will it overheat?Dann Corbit wrote: ↑Wed Aug 22, 2018 1:32 am I just bought a 1080 Ti because you can get them under $700 now.
PLS I HAVE TO KNOW
Moderators: hgm, Rebel, chrisw
will it overheat?Dann Corbit wrote: ↑Wed Aug 22, 2018 1:32 am I just bought a 1080 Ti because you can get them under $700 now.
It would be good if you are right, but it would also be a bit odd that Nvidia would eat into the profits of their more expensive cards.jkiliani wrote: ↑Wed Aug 22, 2018 3:48 amI think this is incorrect. While we don't have actual test benchmarks yet, the RTX lineup shares wiith the Titan V one important advantage over the GTX 10x0 cards: It can utilize fp16 inference fully, which gives a factor of 2 to speed in addition to the TFLOPS you posted. Currently, a Titan V can do around triple the Leela NPS that a 1080Ti can do, and the 2080Ti should be very close to that.Werewolf wrote: ↑Tue Aug 21, 2018 11:00 am Here's some better info, based on what's now released and in terms of TFLOPS, rather than FPS or something silly like that.
Titan RTX (??)
Quadro RTX 6000 - 15.9
Titan V - 14.9 (29.8 half P)
2080 Ti - 13.4
Quadro P6000 - 11.7
1080 Ti - 11.3
Quadro RTX 5000 - 10.6
2080 - 10.1
Quadro P5000 - 9.5
1080 - 8.9
2070 - 7.5
1060 - 4.4
For some reason Wikipedia doesn't list the FP16 performance of the Quadro cards. They definitely do half precision?Milos wrote: ↑Wed Aug 22, 2018 4:22 amWhy this BS-ing when it is also known that neither 2070, nor 2080, nor 2080Ti will have real FP16, i.e. all 3 will have it as 10xx cards at 1:64 rate?jkiliani wrote: ↑Wed Aug 22, 2018 3:48 amI think this is incorrect. While we don't have actual test benchmarks yet, the RTX lineup shares wiith the Titan V one important advantage over the GTX 10x0 cards: It can utilize fp16 inference fully, which gives a factor of 2 to speed in addition to the TFLOPS you posted. Currently, a Titan V can do around triple the Leela NPS that a 1080Ti can do, and the 2080Ti should be very close to that.Werewolf wrote: ↑Tue Aug 21, 2018 11:00 am Here's some better info, based on what's now released and in terms of TFLOPS, rather than FPS or something silly like that.
Titan RTX (??)
Quadro RTX 6000 - 15.9
Titan V - 14.9 (29.8 half P)
2080 Ti - 13.4
Quadro P6000 - 11.7
1080 Ti - 11.3
Quadro RTX 5000 - 10.6
2080 - 10.1
Quadro P5000 - 9.5
1080 - 8.9
2070 - 7.5
1060 - 4.4
Only Quadro's and Titan RTX will have actual FP16.
Nothing is sure before someone actually tests card for specific performance, but there are quite a few indicators.Werewolf wrote: ↑Wed Aug 22, 2018 11:02 amFor some reason Wikipedia doesn't list the FP16 performance of the Quadro cards. They definitely do half precision?Milos wrote: ↑Wed Aug 22, 2018 4:22 amWhy this BS-ing when it is also known that neither 2070, nor 2080, nor 2080Ti will have real FP16, i.e. all 3 will have it as 10xx cards at 1:64 rate?jkiliani wrote: ↑Wed Aug 22, 2018 3:48 amI think this is incorrect. While we don't have actual test benchmarks yet, the RTX lineup shares wiith the Titan V one important advantage over the GTX 10x0 cards: It can utilize fp16 inference fully, which gives a factor of 2 to speed in addition to the TFLOPS you posted. Currently, a Titan V can do around triple the Leela NPS that a 1080Ti can do, and the 2080Ti should be very close to that.Werewolf wrote: ↑Tue Aug 21, 2018 11:00 am Here's some better info, based on what's now released and in terms of TFLOPS, rather than FPS or something silly like that.
Titan RTX (??)
Quadro RTX 6000 - 15.9
Titan V - 14.9 (29.8 half P)
2080 Ti - 13.4
Quadro P6000 - 11.7
1080 Ti - 11.3
Quadro RTX 5000 - 10.6
2080 - 10.1
Quadro P5000 - 9.5
1080 - 8.9
2070 - 7.5
1060 - 4.4
Only Quadro's and Titan RTX will have actual FP16.
https://en.wikipedia.org/wiki/List_of_N ... xxx_series
Tensor core performance on RTX 8000 was explicitly mentioned during the new Quadro cards reveal.Milos wrote: ↑Wed Aug 22, 2018 12:38 pmNothing is sure before someone actually tests card for specific performance, but there are quite a few indicators.Werewolf wrote: ↑Wed Aug 22, 2018 11:02 am For some reason Wikipedia doesn't list the FP16 performance of the Quadro cards. They definitely do half precision?
https://en.wikipedia.org/wiki/List_of_N ... xxx_series
If you look for example fp64 performance it is real one (1:2) while in the past it was 1:32.
There are some benchmarks showing that lc0 is ~ 3x faster on Titan V than on 1080 Ti
I doubt it.whereagles wrote: ↑Wed Aug 22, 2018 10:44 amwill it overheat?Dann Corbit wrote: ↑Wed Aug 22, 2018 1:32 am I just bought a 1080 Ti because you can get them under $700 now.
PLS I HAVE TO KNOW
Saw this on the blog today:mirek wrote: ↑Wed Aug 22, 2018 7:03 pmThere are some benchmarks showing that lc0 is ~ 3x faster on Titan V than on 1080 Ti
Huge part of it I am sure comes from efficient fp16 operations that are enabled on tensor cores.
Also worth noting is that while Titan V has very similar specs to RTX 8000 (110 TFLOPs fp16)
and thus should be theoretically about 10x faster then 1080 TI (11 TFLOPs fp32) this is clearly not the case.
I am not sure if current implementation could be further optimized to take better advantage of the tensor cores or if there
is some fundamental limit i.e. like saturated memory bandwidth for current NN architectire.