Slashdot Mirror

← Back to Stories (view on slashdot.org)

It's Official — AMD Will Retire the ATI Brand

Posted by timothy on from the rose-by-any-other-name dept.

J. Dzhugashvili writes "A little over four years have passed since AMD purchased ATI. In May of last year, AMD took the remains of the Canadian graphics company and melded them into a monolithic products group, which combined processors, graphics, and platforms. Now, AMD is about to take the next step: kill the ATI brand altogether. The company has officially announced the move, saying it plans to label its next generation of graphics cards 'AMD Radeon' and 'AMD FirePro,' with new logos to match. The move has a lot to do with the incoming arrival of products like Ontario and Llano, which will combine AMD processing and graphics in single slabs of silicon."

17 of 324 comments (clear)

  1. Great news by mangu · · Score: 4, Interesting

    "The move has a lot to do with the incoming arrival of products like Ontario and Llano, which will combine AMD processing and graphics in single slabs of silicon."

    Good. Getting rid of the PCI-e bus between CPU and GPU is one important step in getting massive parallelism to work well.

    Since we hit the 3 GHz barrier, where the speed of light itself becomes a limit, putting the processing elements physically closer is essential to get better performance. Now let's see them put 4 GB or so of fast RAM on the same chip.

    1. Re:Great news by mangu · · Score: 5, Informative

      With a 3 GHz clock, a signal at the speed of light travels 10 cm during one clock cycle. This means that if a chip needs data from another and there's a distance of five centimeters or more between both chips the data will not arrive in the same clock cycle.

    2. Re:Great news by data2 · · Score: 4, Interesting

      So with current die-sizes of about 146mm^2, assuming it's really square, we have a maximum length of about 1.7cm. Sounds like we can go up to 9Ghz, at least if we are just using the speed of light in vacuum.

    3. Re:Great news by bertok · · Score: 5, Informative

      Yeah, 3ghz doesn't come close to the light speed barrier. i think the issue is more from heat dissipation and electron bleed...

      moving the gpu on-die will fix the latency associated with the pci-e bus, but it's not because of the reasons you seem to believe

      Want to bet?

      At 3 GHz, light moves just 7.2 cm, given a typical upper range for the velocity factor of copper of 0.72. Silicon and fibre optics are usually worse, with a VF between 0.4 and 0.6, or between 4 and 6cm per clock. That's barely enough to traverse a CPU die, let alone the motherboard. Moving parts physically closer together has a lot to do with the speed of light!

    4. Re:Great news by mangu · · Score: 4, Informative

      we have a maximum length of about 1.7cm. Sounds like we can go up to 9Ghz, at least if we are just using the speed of light in vacuum.

      Assuming the signals travel in a straight line. If you look at current motherboards and video cards, you'll notice that many of the copper traces are "wiggly", not straight. That is done in order to get bits in parallel buses to arrive at the same time, and conductor traces on the chips must be designed similarly, it's the longest distance that any of the bits must travel that limits the others.

      Besides, there are capacitance and inductance effects to be considered. Transitions from one to zero and vice-versa aren't instantaneous and that must be taken into account.

      One could say that 9 GHz would be the absolute physical limit for a 1.7 cm chip and the technical limit is somewhat lower than that.

      For a set of chips on a board, the absolute physical limit is much lower, and that's the reason why on-chip cache memory has become so important lately.

    5. Re:Great news by Knuckles · · Score: 5, Informative

      Reading comprehension fail. Nobody said that you can't go above 3 GHz for the CPU, but that if you do, if a chip needs data from another and there's a distance of five centimeters or more between both chips the data will not arrive in the same clock cycle

      --
      "When I first heard Daydream Nation it quite frankly scared the living shit out of me." -- Matthew Stearns
    6. Re:Great news by dylan_- · · Score: 4, Insightful

      Really? So when did we all get to using optical interconnects? Electricity doesn't travel at the speed of light.

      We're not, but even if we were, that's the fundamental limit. Electricity traveling slower than this makes the problem worse.

      And even if it did, for your random, uninformed postulation to be true

      You've clearly misunderstood his post, so adding insults just makes you look foolish.

      we would need evidence that chips could not practically run faster than 3GHz. Unfortunately for you, that is not the case.

      No we wouldn't. If it can't be done in one clock cycle, it'll be done in two (or more). Who said anything about this limiting clock speed?

      Anyway, at a higher clock speed, the problem becomes even more pronounced. With a 3.8 GHz clock, a signal at the speed of light only travels 7.9 cm during one clock cycle (but let's estimate about 6.5 cm for electricity).

      --
      Igor Presnyakov stole my hat
    7. Re:Great news by IndustrialComplex · · Score: 4, Informative

      Want to bet?

      At 3 GHz, light moves just 7.2 cm, given a typical upper range for the velocity factor of copper of 0.72. Silicon and fibre optics are usually worse, with a VF between 0.4 and 0.6, or between 4 and 6cm per clock. That's barely enough to traverse a CPU die, let alone the motherboard. Moving parts physically closer together has a lot to do with the speed of light!

      I really would mod this informative, since I was about to make a similar point. I think a lot of the confusion is that people hear things like the Speed of Light in terms of Kilometers per second, and it gets filed away by the brain as inconsequential for scales which are measured in centimeters and MUCH smaller.

      But when you realize that that scale which is only a factor measured in millions meters per second is being divided into segments that are fractions of billionths of a second, the speed of light manifests in a much more physically understandable term.

      --
      Out of modpoints but really liked a post? 1BDkF6TtmmeZ3yqXbz9yhdYVqRYnwFoXDj
    8. Re:Great news by mangu · · Score: 5, Interesting

      There's an anecdote that admiral Grace Hopper gave "nanoseconds" as gifts:

      "Although she was an interesting and competent speaker, the most memorable part of these talks was her illustration of a nanosecond. She salvaged an obsolete Bell System 25 pair telephone cable, cut it to 11.8 inch (30 cm) lengths (which is the distance that light travels in one nanosecond) and handed out the individual wires to her listeners"

      I've also read about someone else giving out "picoseconds" in the form of tiny mustard seeds to illustrate how much the speed of light limits data processing.

  2. Wil this affect open source drivers by La+Gris · · Score: 4, Interesting

    Are there any deeper changes to come behind the re-brand? ATi involved in producing open source drivers ans specs for their GPU. Will this name change carry some bad news about the current openness?

    --
    Léa Gris
    1. Re:Wil this affect open source drivers by Ironhandx · · Score: 5, Informative

      ATI really only started doing that after they were acquired by AMD so I wouldn't worry too much.

  3. Little bit of hate? by Anonymous Coward · · Score: 5, Funny

    In May of last year, AMD took the remains of the Canadian graphics company and melded them into a monolithic products group, which combined processors, graphics, and platforms. Now, AMD is about to take the next step: kill the ATI brand altogether.

    Oh, please, J. Dzhugashvili, don't hold back. Tell us how you REALLY feel. What'd the rejected original form of this summary look like?

    In May of last year, the poor, innocent Canadian angels of technology, ATI, had their very remains tortured and raped by the evil, evil AMD, cruelly melded into a hideous abomination of a monolithic products group, creating an unholy, soulless combination of processors, graphics, and platforms. Now, the faceless anti-christ forces of AMD plan to take the next step in their plans to destroy all that is good in the world: Slaughter the angelic ATI brand altogether, laughing with sadistic glee as it begs for mercy in a futile appeal to the quickly-evaporating last shreds of AMD's humanity and compassion, ATI having never having harmed a fly in its too-short, sad, sad life.

  4. Classic example of not reading the article... by maweki · · Score: 5, Informative

    because it states "The badges you see above will be used for systems with discrete Radeon and FirePro graphics cards. The lower row omits the AMD logo, so PC makers shipping Intel-based systems will be able to avoid the oil-and-water combo of Intel and AMD branding, if they wish."

  5. Re:Let The Confustion Begin by cbiltcliffe · · Score: 4, Insightful

    The confusion is that most regular people are only marginally aware of an AMD/Intel distinction, although don't know what it means, and don't know at all ATI or nVidia.

    Fixed that for you.

    --
    "City hall" in German is "Rathaus" Kinda explains a few things......
  6. Opportunity knocking for AMD here... by Qubit · · Score: 4, Insightful

    ...AMD's prepping for their integrated CPU/GPU launch. ...
    I would image that better Linux drivers might come down the pipeline, though...they'd definitely loose out on a potential market if they completely ignored the issue.

    I'd go one step further and say that I think that AMD has an opportunity to highlight their hardware here.

    Intel's CPUs and integrated graphics have long had great support in the Linux kernel. Because Intel controls the tech, they can actually provide the correct and full source for the graphics drivers. The problem is that Intel integrated graphics aren't ever anything special.

    If AMD is seriously working on integrating their graphics cards and processors -- perhaps even onto the same die -- then they have an opportunity to provide a much more powerful, integrated hardware platform with fully-open drivers. Intel can't compete with that kind of setup, especially as NVidea appears to have an aversion to opening the source to their graphics card drivers.

    --

    coding is life /* the rest is */
  7. Re:Justice Department on vacation since 1980 by Murdoch5 · · Score: 4, Interesting

    This was a great merg. This merg lead to the first decent Ati drivers being created on the Linux side. If this wouldn't of happened then how much longer would ATI of survived. They basicly said FU to Linux and ignored it. Great Merg.

  8. Re:fglrx by MostAwesomeDude · · Score: 5, Informative

    fglrx support for r500 and earlier (anything before the HD lines) is already delegated to the open-source drivers. We're working on getting r800 (redwood) support for acceleration together, and r600 support is getting better by the day.

    --
    ~ C.