Monday, May 12th 2014

AMD to Launch New Single-GPU Card This Summer, to Take on GTX 780 Ti

AMD is reportedly working on a new single-GPU graphics card SKU to compete with the likes of GeForce GTX 780 Ti, and perhaps even take a swing at the GTX TITAN Black, since it's not too far ahead of the GTX 780 Ti at single-display gaming. The new SKU will be more than just a clock-speed bump, it will leverage HBM (high-bandwidth memory), a cutting-edge new technology that relies on stacking multiple DRAM dies with dedicated memory paths into a single package, cutting down on power-draw, thermals, and PCB real-estate.

The first kind of HBMs to hit the market are 8 Gbit 4Hi, which will interface with the GPU over a 128-bit wide path, which means there will be just four memory packages on the card (since the "Hawaii" silicon features a 512-bit wide memory bus), with improvements in the area of power-draw and heat output. The memory could be clocked higher, too. Sadly, memory bandwidth is not the prime-mover in VGA performance, and AMD will have to offer higher GPU clocks for the card to stand a chance against NVIDIA's high-end single-GPU offerings. As for the name this card would bear, we get a sense of deja vu about how NVIDIA launched the single-GPU GeForce 7950 GTX alongside the dual-GPU 7950 GX2, replacing the 7900 GTX. And so, it wouldn't surprise us if AMD named it Radeon R9 295X.
Source: VideoCardz
Add your own comment

34 Comments on AMD to Launch New Single-GPU Card This Summer, to Take on GTX 780 Ti

#26
TheoneandonlyMrK
Hitman_Actualyawn, already developed by Nvidia (pascal)
Oh yeah nvidia the hybrid memory makers not.
They already pr'd the shit out of tsv linked on die memory with volta too but that's not happening either.
And regardless the memory has squat all to do with nvidia.
Posted on Reply
#27
Casecutter
Hitman_Actualyawn, already developed by Nvidia (pascal)
No they just dumped Volta to now go and announced the engineering on stacked DRM. AMD is co-developing HBM with SK Hynix for more than the past 6 months, with this saying it will be in the product in a couple of months... Pascal by Nvidias' own road map not till 2016. Nice...
SteevoA die respin with less memory interface and another set of cores in its place, or some extra on die memory, or lots of tweaks with that much real estate to use.

At the worst we have some extra cores, at the best we have better thermals. Either of which could mean higher performance, in the middle it could be a smaller cooler die and cost less too.
Exactly, if they have 8 memory controllers now and 3/4 of that real estate is freed-up they could simply unpack the transistor density, which is a major contributor to thermals, then just give it more clock. Correcting the heat and consequently the power all on a less complex, smaller PCB, while perhaps even a smaller die that further improves cost... then think what what the LE version would be like! Hawaii 2.0 could be a big boon for us all becauses TSCM not having 20nm here as promised.

Let’s face it both sides are looking for contingency to 20nm being late/broke, who knows.
Posted on Reply
#28
arbiter
buildzoidProof that the Hawaii cores on R9 295X2 pull less than 200W each
So ram power draw = 50/0.85 = 58W
GPU power draw = 200/0.85 = 236W
236W+236W+58W = 528W
W1zz's review says that peak gaming is 500W so my numbers are a little too big.
That means that AMD has a stock pile of sub 200W Hawaii chips so this could very easily be a 1100mhz or 1150mhz Hawaii chip.
The last option is that AMD has gone to GloFlo's 28nm SOI which would allow then to clock higher at the cost of a power draw increase and a cost of production increase.
Um funny how that x2's gpu's pull less then 200watts yet single cards are known to be 300+watter's. With that said most reviews i seen put x2 card at 600+ watts so saying they are under 200 watts is a stretched and AMD saying the card is only 500watt TDP is well given AMD's history of saying TDP is this and it ends up being 20-30% higher, yea.
Posted on Reply
#29
GhostRyder
arbiterUm funny how that x2's gpu's pull less then 200watts yet single cards are known to be 300+watter's. With that said most reviews i seen put x2 card at 600+ watts so saying they are under 200 watts is a stretched and AMD saying the card is only 500watt TDP is well given AMD's history of saying TDP is this and it ends up being 20-30% higher, yea.
Well Dual GPU's tend to normally be binned chips that are better power consumption, clocking, and such. Such as the case with this compared to the normal reference 290X chips. That is why in many (If not most) cases the Dual GPU cards use less power (Clock for clock) compared to 2 separate cards. Both Nvidia and AMD do this to try and make the dual GPU cards much more appealing to consumers because they will be better fits in the scenarios that dual GPU cards typically fill (Reduced space for high GPU setups). But also the other thing is your talking about Separate PCB cards and such which are including the total combined power usage of that card (Fan and all the bells and whistles) to a card with 2 GPU's on one PCB cramming everything on one device.
Posted on Reply
#30
arbiter
GhostRyderWell Dual GPU's tend to normally be binned chips that are better power consumption, clocking, and such. Such as the case with this compared to the normal reference 290X chips. That is why in many (If not most) cases the Dual GPU cards use less power (Clock for clock) compared to 2 separate cards. Both Nvidia and AMD do this to try and make the dual GPU cards much more appealing to consumers because they will be better fits in the scenarios that dual GPU cards typically fill (Reduced space for high GPU setups). But also the other thing is your talking about Separate PCB cards and such which are including the total combined power usage of that card (Fan and all the bells and whistles) to a card with 2 GPU's on one PCB cramming everything on one device.
Point i mean is if you look at most reviews, the card pulls 600+ watts so hence what i said AMD making claims of xxx TDP when its really higher.
Posted on Reply
#31
GhostRyder
arbiterPoint i mean is if you look at most reviews, the card pulls 600+ watts so hence what i said AMD making claims of xxx TDP when its really higher.
All TDP's are lower than what the actual power draw is, heres a good example:
www.anandtech.com/show/7492/the-geforce-gtx-780-ti-review/15

Compare any of these cards to what the TDP says, heres the 780ti.
www.geforce.com/hardware/desktop-gpus/geforce-gtx-780-ti/specifications

Its power under load came to 372 but its TDP is listed as 250. Thats just how things are, the TDP is not the reality of what the card actually draws no matter which one it is or which brand it is. TDP is the Thermal Design power (Or Thermal Design Point in some cases) and is labeled as an average useage peak power rather than the max power CPU or GPU would use (Or whatever your comparing). Its used in reality as a reference point beyond anything at this day and age rather than being a defining factor.
Posted on Reply
#32
HumanSmoke
buildzoidI wonder what they will do to get more performance because if there is one thing Hawaii doesn't need then it's memory speed. They've got to either add more cores or clock it 100+mhz higher to catch up to the 780Ti.
Adding cores is unlikely because that would need a new die. And a 10% clockspeed increase would mean that AMD has been with holding some really well binned chips. Which is very likely because the R9 295X2 chips pull less than 200W from the VRM output side since the memory pulls around 50W from the VRM and there is a 10-15% efficiency loss on the VRMs.
Proof that the Hawaii cores on R9 295X2 pull less than 200W each
So ram power draw = 50/0.85 = 58W
GPU power draw = 200/0.85 = 236W
236W+236W+58W = 528W
You're missing one very important point- two (or more) GPUs working in concert in the same CFX/SLI system almost always result in a lower sustained GPU load for each.

By your theory, adding a second board to enable CFX/SLI means that the second board is automatically binned to a higher standard.

[Source #1] [Source #2] [Source #3]
Posted on Reply
#33
harry90
its about time! nvidia is going down again!!!!!!!!!!! even if its just for a few months.
Posted on Reply
#34
arbiter
harry90its about time! nvidia is going down again!!!!!!!!!!! even if its just for a few months.
no timetables are on either side, though since ES sample was shipped by nvidia labeled GM208 not to long ago which reared up online could lead to believe new gpu is pretty close. as for AMD don't know how close if they even are.
Posted on Reply
Add your own comment
Nov 22nd, 2024 13:15 EST change timezone

New Forum Posts

Popular Reviews

Controversial News Posts