Associate
- Joined
- 19 Jun 2017
- Posts
- 1,029
#Render Backends per Shader engine = 4 or total of 16
That's just 64 rops for navi 21.. doesn't add up.. I will watch Paul meantime
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
#Render Backends per Shader engine = 4 or total of 16
That's just 64 rops for navi 21
Ladies and gentlemen, my names Paul................
Golly gosh do I have some info for you today
Also, Navi 22 max clock 2.5ghz joizus. Heres hoping 80cu Navi 21 can hit close to that under water
That's just GPU power though, got to add in board+memIf these are right then it is 2.2Ghz at 238W, so pushing 300W will maybe get 2.5Ghz out of them. Obviously this is pure speculation and I am not basing it on anything.
Is that what the voices in your head are saying?But the ray-tracing performance is expected to be slightly ahead of Turing and way way below Ampere
Which would mean that Navi 3X and Navi 4X should be the proper, fixed cards.
But the ray-tracing performance is expected to be slightly ahead of Turing and way way below Ampere
Which would mean that Navi 3X and Navi 4X should be the proper, fixed cards.
Is that what the voices in your head are saying?
Hahaha, have you watched hardware unboxed vids looking at RT acceleration performance on ampere? I'll give you the TLDW, ampere has about 10% improvement in RT acceleration vs Turing. 10%
If rdna2 is only a little bit better than Turing than its the same as ampere
Golly gosh do I have some info for you today
Also, Navi 22 max clock 2.5ghz joizus. Heres hoping 80cu Navi 21 can hit close to that under water
Im watching the vid and has saying the same thing as old mate up there regarding ampere RT performance, that it's a lot faster than Turing. It's not. It only *appears* to be because the 3080 is faster than the 2080ti. The 3080 has the same performance impact when switching RT on as turing.Ladies and gentlemen, my names Paul................
"way way" below Ampere is Turing. Have you not seen any of the 3080 and 3090 reviews? Ampere's RT is still rubbish. Better than Turing but worse than Ampere isn't exactly a wide range to work with.But the ray-tracing performance is expected to be slightly ahead of Turing and way way below Ampere
Which would mean that Navi 3X and Navi 4X should be the proper, fixed cards.
I just replied mention this vid.Are you trolling or what? The guy is Paul and video is just above your posts. Watch it.
Ah, so it's a random Youtuber with some hot "leaks"? No, I think I'll pass thanks. Less reliable than the voices in your head.Are you trolling or what? The guy is Paul and video is just above your posts. Watch it.
Ah, so it's a random Youtuber with some hot "leaks"? No, I think I'll pass thanks. Less reliable than the voices in your head.
RTX performance Turing vs Ampere:
Control RTX:
Quake 2 RTX:
https://www.eurogamer.net/articles/digitalfoundry-2020-nvidia-geforce-rtx-3090-review?page=5
Quake 2
3080 65 FPS
3090 75 FPS +15%
Is that anything we don't already know?