D:
also why do people keep insisting that some high end card will come on may? we know how nvidia works and since we havent seen not even a rumor about potential reviews it means the card is still away
Well, there is all this talk of modular GPUs. Polaris 10 Erector Set patent pending.
If i had to save cash for a new GPU until 20178, i suppose i could buy entire AMD by then
Not anytime before 2017 at the earliest, besides what you're talking about is the notebook market & I doubt Intel can come even close to the 750Ti (or 950) with their best IGP two years from now.
I'm not sure humans would still exist on this earth by then, global warming & all that D:
@NeoLuxembourg
I posted about that change already a few times.
Pascal finally has PROPER and FUNCTIONAL preemption. NVIDIA has been lying about Maxwell's capability in this aspect, where they tell devs yes they have it... except it doesn't work, even their priority preemption queues can get stuck behind a draw call. -_-
Pascal will have half of what's needed for proper Async Compute. Basically it will no longer require a slow context switch for graphics <-> compute queues. If there's a graphics draw call in the pipe, a priority compute queue can immediately suspend that graphics call and gets processed.
This is what they refer to as fine-grained preemption. It also means Pascal will not suffer like Maxwell and Kepler when games use a lot of compute, since it can switch much faster, there's no idle time between graphics/compute tasks that causes a performance loss the more compute is used.
It's a great change for modern games and VR. I think they will finally be able to get motion to photon latency below their current best of 25ms and it will be heavily advertised for VR.
In simple words. Pascal performance will not tank with using Asynchronous Compute. The other side of this is that it will also not get benefit from it. But the devs can always leave "Async=1" in command list.
Yes. It won't tank in compute heavy games either. But the biggest bonus is priority preemption will function properly for VR timewarp.
Zolkorn says the cards are ready, should be launched next month (reference models), while custom/manufacturer models will be shown at Computex. They also hint that AMD postponed their cards in order to be more competitive. Help with the translation would be appreciated.
NVIDIA Pascal GTX 1080 and GTX 1070 could come sooner than expected. See you next month!
www.zolkorn.com/news/nvidia-might-launch-geforce-gtx-1000-series-soon
Let's not forget Pascal comes with high clocks by default if we can extrapolate the GP100 specs to the GP104. I doubt GloFo can reach such high clocks as TSMC. I suppose the the full Polaris 10 will compete with the GTX 1070 at best and be two months late.
Nvidia did exactly the same with the GK104. The first leaks showed the top card as the GTX670(there was a shroud picture) and it running at 800MHZ to 900MHZ and that was not long after the HD7970 reached retail availability. It appears Nvidia was tuning the clocks to the 1.1GHZ to 1.2GHZ range because they realised they could beat the HD7970 and launch it as the GTX680,and AMD even admitted they launched the HD7970 at too low a clockspeed as they were being conservative.
Considering that Polaris 10 is meant to be 232mm2 and the GP104 around 300mm2,if AMD adjusting the clocks means they can be more competitive with a 30% larger part that would be a surprise.
It was like with the GK104,the early samples leaked were clocked much lower,and the evidence pointed to Nvidia adjusting the clockspeeds on the GPU so it could beat the Tahiti at launch.
If it could not compete with some adjustments,then AMD would be aiming to launch the cards as early as possible to maximise sales.
None of this makes any sense... The 670 is a cut down GK104, the full dies were going to be sold either way. The base clock for the 670 is 915MHz. I'm not sure where you got 1.1-1.2GHz, as even the 680's base clock is 1006MHz.
He's talking about the naming of the top-end card, something I've talked about before. Back in late 2011/early 2012, the first leaks suggested that the fastest GK104 would be called the 660 Ti, then later leaks suggested the card would be named as the 670. Nvidia finally settled on the 680 after realising they could fleece their buyers due to Tahiti being so mediocre.
None of this makes any sense... The 670 is a cut down GK104, the full dies were going to be sold either way. The base clock for the 670 is 915MHz. I'm not sure where you got 1.1-1.2GHz, as even the 680's base clock is 1006MHz.
Unless AMD is set to destroy Nvidia in perf/ mm2 (a reversal of Maxwell vs. Fiji, Hawaii and Tonga), then they will be best served to just release ASAP instead of holding back. The only adjustments AMD will have to make with launching after Nvidia is on pricing.
He's talking about Nvidia speeding up GK104 to compete with AMD's 7970, and you're stating the opposite...
It would not surprise me if they thought P10 was not competitive with the GP104,but probably realise it is now.
No it's the same thing. By launching at higher clock speeds (lower yields obviously) they were able to beat the 7970 by enough to claim clear top spot by 10%.
Somebody at Nvidia even made a comment about them being "not impressed" by Tahiti before GK104 launched - http://www.xbitlabs.com/news/graphi...We_Expected_More_from_AMD_Radeon_HD_7970.html
It was clear that they had a fast part for the midrange, what they realised was that with higher clocks they had a cheap (to manufacture) part for the high-end, because Tahiti underwhelmed. What was supposed to have been the GTX 660 became the GTX 680.
Unless AMD is set to destroy Nvidia in perf/ mm2 (a reversal of Maxwell vs. Fiji, Hawaii and Tonga), then they will be best served to just release ASAP instead of holding back. The only adjustments AMD will have to make with launching after Nvidia is on pricing.
Yep, the funny part is many said this at the time, but the ADF denounced this simple fact. However, they now say the 680 was midrange.
What is this? I remember back then the consensus was Gk104 is clearly a mid-range chip being pushed at high-end prices.
According to what taiwanese insiders revealed (do not know the dealers or partners), GTX1070's public version will sell for NT $ 19990, while GTX1080 will sell for NT $ 27990.
$650 for GP104? It better wipe the floor with 980 Ti or that's a serious milking.