Severely CPU overhead of GTX1080Ti with RYZEN CPUs in DX-12 ??

Page 2 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
Civ VI is a complete turd of a game in general. Broken AI and negative steam reviews aside, 84-100fps "requiring" an 8C/16T CPU + 1080Ti for this? How can people even use the game for performance reviews with a straight face? It literally looks 10x worse than Age of Empires 1 (1997)...

Never played it myself, but it doesn't seem well optimized in DX12 that's for sure. AMD seems to gain under DX12, but that's not saying much as their DX11 performance in the game is atrocious. Also, AMD's DX12 performance is still slower than NVidia's DX11 performance in Civ VI.
 

AtenRa

Lifer
Feb 2, 2009
14,003
3,361
136
Never played it myself, but it doesn't seem well optimized in DX12 that's for sure. AMD seems to gain under DX12, but that's not saying much as their DX11 performance in the game is atrocious. Also, AMD's DX12 performance is still slower than NVidia's DX11 performance in Civ VI.

I would like to see this with slower CPUs like Pentiums, Core i3s, R3 Ryzen etc. Because it seems that when there is no high performance CPU the NV dGPU is loosing steam.
 
Reactions: kawi6rr and Drazick

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
I would like to see this with slower CPUs like Pentiums, Core i3s, R3 Ryzen etc. Because it seems that when there is no high performance CPU the NV dGPU is loosing steam.

I wouldn't mind seeing that test myself to be honest, just out of curiosity. It would test the theory about NVidia requiring a more powerful CPU due to the software instruction scheduler.
 

eek2121

Diamond Member
Aug 2, 2005
3,051
4,273
136
NVidia hardware has no issues with DX12. The problem is that DX12 games vary greatly in their level of optimization due to the skill and knowledge required to properly implement it. Another big problem is that beating NVidia's DX11 driver is really hard for developers to do, as the DX11 driver is super optimized and mimics some of the functions of DX12. That's why a game might run slower in DX12 than DX11 for NVidia. With AMD, it's not really a problem because their DX11 driver is nowhere near as efficient as NVidia's.



NVidia gains more from DX12 in Hitman than AMD. Other great examples of NVidia performing well with DX12 is Forza Horizon 3, Gears of War 4, The Division, Sniper Elite 4. Also, Doom runs great on NVidia with Vulkan, a similar low level API.

I cannot necessarily agree with that. I've played with DX12 on both Nvidia GPUs (1080ti) and AMD GPUs (r9 290). Each GPU has it's quirks. Nvidia seems to do 'ok' at DX11 titles and some of the earlier DX12 titles, however, the more you optimize for DX12 (especially when optimizing for higher core counts) the more things begin to fall apart. I'm not saying that the potential isn't there, but if it is, Nvidia clearly is not taking advantage of it.
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
I cannot necessarily agree with that. I've played with DX12 on both Nvidia GPUs (1080ti) and AMD GPUs (r9 290). Each GPU has it's quirks. Nvidia seems to do 'ok' at DX11 titles and some of the earlier DX12 titles, however, the more you optimize for DX12 (especially when optimizing for higher core counts) the more things begin to fall apart. I'm not saying that the potential isn't there, but if it is, Nvidia clearly is not taking advantage of it.

Define "fall apart." Are you telling me that your R9 290 is faster than a GTX 1080 Ti in DX12 I hope not, because that would be very laughable. Like it or not, NVidia makes the fastest GPUs right now, and that's for both DX11 and DX12. However, DX12 is still relatively half baked. The most crucial part, SM6.0 is only now just available with the launch of the Windows 10 Creators fall update. It's going to be a while before games truly start exploiting DX12, and for developers to get really good at optimizing for it.
 
Reactions: Phynaz

Ancalagon44

Diamond Member
Feb 17, 2010
3,274
202
106
This is a vast oversimplification of the actual issue. While NVidia does instruction scheduling in software, actual resource scheduling is done in hardware; and this includes asynchronous compute! My guess to explain why NVidia takes such a big hit with AMD CPUs, is probably because the compiler is hyper optimized around Intel's Core series architectures, and the instruction latencies of those CPUs. With AMD CPUs having lower IPC than their Intel counterparts, it's playing havoc with the compilers ability to properly optimize the instruction stream in a timely manner for the GPU.

But why was this not so visible when AMD's Bulldozer was their best CPU? Bulldozer had much lower IPC than Ryzen, as well as worse single threaded and multi threaded performance. Besides, relative to Intel Core CPUs of the time, it was much further behind than Ryzen is behind say Kaby Lake.

Carfax83 would you care to disclose what your relationship is with nvidia?

NVidia hardware has no issues with DX12. The problem is that DX12 games vary greatly in their level of optimization due to the skill and knowledge required to properly implement it. Another big problem is that beating NVidia's DX11 driver is really hard for developers to do, as the DX11 driver is super optimized and mimics some of the functions of DX12. That's why a game might run slower in DX12 than DX11 for NVidia. With AMD, it's not really a problem because their DX11 driver is nowhere near as efficient as NVidia's.



NVidia gains more from DX12 in Hitman than AMD. Other great examples of NVidia performing well with DX12 is Forza Horizon 3, Gears of War 4, The Division, Sniper Elite 4. Also, Doom runs great on NVidia with Vulkan, a similar low level API.

We've got multiple contradictory facts here. Something does not add up.

1. Civ 6's DX12 implementation is badly programmed
2. Civ 6's DX12 implementation runs well on AMD hardware
3. Nvidia has no DX12 issues

Now, if #1 is true, then logically #2 cannot be true. How can Civ 6 have a lousy DX12 implementation and yet run well on AMD hardware? If it did indeed have a lousy DX12 implementation, one would expect it to run poorly on ALL hardware, not only nvidia's hardware.

That leaves fact #3...
 

TheELF

Diamond Member
Dec 22, 2012
3,991
744
126
We've got multiple contradictory facts here. Something does not add up.
If you play the game and search the relevant forums you will see that the game seemingly randomly runs on as many threads as it pleases...For some people it only runs on one thread causing problems for others it runs well hitting 100% usage on 8 cores + .
You can't draw any conclusions on completely unsteady software.
If at least they (bench sites) would include cpu usage for each run you'd might be able to draw at least some conclusions,but like that it's completely irrelevant.
 
Reactions: Phynaz

Ancalagon44

Diamond Member
Feb 17, 2010
3,274
202
106
If you play the game and search the relevant forums you will see that the game seemingly randomly runs on as many threads as it pleases...For some people it only runs on one thread causing problems for others it runs well hitting 100% usage on 8 cores + .
You can't draw any conclusions on completely unsteady software.
If at least they (bench sites) would include cpu usage for each run you'd might be able to draw at least some conclusions,but like that it's completely irrelevant.

That's irrelevant unless can you prove that the game runs on more threads when using an AMD graphics card than when using an nvidia card.

If the game uses an arbitrary number of threads with either an AMD or nvidia graphics card, then one would expect performance on both to be equally bad, not so?

However, performance on AMD graphics cards is consistently good under DX12.
 

Qwertilot

Golden Member
Nov 28, 2013
1,604
257
126
No, he means it runs a random number of threads and so trying to use its benchmarks to infer anything is, well, silly
(I have no idea if this is strictly accurate mind you.).
 
Reactions: Phynaz

TheELF

Diamond Member
Dec 22, 2012
3,991
744
126
That's irrelevant unless can you prove that the game runs on more threads when using an AMD graphics card than when using an nvidia card.
The thing is that we don't know if the i7-7700k is pushing the nvidia card as hard as possible because we don't know if the game is running the correct number of threads on intel cpus...if you noticed the i7-7700k has the same FPS on the vega card,this could be due to the game not running enough threads.
 

eek2121

Diamond Member
Aug 2, 2005
3,051
4,273
136
Define "fall apart." Are you telling me that your R9 290 is faster than a GTX 1080 Ti in DX12 I hope not, because that would be very laughable. Like it or not, NVidia makes the fastest GPUs right now, and that's for both DX11 and DX12. However, DX12 is still relatively half baked. The most crucial part, SM6.0 is only now just available with the launch of the Windows 10 Creators fall update. It's going to be a while before games truly start exploiting DX12, and for developers to get really good at optimizing for it.

No, I'm saying the performance characteristics of ANY Nvidia card are very different from ANY AMD card.
 

Carfax83

Diamond Member
Nov 1, 2010
6,841
1,536
136
But why was this not so visible when AMD's Bulldozer was their best CPU? Bulldozer had much lower IPC than Ryzen, as well as worse single threaded and multi threaded performance. Besides, relative to Intel Core CPUs of the time, it was much further behind than Ryzen is behind say Kaby Lake.

Who said it wasn't visible? Computerbase.de exposed this with AMD's Vishera core last year if I recall and somebody made a thread about it in the CPU forums.

Carfax83 would you care to disclose what your relationship is with nvidia?

There's nothing to disclose. I'm curious as to what makes you think I have any sort of official relationship with NVidia
We've got multiple contradictory facts here. Something does not add up.

1. Civ 6's DX12 implementation is badly programmed
2. Civ 6's DX12 implementation runs well on AMD hardware
3. Nvidia has no DX12 issues

Now, if #1 is true, then logically #2 cannot be true. How can Civ 6 have a lousy DX12 implementation and yet run well on AMD hardware? If it did indeed have a lousy DX12 implementation, one would expect it to run poorly on ALL hardware, not only nvidia's hardware.

That leaves fact #3...

The reason it might seem contradictory to you, is because what you stated are not facts. This is how it is in reality:

1) Civ VI's DX12 implementation is mediocre and subpar.

2) Civ VI's DX12 implementation runs well on AMD hardware only in comparison to DX11. AMD's DX11 performance in this game is absolutely horrendous. GTX 1080 is 61% faster than Vega 64 in Civ VI DX11 according to Hardware.fr, which is an unusually large gap.

3) NVidia has no DX12 issues, but it is harder for developers to match, much less beat their DX11 driver, which mimics some of the functions of DX12. This is shown by AMD's DX12 performance still being significantly slower than NVidia's DX11 performance in Civ VI.

Now, if #1 is true, then logically #2 cannot be true. How can Civ 6 have a lousy DX12 implementation and yet run well on AMD hardware? If it did indeed have a lousy DX12 implementation, one would expect it to run poorly on ALL hardware, not only nvidia's hardware.

It's much easier for developers to exceed AMD's DX11 performance because their DX11 driver isn't very efficient to begin with. So even a mediocre DX12 implementation like in Civ VI runs faster in DX12 mode on AMD hardware, whereas with NVidia it runs slower because developers actually have to do a good job to get it to run faster on NVidia hardware.
 
Reactions: ozzy702
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |