AMD's Polaris graphics cards rumored to launch in late May

[dividebyzero]

Assuming that the 1080 can overclock as well. We don't know how well the GDDR5x will react to an overclock. It's not a huge shift like HBM but it can still cause issues.

You didn't even bother to follow the link I provided did you?

GeForce GTX 1080 has the memory clocked at 2.5 GHz but we do expect some of the samples clocking at 2.75-3.5 GHz (11-14 Gbps). That would raise the available bandwidth from 320GB/s to 352-448 GB/s and we do expect to see extreme overclockers pushing the memory even more. If Micron adopts 10nm process for GDDR5X, we’ll get to 4 GHz clock / 16 Gbps rather sooner than later.

If you'd bothered to follow the earlier links I posted (or the Micron press brief, or any number of sites that carried the story) when Micron was sampling GDDR5X, you would also know that the memory has some considerable headroom since it uses the same process node as GDDR5 but uses 1.35V rather than 1.5V.

 

[Evernessince]

You didn't even bother to follow the link I provided did you?

If you'd bothered to follow the earlier links I posted (or the Micron press brief, or any number of sites that carried the story) when Micron was sampling GDDR5X, you would also know that the memory has some considerable headroom since it uses the same process node as GDDR5 but uses 1.35V rather than 1.5V.

That's an assumption. Just because it runs at a lower voltage doesn't mean it has more headroom. If it were using a half-node they would have already entered into volume production. These are really early samples as well, for all we know Nvidia could very well increase the voltage to increase the yields.

 

[dividebyzero]

That's an assumption. Just because it runs at a lower voltage doesn't mean it has more headroom. If it were using a half-node they would have already entered into volume production. These are really early samples as well, for all we know Nvidia could very well increase the voltage to increase the yields.

Remember the part where I said:

follow the earlier links I posted (or the Micron press brief, or any number of sites that carried the story) when Micron was sampling GDDR5X,

you might have noted that 10000MHz effective was the baseline for GDDR5X for standardization (timings and latency) for a catalogue product, but the company had pushed the same 20nm silicon to 13000MHz effective during testing.

At this point I'm not even going to go through my old posts to find the links or the press deck, because as you've amply demonstrated - like your claims of Pascal requiring LN2 to reach 2.1GHz (when the sample shown was just picked at random from a number of Maingear systems running demos) that when shown to be wrong, you just move onto trolling another facet of non-AMD graphics - usually as equally uninformed as the previous attempts.

I made you a wager regarding whether Pascal would require LN2 cooling to reach 2.1GHz as per your assertion

How about a friendly wager? If the GTX 1080 requires LN2 to reach 2.1GHz I'll donate a token $US100 via PayPal to the registered charity of your nomination. If the GTX 1080 is capable of reaching 2.1GHz with conventional (non sub-zero) cooling, you donate the same amount to my nominated registered charity.

...you quickly skulked off and left the thread.
I'll make the same offer regarding GDDR5X overclocking. If GDDR5X overclocking is a bust, I donate. If it overclocks as a percentage over stock as well as GDDR5, you donate.

I'm guessing you just like to put the FUD out there, but have zero confidence in what you are spouting.

You really should just migrate to wccftech. 90% of the people there just troll for the enjoyment, and 89% of them don't question because they don't follow tech past the headlines either. You'd really fit in seamlessly.

 

[Puiu]

Why are people arguing over rumors and things some people said at a PR event? I know you guys are fans of AMD or Nvidia, but this is ridiculous. at least argue after we see the benchmarks and street prices.

 

[BBlair]

Didn't AMD just release the 300 series? I doubt they are releasing new GPU architecture this soon! Besides the 300 series is doing very well, despite being overclocked 7000 series cards with slower memory buses on some (380/380X). What AMD needs to focus on is their CPU release. The Fury and Fury X will do fine for awhile against the 1070 and 1080 in price to performance. Besides the older R9 290 is still overkill for most games out today.

 

[Evernessince]

Remember the part where I said:

you might have noted that 10000MHz effective was the baseline for GDDR5X for standardization (timings and latency) for a catalogue product, but the company had pushed the same 20nm silicon to 13000MHz effective during testing.

At this point I'm not even going to go through my old posts to find the links or the press deck, because as you've amply demonstrated - like your claims of Pascal requiring LN2 to reach 2.1GHz (when the sample shown was just picked at random from a number of Maingear systems running demos) that when shown to be wrong, you just move onto trolling another facet of non-AMD graphics - usually as equally uninformed as the previous attempts.

I made you a wager regarding whether Pascal would require LN2 cooling to reach 2.1GHz as per your assertion

...you quickly skulked off and left the thread.
I'll make the same offer regarding GDDR5X overclocking. If GDDR5X overclocking is a bust, I donate. If it overclocks as a percentage over stock as well as GDDR5, you donate.

I'm guessing you just like to put the FUD out there, but have zero confidence in what you are spouting.

You really should just migrate to wccftech. 90% of the people there just troll for the enjoyment, and 89% of them don't question because they don't follow tech past the headlines either. You'd really fit in seamlessly.

Actually you made a wager that Pascal would not consume more power and you were wrong. You're the one pulling the troll card when you have insulted me in nearly every post. I have at least 7 posts with you calling names. I pray to god you don't have a wife or kids because you put down someone every chance you get. I'm ignoring you, I don't need to be harassed at every turn.

 

[amstech]

You're the one pulling the troll card when you have insulted me in nearly every post. I have at least 7 posts with you calling names. I pray to god you don't have a wife or kids because you put down someone every chance you get. I'm ignoring you, I don't need to be harassed at every turn.

Lol.

 

[Evernessince]

Lol.

Indeed

 

[dividebyzero]

Lol.

Oh yes, very lol...
Post #3:

Pretty decent air cooled clock speed:

Post #33

I wouldn't be surprised if Nvidia only got those results using liquid nitrogen with a cherry picked card.

Post #35

...and there it is! he shoots...he trolls!. The demo system was clearly shown during both the presentation wrap up, the Doom Vulkan demo, and the in-depth seminar today.......Does this look like liquid nitrogen?

How about a friendly wager? If the GTX 1080 requires LN2 to reach 2.1GHz I'll donate a token $US100 via PayPal to the registered charity of your nomination. If the GTX 1080 is capable of reaching 2.1GHz with conventional (non sub-zero) cooling, you donate the same amount to my nominated registered charity.

I'd say that is pretty unequivocal

As for the whole

Actually you made a wager that Pascal would not consume more power and you were wrong.

Here's that thread and no such thing was stated, nor in any other- quelle surprise! So you are a liar as well as a troll. I think I might just report you. Printing false accusations are probably a forum infringement.

I have at least 7 posts with you calling names.

Better add this one to your trainspotters notebook.

I pray to god you don't have a wife or kids because you put down someone every chance you get.

Only misinformation spreaders, shills, trolls, and people who devote thousands of words to an argument yet can't even be bothered fact checking the information central to their argument no matter how many times it is spoon fed to them. I'm happy to say I seldom run into people like that IRL.

 

[Phr3d]

Wow..
just.. Wow

tnx for the info and links, as always, DBZ

 

[Bullettube]

Hello? "Gamers wanting a true AMD competitor to the GTX 1080 may have to wait until early 2017," I hope that was a typo?

 

[mailpup]

Hello? "Gamers wanting a true AMD competitor to the GTX 1080 may have to wait until early 2017," I hope that was a typo?

Since the article was from May 2016, not necessarily.