The AMD Radeon RX 480 is expected to feature graphics performance levels between the GeForce GTX 970 and GeForce GTX 980 graphics card so we can expect some decent numbers from this cost effective solution.

http://wccftech.com/amd-radeon-rx-480-polaris-10-launch/#ixzz4Ak4vlFIn

That is all very interesting, but at 150 watts the TDP is also between the GTX 970 and 980. So AMD is now effectively competing with Maxwell (if you don't need CUDA of course), but I don't see anything that says they can compete against Pascal. It is good to have another choice, and the price is right, but it has to be to compete with year (or two) old technology.

Read through the Einstein thread. Why anyone would buy NVidia cards for running Einstein is beyond me. Maybe the new ones will perform better but I'm skeptical. I run mostly NVidia but that's because I primarily crunch GPUgrid. Have tried them on other projects and generally they're poor performers compared with AMD. Maybe I just haven't found the right project. Are there any other projects in which NV cards perform well?

I don't know the AMD cards' credit/watt ratio, but my GTX980Ti can process a Binary Radio Pulsar Search (Parkes PMPS XT) v1.57 (BRP6-Beta-cuda55) task in 1860~2000 sec. By a quick browse on the top hosts list I could not find any GPU (including AMD and NVidia) which can process a workunit from this batch faster than this. Maybe I'm a record holder at Einstein@home too?
EDIT: ok, I know that the user can set the number of simultaneous Einstein@home tasks in their profile for maximizing GPU usage/throughput which hurts runtimes, but I'm not sure if it's worth doing on Linux hosts, and I've checked a couple of such hosts too.

HI,
we expect great performance from the GTX1080 but at the moment we don't have any.
As soon as we have them, we need to recompile the code for them and check it.

At the moment, the app will crash on any new pascal gpu.

gdf

Does anyone have a GTX 1080 already?

Will wait for the 1080ti Classified and by that time the architecture issues should be worked out.

---

1 Corinthians 9:16 "For though I preach the gospel, I have nothing to glory of: for necessity is laid upon me; yea, woe is unto me, if I preach not the gospel!"
Ephesians 6:18-20, please ;-)
http://tbc-pa.org

we expect great performance from the GTX1080 but at the moment we don't have any.
As soon as we have them, we need to recompile the code for them and check it.

When will this happen?

Does anyone have a GTX 1080 already?

Will wait for the 1080ti Classified and by that time the architecture issues should be worked out.

I keep hoping to get some news, I know if I don't want for the custom cooled ti version I'll really regret it, but not seeing any news will make the 1080gtx tempting once the prices drop.

Does anyone have a GTX 1080 already?

Will wait for the 1080ti Classified and by that time the architecture issues should be worked out.

I keep hoping to get some news, I know if I don't want for the custom cooled ti version I'll really regret it, but not seeing any news will make the 1080gtx tempting once the prices drop.

You can see here who has it and who doesn't and which models too:
http://www.nowinstock.net/

Picked up an EVGA 1080 on launch day - silly prices here in the UK.

Cool & quiet - I'm using the Founder Edition in a SFF ..... performance is better than a 980Ti (at PrimeGrid anyway)

Any idea when the project will be able to support these card?....

Thanks.

When they get a GTX1080/GTX1070 to work with they need to recompile the app using the latest CUDA 8 dev kit, then perform some in-house alpha testing and then Beta test it here. Might also be compatibility issues with previous generations which would need to be ironed out. My guess is several weeks minimum but possibly after the summer. Don't know if they can run multiple app versions, but would be best to.

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

When they get a GTX1080/GTX1070 to work with they need to recompile the app using the latest CUDA 8 dev kit, then perform some in-house alpha testing and then Beta test it here. Might also be compatibility issues with previous generations which would need to be ironed out. My guess is several weeks minimum but possibly after the summer. Don't know if they can run multiple app versions, but would be best to.

Personally hope that this process takes a while as it will most likely forebode yet another WU duration and upload size increase :-(

Today I've ordered a Gainward GTX 1080 Phoenix, so I hope that things will rev up here, as the Pascals fill the market thus the computers of the potential crunchers in the following weeks.

Eagerly waiting for GPUGrid to support GTX 10 series cards before I trade up.

(Anyone interested in buying a GTX 960 or 970? Or even the 980Ti? Send me a PM if so. I'd love for them to go to another cruncher.)

When they get a GTX1080/GTX1070 to work with they need to recompile the app using the latest CUDA 8 dev kit, then perform some in-house alpha testing and then Beta test it here. Might also be compatibility issues with previous generations which would need to be ironed out. My guess is several weeks minimum but possibly after the summer. Don't know if they can run multiple app versions, but would be best to.

I still shudder when I think of that August crash a few years ago when everyone went off to Majorca. It was a month of disaster. But things have been much better recently, and I hope there have been some lessons learned.

While they probably won’t be of any use here AMD/ATI's RX 480 is due to launch on 29th June 2016. For gaming it will likely compete with the GTX1070 and in crossfire may well outperform one GTX1080. In terms of gaming value it will be a competitive card. Hopefully this will drive down the price of the GTX1080 and GTX1070 but it will also reduce the sell-on value of most existing cards as will the RX 470 and RX460, also set to launch in 2 days.

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

The Radeon RX 480 was released today. It's a mid-range card in terms of gaming performance & competitive at the $200 to $240 price.
On the negative it doesn't square up to a GTX1070 and performance/Watt isn't great for a 14nm based GPU. It is however competitive against high end previous generation cards and in crossfire could still match a GTX1070 if not a GTX1080. It's aimed at 1080p monitors but isn't great at higher resolutions. Was hoping for better but it's a bit unfair to be comparing a mid-range card with high end cards. On a positive it should still help reduce NV prices and NV has supposedly leaked some details of a GTX1060. Two RX480's should compete enough to reduce 1080 and 1070 prices. Any remaining GTX900 series cards will devalue slightly too, and any future 1060 and below will have direct competition either with the 480 or the 470 or 460.

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Competition is good for all of us.

skgiven wrote:

Two RX480's should compete enough to reduce 1080 and 1070 prices. Any remaining GTX900 series cards will devalue slightly too, and any future 1060 and below will have direct competition either with the 480 or the 470 or 460.

Beyond wrote:

Competition is good for all of us.

I think there's no real competition between AMD's RX480 and NVidia's GTX1080-1070, as they're playing in a different league. Expecting that a mid-range card will reduce the price of a high-end card is in vain. This is like if you would expect that the reduced price of the GTX980Ti will reduce the price of the GTX1080, because two GTX980Ti is faster than one GTX1080. If someone has an SLI or Crossfire capable MB which is more expensive than an MB without this capability, I would expect that this owner would buy the more expensive GPU as well, or even more of them. So I expect that the price of the GTX1080 won't be reduced significantly in the near future. If something could drive the price of the GTX1080 down is the GP-102 chip based cards. But NVidia would be a fool to shoot themselves in the foot, so I expect they will release this chip only in a form of a very expensive Titan XYZ card, just as they did it with the largest Maxwell chip. Perhaps a GTX 1080 Ti will be released before Christmas based on a partially disabled GP-102 chip.

My Gainward GTX 1080 Phoenix GLH card has arrived.

So I've joined the club of the "participants requesting a new app".
I'm offering my help to test the new app when it's ready.
I can also give remote access to the host which the card will reside soon.

My first observations with the GTX 1080 while crunching Einstein@home are the following:
It's boosting to 2025-2038MHz
The Maxwell's memory underclocking problem is present with Pascals
Comparing to the GTX 980Ti @1400MHz:
The power consumption is much less
The processing speed is the same (which is a little bit disappointing, but the E@H app is said to be CUDA5.5 but according to the stderr output it's using CUDA3.2)
I've tried to run single tasks at first, but I've set it to crunch 2 tasks simultaneously overnight.
You can follow the progress of my host here.

My first observations with the GTX 1080 while crunching Einstein@home are the following:
It's boosting to 2025-2038MHz
The Maxwell's memory underclocking problem is present with Pascals
Comparing to the GTX 980Ti @1400MHz:
The power consumption is much less
The processing speed is the same (which is a little bit disappointing, but the E@H app is said to be CUDA5.5 but according to the stderr output it's using CUDA3.2)
I've tried to run single tasks at first, but I've set it to crunch 2 tasks simultaneously overnight.
You can follow the progress of my host here.

Running 2 Parkes PMPS XT units simultaneously picked up about 15% net RAC on my windows 10 computer with 980ti cards the last time I ran them, a little bit less on windows xp computer with the 980ti card, with the Arecibo units the pick up was insignificant for both computers.

I see that you got the card running on windows xp computer, did you have to use any kind of trick to do that?