mesa/src/intel/vulkan/grl
Lionel Landwerlin e9fa840eed anv: implement EDS2.extendedDynamicState2PatchControlPoints
We make the compiler assume the worst possible case (it's not great
because we have to burn 32 GRFs of potential input data) and then we
push the actual value through push constants.

This enables VK_EXT_gpl usage on zink, which causes two traces to change
their results.  Raven is an imperceptible change, blender has missing
original pngs but looks plausible.

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22378>
2023-05-24 18:32:07 +00:00
..
gpu
include anv/grl: Use union for reinterpreting integer as float 2023-02-14 12:59:44 +00:00
.gitignore anv: adding parsetab.py to the .gitignore for grl 2022-10-20 02:24:39 +00:00
genX_grl.h anv: compute the largest GRL kernel scratch size 2023-03-31 14:18:58 +00:00
genX_grl_dispatch.c anv: implement EDS2.extendedDynamicState2PatchControlPoints 2023-05-24 18:32:07 +00:00
genX_grl_uuid.cpp intel/vk/grl: genX-ify genX_grl_uuid.cpp 2023-03-03 21:37:19 +00:00
grl_cl_kernel_gen.py intel/vk/grl: genX-ify grl_cl_kernel_name() 2023-03-03 21:37:19 +00:00
grl_metakernel_gen.py intel/genxml: Add genX_rt_pack.h 2022-12-09 01:43:39 +00:00
grl_parser.py
grl_structs.h anv: Build BVHs on the GPU with GRL 2022-09-28 05:38:37 +00:00
meson.build intel: Disable shader cache when executing intel_clc during the build 2023-05-11 23:00:01 +00:00