Overclock.net › Forums › Industry News › Video Game News › [computerbase.de] DOOM + Vulkan Benchmarked.
New Posts  All Forums:Forum Nav:

[computerbase.de] DOOM + Vulkan Benchmarked. - Page 31

post #301 of 632
bias everywhere
post #302 of 632
Quote:
Originally Posted by magnek View Post

Are you actually taking what they said at face value?

lol no tongue.gif

Most of my posts on this topic haven't been serious and admittedly were a bit too troll-y. I deserved to have them deleted in the Futuremark thread.

Quite honestly, I think this is the first time in a long time that good competition has started to brew, and it's this kind of competition that pushes technology forward. AMD really needs this right now, and AMD is needed to keep Nvidia in check.

I was being serious about the fact that I think AMD fans will definitely be really vocal about their perceived injustice if games/benchmarks don't show the improvements they think these new APIs should bring.

Unfortunately, the architectures are currently very different and as such, developers will naturally have to make choices to benefit their market. This is normal, and AMD has a good start with all consoles having their hardware. As we see Nvidia adopt a similar architecture, then we can get back to focusing on which architecture is better instead of the shady area of blaming developers.
My main PC
(8 items)
 
  
CPUMotherboardGraphicsRAM
Intel i7 6700k Asus ROG Maximus VIII Gene Nvidia GTX 1080Ti G.Skill Ripjaws 
Hard DriveOSKeyboardPower
Samsung 850 EVO  Windows 10 Razer Blackwidow Chroma EVGA Supernova 1300w 
  hide details  
Reply
My main PC
(8 items)
 
  
CPUMotherboardGraphicsRAM
Intel i7 6700k Asus ROG Maximus VIII Gene Nvidia GTX 1080Ti G.Skill Ripjaws 
Hard DriveOSKeyboardPower
Samsung 850 EVO  Windows 10 Razer Blackwidow Chroma EVGA Supernova 1300w 
  hide details  
Reply
post #303 of 632
also vulkan/opengl can be monitored at low level like DX11/DX12 to see how asynchronous compute works?
Wanted: [WTB] GPU upgrade
$210 (USD) or best offer
  
Reply
Wanted: [WTB] GPU upgrade
$210 (USD) or best offer
  
Reply
post #304 of 632
Quote:
Originally Posted by PontiacGTX View Post

also vulkan/opengl can be monitored at low level like DX11/DX12 to see how asynchronous compute works?

What that even means?

You can create asynchronous compute with dx12/vulcan. Do you expect that they cant debug them?
Workstation
(4 items)
 
  
CPUMotherboardGraphicsMonitor
Xeon E5-2690 Supermicro 2011 Nvidia GP100/ Vega FE Dell ultrasharp 4k 
  hide details  
Reply
Workstation
(4 items)
 
  
CPUMotherboardGraphicsMonitor
Xeon E5-2690 Supermicro 2011 Nvidia GP100/ Vega FE Dell ultrasharp 4k 
  hide details  
Reply
post #305 of 632
Quote:
Originally Posted by sugarhell View Post

What that even means?

You can create asynchronous compute with dx12/vulcan. Do you expect that they cant debug them?
I mean if you can check how the game queues are done like GPUView allows
Wanted: [WTB] GPU upgrade
$210 (USD) or best offer
  
Reply
Wanted: [WTB] GPU upgrade
$210 (USD) or best offer
  
Reply
post #306 of 632
Quote:
Originally Posted by Remij View Post

lol no tongue.gif

Most of my posts on this topic haven't been serious and admittedly were a bit too troll-y. I deserved to have them deleted in the Futuremark thread.

Quite honestly, I think this is the first time in a long time that good competition has started to brew, and it's this kind of competition that pushes technology forward. AMD really needs this right now, and AMD is needed to keep Nvidia in check.

I was being serious about the fact that I think AMD fans will definitely be really vocal about their perceived injustice if games/benchmarks don't show the improvements they think these new APIs should bring.

Unfortunately, the architectures are currently very different and as such, developers will naturally have to make choices to benefit their market. This is normal, and AMD has a good start with all consoles having their hardware. As we see Nvidia adopt a similar architecture, then we can get back to focusing on which architecture is better instead of the shady area of blaming developers.

lol I see

As for perceived injustices, I think it's fair to say people shouldn't expect more than ~15% improvement with async, given the results we've seen with AotS. But I can agree that nobody should have the expectation that Fury X is going to suddenly see 60% gains in every title across the board.
post #307 of 632
Quote:
Originally Posted by magnek View Post

lol I see

As for perceived injustices, I think it's fair to say people shouldn't expect more than ~15% improvement with async, given the results we've seen with AotS. But I can agree that nobody should have the expectation that Fury X is going to suddenly see 60% gains in every title across the board.

Ashes of the Singularity

31 > 41 = +32%

DX11
http://i.imgur.com/BsE3XRH.jpg


DX12
http://i.imgur.com/noR7OWl.jpg



Total Warhammer DX11VS DX12

290x +[1080p Ultra Settings] >54 > 81 = +49.9% Performance gain.

DX11
http://i.imgur.com/mgmozPw.jpg

DX12
http://i.imgur.com/YF5fBgG.jpg
Edited by Eroticus - 7/16/16 at 4:41pm
PCRIUS
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel® Core™ i7-3930K Processor (12M Cache, up ... SABERTOOTH X79 Tuf EVGA GeForce GTX 1080 Ti FTW3 HYBRID  G.Skill Trident X 32GB 2400mhz C10 
Hard DriveCoolingOSMonitor
C:/Samsung 840 EVO 1TB - D:/7.27 TB of Storage ... Corsair H100i Windows 10 (64bit) LG 34UC98-W FreeSync 75hz 
KeyboardPowerCaseMouse
Logitech G410 Corsair AX1200i  Crystal Series 570X Logitech G900 
Audio
Asus Xonar D2X 
  hide details  
Reply
PCRIUS
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel® Core™ i7-3930K Processor (12M Cache, up ... SABERTOOTH X79 Tuf EVGA GeForce GTX 1080 Ti FTW3 HYBRID  G.Skill Trident X 32GB 2400mhz C10 
Hard DriveCoolingOSMonitor
C:/Samsung 840 EVO 1TB - D:/7.27 TB of Storage ... Corsair H100i Windows 10 (64bit) LG 34UC98-W FreeSync 75hz 
KeyboardPowerCaseMouse
Logitech G410 Corsair AX1200i  Crystal Series 570X Logitech G900 
Audio
Asus Xonar D2X 
  hide details  
Reply
post #308 of 632
Ok wait a second now, since 3dmar invalidates our score whoever we disables tess in driver, why is no the same with async on Maxwell?
That's a driver cheat too.
Bartholomew I
(15 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-4770K Gigabyte GA-Z87X-UD3H STRIX-R9390-DC3OC-8GD5-GAMING Corsair Vengeance Pro  
Hard DriveHard DriveOptical DriveCooling
Kingston SSDNow V300 Western Digital WD Green WD10EADS Lite-On Super AllWrite IHAS124-04  Cooler Master: Hyper 212 EVO 
OSMonitorKeyboardPower
Microsoft Windows 10 Pro 64-bit  Dell UltraSharp U2312HM  Genius GX Imperator I  Corsair AX760  
CaseMouseOther
Cooler Master: HAF 932 Advanced Bloody Multi-Core Gun 3 V8 Thrustmaster Ferrari F430 Force Feedback Racing... 
  hide details  
Reply
Bartholomew I
(15 items)
 
  
CPUMotherboardGraphicsRAM
Intel Core i7-4770K Gigabyte GA-Z87X-UD3H STRIX-R9390-DC3OC-8GD5-GAMING Corsair Vengeance Pro  
Hard DriveHard DriveOptical DriveCooling
Kingston SSDNow V300 Western Digital WD Green WD10EADS Lite-On Super AllWrite IHAS124-04  Cooler Master: Hyper 212 EVO 
OSMonitorKeyboardPower
Microsoft Windows 10 Pro 64-bit  Dell UltraSharp U2312HM  Genius GX Imperator I  Corsair AX760  
CaseMouseOther
Cooler Master: HAF 932 Advanced Bloody Multi-Core Gun 3 V8 Thrustmaster Ferrari F430 Force Feedback Racing... 
  hide details  
Reply
post #309 of 632
Quote:
Originally Posted by Eroticus View Post

Ashes of the Singularity

31 > 41 = +32%

DX11
http://i.imgur.com/BsE3XRH.jpg


DX12
http://i.imgur.com/noR7OWl.jpg



Total Warhammer DX11VS DX12

290x +[1080p Ultra Settings] >49.9% Performance gain.

http://i.imgur.com/YF5fBgG.jpg

http://i.imgur.com/mgmozPw.jpg

See this is the problem. First off, people think DX11 = async off, and DX12 = async on. The reason those gains are as such is due to much more than async.. so it's not even comparable... unless there is a test where you can specifically turn async on/off. And even then it might not be 'fully' on or off.

Async utilization will naturally vary between games/benchmarks and even GPUs within the GCN architecture. It's about constantly keeping the GPU fed, lower end GPUs with less resources sitting idle will not see the same potential benefit as a higher end GPU with more CUs to spare to handle things in parallel. So it's not just a case of turning it on or off and expecting gains. It's going to be highly specific to each game and how the developers choose to offload and balance the work distribution to the benefit the game's performance.

Also, it's not so trivial and developers are themselves learning as they go. So blaming developers by citing improvements from other games in completely different scenarios is dubious.
My main PC
(8 items)
 
  
CPUMotherboardGraphicsRAM
Intel i7 6700k Asus ROG Maximus VIII Gene Nvidia GTX 1080Ti G.Skill Ripjaws 
Hard DriveOSKeyboardPower
Samsung 850 EVO  Windows 10 Razer Blackwidow Chroma EVGA Supernova 1300w 
  hide details  
Reply
My main PC
(8 items)
 
  
CPUMotherboardGraphicsRAM
Intel i7 6700k Asus ROG Maximus VIII Gene Nvidia GTX 1080Ti G.Skill Ripjaws 
Hard DriveOSKeyboardPower
Samsung 850 EVO  Windows 10 Razer Blackwidow Chroma EVGA Supernova 1300w 
  hide details  
Reply
post #310 of 632
Timespy Graphics test 1 Async view. R9 290.

New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Video Game News
Overclock.net › Forums › Industry News › Video Game News › [computerbase.de] DOOM + Vulkan Benchmarked.