > "Rob" <> wrote in message
    > news:1141097307.167219@ftpsrv1...
    >> They will be releasing a lot of faster chips once Vista comes out.
    >> Basically Microsoft appears to have slowed it down, by not releasing a
    >> new version of windows for many years.
    >>
    >>
    >> "news.xtra.co.nz" <> wrote in message
    >> news:qWnMf.154638$...
    >>>
    >>> "Shane" <-a-geek.net> wrote in message
    >>> news:dtrqrd$1it$...
    >>>> http://www.newscientist.com/article.ns?id=mg18925344.900&feedId=info-tech_rss20
    >>>>
    >>>
    >>> but, has moores law held true for the last 3 years?
    >>>
    >>> 3 years ago (early 2003), I bought a pc with a 3ghz intel processor.
    >>> Looking around today, I should be able to find a pc with the equivalent
    >>> power of a 12ghz processor.
    >>>
    >>> I bet there aren't any pc's that could encode video 3 times faster than
    >>> my machine.
    >>>
    >>> Multi core technology doesn't count either. It should be the output from
    >>> a single processor that counts, (to compare apples with apples)
    >>>

    >>
    >>

    >
    >


    This is my personal opinion, and I have also read articles with similar
    views. The fact is, with windows xp, most computer buyers (the target market
    of businesses and home users) don't need a computer faster than 3 Ghz. There
    really hasn't been much of a speed increase in computers for a good couple
    of years, which matches the fact that their hasn't been a new release of
    windows.
    However when Vista is released, people will be wanting to upgrade to it. The
    fact is, most people don't buy a standalone operating system (they want
    things as easy and simple as possible), so they buy the computer bundled
    with the OEM windows license all preinstalled. This is a win win situation
    for both microsoft and intel, especially as Vista has such high processor
    requirements to run all it's features and eye candy.
     
    Rob, Mar 1, 2006
    #15
  16. On Wed, 01 Mar 2006 14:21:43 +1300, Mercury wrote:

    > Frankly I have been astonished that Intel has give away such a large chunk
    > of its business to AMD so quickly.


    Intel did not "give" that business away. Intel's current products are not
    as good as AMD's products, and so the industry quite rightly is going with
    the better product - produced by AMD.

    Moore's Law has nothing to do with heat or speed. It was an observation
    on how transistor density on a single integrated circut had increased over
    time, and how it was likely to keep on increasing.


    Have A Nice Cup of Tea

    --
    Jono Bacon: "I deal with companies every day that are moving over to Linux, and
    it does all the things that they want."
     
    Have A Nice Cup of Tea, Mar 1, 2006
    #16
  17. On Wed, 01 Mar 2006 14:51:54 +1300, Rob wrote:

    > However when Vista is released, people will be wanting to upgrade to it.


    Only if they're clueless morons who don't know what they'll be letting
    themselves in for. (resource hog, Digital Restrictions Managemetn)

    In comparison with Longhorn/Vista/<insert-current-name-here> big desktops
    like KDE and Gnome will positively fly along at lightning speed and with,
    comparitively, a miniscule memory footprint.

    Micro$oft Windows Vista is arguably one of the better reasons to start
    using a contemporary release of Linux.


    Have A Nice Cup of Tea

    --
    Jono Bacon: "I deal with companies every day that are moving over to Linux, and
    it does all the things that they want."
     
    Have A Nice Cup of Tea, Mar 1, 2006
    #17
  18. Shane

    Mercury Guest

    You need to read the original article by Mr Moore.

    How else can we interprit Intel's action? "Give away", "Stolen", "Fought
    furiously for".... IMO, they made it so easy for AMD that it was a Give
    Away. AMD has worked well to maximise the benefit for its self, but if AMD
    did not exist, Intel's actions and failures still equate to a huge loss of
    sales, so they have given away those sales.

    Put it another way, if they had stuck to Moores "Law" and had produced a 6,
    10, 16, and 30 GHZ CPU over the last few years then I along with many many
    others would have bough some of them, but they do not exist to purchase off
    Intel (nor AMD unfortunately) and the only real improvements in technology
    has come from AMD so, again, Intel has tossed out sales and given the sales
    and advantage to AMD. AMD has earned substantial credit in the process.

    Ex. Intel Fan Boy.


    Thanks for the tea.




    "Have A Nice Cup of Tea" <> wrote in message
    news:p...
    > On Wed, 01 Mar 2006 14:21:43 +1300, Mercury wrote:
    >
    >> Frankly I have been astonished that Intel has give away such a large
    >> chunk
    >> of its business to AMD so quickly.

    >
    > Intel did not "give" that business away. Intel's current products are not
    > as good as AMD's products, and so the industry quite rightly is going with
    > the better product - produced by AMD.
    >
    > Moore's Law has nothing to do with heat or speed. It was an observation
    > on how transistor density on a single integrated circut had increased over
    > time, and how it was likely to keep on increasing.
    >
    >
    > Have A Nice Cup of Tea
    >
    > --
    > Jono Bacon: "I deal with companies every day that are moving over to
    > Linux, and
    > it does all the things that they want."
    >
     
    Mercury, Mar 1, 2006
    #18
  19. Shane

    Mercury Guest

    <snip>
    >
    > This is my personal opinion, and I have also read articles with similar
    > views. The fact is, with windows xp, most computer buyers (the target
    > market of businesses and home users) don't need a computer faster than 3
    > Ghz. There really hasn't been much of a speed increase in computers for a
    > good couple of years, which matches the fact that their hasn't been a new
    > release of windows.
    > However when Vista is released, people will be wanting to upgrade to it.
    > The fact is, most people don't buy a standalone operating system (they
    > want things as easy and simple as possible), so they buy the computer
    > bundled with the OEM windows license all preinstalled. This is a win win
    > situation for both microsoft and intel, especially as Vista has such high
    > processor requirements to run all it's features and eye candy.


    Thats all true.
     
    Mercury, Mar 1, 2006
    #19
  20. On Wed, 01 Mar 2006 15:32:24 +1300, Mercury wrote:

    > You need to read the original article by Mr Moore.
    >
    > How else can we interprit Intel's action? "Give away", "Stolen", "Fought
    > furiously for".... IMO, they made it so easy for AMD that it was a Give
    > Away. AMD has worked well to maximise the benefit for its self, but if AMD
    > did not exist, Intel's actions and failures still equate to a huge loss of
    > sales, so they have given away those sales.


    Moore's law is an observation on how the density of transistors on a
    single integrated circut had changed over time. That is all. Nothing to do
    with heat or speed. (altho' heat dissipation and clock speed are directly
    affected by density and voltage)

    Intel did not "give away" anything. It just developed a dud product in the
    name of faster clock speeds. AMD just went and produced a CPU that could
    do more work.


    Have A Nice Cup of Tea

    --
    Buffer-overflow vulnerabilities are simply programming errors; they occur when
    coders fail to deploy proper memory-management techniques.
     
    Have A Nice Cup of Tea, Mar 1, 2006
    #20
    1. Advertising

Want to reply to this thread or ask your own question?

It takes just 2 minutes to sign up (and it's free!). Just click the sign up button to choose a username and then you can ask your own questions on the forum.
Similar Threads
  1. =?Utf-8?B?U2NyZWFtZXI=?=

    Can't hold a connection?

    =?Utf-8?B?U2NyZWFtZXI=?=, Dec 31, 2004, in forum: Wireless Networking
    Replies:
    1
    Views:
    614
    =?Utf-8?B?UG90ZW56YQ==?=
    Dec 31, 2004
  2. Posco

    Firefox 1.1 put on hold

    Posco, Feb 2, 2005, in forum: Firefox
    Replies:
    0
    Views:
    415
    Posco
    Feb 2, 2005
  3. mp3maniac

    call manager and music-on-hold

    mp3maniac, Nov 10, 2004, in forum: Cisco
    Replies:
    0
    Views:
    518
    mp3maniac
    Nov 10, 2004
  4. Cen
    Replies:
    2
    Views:
    17,652
  5. Giuen
    Replies:
    0
    Views:
    1,179
    Giuen
    Sep 12, 2008
Loading...

Share This Page