AMDVLK Driver Lands Half-Float Additions, Many Other Improvements

Written by Michael Larabel in Radeon on 27 May 2018 at 07:30 AM EDT. 3 Comments
RADEON
There's been another weekly-ish public code push to the AMDVLK open-source AMD Vulkan Linux driver stack and this time around it's heavy on feature work.

There has been a fair amount of changes pertaining to half-float (FP16) support including support for the AMD_gpu_shader_half_float extension, prepping for VK_AMD_gpu_shader_half_float_fetch, FP16 interpolation intrinsics and register settings, and more.

This latest public code drop is also important as it now enables on-chip geometry shader by default for all GFX6 through GFX8 hardware, basically all pre-Vega GCN hardware.

There is also a barrier optimization, supporting dual source blends within the LLPC compiler, a Rise of the Tomb Raider workaround/optimization, more image intrinsic work, and various fixes.

The PAL abstraction layer code was also updated on Friday with various fixes.

Those wishing to build the AMDVLK Vulkan driver from source can obtain the latest sources via GitHub.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week