• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

Futuremark Releases 3DMark v2.3.3663 - Adds Vulkan Support

Raevenlord

News Editor
Joined
Aug 12, 2016
Messages
3,755 (1.18/day)
Location
Portugal
System Name The Ryzening
Processor AMD Ryzen 9 5900X
Motherboard MSI X570 MAG TOMAHAWK
Cooling Lian Li Galahad 360mm AIO
Memory 32 GB G.Skill Trident Z F4-3733 (4x 8 GB)
Video Card(s) Gigabyte RTX 3070 Ti
Storage Boot: Transcend MTE220S 2TB, Kintson A2000 1TB, Seagate Firewolf Pro 14 TB
Display(s) Acer Nitro VG270UP (1440p 144 Hz IPS)
Case Lian Li O11DX Dynamic White
Audio Device(s) iFi Audio Zen DAC
Power Supply Seasonic Focus+ 750 W
Mouse Cooler Master Masterkeys Lite L
Keyboard Cooler Master Masterkeys Lite L
Software Windows 10 x64
Futuremark has just released a major update to its 3DMark benchmarking suite, adding Vulkan support while simultaneously axing its cousin, Mantle. This means that the API Overhead test now uses a Vulkan path instead of its previous Mantle one, which is sure to lead several enthusiasts into a frenzy of benchmarking under the Khronos's API (which has just recently been announced will offer support for multi-GPU in Windows 10, 8.x, 7, and Linux operating systems.)

Check some of the new features, improvements and fixes on the new version right after the break. You can download this piece of software right here on TPU - just follow the link below.



Download: Futuremark 3DMark + TimeSpy v2.3.3663



New
Added Vulkan support to the API Overhead feature test. Use the API Overhead feature test to compare Vulkan, DirectX 12, and DirectX 11 API performance on your PC. The Vulkan test requires compatible video drivers with Vulkan support. Check with your GPU vendor for Vulkan driver support if your hardware is unable to run the test. Note that the Vulkan test replaces the Mantle test found in previous versions of 3DMark.

Improved
SystemInfo scan time greatly improved on X99 systems.

Fixed
  • Fixed an issue that could cause the API Overhead feature test to fail to show a score at the end of an otherwise normal run on some systems.
  • Fixed Time Spy test to properly recover from a corrupted shader cache - if runtime compiled shaders are found to be corrupted, they are deleted and recompiled. Uninstallation also now completely removes the shader cache folder.
  • Fixed a scaling issue that could cause parts of the UI to end up outside the display area on 1080p monitors with 150% DPI scaling. UI will now scale appropriately even on high DPI scaling settings.



View at TechPowerUp Main Site
 
If I'm not mistaken, first time with anything else than Direct3D?

may this be the end of DirectX (I hope) ?
 
Vulken is being addopted worryingly slow since announced. DXs death is not in thw horizon atm
 
Vulken is being addopted worryingly slow since announced. DXs death is not in thw horizon atm

DX12 introduction is slow too.
Vulkan is often chosen above DX12, game engines are often sold so when the first Vulkan based engine is finished properly then we'll see a lot of vulkan games out there.
and or DX12
 
Vulken is being addopted worryingly slow since announced. DXs death is not in thw horizon atm
Apparently once a title is ported in DX12 it requires little extra effort to further port it in Vulkan.
Considering that Vulkan is not OS-dependent like DX12, which is tied to Win10, it actually has a fair chance of overcoming DirectX as platform of choice.
Time will tell of course ^^
 
Also it would be nice to point out that you CANNOT compare APIs without purchasing the Advance Edition.
 
Also it would be nice to point out that you CANNOT compare APIs without purchasing the Advance Edition.

Indeed, got that a bit cheaper via a Humble Bundle, I'll humour myself and try it later today.
 
If I'm not mistaken, first time with anything else than Direct3D?

may this be the end of DirectX (I hope) ?
Well, it's right there in the announcement:
Note that the Vulkan test replaces the Mantle test found in previous versions of 3DMark.

So yes, you are mistaken. Also, this seems to be used just for the API overhead test. It's also a little over a year after Vulkan has been made available. Hardly the death knell for DX (though, I'd prefer an open, cross platform API be the norm).


Edit: Ha, the API overhead test is not available in the free version. Joke's on me.
 
Last edited:
DX12 introduction is slow too.
Vulkan is often chosen above DX12, game engines are often sold so when the first Vulkan based engine is finished properly then we'll see a lot of vulkan games out there.
and or DX12

Often? Like in two games only? Doom and The Talos Principle? As much as I like Vulkan and cross platform graphics APIs, Vulkan has approximately the same traction as OpenGL before it.

(Dota 2 - a port from D3D, vkQuake - a joke, Roblox - another joke, Star Citizen - not sure if it ever gets a release).

People fail not understand one extremely important thing: coding for Vulkan/D3D is like going from Java to assembler: enormous complexity, very difficult to debug and often zero or negative gains over D3D 11/OpenGL 4.5 unless you're very talented.

Also D3D11 applications run equally fast on both* vendors unless you seriously f*cked up, however for Vulkan/D3D12 you have to find ways to make your code run equally fast on two substantially different hardware implementations.

*Sorry, I've never mentioned Intel but they have no worthy GPUs whatsoever.
 
Last edited:
My results with my current system:

apioverheadtestdx11-12-vulkan.png
 
If I'm not mistaken, first time with anything else than Direct3D?

may this be the end of DirectX (I hope) ?
Mantel was great. AMD did a great job. MS tried to stop it with DX12. DX12 seems to have many Mantel similarities.

Then Vulcan (Mantel Re named) comes out. Offers better fps, visuals and dev friendly. Versus DX12. And it's multi platform.

Vulcan is the obvious choice.
 
Futuremark is becoming a joke with this second advertisement of Nvidia cards. Time Spy was the first one.
 
Plenty of devs went DX12 over Vulkan as DX12 was more fully featured initially. I feel this will start to drop as Vulkan has started adding missing features, as what self-serving studio would limit its audience when it can more easily target other platforms?

(For anyone about to mention OpenGL - OGL was a joke).
 
Mantel was great. AMD did a great job. MS tried to stop it with DX12. DX12 seems to have many Mantel similarities.

Then Vulcan (Mantel Re named) comes out. Offers better fps, visuals and dev friendly. Versus DX12. And it's multi platform.

Vulcan is the obvious choice.

Care to explain that?

Also, it's Vulkan and Mantle.
 
I had to install the 378.92 drivers before the API overhead test would run, but it definitely gave the best results using Vulkan.

And why is there already butt hurt going on? If Mantle = Vulkan, i say thanks AMD and bring it on devs. :P
 
Care to explain that?

Also, it's Vulkan and Mantle.
Explain what?

Vulcan is pretty much Mantle.
* Vulkan is derived from and built upon components of AMD' s Mantle API, which was donated by AMD to Khronos!!!

Vulcan is Multi - Platform. DX12 is not.
DX12 has many similarities to Mantle.

One key Vulcan benefit: Vulkan is also able to better distribute work amongst multiple CPU cores.
Multi Threading = Vulcan and the future of PC Gaming.
Etc.,......
 
Last edited:
Vulkan will be great, mainly because consoles run on AMD hardware, and GCN chips proven to show the very best potential on Vulkan platform. See Doom for example on AMD cards. They show greater FPS and lower latencies compared to DX.
 
Vulkan will be great, mainly because consoles run on AMD hardware, and GCN chips proven to show the very best potential on Vulkan platform. See Doom for example on AMD cards. They show greater FPS and lower latencies compared to DX.
Yes but Vulcan based Benchmarks also show significant performance on Nvidia GPU's too. It's really a Win Win situation for everybody.
 
It's only showing the overhead caused by different API's right? It should score better in the end on AMD hardware.
 
It's only showing the overhead caused by different API's right? It should score better in the end on AMD hardware.
I'm not sure about that. I've seen many gaming Benchmarks that show better performance and visuals all across the board regardless of hardware used. Though you could be right.

Perhaps TechPowerUp can do some Vulcan testing. @ 1080p and 1440p.

1440p being the next screen tech to replace 1080p.
 
API Overhead test

Aka the overhead in between DX11, DX12 and Vulkan, former Mantle.

So it should technically perform better on AMD hardware. That's my point :P

Doom is a good example on practical use in various API's. Vulkan works best.
 
Aka the overhead in between DX11, DX12 and Vulkan, former Mantle.

So it should technically perform better on AMD hardware. That's my point :p

Doom is a good example on practical use in various API's. Vulkan works best.
Ah OK I now understand your point. Lol
 
eople fail not understand one extremely important thing: coding for Vulkan/D3D is like going from Java to assembler: enormous complexity, very difficult to debug and often zero or negative gains over D3D 11/OpenGL 4.5 unless you're very talented.
Common man, don't insert Java into discussion. JAVA is the worst invention of humanity after Politics and Religion. Common! Lazy programmers are using Java.
Cannot compare Vulkan with D3D12. ;)
 
Back
Top