** The Official Nvidia GeForce 'Pascal' Thread - for general gossip and discussions **

[D.P.]

Async is disabled for all nVidia GPUs in Ashes. Check this forum post:
https://forum.beyond3d.com/threads/...nd-analysis-thread.57188/page-64#post-1915300

Yes,I posted this earlier. WHIch means anyone drawing conclusions from these benchmarks are wrong.

Async is disabled for nvidia cards until oxide can optimize their async code for maxwell cards. Oxide don't have a 1080 to work with so they haven't had a chance to optimize an async path for Pascal yet.

Different architectures perform best with different async work loads, this is true within different versions of GCN let alone between vendors.

 

[D.P.]

Its all about performance I couldn't care less how it is achieved.

I am not even convinced that Async will a: be used that often and if it is it will only be on a select few titles and b: will be fairly irrelevant to the performance achieved by brute forcing on Nvidia hardware. Therefore a purchasing decision using Async as a major positive seems pointless to me.

You are quit right.
Async is a way to potentially get better utilization of the GPU, it isn't a requirement to get good performance if the GPU architecture already has good utilization. Just look at the theoretical peak performance of the FuryX and 980Ti, the former should smash the latter but Nvidia has a deign than can ensure the card reaches peak performance much more readily, and is not bottlenecked or dunker utilizing the compute power. Thus nvidia will never see as big gains and spending a significant transistor budget on something with much less gains is not particularly useful to them, at this stage.

Interestingly the rumours of Polaris sound like it is moving in the direction of Maxwell with a much faster command processor and reduced compute units that will help improve resource utilization. Async compute may be less beneficial on Polaris than Hawaii or Fiji.


Down the road it will probably get harder and harder to maintain full utilization so async compute will grow in importance form generation to generation, but it will never replace the importance of being able to fully utilize all GPU resources and minimize bottlenecks.

 

[Five.Stars]

Well a FE card costs $699 which equates to about £478. Rounding it off to £500 would probably be the way to go but i really doubt that will happen, probably £550 plus.

You need to add vat which is an additional ~£95 which puts 1080FE at ~£580

Then you have to take in to account retailers adding a bit on to massage their own margins!

 

[D.P.]

My point was that the 1080 is no faster in DX12 than DX11. It goes from 53.7fps to 53.3fps in AoTS and from 47.7fps to 47 fps in Hitman which means it actually drops a bit in DX12 just like the Maxwell cards.
The clockspeed pushes it past the other cards but the alleged addition of Async does not do anything for it unlike the FuryX which appears to show improvements over DX11. AoTS doesn't have Async enabled for the 1080 and maybe thats true for Hitman too.
The FuryX gains 1 fps in DX12 while the 1080 loses almost 1 fps.

That just means that Nvidia's DX11 drivers are better than the developers DX12 code path, which is hardly surprising. Maxwell and pascal as are not draw call limited in these games so see no advantage in moving to DX12.

 

[harney]

Funny to see the price argument (discussion) has now spread to the 1070. Keep expectations low, so you either won't be disapointed or you'll be pleasantly suprised. Expect much higher than what the 970 is currently at, especially considering the 970 has had competition for a while and we currently don't know whether the 1070 will have any products competing with it from AMD.



He kinda did, he mentioned a bit about exchange rates (which triggered myself to then ramble on about the economy going off-topic). Methinks it's a clue that the UK will get shafted for pricing. Alas, not a though.

The retailers like OCUK don't get too much say over the pricing. If Nvidia supplies them with FE 1080s £600 a piece, then selling them at any less than £600 would be a loss to the retailer and it would do more damage actually stocking and selling them at that price. The retailers must make at least some profit to pay the wages of the folks who work there and pay for the site/warehouse. And it allows them to occasionally do crazy deals where they might sell items at a loss. But don't expect it anytime soon for a 1080, profit margins are 'usually' better on cheaper products like the 970. Other businesses need to make a profit, not just Nvidia lol.

Yep agree so nvidia have stitched us ALL right up with this new ref...err flounders ed...

 

[tommybhoy]

lol

Almost missed that one.

Wow, Akward, 'reference oops I mean founder edition'

Poor chump

 

[easyrider]

Are you being serious or joking ??? as this was my plan all along how dare u i should have copy righted it

got a 980 g1 ti cheap getting 1491 core just shy of 8000 mem with +24 with stock bios

with custom bios not finished testing as of yet i am upto 1545core mem is same but at max volts testing more good temps so far below 68 69c fan curved getting 69 to 72% fan speed

but i am sticking with air ..

As of this morning I was but the guy has decided to keep it...

 

[queamin]

As of this morning I was but the guy has decided to keep it...

At least he never offered you it back with a £50 increase and called it a easy shuffle that would be funny .

 

[harney]

That is just plain scary should have TOM! in there

 

[harney]

As of this morning I was but the guy has decided to keep it...

I am sure you will pick one up what did you sell yours if u do not mind me asking ....

There all creeping back up.. now that the dust as settled but i am sure you will get one ...the best thing about going 2nd hand is if the buying give you details of its OC ability then saves you dice rolling

 

[AlamoX]

nvidia's tactic for Async kinda sux, since they still dont excel in it yet, they do not want to fully implement it yet, to try and prevent broader adoption for now.
the problem with this, it's much like DX12 games made with a lower common denominator directx11, the game can have much more drawcalls, it can use more cpu but it doesnt because they had to make it for DX11 and the game is tuned down for it, so the game doesnt evolve to a new generation.
for async compute, it's more than latency and fully utilizing the the GPU, but the game it self can benefit a lot from a game made with async shader from the ground up, you get better lighting, much more particles per frame, more complexe geometry, with lesser performance impact, the game while drawing textures can at the same time calculate lighting, apply post process effects, and so on, who doesnt hate when he loads the screen in pieces everytime you load or port.
async compute is much more than pre-emption, to say that it has async because it does pre-emption, is not accurate.
anyway this sux because like microsoft was standing in the way of PC gaming evolving for years, Nvidia now is doing the same with async.

 

[Legend]

What I don't understand is WHY are Nvidia not taking Async fully on board and utilising it properly? Makes no sense to me, surely it's a win win?? It can't be a technical hurdle too high given their resources?!

 

[Bazzards]

Perhaps they just don't see the benefit of it? why bother if you have the horsepower without it?

 

[AlamoX]

What I don't understand is WHY are Nvidia not taking Async fully on board and utilising it properly? Makes no sense to me, surely it's a win win?? It can't be a technical hurdle too high given their resources?!

because AMD is better at it, if nvidia adds it, devs will use it, and AMD will have an upper hand, so untill nvidia catchs up to AMD on async, they wont add it in hardware, to try and dissuade Devs from using it.
here is a Quote from Aquanox Dev:

We aim to develop a game that is enjoyable to everyone who wishes to join the world of Aqua. Implementing and/or focusing on technologies that would limit certain people from accessing the game is entirely against our philosophy of being a community focused developer. If at any point, there will be an implementation possible that will not limit NVIDIA card users, then we will certainly explore this option as well.

 

[provost]

What I don't understand is WHY are Nvidia not taking Async fully on board and utilising it properly? Makes no sense to me, surely it's a win win?? It can't be a technical hurdle too high given their resources?!

Controlling "Performance" = Optimizing Profitability?

 

[Born_2_Kill_83]

As of this morning I was but the guy has decided to keep it...

After all that you want a Ti again, or am I reading this wrong?

 

[imginy]

I really like the sound of fast sync, being able to play games on my big tv without the massive input lag of vsync.

I havent heard much talk of this fast sync, is it going to be on the full range of nvidia cards?

Do AMD have anything similar?

Thanks

 

[Gregster]

I really like the sound of fast sync, being able to play games on my big tv without the massive input lag of vsync.

I havent heard much talk of this fast sync, is it going to be on the full range of nvidia cards?

Do AMD have anything similar?

Thanks

I am not sure if it will be backward compatible but it will be part of the 1080 and 1070 cards. I am also sure that AMD will copy this and add their own version at some point.

 

[imginy]

I am not sure if it will be backward compatible but it will be part of the 1080 and 1070 cards. I am also sure that AMD will copy this and add their own version at some point.

I had no interest in new cards but 1070 sounding pretty good right now

 

[Baboonanza]

I am not sure if it will be backward compatible but it will be part of the 1080 and 1070 cards. I am also sure that AMD will copy this and add their own version at some point.

Surely there must be some hardware reason why this wasn't done before.