Do you mean GTX680? 7970 was always way faster than GTX580.7970 has aged really well. It now beats GTX 580 in most games, while it was certainly behind it at launch. 3 GB of memory + excellent compute performance is nice for current titles.
Do you mean GTX680? 7970 was always way faster than GTX580.7970 has aged really well. It now beats GTX 580 in most games, while it was certainly behind it at launch. 3 GB of memory + excellent compute performance is nice for current titles.
I am really disappointed.Tier 1 according to hardware.fr:
http://www.hardware.fr/articles/948-6/specifications-direct3d-12.html
It seems like Conservative Rasterization Tier 2 is the only new thing Pascal is bringing above Maxwell.
Alessio why the hangup on the Resource Heap Tier? What so great about having different resource types on the same heap?I am really disappointed.
Efficient aliasing techniques? Or just simply less overhead due different heaps indirections...Alessio why the hangup on the Resource Heap Tier? What so great about having different resource types on the same heap?
As for RB-3, I hoped NV quitted with its sadomasochistic limits about constant buffer data and views :\I'm suprised that there is no GS bypass although Maxwell seems to support something similar already (In OGL).
FP16 is probably GP100 exclusive. (64 ALUs per SM, more shared-memory, FP16, FP64).
Personally I didn't expected RB T3 but I hoped for CR2-3 and Nvidia delivers CR2, so at least something.
Well now it's Polaris turn (Which I guess will be "dissapointing" too).
Is aliasing between a CB and a texture really a common thing to do?Efficient aliasing techniques?
I don't know what you mean by heap indirections, could you explain?Or just simply less overhead due different heaps indirections...
It is not only about buffers and surfaces, but also DS/RT surfaces... On tier 1 hardware of resource heap you cannot have different resource type in the same heap (https://msdn.microsoft.com/en-us/library/windows/desktop/dn986743.aspx). This limit your memory aliasing possibilities. I bet a complete general purpose aliasing opens the door of a lot of techniques and optimizations. Manual memory management is one of the key-features of D3D12 after all, and IHVs should not be afraid to give developers the possibility to implement such techniques just because they fear their driver will lose control of your hardware and so possible driver-side optimizations (the same reasoning apply to multi-GPU too, and at least one developer - Oxide - prove that developers can handle things better then drivers on complex software such today AAA games).Is aliasing between a CB and a texture really a common thing to do?
I mean the need (of the driver) to dereference resource heap pointers (never try to manually dereference a gpu address!).I don't know what you mean by heap indirections, could you explain?