Overclock.net › Forums › Industry News › Hardware News › [Various] Futuremark Releases 3DMark Time Spy DirectX 12 Benchmark
New Posts  All Forums:Forum Nav:

[Various] Futuremark Releases 3DMark Time Spy DirectX 12 Benchmark - Page 16

post #151 of 772
Why not post some scores and take the Async bickering to another thread? Just a suggestion for those of us that just want to see scores.
post #152 of 772
Quote:
Originally Posted by Kpjoslee View Post

AI has nothing to do with Async Compute. It deals with Compute queues for supporting GPU tasks such as physics, lighting, n post-processing. Compute in GCN only deals with graphics, not non-graphics. Complex AI would both affect Nvidia and AMD gpus negatively regardless of how Async operates.

AI keeps the CPU busy.

This affects AMD under DX11 for other reasons but for nVIDIA it affects their drivers ability to schedule tasks. If you have less CPU load then you have more CPU time in order to efficiently utilize nVIDIAs software scheduling features.

I never said AI had anything to do with Async-compute. I said that AI affects the CPU and that the CPU is what feeds the GPU.

As for Complex AI affecting both AMD and nVIDIA in the same manner... Not under DX12/Vulkan. Because of ACEs and the hardware scheduler found on GCN coupled with the parallel nature of GCN (several ACEs) which work in conjunction with the Multi-Threaded rendering capabilities of the DX12 and Vulkan APIs.

For 3DMark... we do not have any of that pesky AI to worry about. In fact we do not even know if Asynchronous Compute + Graphics is being used or just Asynchronous Compute. If it is the latter then this would explain why both a GTX 970 and GTX 980 Ti can run the code properly without a performance loss. They both should be seeing a performance loss if this test actually is using Asynchronous Compute + Graphics. Something tells me it is not due to this.
Edited by Mahigan - 7/14/16 at 5:06pm
Kn0wledge
(20 items)
 
Pati3nce
(14 items)
 
Wisd0m
(10 items)
 
Reply
Kn0wledge
(20 items)
 
Pati3nce
(14 items)
 
Wisd0m
(10 items)
 
Reply
post #153 of 772
I
Quote:
Originally Posted by ChevChelios View Post


here come the excuses smile.gif

Quote:
Originally Posted by ChevChelios View Post

1070 & 1080 get ~6-7% higher score with async enabled vs async disabled

Not at all. I wouldn't compare anything to 1080 1070 anyway. 480 is a $250 gpu. It's just, 280x has 2 ACE 16 commands total which could boost it over 960 on dx12. And there are some cases it does in dx12 games. Weird it's exactly the same on time spy.
Intel Evilnow
(18 items)
 
   
CPUMotherboardGraphicsRAM
i5 2500k 4ghz @ Offset -0.015 Asus P8P67 Evo (bios 3207) Sapphire 280x Tri-x 3GB OC (Stock 1020/1500 Non... G.Skill RipjawsX 2x4gb 1866mhz 9-10-9-28-2n @ 1.5v 
Hard DriveHard DriveHard DriveHard Drive
SHSS37A120G WD5000AAKX-001CA0 WD20EARX WD20EZRZ 
Hard DriveOptical DriveCoolingOS
WD5001AALS-00L3B2 (Now External) ASUS DRW-1814BLT Noctua NH-u12p SE2 Windows 10 Pro 
MonitorKeyboardPowerCase
Asus VH242H Wobbly Stand :) Microsoft Ergo 4000 Enermax Infiniti 650 (28a,28a,30a) Cooler Master haf 912 Advanced 
MouseOther
A4tech x7 F3 Sunbeam RHK-EX-BA Rheobus-Extreme Fan Controlle... 
CPUMotherboardGraphicsRAM
Phenom II x6 1090t BE 3.6/4.0 Turbo@def.volt MSI K9A2 Platinum v1 Sapphire HD6850 1GB 850/1100@def.volt Kingston 2x2gb Hyperx 1066 5-5-5-15 
Hard DriveHard DriveOptical DriveOS
Western Digital WD5001AALS Seagate Barracuda ST3250410AS Asus DRW-1814BLT Windows 7 Ultimate x64 SP1 
MonitorKeyboardPowerCase
Asus VH242H 23.6" Wobbly Stand :D Microsoft Ergo 4000 Enermax Infiniti 650w (28a,28a,30a) Thermaltake Kandalf SuperTower 
Mouse
A4 tech Swop-3 
  hide details  
Reply
Intel Evilnow
(18 items)
 
   
CPUMotherboardGraphicsRAM
i5 2500k 4ghz @ Offset -0.015 Asus P8P67 Evo (bios 3207) Sapphire 280x Tri-x 3GB OC (Stock 1020/1500 Non... G.Skill RipjawsX 2x4gb 1866mhz 9-10-9-28-2n @ 1.5v 
Hard DriveHard DriveHard DriveHard Drive
SHSS37A120G WD5000AAKX-001CA0 WD20EARX WD20EZRZ 
Hard DriveOptical DriveCoolingOS
WD5001AALS-00L3B2 (Now External) ASUS DRW-1814BLT Noctua NH-u12p SE2 Windows 10 Pro 
MonitorKeyboardPowerCase
Asus VH242H Wobbly Stand :) Microsoft Ergo 4000 Enermax Infiniti 650 (28a,28a,30a) Cooler Master haf 912 Advanced 
MouseOther
A4tech x7 F3 Sunbeam RHK-EX-BA Rheobus-Extreme Fan Controlle... 
CPUMotherboardGraphicsRAM
Phenom II x6 1090t BE 3.6/4.0 Turbo@def.volt MSI K9A2 Platinum v1 Sapphire HD6850 1GB 850/1100@def.volt Kingston 2x2gb Hyperx 1066 5-5-5-15 
Hard DriveHard DriveOptical DriveOS
Western Digital WD5001AALS Seagate Barracuda ST3250410AS Asus DRW-1814BLT Windows 7 Ultimate x64 SP1 
MonitorKeyboardPowerCase
Asus VH242H 23.6" Wobbly Stand :D Microsoft Ergo 4000 Enermax Infiniti 650w (28a,28a,30a) Thermaltake Kandalf SuperTower 
Mouse
A4 tech Swop-3 
  hide details  
Reply
post #154 of 772
Quote:
Originally Posted by Mahigan View Post

AI keeps the CPU busy.

This affects AMD under DX11 for other reasons but for nVIDIA it affects their drivers ability to schedule tasks. If you have less CPU load then you have more CPU time in order to efficiently utilize nVIDIAs software scheduling features.

I never said AI had anything to do with Async-compute. I said that AI affects the CPU and that the CPU is what feeds the GPU.

Mahigan, can't we just run this through a profiler and determine whether, or not, Pascal canrahp handle concurrent execution of graphics and compute?
post #155 of 772
Quote:
Originally Posted by Mahigan View Post

AI keeps the CPU busy.

This affects AMD under DX11 for other reasons but for nVIDIA it affects their drivers ability to schedule tasks. If you have less CPU load then you have more CPU time in order to efficiently utilize nVIDIAs software scheduling features.

I never said AI had anything to do with Async-compute. I said that AI affects the CPU and that the CPU is what feeds the GPU.

Besides Async issue, Nvidia GPUs also benefits from DX12 in terms of CPU overhead so i doubt CPU load would be an issue, not to the point where software scheduling would be an issue. Because games are far more likely GPU bound way before it would be CPU bound. Of course it will n ever be as efficient as fully hardware supported Async, but at least it will get the job done for Pascal generation (When it gets properly supported in games and drivers of course lol)
My home PC
(16 items)
 
  
CPUMotherboardGraphicsRAM
AMD Threadripper 1950x Gigabyte Aorus X399 Gaming 7  MSI Geforce GTX 1080ti Gaming X G.Skill DDR4 3600 CL16 
Hard DriveHard DriveCoolingOS
Samsung Evo 840 500GB Samsung 960 Pro 500GB Noctua NH-U14S TR4 Windows 10 Pro 
MonitorMonitorKeyboardPower
Dell U2711 Samsung 55" 4k Corsair K70  EVGA SuperNova G2 1300W 
CaseMouseAudio
Corsair Carbide Air 540 Logitech G502 Denon AVR-X3300W 
  hide details  
Reply
My home PC
(16 items)
 
  
CPUMotherboardGraphicsRAM
AMD Threadripper 1950x Gigabyte Aorus X399 Gaming 7  MSI Geforce GTX 1080ti Gaming X G.Skill DDR4 3600 CL16 
Hard DriveHard DriveCoolingOS
Samsung Evo 840 500GB Samsung 960 Pro 500GB Noctua NH-U14S TR4 Windows 10 Pro 
MonitorMonitorKeyboardPower
Dell U2711 Samsung 55" 4k Corsair K70  EVGA SuperNova G2 1300W 
CaseMouseAudio
Corsair Carbide Air 540 Logitech G502 Denon AVR-X3300W 
  hide details  
Reply
post #156 of 772
MSI GTX 1070 Gaming (non X)

Stock: http://www.3dmark.com/3dm/13210863?

Overclocked: http://www.3dmark.com/3dm/13211041?
Computer
(14 items)
 
  
CPUMotherboardGraphicsRAM
i7-4790k Gigabyte Z97X Gaming 7 Nvidia GTX 1080ti FE (EK block) CORSAIR Vengeance 
Hard DriveHard DriveCoolingOS
Samsung 850 Evo Mushkin Reactor Custom Loop Windows 10 
MonitorKeyboardPowerCase
Ben Q BL3201PT Logitech G110 EVGA 1300w Thermatake Core P5 
MouseAudio
LOGITECH G502 PROTEUS CORE Corsair 2100 
  hide details  
Reply
Computer
(14 items)
 
  
CPUMotherboardGraphicsRAM
i7-4790k Gigabyte Z97X Gaming 7 Nvidia GTX 1080ti FE (EK block) CORSAIR Vengeance 
Hard DriveHard DriveCoolingOS
Samsung 850 Evo Mushkin Reactor Custom Loop Windows 10 
MonitorKeyboardPowerCase
Ben Q BL3201PT Logitech G110 EVGA 1300w Thermatake Core P5 
MouseAudio
LOGITECH G502 PROTEUS CORE Corsair 2100 
  hide details  
Reply
post #157 of 772
Not much difference with async compute on or off

ON
http://www.3dmark.com/spy/17527

OFF
http://www.3dmark.com/3dm/13210332?
post #158 of 772
Quote:
Originally Posted by ChevChelios View Post


here come the excuses smile.gif

Yep, right on cue.

Well, it's not really Async
They aren't using much Async, just a bit
The benchmark is easy to trick
It's not properly utilizing Radeon hardware

rolleyes.gif
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 #159 of 772
Quote:
Originally Posted by jtom320 View Post

The async thing bothers me because it's a muddied issue that no one here really understands because none of us are engineers (for the most part). Nvidia cards however make use of it and do show gains. Regardless of whether it's through hardware, software or a combination of both.

They do and they show gains, nobody is (or should be) denying this. Even before this we had 1080 showing a 2.8% gain in AotS at 1440p so we know it's not doing nothing. But a 7% improvement in a synthetic benchmark just isn't anything to get overly excited about is all. But most importantly, it just gives those looking to stir the pot more ammo so to speak, as if there isn't enough bickering going on here already.
post #160 of 772
No excuses needed really from AMD fans from what i see Radeons are stronger in this bench vs NV than they were in Firestrike , you have older radeons bettering newer gen NV cards too. 280x beating GTX780 ... ouch (nearly beats the 780ti too). Fury X beating 980ti and TX without OCs taken into account from some reviews ( i think it was techpowerups ).

1070 and 1080 get some sort of boost from async (whatever you want it to call it) which helps them to stay at the top - just. Its about half the boost the radeons get. The 480 doesn't have as many stream processors so its logical its more tapped out. Fury X has the most, just like 1080 has the most cuda cores thats why see the largest async gains there.

1070 OC looks like its just inline with where my TX setup will be , find out tonight when i do a run.

When you translate this benches card to card levels to most DX12 games its actually not far from the truth .. the Fury X is quite close to the 1070 in dx12 games and in vulkan slightly ahead (so far).
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [Various] Futuremark Releases 3DMark Time Spy DirectX 12 Benchmark