Sunday, October 6th 2019

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

According to the sources over at Igor's Lab, NVIDIA could launch its next generation of GPUs, codenamed "Ampere", as soon as first half of the 2020 arrives. Having just recently launched GeForce RTX Super lineup, NVIDIA could surprise us again in the coming months with replacement for it's Turing lineup of graphics cards. Expected to directly replace high-end GPU models that are currently present, like GeForce RTX 2080 Ti and RTX 2080 Super, Ampere should bring many performance and technology advancements a new graphics card generation is usually associated with.

For starters, we could expect a notable die shrink to take place in form of 7 nm node, which will replace the aging 12 nm process that Turing is currently being built on. This alone should bring more than 50% increase in transistor density, resulting in much more performance and lower power consumption compared to previous generation. NVIDIA's foundry of choice is still unknown, however current speculations are predicting that Samsung will manufacture Ampere, possibly due to delivery issues that are taking place at TSMC. Architectural improvements should take place as well. Ray tracing is expected to persist and get enhanced with possibly more hardware allocated for it, along with better software to support the ray tracing ecosystem of applications.
Source: Igor's Lab via WCCFTech
Add your own comment

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

#26
Anymal
ChomiqCould 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.
Posted on Reply
#28
EarthDog
Bjorn_Of_IcelandHow 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.:p
Posted on Reply
#29
las
efikkanFirst 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 :roll:

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.
Posted on Reply
#30
Chomiq
AnymalWhat 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.
Posted on Reply
#31
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.
lasHaha 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 :roll:

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.
Posted on Reply
#32
efikkan
AnymalToo 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.
Posted on Reply
#33
EarthDog
Hyderzwow 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. ;)
Posted on Reply
Add your own comment
Nov 20th, 2026 01:25 PST change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts