How Much Video RAM Is Needed For Catalyst R3 Graphics?

[gens]

just to correct
pages can be greater then 4k

for amd64
"The virtual addresses are divided as follows: 16 bits unused, nine bits each for four tree levels (for a total of 36 bits), and the 12 lowest bits directly copied to the result. With 2 MB pages, there are only three levels of page table, for a total of 27 bits used in paging and 21 bits of offset. Some newer CPUs also support a 1 GB page with two levels of paging and 30 bits of offset."

wiki has some pictures on this

[bridgman]

The GPU uses a different MMU (look for references to "GPUVM")...

The only case where GPU has the same MMU options as CPU is when running under HSA, where the IOMMUv2 hardware shares the CPU's page tables (at least under Linux).

[gens]

Thank you

[Kivada]

This is one of the most interesting phoronix articles I've seen in a while. I'm quite surprised that there is little return in using more than 512MB. Does this mean that there would also be little different in performance between a GPU with 512MB vs 1024MB using the same processing unit?

I wouldn't think so because otherwise it simply wouldn't make sense to get the 2048MB version of cards intead of the 1024MB, where we do see a performance difference. There must be some other bottle neck going on. Could it be the bus? Or is it something inherent to how APUs work?

Any insight would be most welcome.

Why would this be surprising? You only have 128 shaders @ 600mhz to work with, compare that to the A10-7850K's 512 shaders running at 720Mhz or the R9 290x's 2816 shaders running at 1Ghz.

These Athlon/Sempron GPUs are enough for older and less demanding titles at lower detail settings. In games that can actually run at a playable framerate you'll hit either max out what those shaders can do or the memory bandwidth for these IGPs.

What is surprising is what they actually can run adequately.

[fuzz]

The GPU uses a different MMU (look for references to "GPUVM")...

The only case where GPU has the same MMU options as CPU is when running under HSA, where the IOMMUv2 hardware shares the CPU's page tables (at least under Linux).

What's the status for HSA with the open source drivers? Is it something that needs to be added or will it just work? HSA is a huge thing and I'd love to see it along with OpenCL 2.0 on radeon.

EDIT:
Spoke too soon? Found this:

https://github.com/HSAFoundation/Linux-HSA-Drivers-And-Images-AMD