AMD Fury X And Fiji Preview

[seinfeld]

Does anyone actually have a 4k 60Hz display without DP1,2? So why the fuss about HDMI 2.0 ...

the Nano is being marketed as ITX HTPC. which most ppl use 4K TV's!!!!!! no 4k 60hz!!
so ppl will just buy the ITX 970

 

[rdc85]

This whole memory 4g things, makes me remember in low tier card...

where 2g GDDR3 card sold much higher than 1g GDDR5 variant (same gpu chip),
even if tested 1g one is better performer... sadly in some market they sold like hot cake...

will wait till proper bench result,..
if indeed smaller HBM can work on par/better than bigger GDDR5...
(very interesting IMO, haven't seen much tech advance in GPU / CPU lately)

 

[rdc85]

..the Nano is being marketed as ITX HTPC. which most ppl use 4K TV's!!!!!! no 4k 60hz!! ..

Most people here that own 4K TV don't event know or care if it's HDMI 1.0 or 2.0, DP 1.0 or 1.2...
sad but true.....

IMO For watching movie u don't need 60 hz.. (most movie still coded to run at 23.96 fps..),
cannot said same if you going for gaming in those TV..

 

[seinfeld]

..the Nano is being marketed as ITX HTPC. which most ppl use 4K TV's!!!!!! no 4k 60hz!! ..

Most people here that own 4K TV don't event know or care if it's HDMI 1.0 or 2.0, DP 1.0 or 1.2...
sad but true.....

IMO For watching movie u don't need 60 hz.. (most movie still coded to run at 23.96 fps..),
cannot said same if you going for gaming in those TV..

but my HTPC We also play games like FIFA on it and our TV is 4K which means Ill have to play that at 30hz! aint nobody got time fo dat!

 

[blackbit75]

This is misleading. While "I" is what commonly called current, it is measured in amount of charge passing through, not intensity of electrons, nor flow of electrons.

Assuming power consumed is at 400W. There is different current ( or amount of charge) being passed in a wire at different voltage. At 110V current will be smaller than at 10V, or 1V. To pass charge ( or current) you will need higher conductor cross section. On a PCB that would mean very wide metal section carrying your current. You also need to take into account that not all power is supplied to core chip, some of it will be fed into all sorts of glue components and some of it will dissipate directly off voltage/current regulators.

Thanks for the explanation. I try to do my best, but I'm very often wrong.

 

[sephirotic]

Does anyone actually have a 4k 60Hz display without DP1,2? So why the fuss about HDMI 2.0 ...

Yes, I do. This is a terrible joke from AMD. I'm glad I didn´t wait and got a Gtx 970 months ago.

 

[master9716]

OMFG no HDMI 2.0!!! I was about to buy one but my 70" 4k tv doesnt support display port only Hdmi 2.0

 

[yhikum]

400A typo? Is it 40A or 400W?

It can't be 400 amps. That's most of your house amps there!!!

not a typo unless AMD put a typo in the slide. The 6 phase power design is capable of delivering 400A - this does not mean that it requires this level of power, simply it can handle that much.
AMD was adament in emphasizing that this card has been overbuild significantly.

This is a correction. Not sure if you mean 6-wire connectors that are commonly used for giving your graphics card some more juice (power). Six wire is not same as six phase power supply. Also, current six wire connects are not rated at 400 amps. You do realize that main voltage supplied by those is 12 volts. If you would pass 400 amps through them they would melt of all insulation and would probably melt over time. If your card is using 240W of power, you would need 20 Amps to feed it. Way less than 400 amps or even 100 amps. At 400 Amps, you would be feeding 4800W of power.

 

[MarkW]

It should be 400w. At 275 watts, it draws 22.91 amps. So there is no way it will ever get to 400 amps.

Well... short of displaying an explosive show... 😛

 

[Vlad Rose]

the Fury X doesn't employ a fan on its dual-slot form factor....yadda yadda yadda.... Without that traditional blower, the company was able to design a fully enclosed, sleek-looking shroud.

so what about the other parts of the card that get hot? with this should can we expect the power lanes to melt or spontaneously combust the shroud due to all the excess heat? will the pcb warp or bend? what about all the vrms and mofsets? doesn't the ddr5 get pretty hot? i imagine there's alot more that needs to be kept cool than just the gpu considering the 200+ watts being pumped into these things?
or are they just going to print a hasbro logo on them and we can have our cake cooked and eat it?

What's really funny is that everyone talk about how hot the AMD cards are, but yet Nvidia's Fermi were famously known for cooking eggs.... lol

https://www.google.com/webhp?sourceid=chrome-instant&ion=1&espv=2&ie=UTF-8#q=nvidia%20cook%20egg

Even then, they worked just as well.

 

[scolaner]

Benchmarks are finally out!!!

http://www.forbes.com/sites/jasonevangelho/2015/06/18/amd-radeon-fury-x-benchmarks-full-specs-new-fiji-graphics-card-beats-nvidias-980-ti/

1) Do you think we DON'T have those same benchmarks and those same press materials?
2) Why would we post the "benchmarks" from a company-issued press deck?

 

[MarkW]

Not all of us, in fact, almost none of us are members of the press. So its interesting for us.

 

[ccampy]

A game wanting to use more re then 4Gb of memory is very different to it needing 4Gb of memory

 

[scolaner]

Not all of us, in fact, almost none of us are members of the press. So its interesting for us.

Right. Members of the press have a responsibility to give readers the best possible information, that is the most informative and helpful, in as timely a manner as possible.

My point is that there's a reason we didn't bother publishing AMD's own benchmarks from its marketing materials. There's no editorial value there. (We make these sorts of editorial decisions all the time. Sure, we could have made a shameless grab for clicks by breathlessly claiming "OMG WORLD'S FIRST FURY BENCHIES," but we don't believe that would actually give readers any useful information.)

I'm not saying that AMD is lying about these numbers or anything, but we certainly can't/won't stand by them. And sure, it may be interesting to look at the numbers, but why would you believe what they say? It's just hearsay, essentially.

We'll post real benchmark numbers from our own labs when the time comes.

 

[MarkW]

Not all of us, in fact, almost none of us are members of the press. So its interesting for us.

I'm not saying that AMD is lying about these numbers or anything, but we certainly can't/won't stand by them. And sure, it may be interesting to look at the numbers, but why would you believe what they say? It's just hearsay, essentially.

We'll post real benchmark numbers from our own labs when the time comes.

Just read the Forbes AMD Fury X Benchmarks. These numbers come from the AMD Press package. It beats the 980Ti in each of the dozen games, and just barely in the one synthetic, 3DMark Firestrike Ultra (4K). That card does look like its a winner. But these are AMD numbers. The embargo on press created benchmarks is still on until the 24th. And they only benchmarked 4K numbers.

Is there a reason for that? I guess we should know in a week.

I guess that was not clear enough? That was right above the link.

 

[none12345]

Man so many people who dont understand electricity here.

There is nothing wrong with the 400 amp number, its normal for GPUs to pull hundreds of amps. They run at less then 1 volt, and when they are several hundred wats, several hundred wats divided by 1 volt = several hundred amps.

Just because the GPU is using hundreds of amps, doesnt mean the VRM is drawing 100s of amps form the power supply. Its drawing most of the power at 12 volts, so 375 watts possible / 12 volts = arround 30 amps max. And once you get out to your wall plug, its more like 3-4 amps from your power supply to your home serverice maximum. And once you get to the power plant, its more like 375 watss / a few hundred thousand volts = microamps.

Of course the 375 number is just what the PCI and 2 6 pin power connectors can supply, NOT what the gpu is actually using. If its using about 250 watts, then thats about 20 amps at your power supply and only 2 amps at your wall.

I dotn know why they even put the 400 amp number in this article. I dont know if they were trying to scare people that this card is using 100s of amps at the GPU when its perfectly normal; or what their intent was.

 

[scolaner]

Not all of us, in fact, almost none of us are members of the press. So its interesting for us.

I'm not saying that AMD is lying about these numbers or anything, but we certainly can't/won't stand by them. And sure, it may be interesting to look at the numbers, but why would you believe what they say? It's just hearsay, essentially.

We'll post real benchmark numbers from our own labs when the time comes.

Just read the Forbes AMD Fury X Benchmarks. These numbers come from the AMD Press package. It beats the 980Ti in each of the dozen games, and just barely in the one synthetic, 3DMark Firestrike Ultra (4K). That card does look like its a winner. But these are AMD numbers. The embargo on press created benchmarks is still on until the 24th. And they only benchmarked 4K numbers.

Is there a reason for that? I guess we should know in a week.

I guess that was not clear enough? That was right above the link.

I can't tell if you agree with me or not.

 

[Mousemonkey]

If Samsung invented HBM, why is only SK Hynix making it? That is a division of Micron.

Something about what you are saying does not add up. AMD clearly states they invented GDDR5, and that they started work on HBM right after GDDR5 happened.

Much like Apple when they claimed that they invented the .mp3 format eh? :lol:

the Fury X doesn't employ a fan on its dual-slot form factor....yadda yadda yadda.... Without that traditional blower, the company was able to design a fully enclosed, sleek-looking shroud.

so what about the other parts of the card that get hot? with this should can we expect the power lanes to melt or spontaneously combust the shroud due to all the excess heat? will the pcb warp or bend? what about all the vrms and mofsets? doesn't the ddr5 get pretty hot? i imagine there's alot more that needs to be kept cool than just the gpu considering the 200+ watts being pumped into these things?
or are they just going to print a hasbro logo on them and we can have our cake cooked and eat it?

What's really funny is that everyone talk about how hot the AMD cards are, but yet Nvidia's Fermi were famously known for cooking eggs.... lol

https://www.google.com/webhp?sourceid=chrome-instant&ion=1&espv=2&ie=UTF-8#q=nvidia%20cook%20egg

Even then, they worked just as well.

Post the video so we can all have a laugh at how bad your memory is please, the egg didn't cook because the white remained runny and clear which is a sign rawness in case you didn't know.

 

[jimmysmitty]

Damn. Haven't seen you around for a while MouseMonkey.

You been "hanging" out?

 

[Mousemonkey]

Damn. Haven't seen you around for a while MouseMonkey.

You been "hanging" out?

You need to pop into the staffroom a bit more often mate. 😉 There has been stuff going on that I'm not going to discuss here. 😀

 

[Blueberries]

At these resolutions it's all about the the number of Stream Processors and size of VRAM and that's why cards like the Titan X will perform better at 4k and especially at 8k; 4GB is incredibly lackluster for what this card is trying to be, obviously AMD tried a different approach and thought only their HBM solution would be enough (I have doubts). Also, with Pascal around the corner it's hard to get excited about a small step up like this.

Still, these are impressive cards from AMD and as always the price/performance is incredibly high.

 

[Mousemonkey]

At these resolutions it's all about the the number of Stream Processors and size of VRAM and that's why cards like the Titan X will perform better at 4k and especially at 8k; 4GB is incredibly lackluster for what this card is trying to be. Also, with Pascal around the corner it's hard to get excited about a small step up like this.

Still, these are impressive cards from AMD and as always the price/performance is incredibly high.

The performance has yet to be ascertained but fingers crossed for good things.

 

[jimmysmitty]

At these resolutions it's all about the the number of Stream Processors and size of VRAM and that's why cards like the Titan X will perform better at 4k and especially at 8k; 4GB is incredibly lackluster for what this card is trying to be. Also, with Pascal around the corner it's hard to get excited about a small step up like this.

Still, these are impressive cards from AMD and as always the price/performance is incredibly high.

The performance has yet to be ascertained but fingers crossed for good things.

Based on what AMD gave us I am going to estimate an average of 25-30% across all games with some being double the performance (very few) and some being 20% or less compared to a current high end R9 290X, not a based model.

 

[Mousemonkey]

At these resolutions it's all about the the number of Stream Processors and size of VRAM and that's why cards like the Titan X will perform better at 4k and especially at 8k; 4GB is incredibly lackluster for what this card is trying to be. Also, with Pascal around the corner it's hard to get excited about a small step up like this.

Still, these are impressive cards from AMD and as always the price/performance is incredibly high.

The performance has yet to be ascertained but fingers crossed for good things.

Based on what AMD gave us I am going to estimate an average of 25-30% across all games with some being double the performance (very few) and some being 20% or less compared to a current high end R9 290X, not a based model.

I know the majority are interested in the gaming performance but I'm more interested in how well they can fold and how hot they get and how much power they use, not forgetting the all important driver stability elephant in the room question of course.

 

[jimmysmitty]

At these resolutions it's all about the the number of Stream Processors and size of VRAM and that's why cards like the Titan X will perform better at 4k and especially at 8k; 4GB is incredibly lackluster for what this card is trying to be. Also, with Pascal around the corner it's hard to get excited about a small step up like this.

Still, these are impressive cards from AMD and as always the price/performance is incredibly high.

The performance has yet to be ascertained but fingers crossed for good things.

Based on what AMD gave us I am going to estimate an average of 25-30% across all games with some being double the performance (very few) and some being 20% or less compared to a current high end R9 290X, not a based model.

I know the majority are interested in the gaming performance but I'm more interested in how well they can fold and how hot they get and how much power they use, not forgetting the all important driver stability elephant in the room question of course.

Fury X will be water so it will probably be running in the 5-60c range, folding might push it to 70c.

As for folding performance that is pretty much tied into the increase in FLOPS so possibly 40-50% better folding performance.

I am going to guess based on TDP though that we will see probably similar to a R9 290X is not maybe 15-20% more.

We will have to wait and see I guess. Damn review embargos....