Following up on this week's Radeon RX 480 launch, there has been some questions raised about the power consumption of the card. This is after some sites whom directly tap the power rails feeding the card discovered that at least some of their samples were pulling more than the standard-allowed 75W over the PCIe slot and/or 6-pin PCIe external power connector.

To that end, it would appear that AMD's staff is working weekend duty, and they have just sent over the following statement.

As you know, we continuously tune our GPUs in order to maximize their performance within their given power envelopes and the speed of the memory interface, which in this case is an unprecedented 8Gbps for GDDR5. Recently, we identified select scenarios where the tuning of some RX 480 boards was not optimal. Fortunately, we can adjust the GPU's tuning via software in order to resolve this issue. We are already testing a driver that implements a fix, and we will provide an update to the community on our progress on Tuesday (July 5, 2016).

If some of the data is to be believed, these cards are exceeding 150W total at times, which would mean there is either something causing them to run in the wrong power state, or they are just outright exeeding their power limit and need to be throttled back. As we don't do per-rail testing I don't have anything meaningful to add at this second, but it will be very interesting to see how AMD responds next week.

Update 07/06: AMD has since released their status update, which you can find here.

Comments Locked

181 Comments

View All Comments

  • Weyoun0 - Tuesday, July 5, 2016 - link

    Always leave it up to AMD religious zealots to turn an article about AMD into unrelated Nvidia bashing.
  • fanofanand - Tuesday, July 5, 2016 - link

    You will never convince the Nvidia employees that post here, not even worth trying.
  • Michael Bay - Sunday, July 3, 2016 - link

    Market rewarded nV for a great card. Damn, looking at 480 here it still is!
  • StrangerGuy - Tuesday, July 5, 2016 - link

    NV lied about nothing, Before and after the discovery 970 is still technically a 56 ROP/4GB card and the performance remained unchanged.

    While AMD is stupid enough is launch a out-of-spec card that is valid grounds for a recall and hoping no one cared or noticed. Already 20% pitiful marketshare and terrible PR and they still pull crap like this, but hey it's all NV fault.
  • Mottoman216 - Tuesday, July 5, 2016 - link

    @ StrangerGuy Umm... No. The original Specs originally claimed 64 ROPS, 2MB L2 Cache, and a usable 4gbs of full speed memory.

    Real Specs - 56 ROPS, 1.75mb L2 Cache, 3.5gbs of full speed memory. the other .5gbs is like @ 1/7ths the speed. so most games with an optimized driver won't even go over that 3.5gbs threshold.

    Do a little more research before you try and act like a white knight.

    http://www.anandtech.com/show/8935/geforce-gtx-970...
  • Mottoman216 - Tuesday, July 5, 2016 - link

    oh and dont get me wrong... at the time the gtx 970 was a good card for the price... NVidia flat out lied their asses off to sell more on pre order. they knew they could get away with it by blaming their PR dept.
  • D. Lister - Wednesday, July 6, 2016 - link

    I agree sir, Nvidia lied, no question. The only thing that could possibly make them worse is if they lied AND didn't deliver on performance.
  • tipoo - Sunday, July 3, 2016 - link

    Skip 30 minutes, and then skip to 53 minutes, but this guy explains whats going on with the power circuitry

    https://www.twitch.tv/buildzoid/v/75850933

    That's what I feared, it's physically wired that way, such that the board is essentially seeing no difference between PCI-E power and 6 pin power, so I wonder what any software or even video bios fix could possibly "fix".

    Why, AMD, why...Anyways, the gist of all this is...Just get a third party board with a better power system (and cooler while you're at it)

    We need a roundup of which third party boards do what with the power, and if any follow AMD off the cliff
  • vladx - Sunday, July 3, 2016 - link

    So you still reward AMD for crap like this? I personally will try to stay as far as possible from AMD products and the same goes for systems I build for other people.
  • Gigaplex - Sunday, July 3, 2016 - link

    Worst case scenario, software or BIOS could underclock the card to reduce total power.

Log in

Don't have an account? Sign up now