PCI Express

Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

Since this is Intel's new chipset, would I be correct in assuming that a
pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
clone out?

Also, have there been any tests to confirm real-world performance gains?
Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
the margin of difference like?

Basically, I am in the market for a new mainboard/cpu/video and while PCIE
is obviously the forward-thinking choice, it seems like it is just barely
emerging and I don't know how this will affect cost-effectiveness. (My
budget is a concern.)
25 answers Last reply
More about express
  1. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    Kevin C. wrote:

    > Since this is Intel's new chipset, would I be correct in assuming that a
    > pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
    > clone out?
    >
    > Also, have there been any tests to confirm real-world performance gains?
    > Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    > the margin of difference like?

    There have been a few sites comparing PCI-E vs AGP for
    the top ATI and nVidia cards. Google should find such
    links for you quickly. The margins I remember seeing
    make it difficult to stop yourself from asking what the
    hell the point of PCI-E graphics is and to instead remember
    that PCI-E is not so much about giving us a step up from AGP
    and is instead about things like replacing PCI with something
    faster and cheaper and simplifying motherboard design
    by eliminating the need for AGP.

    In other words, PCI-E graphics at this stage is all about
    marketing to idiots who have to have the latest and
    greatest even if the bang/buck ratio is poor.

    >
    > Basically, I am in the market for a new mainboard/cpu/video and while PCIE
    > is obviously the forward-thinking choice, it seems like it is just barely
    > emerging and I don't know how this will affect cost-effectiveness. (My
    > budget is a concern.)
    >
    >

    VIA has the K8T890 chipset for AMD64 and the PT890 for P4,
    both offering PCI-E. Haven't heard of any mobos available
    with either of those yet.

    nVidia has something under development too, but I
    can't remember the status of it. About all I remember
    reading is that the nForce3 150 and 250 series chipsets
    do not support PCI-E, but that the next generation will.

    For those on a tight budget - including me and apparently
    you too - keep in mind that so far no one is making PCI-E
    video cards for the low end of the market. PCI-E video
    cards are so far planned only for the pricey top-shelf stuff.
  2. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Sun, 25 Jul 2004 01:25:09 GMT, "Kevin C." <nomail@fake.com> wrote:

    >Also, have there been any tests to confirm real-world performance gains?
    >Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    >the margin of difference like?

    http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2091&p=12

    Basically as expected, no real difference since slot bandwidth has not
    been the graphics bottleneck for a long while. There were no
    significant improvements between 4x and 8x AGP so PCI-E doesn't do
    much either.

    --
    L.Angel: I'm looking for web design work.
    If you need basic to med complexity webpages at affordable rates, email me :)
    Standard HTML, SHTML, MySQL + PHP or ASP, Javascript.
    If you really want, FrontPage & DreamWeaver too.
    But keep in mind you pay extra bandwidth for their bloated code
  3. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Sun, 25 Jul 2004 01:25:09 GMT, "Kevin C." <nomail@fake.com> wrote:
    >Since this is Intel's new chipset, would I be correct in assuming that a
    >pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
    >clone out?

    For the moment, yes. VIA, nVidia and SiS all have PCI Express
    chipsets for the Athlon64 planned for this year though.

    >Also, have there been any tests to confirm real-world performance gains?
    >Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    >the margin of difference like?

    0% pretty much across the board. AGP 8x had far more bandwidth than
    was actually used, so doubling again did absolutely nothing. Maybe 4
    or 5 years down the line it will make a difference, but for right now
    it's a none-issue.

    >Basically, I am in the market for a new mainboard/cpu/video and while PCIE
    >is obviously the forward-thinking choice, it seems like it is just barely
    >emerging and I don't know how this will affect cost-effectiveness. (My
    >budget is a concern.)

    At the moment it will pump up the price for no improvement in
    performance. In the long run though it *should* be cheaper. The real
    idea behind PCI-Express was to get more bandwidth out of fewer pins,
    so long-term that should translate to lower costs, even if it doesn't
    necessarily help performance. However in the short-term the "first on
    the block" factor will keep prices high.

    -------------
    Tony Hill
    hilla <underscore> 20 <at> yahoo <dot> ca
  4. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow@sasktel.net> wrote in message
    news:10g6688na9ciuc3@corp.supernews.com...
    > Kevin C. wrote:
    >
    >> Since this is Intel's new chipset, would I be correct in assuming that a
    >> pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
    >> clone out?
    >>
    >> Also, have there been any tests to confirm real-world performance gains?
    >> Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    >> the margin of difference like?
    >
    > There have been a few sites comparing PCI-E vs AGP for
    > the top ATI and nVidia cards. Google should find such
    > links for you quickly. The margins I remember seeing
    > make it difficult to stop yourself from asking what the
    > hell the point of PCI-E graphics is and to instead remember
    > that PCI-E is not so much about giving us a step up from AGP
    > and is instead about things like replacing PCI with something
    > faster and cheaper and simplifying motherboard design
    > by eliminating the need for AGP.

    What I would like to have, rather than more 3D speed
    (I don't need 3D at all) is more screen real estate. The
    cheapest way to get that seems to be with
    multiple monitors. I have a double-head Matrox
    card right now but triple head (fanless too) would be nicer. :)

    AJ
  5. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    Me wrote:
    > "Rob Stow" <rob.stow@sasktel.net> wrote in message
    > news:10g6688na9ciuc3@corp.supernews.com...
    >
    >>Kevin C. wrote:
    >>
    >>
    >>>Since this is Intel's new chipset, would I be correct in assuming that a
    >>>pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
    >>>clone out?
    >>>
    >>>Also, have there been any tests to confirm real-world performance gains?
    >>>Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    >>>the margin of difference like?
    >>
    >>There have been a few sites comparing PCI-E vs AGP for
    >>the top ATI and nVidia cards. Google should find such
    >>links for you quickly. The margins I remember seeing
    >>make it difficult to stop yourself from asking what the
    >>hell the point of PCI-E graphics is and to instead remember
    >>that PCI-E is not so much about giving us a step up from AGP
    >>and is instead about things like replacing PCI with something
    >>faster and cheaper and simplifying motherboard design
    >>by eliminating the need for AGP.
    >
    >
    > What I would like to have, rather than more 3D speed
    > (I don't need 3D at all) is more screen real estate. The
    > cheapest way to get that seems to be with
    > multiple monitors. I have a double-head Matrox
    > card right now but triple head (fanless too) would be nicer. :)
    >

    Since you don't need 3D, a quad-head Matrox G200 or
    G450 would do you nicely. However, they cost an
    arm and a leg.

    A much cheaper solution is to use a pair of dual-head
    G450's or a G450 and a G550 - either both PCI or one
    PCI and one AGP. I believe Matrox also recently
    started selling a PCI version of one of their
    P-series cards.

    --
    Reply to rob.stow.nospam@shaw.ca
    Do not remove anything.
  6. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:Qx4Vc.151895$J06.144696@pd7tw2no...
    > Me wrote:
    >> "Rob Stow" <rob.stow@sasktel.net> wrote in message news:10g6688na9ciuc3@corp.supernews.com...
    >>
    > Since you don't need 3D, a quad-head Matrox G200 or
    > G450 would do you nicely. However, they cost an
    > arm and a leg.
    >
    > A much cheaper solution is to use a pair of dual-head
    > G450's or a G450 and a G550 - either both PCI or one
    > PCI and one AGP. I believe Matrox also recently
    > started selling a PCI version of one of their
    > P-series cards.

    4 monitors would be too much though. 3 would form a nice
    symmetrical viewing pattern: front, left, right. The G450 PCI
    is what I have now (kinda slow on my 400 MHz AMD machine
    but nice text). I was going to get the P650 (but I don't think that
    will do 1600x1200x3 and that's what I want). Now if I could use
    the motherboard's built-in graphics AND the 2 G450 ports, I'd
    be all set (soon I'll have a new Intel motherboard)!

    I wonder if having 3 CRTs pointing at me poses some kind of
    health risk (?). I can't afford LCD (maybe I should wait til I can).

    AJ
  7. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    Me wrote:
    > "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:Qx4Vc.151895$J06.144696@pd7tw2no...
    >
    >>Me wrote:
    >>
    >>>"Rob Stow" <rob.stow@sasktel.net> wrote in message news:10g6688na9ciuc3@corp.supernews.com...
    >>>
    >>
    >>Since you don't need 3D, a quad-head Matrox G200 or
    >>G450 would do you nicely. However, they cost an
    >>arm and a leg.
    >>
    >>A much cheaper solution is to use a pair of dual-head
    >>G450's or a G450 and a G550 - either both PCI or one
    >>PCI and one AGP. I believe Matrox also recently
    >>started selling a PCI version of one of their
    >>P-series cards.
    >
    >
    > 4 monitors would be too much though. 3 would form a nice
    > symmetrical viewing pattern: front, left, right.

    A pair of dual-head video cards in no way requires you to
    attach a monitor to all four "heads". 4 would be the
    upper limit - nothing stopping you from using 3, 2, or
    even just 1 monitor.

    > The G450 PCI
    > is what I have now (kinda slow on my 400 MHz AMD machine
    > but nice text). I was going to get the P650 (but I don't think that
    > will do 1600x1200x3 and that's what I want). Now if I could use
    > the motherboard's built-in graphics AND the 2 G450 ports, I'd
    > be all set (soon I'll have a new Intel motherboard)!

    Give it a try and see if it works. The Intel/Matrox combo
    might not play together nicely or they might play nicely
    with some OSes and not others. Nothing stopping you from
    later disabling the Intel video and adding another Matrox
    card if that is what it takes to get you your 3 monitor
    setup.

    >
    > I wonder if having 3 CRTs pointing at me poses some kind of
    > health risk (?).

    I know someone who spent a decade in front of a 4 x 21"
    setup until the prices for large LCDs came down enough
    for his company to replace the CRTs. He had problems
    with kinks in his neck when he had to spend a lot of
    time looking at the two upper monitors (they were arranged
    in a 2 x 2 pattern), but that was about the extent of his
    health problems.

    > I can't afford LCD (maybe I should wait til I can).
    >
    > AJ
    >
    >


    --
    Reply to rob.stow.nospam@shaw.ca
    Do not remove anything.
  8. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Fri, 20 Aug 2004 03:47:59 GMT, "Me" <ng@newsgroups.net> wrote:

    >
    >"Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:Qx4Vc.151895$J06.144696@pd7tw2no...
    >> Me wrote:
    >>> "Rob Stow" <rob.stow@sasktel.net> wrote in message news:10g6688na9ciuc3@corp.supernews.com...
    >>>
    >> Since you don't need 3D, a quad-head Matrox G200 or
    >> G450 would do you nicely. However, they cost an
    >> arm and a leg.
    >>
    >> A much cheaper solution is to use a pair of dual-head
    >> G450's or a G450 and a G550 - either both PCI or one
    >> PCI and one AGP. I believe Matrox also recently
    >> started selling a PCI version of one of their
    >> P-series cards.
    >
    >4 monitors would be too much though. 3 would form a nice
    >symmetrical viewing pattern: front, left, right. The G450 PCI
    >is what I have now (kinda slow on my 400 MHz AMD machine
    >but nice text). I was going to get the P650 (but I don't think that
    >will do 1600x1200x3 and that's what I want). Now if I could use
    >the motherboard's built-in graphics AND the 2 G450 ports, I'd
    >be all set (soon I'll have a new Intel motherboard)!
    >
    >I wonder if having 3 CRTs pointing at me poses some kind of
    >health risk (?). I can't afford LCD (maybe I should wait til I can).

    I've been running triple-headed systems for years, my current dual P4 3ghz
    Xeon box sports a Parhelia 512 with three 21" tubes.

    The triple 21s are wonderful for 53 year old eyes...

    /daytripper (...and no obvious chromosome damage - yet ;-)
  9. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Fri, 20 Aug 2004 20:51:31 GMT, daytripper
    <day_trippr@REMOVEyahoo.com> wrote:
    >I've been running triple-headed systems for years, my current dual P4 3ghz
    >Xeon box sports a Parhelia 512 with three 21" tubes.

    Show off! :>

    -------------
    Tony Hill
    hilla <underscore> 20 <at> yahoo <dot> ca
  10. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Fri, 20 Aug 2004 16:08:53 GMT, Rob Stow <rob.stow.nospam@shaw.ca>
    wrote:
    >> The G450 PCI
    >> is what I have now (kinda slow on my 400 MHz AMD machine
    >> but nice text). I was going to get the P650 (but I don't think that
    >> will do 1600x1200x3 and that's what I want). Now if I could use
    >> the motherboard's built-in graphics AND the 2 G450 ports, I'd
    >> be all set (soon I'll have a new Intel motherboard)!
    >
    >Give it a try and see if it works. The Intel/Matrox combo
    >might not play together nicely or they might play nicely
    >with some OSes and not others. Nothing stopping you from
    >later disabling the Intel video and adding another Matrox
    >card if that is what it takes to get you your 3 monitor
    >setup.

    Intel's integrated graphics will not work with an AGP card, but should
    play ok with a PCI one. The trick would be more with the multi-head
    software side of things, particularly under Win2K (earlier versions of
    Windows probably won't work at all). Under WinXP they should work ok
    though, and Linux/X-Windows shouldn't be any problem at all.

    -------------
    Tony Hill
    hilla <underscore> 20 <at> yahoo <dot> ca
  11. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:pmpVc.161582$J06.95121@pd7tw2no...
    > Me wrote:
    >> "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:Qx4Vc.151895$J06.144696@pd7tw2no...
    >>
    >>>Me wrote:
    >>>
    >>>>"Rob Stow" <rob.stow@sasktel.net> wrote in message news:10g6688na9ciuc3@corp.supernews.com...
    >>>>
    >>>
    >>>Since you don't need 3D, a quad-head Matrox G200 or
    >>>G450 would do you nicely. However, they cost an
    >>>arm and a leg.
    >>>
    >>>A much cheaper solution is to use a pair of dual-head
    >>>G450's or a G450 and a G550 - either both PCI or one
    >>>PCI and one AGP. I believe Matrox also recently
    >>>started selling a PCI version of one of their
    >>>P-series cards.
    >>
    >>
    >> 4 monitors would be too much though. 3 would form a nice
    >> symmetrical viewing pattern: front, left, right.
    >
    > A pair of dual-head video cards in no way requires you to
    > attach a monitor to all four "heads". 4 would be the
    > upper limit - nothing stopping you from using 3, 2, or
    > even just 1 monitor.

    I realize that.

    >
    >> The G450 PCI
    >> is what I have now (kinda slow on my 400 MHz AMD machine
    >> but nice text). I was going to get the P650 (but I don't think that
    >> will do 1600x1200x3 and that's what I want). Now if I could use
    >> the motherboard's built-in graphics AND the 2 G450 ports, I'd
    >> be all set (soon I'll have a new Intel motherboard)!
    >
    > Give it a try and see if it works.

    My current board in the BIOS setup has an option to choose
    either a PCI video card or the onboard graphics.

    > The Intel/Matrox combo
    > might not play together nicely or they might play nicely
    > with some OSes and not others.

    Has anyone tried this and gotten it to work? (On-board vid plus
    PCI or AGP vid).

    > Nothing stopping you from
    > later disabling the Intel video and adding another Matrox
    > card if that is what it takes to get you your 3 monitor
    > setup.

    That's probably what I'll have to do. But maybe I'll get the
    P650 (still passively cooled) and use that until I accumulate a 3rd
    monitor and then add my G450 to the setup (I just found out from
    a monitor repair guy that my 2nd monitor "isn't worth fixing" so I've
    just one now).

    >> I wonder if having 3 CRTs pointing at me poses some kind of
    >> health risk (?).
    >
    > I know someone who spent a decade in front of a 4 x 21"
    > setup until the prices for large LCDs came down enough
    > for his company to replace the CRTs. He had problems
    > with kinks in his neck when he had to spend a lot of
    > time looking at the two upper monitors (they were arranged
    > in a 2 x 2 pattern), but that was about the extent of his
    > health problems.

    I think only scientific study/facts are valid for this concern (that is,
    I know someone who has smoked for 40 years, 3 packs a day
    and is still "fine". But I tend to heed the surgeon general's
    warning anyway). I have a feeling the newer TCO certified
    monitors cause little problems though.

    AJ
  12. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "daytripper" <day_trippr@REMOVEyahoo.com> wrote in message news:troci05neomjevbl23qvnjand1e9raomvm@4ax.com...
    > On Fri, 20 Aug 2004 03:47:59 GMT, "Me" <ng@newsgroups.net> wrote:

    >>I wonder if having 3 CRTs pointing at me poses some kind of
    >>health risk (?). I can't afford LCD (maybe I should wait til I can).
    >
    > I've been running triple-headed systems for years, my current dual P4 3ghz
    > Xeon box sports a Parhelia 512 with three 21" tubes.

    Wow! Can you say "high end"?! I have one 19", one 17" (broken :(, I drove
    it at 5 KHz more than its rating for a long time until I smoked it). I'll probably
    get another 19" to keep costs down (about half the price of 21").

    AJ
  13. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    AJ wrote:

    > "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:pmpVc.161582$J06.95121@pd7tw2no...
    >
    >>Me wrote:
    >>
    >>>"Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:Qx4Vc.151895$J06.144696@pd7tw2no...
    >>>
    >>>
    >>>>Me wrote:
    >>>>
    >>>>
    >>>>>"Rob Stow" <rob.stow@sasktel.net> wrote in message news:10g6688na9ciuc3@corp.supernews.com...
    >>>>>
    >>>>
    >>>>Since you don't need 3D, a quad-head Matrox G200 or
    >>>>G450 would do you nicely. However, they cost an
    >>>>arm and a leg.
    >>>>
    >>>>A much cheaper solution is to use a pair of dual-head
    >>>>G450's or a G450 and a G550 - either both PCI or one
    >>>>PCI and one AGP. I believe Matrox also recently
    >>>>started selling a PCI version of one of their
    >>>>P-series cards.
    >>>
    >>>
    >>>4 monitors would be too much though. 3 would form a nice
    >>>symmetrical viewing pattern: front, left, right.
    >>
    >>A pair of dual-head video cards in no way requires you to
    >>attach a monitor to all four "heads". 4 would be the
    >>upper limit - nothing stopping you from using 3, 2, or
    >>even just 1 monitor.
    >
    >
    > I realize that.
    >
    >
    >>>The G450 PCI
    >>>is what I have now (kinda slow on my 400 MHz AMD machine
    >>>but nice text). I was going to get the P650 (but I don't think that
    >>>will do 1600x1200x3 and that's what I want). Now if I could use
    >>>the motherboard's built-in graphics AND the 2 G450 ports, I'd
    >>>be all set (soon I'll have a new Intel motherboard)!
    >>
    >>Give it a try and see if it works.
    >
    >
    > My current board in the BIOS setup has an option to choose
    > either a PCI video card or the onboard graphics.

    What, no AGP slot ? Cheap board.

    In any case, that BIOS option is most probably just
    for selecting the primary display adapter. If you
    select PCI, it will probably disable the integrated
    AGP video, but if you select the integrated AGP it
    should not affect your ability to also use a PCI card.

    >
    >
    >>The Intel/Matrox combo
    >>might not play together nicely or they might play nicely
    >>with some OSes and not others.
    >
    >
    > Has anyone tried this and gotten it to work? (On-board vid plus
    > PCI or AGP vid).
    >

    Yup. The system I am currently using has integrated
    nVidia GeForce AGP video. Just for you I also added
    a Matrox G400 PCI dualhead. Works fine with one monitor
    on the integrated AGP and one on the G400. Can't test
    a 3 monitor setup because I only have 2 monitors here
    at home. OS = W2K Pro. Can only make it work with
    separate desktops for each monitor. (Single desktop
    across both monitors works if I put both on
    the G400 and disable the integrated AGP.)

    Note that integrated AGP video plus a card in an AGP
    slot will never work. Simply a limitation of the AGP
    standard.

    >
    >>Nothing stopping you from
    >>later disabling the Intel video and adding another Matrox
    >>card if that is what it takes to get you your 3 monitor
    >>setup.
    >
    >
    > That's probably what I'll have to do. But maybe I'll get the
    > P650 (still passively cooled) and use that until I accumulate a 3rd
    > monitor and then add my G450 to the setup (I just found out from
    > a monitor repair guy that my 2nd monitor "isn't worth fixing" so I've
    > just one now).
    >
    >
    >>>I wonder if having 3 CRTs pointing at me poses some kind of
    >>>health risk (?).
    >>
    >>I know someone who spent a decade in front of a 4 x 21"
    >>setup until the prices for large LCDs came down enough
    >>for his company to replace the CRTs. He had problems
    >>with kinks in his neck when he had to spend a lot of
    >>time looking at the two upper monitors (they were arranged
    >>in a 2 x 2 pattern), but that was about the extent of his
    >>health problems.
    >
    >
    > I think only scientific study/facts are valid for this concern (that is,
    > I know someone who has smoked for 40 years, 3 packs a day
    > and is still "fine". But I tend to heed the surgeon general's
    > warning anyway). I have a feeling the newer TCO certified
    > monitors cause little problems though.
    >

    I intended my health comment to be tongue-in-cheek.
    Some things just don't work in text because you can't see
    the other guy going nudge-nudge, wink-wink.

    --
    Reply to rob.stow.nospam@shaw.ca
    Do not remove anything.
  14. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:AMBVc.160192$M95.112520@pd7tw1no...

    > What, no AGP slot ? Cheap board.

    OLD board. (OK, budget board when it was new too).

    > In any case, that BIOS option is most probably just
    > for selecting the primary display adapter. If you
    > select PCI, it will probably disable the integrated
    > AGP video, but if you select the integrated AGP it
    > should not affect your ability to also use a PCI card.

    Sounds reasonable. The new MB I'm probably gonna get
    is the 865GBFLK. I may have all the video hardware I
    need then if I got a 3rd monitor and the onboard graphics
    can be used.

    >> Has anyone tried this and gotten it to work? (On-board vid plus
    >> PCI or AGP vid).
    >>
    >
    > Yup. The system I am currently using has integrated
    > nVidia GeForce AGP video. Just for you I also added
    > a Matrox G400 PCI dualhead. Works fine with one monitor
    > on the integrated AGP and one on the G400. Can't test
    > a 3 monitor setup because I only have 2 monitors here
    > at home. OS = W2K Pro. Can only make it work with
    > separate desktops for each monitor. (Single desktop
    > across both monitors works if I put both on
    > the G400 and disable the integrated AGP.)

    Cool. I just have to save up for a monitor and not another
    video card then. :)

    >
    > Note that integrated AGP video plus a card in an AGP
    > slot will never work. Simply a limitation of the AGP
    > standard.

    And a dead standard apparently with the introduction of
    PCIe. I'm glad I don't have any of those "old relics". ;)

    >>>I know someone who spent a decade in front of a 4 x 21"
    >>>setup until the prices for large LCDs came down enough
    >>>for his company to replace the CRTs. He had problems
    >>>with kinks in his neck when he had to spend a lot of
    >>>time looking at the two upper monitors (they were arranged
    >>>in a 2 x 2 pattern), but that was about the extent of his
    >>>health problems.
    >>
    >>
    >> I think only scientific study/facts are valid for this concern (that is,
    >> I know someone who has smoked for 40 years, 3 packs a day
    >> and is still "fine". But I tend to heed the surgeon general's
    >> warning anyway). I have a feeling the newer TCO certified
    >> monitors cause little problems though.
    >>
    >
    > I intended my health comment to be tongue-in-cheek.

    Oh, OK.

    > Some things just don't work in text because you can't see
    > the other guy going nudge-nudge, wink-wink.

    Well that's what emoticons are for.

    AJ
  15. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message news:uhrdi0li7f0q4u1dq1k72b191o40sho5o3@4ax.com...
    > On Fri, 20 Aug 2004 16:08:53 GMT, Rob Stow <rob.stow.nospam@shaw.ca>
    > wrote:
    > Intel's integrated graphics will not work with an AGP card, but should
    > play ok with a PCI one. The trick would be more with the multi-head
    > software side of things, particularly under Win2K (earlier versions of
    > Windows probably won't work at all). Under WinXP they should work ok
    > though, and Linux/X-Windows shouldn't be any problem at all.

    I have a feeling that the Matrox P650 isn't offered in PCI, with AGP going
    away and what you said above, I'd hate to buy into the technology.

    AJ
  16. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    AJ wrote:
    > "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message news:uhrdi0li7f0q4u1dq1k72b191o40sho5o3@4ax.com...
    >
    >>On Fri, 20 Aug 2004 16:08:53 GMT, Rob Stow <rob.stow.nospam@shaw.ca>
    >>wrote:
    >>Intel's integrated graphics will not work with an AGP card, but should
    >>play ok with a PCI one. The trick would be more with the multi-head
    >>software side of things, particularly under Win2K (earlier versions of
    >>Windows probably won't work at all). Under WinXP they should work ok
    >>though, and Linux/X-Windows shouldn't be any problem at all.
    >
    >
    > I have a feeling that the Matrox P650 isn't offered in PCI, with AGP going
    > away and what you said above, I'd hate to buy into the technology.
    >

    There are both PCI and AGP versions for the Parhelia,
    but AFAIK only AGP for the P650 and P750.

    And AGP will be around for a while yet. And even if
    you do become one of the early adopters of PCI-E,
    motherboards with two 16 lane PCI-E slots will cost
    a pretty penny and so far only the high-end video cards
    are slated for release in PCI-E versions. For at least
    the next year, the only reasonably priced solution for
    someone with your needs is going to be one of the
    following:
    integrated AGP + PCI
    AGP card + PCI
    PCI + PCI

    Probably the cheapest PCI-E solution for you will be
    one of the transitional motherboards that will have
    a single PCI-E 16e slot and at one or both of the
    following:
    AGP slot
    Legacy PCI slots

    However, so far my it appears that the transitional
    motherboards in the works that have both PCI-E 16e and
    AGP slots will let you use only one of those two slots.


    --
    Reply to rob.stow.nospam@shaw.ca
    Do not remove anything.
  17. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:trKVc.172835$J06.146980@pd7tw2no...
    > AJ wrote:
    >> "Tony Hill" <hilla_nospam_20@yahoo.ca> wrote in message news:uhrdi0li7f0q4u1dq1k72b191o40sho5o3@4ax.com...
    >>
    >>>On Fri, 20 Aug 2004 16:08:53 GMT, Rob Stow <rob.stow.nospam@shaw.ca>
    >>>wrote:
    >>>Intel's integrated graphics will not work with an AGP card, but should
    >>>play ok with a PCI one. The trick would be more with the multi-head
    >>>software side of things, particularly under Win2K (earlier versions of
    >>>Windows probably won't work at all). Under WinXP they should work ok
    >>>though, and Linux/X-Windows shouldn't be any problem at all.
    >>
    >>
    >> I have a feeling that the Matrox P650 isn't offered in PCI, with AGP going
    >> away and what you said above, I'd hate to buy into the technology.
    >>
    >
    > There are both PCI and AGP versions for the Parhelia,
    > but AFAIK only AGP for the P650 and P750.
    >
    > And AGP will be around for a while yet.

    There's no AGP on the new Intel socket T boards.

    > And even if
    > you do become one of the early adopters of PCI-E,
    > motherboards with two 16 lane PCI-E slots will cost
    > a pretty penny and so far only the high-end video cards
    > are slated for release in PCI-E versions.

    I was thinking PCI, not PCIe for my needs.

    > For at least
    > the next year, the only reasonably priced solution for
    > someone with your needs is going to be one of the
    > following:
    > integrated AGP + PCI
    > AGP card + PCI
    > PCI + PCI

    Yep!

    > Probably the cheapest PCI-E solution for you will be
    > one of the transitional motherboards that will have
    > a single PCI-E 16e slot and at one or both of the
    > following:
    > AGP slot
    > Legacy PCI slots

    I'm not buying a PCIe board because I don't want Prescott
    technology or the higher prices of the boards.

    > However, so far my it appears that the transitional
    > motherboards in the works that have both PCI-E 16e and
    > AGP slots will let you use only one of those two slots.

    Not Intel, as far I can tell. PCIe only.

    AJ
  18. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    AJ wrote:

    > "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:trKVc.172835$J06.146980@pd7tw2no...
    >>
    >>And AGP will be around for a while yet.
    >
    >
    > There's no AGP on the new Intel socket T boards.

    And good luck on getting your hands on one of those
    boards or a processor for one of those boards.

    I know someone who is desperate for a Socket T
    mobo\cpu combo and the vendors are telling him he'll
    be lucky to get one before 2005. All production -
    what little there is so far - is apparently going
    only to the big computer manufacturers for the next
    few months.

    --
    Reply to rob.stow.nospam@shaw.ca
    Do not remove anything.
  19. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    On Sun, 22 Aug 2004 01:54:33 GMT, Rob Stow <rob.stow.nospam@shaw.ca> wrote:

    >AJ wrote:
    >
    >> "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:trKVc.172835$J06.146980@pd7tw2no...
    >>>
    >>>And AGP will be around for a while yet.
    >>
    >>
    >> There's no AGP on the new Intel socket T boards.
    >
    >And good luck on getting your hands on one of those
    >boards or a processor for one of those boards.
    >
    >I know someone who is desperate for a Socket T
    >mobo\cpu combo and the vendors are telling him he'll
    >be lucky to get one before 2005. All production -
    >what little there is so far - is apparently going
    >only to the big computer manufacturers for the next
    >few months.

    otoh, maybe it's the plethora of errata - and some pretty scary ones at that -
    that are delaying deployment?

    /daytripper (some of those bugs are effing ugly...)
  20. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:t1TVc.170504$M95.25786@pd7tw1no...
    > AJ wrote:
    >
    >> "Rob Stow" <rob.stow.nospam@shaw.ca> wrote in message news:trKVc.172835$J06.146980@pd7tw2no...
    >>>
    >>>And AGP will be around for a while yet.
    >>
    >>
    >> There's no AGP on the new Intel socket T boards.
    >
    > And good luck on getting your hands on one of those
    > boards or a processor for one of those boards.
    >
    > I know someone who is desperate for a Socket T
    > mobo\cpu combo and the vendors are telling him he'll
    > be lucky to get one before 2005. All production -
    > what little there is so far - is apparently going
    > only to the big computer manufacturers for the next
    > few months.

    As far as I care, all the changes are to be swallowed at once:
    BTX, 90 nm, PCIe, SATA II. I won't care for a couple of years
    at least. Unless the old stuff runs out. I'm not an early adopter.
    The point is though that the current generation of boards has
    already nixed AGP.

    AJ
  21. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    In article <trKVc.172835$J06.146980@pd7tw2no>,
    Rob Stow <rob.stow.nospam@shaw.ca> wrote:
    >There are both PCI and AGP versions for the Parhelia,
    >but AFAIK only AGP for the P650 and P750.

    Matrox just introduced a low profile PCI version of the P650.
    It should come with both low profile and standard size brackets.
    You can use it with either dual DVI or dual VGA monitors.
    (And no, I don't know why there isn't an AGP version ...)
  22. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    "dhs" <dhs@cs.utexas.edu> wrote in message news:cgd3qa$shu$1@bubble.cs.utexas.edu...
    > In article <trKVc.172835$J06.146980@pd7tw2no>,
    > Rob Stow <rob.stow.nospam@shaw.ca> wrote:
    >>There are both PCI and AGP versions for the Parhelia,
    >>but AFAIK only AGP for the P650 and P750.
    >
    > Matrox just introduced a low profile PCI version of the P650.

    Cool!

    > It should come with both low profile and standard size brackets.
    > You can use it with either dual DVI or dual VGA monitors.
    > (And no, I don't know why there isn't an AGP version ...)

    Probably because AGP is dead going forward?

    AJ
  23. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    Kevin C. a écrit :

    > Since this is Intel's new chipset, would I be correct in assuming that a
    > pcie mainboard would only support P4s (no AMD)? At least, before Via gets a
    > clone out?
    >
    > Also, have there been any tests to confirm real-world performance gains?
    > Something comparing AGP 8x to PCIE 16x, with comparable GPUs? If so, what is
    > the margin of difference like?
    >
    > Basically, I am in the market for a new mainboard/cpu/video and while PCIE
    > is obviously the forward-thinking choice, it seems like it is just barely
    > emerging and I don't know how this will affect cost-effectiveness. (My
    > budget is a concern.)
    >
    >
    Hi !

    There are tests but which I known are in french, use google.
    The test I've read said that it doesn't worth the cost for now : in fact
    even AGP 4x isn't used at it's full potential, years after its release,
    AGP 8x the same and even the same for PCI Express which was just
    released a month ago. I have even see that you loose perf with DDR-2 !
  24. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    /*
    The test I've read said that it doesn't worth the cost for now : in fact
    even AGP 4x isn't used at it's full potential, years after its release,
    AGP 8x the same and even the same for PCI Express which was just
    released a month ago. I have even see that you loose perf with DDR-2 !
    */

    It does not come as a surprise that AGP x, 4x et cetera are NOT used to
    their "full potential" as it is much more efficient to keep the working set
    in GPU local memory. Initially, when AGP was launched some vendors promoted
    use of "DIME" feature of AGP, including Matrox Graphics with their G200
    series of products. While DIME was "okay" speed it still was a lot slower
    than rendering from local memory. During the years the gap between the two
    has just grown wider.. using AGP 8x to it's "full potential" just doesn't
    make any sense, unless there is data constantly generated by the CPU and
    pushed to the GPU.. even this is less practical now that GPU's are much more
    programmable than the fixed pipeline model that we have to deal with just a
    few years ago.. basicly we can do with a much smaller seed data and
    synthesize data in the GPU.

    Introduction of VS 3.0 with vertex samplers is important step since now we
    can synthesize data with pixel program, render into texture and use that as
    input to next pass vertex program. Latencies these techniques introduce can
    be amortized in practise.

    What PCI Express brings to the developers is a window to completely
    different kind of uses of GPU the most important factor in this is that the
    bus is full bandwidth to both directions, finally it is feasible to read
    back from GPU memory to system memory. Thinking PCI Express only as
    increased bandwidth is very narrow-minded and shows that whoever makes these
    claims does have shallow understanding of modern GPU programming. Propably
    some journalist without technical background, just a lucky guess..
  25. Archived from groups: comp.sys.ibm.pc.hardware.chips (More info?)

    Uh, in short: PCI Express doesn't bring any new value to contemporary
    applications, they wouldn't use the extra bandwidth anyway. What PCI Express
    does is that it allows a completely new breed of applications to be
    developed which would be completely unthinkable due to performance reasons
    in curreny bus architechtures on PC, such as AGP. In this light for the
    first year or two PCI Express is something that developers will fall in love
    with and the labours of love should be apparent 9 months later.

    This is to say.. consumers shouldn't look forward to immediate benefits,
    hardware still needs software to dance.
Ask a new question

Read More

CPUs PCI Express