NVIDIA today revealed their new lineup of graphics cards, a refresh of the current series called the “GeForce RTX SUPER Series” which includes the GeForce RTX 2060 SUPER, GeForce RTX 2070 SUPER and GeForce RTX 2080 SUPER.
Direct Link
Coming as a result of what NVIDIA said is "nearly a year of architectural and process optimizations", you can see some of the details on each below:
- GeForce RTX 2060 SUPER GPU - Starting at $399, Available July 9
- Up to 22% faster (average 15%) than RTX 2060
- 8GB GDDR6 - 2GB more than the RTX 2060
- Faster than GTX 1080
- 7+7 TOPs (FP32+INT32) and 57 Tensor TFLOPs
- GeForce RTX 2070 SUPER GPU - Starting at $499, Available July 9
- Up to 24% faster (average 16%) than RTX 2070
- Faster than GTX 1080 Ti
- 9+9 TOPs (FP32+INT32) and 73 Tensor TFLOPs
- GeForce RTX 2080 SUPER GPU - Starting at $699, Available July 23
- Memory speed cranked up to 15.5Gbps
- Faster than TITAN Xp
- 11+11 TOPs (FP32+INT32) and 89 Tensor TFLOPs
This is all making my current 980ti seem a little antiquated, given that it was released way back in 2015 but it’s still a pretty good GPU. When I finally come to upgrade, it’s nice to see even more options on the table. Especially nice, that NVIDIA are pricing these new "SUPER" units at around the same as the existing cards. They could have come up with a better name though!
NVIDIA also announced the FrameView application designed to let you measure framerates, frame times, power, and performance-per-watt on a wide range of graphics cards. Only Windows was mentioned with this though, sadly.
You can see their official announcement here and also here.
Article taken from GamingOnLinux.com.
trawzified Jul 2, 2019
gradyvuckovic Jul 2, 2019
Quoting: HoriIn case you thought that the post-GTX naming convention wasn't bad enough...
I wonder even more about GTX 1660 - why isn't it GTX 1160?
Quoting: gradyvuckovicWhat about GPU memory? Any change there?
The old RTX 2600 only had 6GB, the new one has 8GB.
I was interested in the old RTX 2070, but the 2060 Super is cheaper and just as fast now.
Quoting: HoriIn case you thought that the post-GTX naming convention wasn't bad enough...
At least it's not taking a page out of the Nintendo (And numerous others) playbook by putting the word "New" in front of it instead.
^_^
AMD finally managed to produce more competitive microarchitecture (RDNA). It's a new hardware implementation of their instruction set (which they kept as GCN). They solved some major efficiency issues that caused high power consumption for them in the past. So in a few iterations, RDNA will be very competitive with Nvidia not only in performance, but also in power efficiency. Nvidia are naturally worried - competition is intensifying.
Regarding new cards, I don't see a point in buying Nvidia today for Linux gamers. With AMD totally caught up on the drivers side (radeonsi / radv) and close to catching up in hardware (RDNA), Nvidia's blob downsides are just not worth it. If you want a card that works properly with the Linux stack, get AMD.
I'll quote the leading Nouveau developer, Ilia Mirkin:
QuoteMoral of the story... just get an Intel or AMD board and move on with life. NVIDIA has no interest in supporting open-source, and so if you want to support open-source, pick a company that aligns with this.
Last edited by Shmerl on 2 July 2019 at 4:45 pm UTC
Patreon
PayPal
See more from me