CadetMahoney
Member
Even the regular 980 price is ridiculous if you ask me.
pretty much.
Even the regular 980 price is ridiculous if you ask me.
Even so, if it costs more than the 980 Ti, AMD is kinda fucked.
And costing less, is kinda fucked if it´s 300+ watts (isn´t AMD 290x already near 300?) compared to 250 for similar performance.
I don't think most people will care if it's within 50 watts. 100W I would start to take notice tho...
Instead, the Radeon R9 Fury X will be the flagship video card, a watercooled part based on the Fiji XT GPU. Under that, we'll have the Radeon R9 Fury, which should be based on the Fiji PRO architecture, with an entire restack of current cards. Under these two new High Bandwidth Memory-powered video cards we'll have the Radeon R9 390X, Radeon R9 390, Radeon R9 390, R9 380, R7 370 and R7 360.
The Radeon R9 Fury X will be a reference card with AIBs not able to change the cooler, but TweakTown can confirm that it will be the short card that has been spotted in the leaked images. The Radeon R9 Fury will see aftermarket coolers placed onto it, so we should see some very interesting cards released under the Radeon R9 Fury family.
The Radeon R9 Fury X has a rumored MSRP of $849, making it $200 more than the NVIDIA GeForce GTX 980 Ti, but $150 cheaper than the Titan X. The Fury X branding is a nice change from AMD, but it does sound awfully close to the Titan X with that big, shiny, overpowering 'X' in its name, doesn't it?
Read more at http://www.tweaktown.com/news/45602...atercooled-hbm-based-flagship-card/index.html
They're saying the engineering samples on beta drivers aren't as fast. That's not a big deal.
Everything has pointed to an August release for the Fury X. The 390X I think is coming first.Is this normal so close to launch though? I mean arent these coming in a few weeks?
Everything has pointed to an August release for the Fury X. The 390X I think is coming first.
Wow if the Fury X really isnt as fast as a 980 Ti enjoy paying $1000 and $650 for the best single GPU cards until high end pascals. Of course if nVidia remain the leaders. there is no rush for this.
Also, if true, nVidia could have priced Ti slightly higher.
Luckily these HBM cards are releasing now. I doubt Nvidia would have cut down a Titan X and released it @ 649.99 if the new series wasn't competitive. Whatever product gives me the best price/performance at the high end gets my money this month. I would prefer to wait until HBM2 cards, but that's going to be awhile and I need something now.
May I proffer that the $850 price leak was/is for the 8GB HBM Fury card that is out in apparently August.
And that the 4GB HBM Fury card out this month will be price competitive with the 980 Ti, or probably slightly cheaper?
Also, looking at the full line of cards being unveiled this month and not the Fury flagships, I bet that 390 is going to offer some serious bang-for-buck.
Since when is an 8GB Fury a sure thing? Also, why would it be faster?The 8GB Fury is going to be monstrous if the 4GB is around 980 Ti performance. I fully expect it to be the fastest single GPU on the market if it releases in August.
Question is, how long will it remain uncontested? Aren't the next Nvidia cards Pascal in 2016? Also, that dual GPU 8GB x2 Fury card is going to be ludicrous. That will probably be out this year too.
http://arstechnica.com/information-...hbm-why-amds-high-bandwidth-memory-matters/2/"4GB is more than sufficient. We've had to go do a little bit of investment in order to better utilise the frame buffer, but we're not really seeing a frame buffer capacity [problem]. You'll be blown away by how much [capacity] is wasted."
Wait why are we saying fury in August?
Pic not therehttp://i.imgur.com/Ac90NZk.jpg
Fiji being held on stage on at Computex. Die looks massive, possibly > 600mm.
Pic not there
Edit, now it is dammit
Afaik AMD already said, they will stay at 250 max.And costing less, is kinda fucked if it´s 300+ watts (isn´t AMD 290x already near 300?) compared to 250 for similar performance. It is like "Maxwell 2"="Sandy Bridge" and "GCN 1-1.3"="Bulldozer".
Afaik AMD already said, they will stay at 250 max.
That's hopeful, but they *would* say that, wouldn't they? And won't a lot be up to the developers?The only thing we really know is they'll release a card with Fiji this month, most likely around e3, and it does seem like it'll be a 4 GB card. The rest is rampant speculation, especially prices and any kind of talk of dual GPU cards.
AMD has already stated that 4GB isn't a problem for them, but people seem to ignore it.
http://arstechnica.com/information-...hbm-why-amds-high-bandwidth-memory-matters/2/
That's hopeful, but they *would* say that, wouldn't they? And won't a lot be up to the developers?
So I wonder how much it will cost me with a build with this card and Skylake.
Guys over at Anandtech are guesstimating a die size of 600+ mm2.
To put this in perspective Hawaii is around 450 mm2 and competes with Big Kepler at around 550mm2.
Now we have AMD launching something close in size to the GM200 or perhaps even larger, I think they have a shot at the crown this time around.
Will 4GB be enough for 4k gaming even if it's significantly faster than the 980Ti? That's the real question.
Will 4GB be enough for 4k gaming even if it's significantly faster than the 980Ti? That's the real question.
Skylake is coming very soon after Broadwell, so we're looking at two jumps in architecture in a very short period of time, meaning the gains should hopefully be more impactful.What's your reasoning for waiting for skylake? Is it hyped to be that much more powerful than a i7 5820k? I'm building my first gaming PC soon and plan on building it around a i7 5820k and Fiji.
Supposedly AMD put engineers on the task of optimizing the use of Vram specifically for HBM. According to AMD, the way Vram is used today is incredibly inefficient. Time will tell I guess
Skylake is coming very soon after Broadwell, so we're looking at two jumps in architecture in a very short period of time, meaning the gains should hopefully be more impactful.
It will be more powerful than a 5820k per core, but we're still just looking at 4 core CPU's for the standard range, so which is better overall will depend on the application. There's good reason to believe that 6 core CPU's could become more advantageous with DX12/Vulkan, though. We'll see.
Since when is an 8GB Fury a sure thing? Also, why would it be faster?
What's your reasoning for waiting for skylake? Is it hyped to be that much more powerful than a i7 5820k? I'm building my first gaming PC soon and plan on building it around a i7 5820k and Fiji.
If you can get the data faster in and out, wouldn't that help?Surely 4GB at higher resolutions is going to be a bottleneck, no?
Actually, it does help! See every jump from one memory architecture to another.If you can get the data faster in and out, wouldn't that help?
Tech-noob asking here.
Actually, it does help! See every jump from one memory architecture to another.
Yeah but I am sure there will be scenarios where 4GB will be a limit. Like at 1440p and 4k mostly. My post was in response to someone who asked how the 8GB version of the Fury card will be faster than the 4GB ones. The memory amount was one reason why it should be faster.