Does Hardware-accelerated GPU Scheduling boost performance - Tested with RTX

DirectX 12 Game Testing - Forza Horizon 4 and Gears 5

Forza Horizon 4 PC Performance Review

DirectX 12 Game Testing - Forza Horizon 4 and Gears 5

DirectX 12 is due to explode in popularity over the next few years, especially as the DirectX 12 Ultimate standardises the API's most advanced features. Until now, DirectX 12 has been held back by its support of old DirectX 11 era graphics cards, a factor which prevented developers from fully utilising the features of newer PCs. That will change with DirectX 12 Ultimate, and that's great news for PC gamers. 

Forza Horizon 4

When Hardware-accelerated GPU Scheduling (HAGS) is enabled, Forza Horizon 4's performance is largely unimpacted. At 1080p framerates are slightly lower when HAGS is enabled. At 1440p, performance is almost identical with HAGS on/off. In contrast, 4K performance is slightly improved when HAGS is enabled. 

With Hardware-accelerated GPU Scheduling mostly impacting GPU memory, it makes sense for the feature to mostly impact scenes where memory bandwidth is a limiting factor. With this in mind, it makes sense that performance improvements are seen at 4K. For the RTX 2060, small gains can also be seen at 1440p. 

It is worth noting that Forza Horizon 4 is mostly CPU-limited at 1080p and 1440p when using our Broadwell-E based games testing system. We are working to update this system to a newer CPU platform over the coming months, as this will help alleviate CPU-based bottlenecks for our future gaming tests.  

Does Hardware-accelerated GPU Scheduling boost performance - Tested with RTX  

Gears 5

For the most part, Gears 5's PC performance appears to be unimpacted by the use of Windows 10's new Hardware-accelerated GPU Scheduling feature. At 1080p, Gears 5 can be a CPU-limited game with an RTX 2080 Ti, and given the large variance in the game's AI behaviour, performance can vary wildly on a run-to-run basis, even at Ultra settings. 


Does Hardware-accelerated GPU Scheduling boost performance - Tested with RTX  

«Prev 1 2 3 4 5 Next»

Most Recent Comments

27-06-2020, 17:47:09

Skeggz
Maybe more of an effect can be provoked when simulating a laptop-like environment, by e.g. restricting the GPU to 8 PCIe-lanes and compare the performance theretoQuote

27-06-2020, 17:51:46

WYP
Quote:
Originally Posted by Skeggz View Post
Maybe more of an effect can be provoked when simulating a laptop-like environment, by e.g. restricting the GPU to 8 PCIe-lanes and compare the performance thereto
That's an interesting hypothesis. Definitely something that's worth investigating.Quote

30-06-2020, 15:58:15

GuardianApe
No input lag tested? It would be nice to see if input lag improved under 100% gpu utilization or some situation like that.Quote

30-06-2020, 18:51:07

NeverBackDown
For anyone looking into a slightly more in depth explanation of exactly what this does MS wrote a blog.
https://devblogs.microsoft.com/direc...pu-scheduling/

While we may not see many performance differences now we can in the future as drivers get better at handling the new offloading work from the CPU. Early drivers after all and they are still going through validation and testing on MS's end. Nvidia and AMD may have the support but doesn't necessarily mean it'll do anything.Quote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.