AMD Ravenridge Vega in a U-tier SKU vs Intel Iris Graphics 650

>>61830809
all over the place... or is the iris 650 that good?

Also forgot to mention gfxbench is reading 300MHz off Vega so it's most likely running with the Radeon GPU profiler on.

>>61830809
I'm seeing a trend of Intel doing a lot better at offscreen FPS than onscreen FPS, it's similar with a gtx1050 too.

https://gfxbench.com/compare.jsp?benchmark=gfx40&did1=53156431&os1=Windows&api1=gl&hwtype1=iGPU&hwname1=AMD+Radeon%28TM%29+Vega+10+Mobile+Graphics&D2=NVIDIA+GeForce+GTX+1050


Might just be drivers at this point.

>>61830809
what does onscreen and offscreen mean?

2months? great, warranty of my laptop expires in decembre

>>61830966


On Screen = GPU drawing operations are performed on a region of memory that goes directly to the display output. Usually also means that the memory in question is managed by the windowing system.

Off Screen = GPU drawing operations are performed on a region of memory that is not directed to the display output and is managed by the program itself. Off Screen rendering is used to generate intermediary images in computer graphics, like reflection maps, shadow maps, postprocessing filters (motion or Depth of Field blur).

>>61830902
It's really weird that it wins some graphic tests against a 1050, which alone is a 35W discrete part with GDDR5

Probably drivers, even against a Radeon part with similar shader count the performance is inconsistent.

>>61830866
Also this, who knows what the real clock is.

Could it be a memory limitation? intel has it's edram and nvidia obviously has its own vram. AMD just uses sys ram. If it's using some generic 2400 ram it could be restricting off screen, since that's a lot of framebuffer manip type stuff, which would be done in ram.

>>61831365
Most likely.

If this is the 15-20W SKU then AMD has hit a homerun

>>61830966
>>61831047
onscreen just means that bench is rendered at the device resolution, offscreen means the bench is rendered at a fixed resolution (usually 1080p)