AMD to launch 300W GPU with High-Bandwidth-Memory

[Tonester0011]

Predictably the usual suspects have this thread in the gutter with-in minutes.

This forum makes up 10% trying to talk about Hardware by 90% of it's members, 90% trying set-off arguments instigated by 10% of it's members.

You clearly missed stulid's post, leave shank's alone...

Can we leave Shankly alone please.

Ta.

 

[ghost.florian]

So we're going back to GTX 480 times.

Such a high TDP means AMD is adding more stream cores and not doing much with the graphics processor architecture itself. This is the strategy they have had on the desktop side for a while now.

Another option would be that they come up with a monster GPU which will hands down outperform the 980.

Let's wait and see. I think we're reaching the end of the R9 290/290x lifecycle.

 

[pandem0nium]

300W wouldn't be that bad noise and temp wise if they ship with that leaked (lol) AIO liquid cooler.

 

[drunkenmaster]

So we're going back to GTX 480 times.

Such a high TDP means AMD is adding more stream cores and not doing much with the graphics processor architecture itself. This is the strategy they have had on the desktop side for a while now.

Another option would be that they come up with a monster GPU which will hands down outperform the 980.

Let's wait and see. I think we're reaching the end of the R9 290/290x lifecycle.

High tdp has relatively little bearing on how much the architecture may or may not be changing. Ultimately adding sub 20% shaders on the same architecture would be almost pointless. They could have added 30% shaders, saved 40W on the memory and ended up with 10% higher power than the 290x, or they could have entirely changed the architecture, saved 40W with HBM and added 50% shader power(be that 50% more shaders, or same number but 50% more powerful, or any combination). 300W isn't directly indicative of either route.

 

[eddyr]

Something to consider, the article pulls from LinkedIn the phrase

300W 2.5D discrete GPU SOC

Assuming it is even referring to TDP, it is including the cooling requirements of the GPU die and HBM stack.
Roll back a year. Had this guy done the same thing he would not be including the TDP/power of board RAM when referring to his involvement in developing the GPU core and its TDP/power figure.

How much power this thing has been designed to use/be able to use and how much power it actually uses shouldn't be taken as the same thing. Depends where they set stock/boost clocks, voltages, power draw and temp limits.

 

[Martini1991]

That's a sick burn Tonester.
I love it.

 

[layte]

Predictably the usual suspects have this thread in the gutter with-in minutes.

This forum makes up 10% trying to talk about Hardware by 90% of it's members, 90% trying set-off arguments instigated by 10% of it's members.

 

[loftie]

Hmmm, I'll wait until it's released to pass judgement. Lets hope it's not actually 300W. If it is it needs to a) have good perf/£l b) not act like a small furnace c) not have a terrible air cooler that rivals an aeroplane in sound volume nor a more unique cooler ala the 295.

Either way interested to see it and if I were nvidia I wouldn't write it off just yet, at the end of the day if it's good performance people will still buy it.

 

[Mal X]

300W wouldn't be that bad noise and temp wise if they ship with that leaked (lol) AIO liquid cooler.

no way, that Radiator hanging out the side is a really bad idea, just design a really good air cooler....the graphics card should be plug and play only

 

[kaku]

Who cares about TDP top-trumps? If it's got the performance to back it up it'll be exciting.

 

[andybird123]

Something to consider, the article pulls from LinkedIn the phrase



Assuming it is even referring to TDP, it is including the cooling requirements of the GPU die and HBM stack.
Roll back a year. Had this guy done the same thing he would not be including the TDP/power of board RAM when referring to his involvement in developing the GPU core and its TDP/power figure.

How much power this thing has been designed to use/be able to use and how much power it actually uses shouldn't be taken as the same thing. Depends where they set stock/boost clocks, voltages, power draw and temp limits.

Nah, it'd be the tdp of the card as a whole, so it would be included anyway

 

[varkanoid]

This is one for my "Rumour Mill Thread"

Anyone know what the name of this card is supposed to be.

The Dodo

 

[Bonjour]

Not fussed about tdp, as long as it has adequate cooling.

 

[humbug]

Also in the news but dead boring -

20nm GPUs not happening

Yields bad beyond repair

We want to make sure that you realize that 20nm GPUs won’t be coming at all. Despite the fact that Nvidia, Qualcomm, Samsung and Apple are doing 20nm SoCs, there won’t be any 20nm GPUs.

From what we know AMD and Nvidia won’t be releasing 20nm GPUs ever, as the yields are so bad that it would not make any sense to manufacture them. It is not economically viable to replace 28nm production with 20nm.

This means the real next big thing technology will be coming with 16nm / 14nm FinFET from TSMC and GlobalFoundries / Samsung respectively, but we know that AMD is working on Caribbean Islands and Fiji as well, while Nvidia has been working on its new chip too.

This doesn’t mean that you cannot pull a small miracle in 28nm, as Nvidia did that back in September 2014 with Maxwell and proved that you can make a big difference with optimization on the same manufacturing process, in case when the new node is not an option.

Despite the lack of 20nm chips we still think that next gen Nvidia and AMD chips bring some innovations and make you want to upgrade in order to buy it to play the latest games on FreeSync or G-Sync monitors, or in 4K/UHD resolutions.

http://www.fudzilla.com/news/graphics/36721-20nm-gpus-not-happening

The Man from Del Monte was right.

 

[bru]

Nah, it'd be the tdp of the card as a whole, so it would be included anyway

I'm not so sure, when different AIB's produce their cards they don't no list different TDP's

But you might be right I'm not sure.

 

[D.P.]

Also it needs to be said that while AMD generally give a TDP that's higher than their actual use. Nvidia bend the truth somewhat about their TDP.

]

Reference 980 can actually use up to 280w..

Try benchmarking actual games!

 

[D.P.]

So imagine like you say if Furmark doesn't allow the cards to max out, yet the 980 is pulling well well well over it's TDP. How much would it pull if Furmark could max it out.

Think about it you thoroughly intelligent people

A 300w TDP AMD card should be fine, a 300w TDP Nvidia wouldn't as it would use about twice that in reality

The 980 isnt pulling over its TDP, the total system I nuking CPU, memory, motherboard, hard drives, USB etc. Is drawing more than the nvidia TDP, so what.

 

[humbug]

The power consumption on Maxwell is not universal for all things.

Some games its pretty good, other games it's no better than a 290.

 

[Boomstick777]

The power consumption on Maxwell is not universal for all things.

Some games its pretty good, other games it's no better than a 290.

+1

Some of these guys have no idea. Just spout what they read. There are loads of benchmarks showing 980's pulling massive watts during gaming just as much as Titan Black etc..

I own a 290X and a 980, I know how much power they use. Facts never stop the sheep though

Lulz.

Personally looking forward to AMD's next card, if it's a power sucking performance monster so be it. Those who are all of a sudden interested in saving the planet and tree hugging can buy a GTX 960 everybody's a winner

Hurry up and release the monster plz AMD !!

Also good call on 20nm Orangey, looks like it's a turnip. I guess it's a long wait for 16nm now then? http://www.fudzilla.com/news/graphics/36721-20nm-gpus-not-happening

 

[Orangey]