RADV Driver Gets Big Patch Series For 8-bit & 16-bit Arithmetic, 8-bit Storage

[phoronix]

Phoronix: RADV Driver Gets Big Patch Series For 8-bit & 16-bit Arithmetic, 8-bit Storage

A set of 38 patches have been sent out that wire in support for the VK_KHR_shader_float16_int8, VK_AMD_gpu_shader_half_float, VK_AMD_gpu_shader_int16, and VK_KHR_8bit_storage extensions...

http://www.phoronix.com/scan.php?page=news_item&px=RADV-8-bit-16-bit-Extensions

[brent]

However, the half-floats support needs LLVM 8.0 or newer due to bugs on LLVM 7.

Sigh. Hopefully, the LLVM release schedule will improve so that we don't have anything like that in the future.

Note that LLVM 8.0.0 isn't even released yet and at the same time there is no further 7.0.x release planned.

[rhysk]

Great to see these feature patches from Rhys Perry, who I understand is a newer and for now independent Mesa developer

[xxmitsu]

He seems to be a knowledgeable person. Mesa and also LLVM. Hope we'll see more contributions from him for Radeons.

[shmerl]

What's the story with radv and adaptive sync? I don't have a VRR monitor, so can't test it. Does it already work or not?

[FireBurn]

What's the story with radv and adaptive sync? I don't have a VRR monitor, so can't test it. Does it already work or not?

What's the got to do with these patches?

[shmerl]

What's the got to do with these patches?

The question is about radv. If you don't know the answer, no point to reply.