NVIDIA Could Launch Next-Generation Ampere GPUs in 1H 2020

[Deleted member 177333]

Seriously, you upgrade every generation?
It would make more sense to buy a higher tier product and keep it for longer.

I already buy pretty high end generally speaking. At times, yes I upgrade generation to generation - but only if I'm actually GPU limited - if I was playing everything at my target resolution & framerates I would stay with the same gear for quite some time, but usually I end up GPU or VRAM limited, lol. Money isn't an issue for me, but at the same time, I'm not going to spend an outrageous amount of money for meager gains such as what the Pascal --> Turing would be - I just don't want to set that kind of precedent for the future. If I were to do that, I'd be sending a message to NVidia that that kind of pricing scheme is okay, when it's not. So I'm holding steady with my 1080 Ti cards for now. Hopefully the 3000 series is more reasonably priced. If not, I'll wait for 2nd-hand Turing cards to come down to more reasonable price ranges.

 

[Anymal]

Could be a response to big Navi launch

What big Navi launch?
Intel wont threat Radeons nor Geforces, just an introduction of the 3rd player. Nvidia should launch Ampere for high end and Pascal on 7nm for midrange.

 

[Bjorn_Of_Iceland]

How many games with raytracing a year after RTX release?

 

[EarthDog]

How many games with raytracing a year after RTX release?

its double digits iirc. One title/rtx on their list was delayed in that time. Did you expect more? Enabling a new technology isnt like flipping a light switch...

I think it has similar market penetration as vulkan...which has been out for years.

 

[las]

First of all get the facts straight; Pascal was the "filler" due to delays of Volta. Turing is derived from Volta and is a major improvement over Maxwell/Pascal. The chips were not "half-baked", like almost every previous GPU generation the last ten years Nvidia did some mid-life refreshes.

The next architecture may very well turn out to be "Ampere", but I haven't seen anything but baseless speculations about it. I'm puzzled how you would know it's a major bump over Turing. "Ampere" might even be a datacenter only GPU for all we know.

I just want to remind people about all the BS about AMD's "Arcturus" which was supposed to be the successor of GCN, but in reality was Vega based.

Haha good one. Turing was a minor improvement over Pascal, the focus was on RTX, not raw performance. Which is why 1080 Ti + OC can easily match RTX 2080 in non-RTX workloads. RTX is useless with Turing anyway. Even 2080 SUPER or 2080 Ti can't do 1440p/60fps with RTX on, aka useless.

Seriously? It's basic knowledge at this point. New arch + 7nm EUV = Huge bump in perf. You'll see.
I smell Turing-owner

Turing has been a huge joke. 2000 series sucked compard to 900 and 1000 series. Especially price vs perf. Turing was not even meant for 12nm in the first place, which is part of the reason why performance sucked so much. 1000 -> 2000 series was the smallest bump in perf ever, gen to gen.

 

[Chomiq]

What big Navi launch?
Intel wont threat Radeons nor Geforces, just an introduction of the 3rd player. Nvidia should launch Ampere for high end and Pascal on 7nm for midrange.

The one that's rumored for late 2019/ early 2020.

 

[Anymal]

Too early, TSMC is delaying 3x, big Navi on unimproved 7nm would need 375w, lol. We will see, probably on 7nm+ as ZEN3, 2H 2020.

Haha good one. Turing was a minor improvement over Pascal, the focus was on RTX, not raw performance. Which is why 1080 Ti + OC can easily match RTX 2080 in non-RTX workloads. RTX is useless with Turing anyway. Even 2080 SUPER or 2080 Ti can't do 1440p/60fps with RTX on, aka useless.

Seriously? It's basic knowledge at this point. New arch + 7nm EUV = Huge bump in perf. You'll see.
I smell Turing-owner

Turing has been a huge joke. 2000 series sucked compard to 900 and 1000 series. Especially price vs perf. Turing was not even meant for 12nm in the first place, which is part of the reason why performance sucked so much. 1000 -> 2000 series was the smallest bump in perf ever, gen to gen.

Maybe, but it was perfect time (80/20 market share) to release it, because AMD is sleeping and in p/W 2 years behind The Green Team.

 

[efikkan]

Too early, TSMC is delaying 3x, big Navi on unimproved 7nm would need 375w, lol. We will see, probably on 7nm+ as ZEN3, 2H 2020.

Yes, that would be challenging. A 60 CU Navi would easily consume ~325-350W, if not more, if they want to keep similar clocks to RX 5700 XT. But more likely, they would have to drop clocks a lot to keep it under 300W.

 

[EarthDog]

wow already? thats pretty quick considering companies generally stretch out about a year before releasing a new gpu.
could it be they want a piece of the market share before new gpus from amd and intel comes into play in 2020?

2080ti/Turing was released 9/2018... a year already.