summaryrefslogtreecommitdiffstats
path: root/src/amd/common
Commit message (Expand)AuthorAgeFilesLines
* ac/llvm: drop pointless wrappers around umsb/imsbDave Airlie2017-10-261-14/+2
* ac/llvm: consolidate find lsb function.Dave Airlie2017-10-263-29/+36
* ac/llvm: drop v4f32empty. (v2)Dave Airlie2017-10-261-12/+0
* ac/llvm: add i1false/i1true to common code.Dave Airlie2017-10-263-41/+33
* ac/llvm: use the ac i32 0/1 and f32 0/1 llvm types.Dave Airlie2017-10-261-60/+52
* ac/nir: move lds declaration/load/store into shared code.Dave Airlie2017-10-263-41/+50
* ac/nir: generate correct instruction for atomic min/max on unsigned imagesMatthew Nicholls2017-10-251-2/+4
* ac: add support for explicit component packingTimothy Arceri2017-10-251-16/+52
* radeonsi: postponed KILL isn't postponed anymore, but maintains WQMMarek Olšák2017-10-242-0/+8
* ac: use llvm.amdgcn.kill with LLVM 6.0Marek Olšák2017-10-241-0/+6
* ac: replace ac_build_kill with ac_build_kill_if_falseMarek Olšák2017-10-243-26/+11
* ac: Silence a compiler warning about results[0].Eric Anholt2017-10-231-0/+1
* ac: Fix a compiler warning for possibly undefined "name"Eric Anholt2017-10-231-1/+1
* amd/common/gfx9: workaround DCC corruption more conservativelyNicolai Hähnle2017-10-231-7/+25
* ac/nir: Only clamp shadow reference on radeonsi.Bas Nieuwenhuizen2017-10-233-2/+8
* ac/nir: Fix nir_texop_lod on GFX for 1D arrays.Bas Nieuwenhuizen2017-10-231-1/+3
* radv/ac/nir: only emit tess factors to storage if tes reads themDave Airlie2017-10-232-2/+3
* ac/nir: Account for compact array index in GS input load from LDS.Bas Nieuwenhuizen2017-10-211-1/+1
* ac/nir: Set larged wrokgroup size for GS on GFX9.Bas Nieuwenhuizen2017-10-211-1/+1
* ac/nir: Take the max workgroup size of all provided shaders.Bas Nieuwenhuizen2017-10-211-1/+6
* radv: Expose VK_EXT_global_priorityAndres Rodriguez2017-10-212-0/+2
* nir: Get rid of nir_shader::stageJason Ekstrand2017-10-202-21/+21
* ac/nir: Fix up GS input vgprs.Bas Nieuwenhuizen2017-10-201-0/+15
* ac/nir: Add loading from LDS for merged GS.Bas Nieuwenhuizen2017-10-201-15/+21
* ac/nir: Add ES output to LDS for GFX9.Bas Nieuwenhuizen2017-10-201-8/+49
* ac/nir: Add merged GS function.Bas Nieuwenhuizen2017-10-201-17/+63
* ac/nir: init full exec mask for merged shaders.Dave Airlie2017-10-203-0/+12
* ac: move some code out of loop in store_tcs_output()Timothy Arceri2017-10-201-5/+5
* radv: Add code to compile merged shaders.Bas Nieuwenhuizen2017-10-191-0/+1
* ac/nir: Add LS-HS input VGPR workaround.Bas Nieuwenhuizen2017-10-191-0/+18
* ac/nir: Compile the bodies of multiple shaders.Bas Nieuwenhuizen2017-10-191-50/+83
* ac/nir: Expand user SGPR descriptions a bit.Bas Nieuwenhuizen2017-10-191-3/+3
* ac/nir: Don't write to the dynamic HS word on GFX9.Bas Nieuwenhuizen2017-10-191-11/+16
* ac/nir: Add function creation for merged LS+HS.Bas Nieuwenhuizen2017-10-191-76/+178
* ac/nir: Make scan_shader_output_decl less dependent on the context.Bas Nieuwenhuizen2017-10-191-14/+17
* ac/nir: Allow ac_shader_variant_info to contain info about multiple stages.Bas Nieuwenhuizen2017-10-191-1/+1
* ac/nir: Change interface to allow multiple source shaders.Bas Nieuwenhuizen2017-10-192-38/+47
* ac/nir: Add HS calling convention.Bas Nieuwenhuizen2017-10-191-1/+4
* ac: Parse the new HS RSRC1 register.Bas Nieuwenhuizen2017-10-191-0/+1
* ac: clean up ac_build_indexed_load function interfacesMarek Olšák2017-10-173-36/+42
* ac: add radeon_info::has_sync_filecros-mesa-17.2.3-vanillachadv/cros-mesa-17.2.3-vanillaMarek Olšák2017-10-122-0/+2
* ac/surface: add ac_surface::is_displayableMarek Olšák2017-10-122-0/+13
* amd: move r600d_common.h into r600gMarek Olšák2017-10-091-135/+0
* radeonsi: shrink r600d_common.h and stop using itMarek Olšák2017-10-092-165/+17
* ac: properly document a buffer.store LLVM workaroundMarek Olšák2017-10-062-6/+9
* ac: silence a warningMarek Olšák2017-10-041-1/+3
* radv: emit fmuladd instead of fma to llvm.Dave Airlie2017-10-041-1/+1
* amd/common: move ac_build_phi from radeonsiNicolai Hähnle2017-10-022-0/+19
* radeonsi: clamp depth comparison value only for fixed point formatsNicolai Hähnle2017-09-291-0/+2
* amd/common: save an instruction in the build_cube_select sequenceNicolai Hähnle2017-09-291-5/+6