Gitiles
Code Review
Sign In
gerrit-public.fairphone.software
/
platform
/
external
/
mesa3d
/
281262281b7fc76016fa216f9c9a6a16a564206d
/
src
/
amd
/
vulkan
/
radv_shader.c
2812622
radv/aco: enable VK_EXT_shader_demote_to_helper_invocation
by Daniel Schürmann
· 5 years ago
a70a998
radv/aco: Setup alternate path in RADV to support the experimental ACO compiler
by Daniel Schürmann
· 5 years ago
0692ae3
ac: move ac_get_num_physical_sgprs into radeon_info
by Marek Olšák
· 5 years ago
ca43006
ac: move ac_get_max_wave64_per_simd into radeon_info
by Marek Olšák
· 5 years ago
5ebc764
radv/gfx10: adjust the GS NGG scratch size for streamout
by Samuel Pitoiset
· 5 years ago
a15b3bc
radv/gfx10: add an option to switch from legacy to NGG streamout
by Samuel Pitoiset
· 5 years ago
5387667
radv/gfx10: declare a LDS symbol for the NGG emit space
by Samuel Pitoiset
· 5 years ago
a9af11f
radv: fill shader info for all stages in the pipeline
by Samuel Pitoiset
· 5 years ago
d95afd8
radeonsi/gfx10: fix wave occupancy computations
by Marek Olšák
· 5 years ago
83499ac
radv: merge radv_shader_variant_info into radv_shader_info
by Samuel Pitoiset
· 5 years ago
9367d2c
nir: allow specifying filter callback in lower_alu_to_scalar
by Vasily Khoruzhick
· 5 years ago
3f5b541
radv: Call nir_propagate_invariant()
by Connor Abbott
· 5 years ago
71a6794
ac/nir: Enable nir_opt_large_constants
by Connor Abbott
· 5 years ago
5dadbab
radv/radeonsi: Don't count read-only data when reporting code size
by Connor Abbott
· 5 years ago
cc3d36b
radv: remove radv_init_llvm_target() helper
by Samuel Pitoiset
· 5 years ago
8d44f83
radv: move lowering PS inputs/outputs at the right place
by Samuel Pitoiset
· 5 years ago
151d699
radv: gather info about PS inputs in the shader info pass
by Samuel Pitoiset
· 5 years ago
49f5ddd
radv: make use of has_ls_vgpr_init_bug
by Samuel Pitoiset
· 5 years ago
2b9c371
ac: add cpdma_prefetch_writes_memory to ac_gpu_info
by Samuel Pitoiset
· 5 years ago
1fd60db
ac,radv,radeonsi: remove LLVM 7 support
by Samuel Pitoiset
· 5 years ago
e73d863
radv: allow to enable VK_AMD_shader_ballot only on GFX8+
by Samuel Pitoiset
· 5 years ago
2e763f7
radv: Use correct vgpr_comp_cnt for VS if both prim_id and instance_id are needed.
by Bas Nieuwenhuizen
· 5 years ago
7740149
nir: merge and extend nir_opt_move_comparisons and nir_opt_move_load_ubo
by Rhys Perry
· 5 years ago
8874af8
radv: Keep shader info when needed.
by Bas Nieuwenhuizen
· 5 years ago
5444d3e
radv: Use string for nir dumping.
by Bas Nieuwenhuizen
· 5 years ago
739a288
radv: Get max workgroup size without nir.
by Bas Nieuwenhuizen
· 5 years ago
290ca0c
radv: Add utility function to calculate max waves.
by Bas Nieuwenhuizen
· 5 years ago
ba8d3c3
radv: Properly use Wave64 for non-NGG GS and copy shader.
by Bas Nieuwenhuizen
· 5 years ago
035406e
radv: Put wave size in shader options/info.
by Bas Nieuwenhuizen
· 5 years ago
72e7b7a
ac/nir,radv: Optimize bounds check for 64 bit CAS.
by Bas Nieuwenhuizen
· 5 years ago
96a5445
radv/gfx10: use the correct target machine for Wave32
by Samuel Pitoiset
· 5 years ago
8a86908
radv/gfx10: add Wave32 support for vertex, tessellation and geometry shaders
by Samuel Pitoiset
· 5 years ago
953bbac
radv/gfx10: add Wave32 support for fragment shaders
by Samuel Pitoiset
· 5 years ago
ea38565
radv/gfx10: add Wave32 support for compute shaders
by Samuel Pitoiset
· 5 years ago
45638e1
radv: Don't include radv_private.h from radv_shader.h
by Daniel Schürmann
· 5 years ago
a69ab1b
radv: Delete unused local variables in optimization loop
by Connor Abbott
· 5 years ago
09abe57
radv/gfx10: emit streamout shader config
by Samuel Pitoiset
· 5 years ago
ea337c8
radv/gfx10: fix VS input VGPRs with the legacy path
by Samuel Pitoiset
· 5 years ago
9343c93
radv: fix dumping disassembly with RADV_DEBUG=shaders
by Samuel Pitoiset
· 5 years ago
64b7386
radv: move nir_opt_conditional_discard out of optimization loop
by Daniel Schürmann
· 5 years ago
451f030
radv: Fix uninitialized warning.
by Bas Nieuwenhuizen
· 5 years ago
921c1d2
ac/rtld: add support for Wave32
by Marek Olšák
· 5 years ago
2ac2b98
radv: fix crash in shader tracing.
by Dave Airlie
· 5 years ago
a20a9d0
radv: dont store disasm string unless keep_shader_info flag set
by Timothy Arceri
· 5 years ago
07ff367
radv/gfx10: implement VK_EXT_post_depth_coverage
by Samuel Pitoiset
· 5 years ago
edf1af6
radv/gfx10: fallback to the legacy path if tess and extreme geometry
by Samuel Pitoiset
· 5 years ago
ed12be1
radv/gfx10: enable OC_LDS_EN for NGG GS if the ES stage is TES
by Samuel Pitoiset
· 5 years ago
f0a90ed
radv/gfx10: allocate ESGS ring space for exporting PrimitiveID
by Samuel Pitoiset
· 5 years ago
e68b55f
radv/gfx10: set HS/GS/CS.WGP_MODE
by Samuel Pitoiset
· 5 years ago
2b6a089
radv: tidy up radv_get_shader_name() and add NGG stages
by Samuel Pitoiset
· 5 years ago
5bbcb3f
radv/gfx10: implement support for GS as NGG
by Samuel Pitoiset
· 5 years ago
7286865
radv/gfx10: Use correct ES shader for es_vgpr_comp_cnt for GS.
by Bas Nieuwenhuizen
· 5 years ago
f18b8a1
radv: Don't optimize after lowering FS inputs
by Connor Abbott
· 5 years ago
3f50007
radv: set correct number of VGPRs for GS on GFX10
by Samuel Pitoiset
· 5 years ago
d2a8b63
radv: fix computing the number of ES VGPRS for TES on GFX10
by Samuel Pitoiset
· 5 years ago
795adbb
radv/gfx10: Add pipeline state support for tess.
by Bas Nieuwenhuizen
· 5 years ago
118a66d
radv: Use NIR barycentric intrinsics
by Connor Abbott
· 5 years ago
27f0c3c
radv: Make FragCoord a sysval
by Connor Abbott
· 5 years ago
e41e932
radv: Lower input attachments in NIR.
by Daniel Schürmann
· 5 years ago
ee21bd7
radv/gfx10: implement NGG support (VS only)
by Samuel Pitoiset
· 5 years ago
aeb5b1a
radv/gfx10: Set MEM_ORDERED flags on shaders.
by Bas Nieuwenhuizen
· 5 years ago
352365c
radv/gfx10: do not set stream output shader config
by Samuel Pitoiset
· 5 years ago
4c82094
radv/gfx10: implement radv_fill_shader_variant()
by Samuel Pitoiset
· 5 years ago
5ff651c
radv: Move more stuff to variant create time.
by Bas Nieuwenhuizen
· 5 years ago
726a31d
radv: Add the concept of radv shader binaries.
by Bas Nieuwenhuizen
· 5 years ago
43f2f01
radv: Add export_prim_id to the shader variant info.
by Bas Nieuwenhuizen
· 5 years ago
7469516
radv: Merge rsrc1/rsrc2 fields with the config fields.
by Bas Nieuwenhuizen
· 5 years ago
74a26af
amd/common/gfx10: add register JSON
by Nicolai Hähnle
· 5 years ago
456557a
nir: Add lower_rotate flag and set to true in all drivers
by Sagar Ghuge
· 5 years ago
d8b079e
radv: rework how the number of VGPRs is computed
by Samuel Pitoiset
· 5 years ago
f4d2c47
radv: the number of VGPR_COMP_CNT for GS is expected to be 0 on GFX8
by Samuel Pitoiset
· 5 years ago
b4477fa
radv: reduce number of VGPRs for TESS_EVAL if primitive ID is not used
by Samuel Pitoiset
· 5 years ago
0daeb1d
amd/common: lower bitfield_extract to ubfe/ibfe.
by Daniel Schürmann
· 6 years ago
48a75e7
amd/common: lower bitfield_insert to bfm & bitfield_select
by Daniel Schürmann
· 6 years ago
c58dff7
radv: enable AMD_shader_ballot with RADV_PERFTEST_SHADER_BALLOT ('shader_ballot')
by Daniel Schürmann
· 6 years ago
7a858f2
spirv/nir: add support for AMD_shader_ballot and Groups capability
by Daniel Schürmann
· 6 years ago
f480b8a
amd/common: use generated register header
by Nicolai Hähnle
· 5 years ago
e45bf01
spirv: Change spirv_to_nir() to return a nir_shader
by Caio Marcelo de Oliveira Filho
· 5 years ago
a3bfdac
radv: Don't re-use entry_point pointer from spirv_to_nir
by Caio Marcelo de Oliveira Filho
· 5 years ago
31a7476
spirv, radv, anv: Replace ptr_type with addr_format
by Caio Marcelo de Oliveira Filho
· 5 years ago
d750183
radv: add a workaround for Monster Hunter World and LLVM 7&8
by Samuel Pitoiset
· 5 years ago
ccfcb9d
ac: rename SI-CIK-VI to GFX6-GFX7-GFX8
by Marek Olšák
· 5 years ago
d0bff89
nir: allow specifying a set of opcodes in lower_alu_to_scalar
by Jonathan Marek
· 5 years ago
1f1007a
nir: Initialize lower_flrp_progress everywhere
by Ian Romanick
· 5 years ago
e19a8fe
radv: call constant folding before opt algebraic
by Timothy Arceri
· 5 years ago
d41cdef
nir: Use the flrp lowering pass instead of nir_opt_algebraic
by Ian Romanick
· 6 years ago
06c9d7f
radv: enable descriptor indexing capabilities
by Juan A. Suarez Romero
· 5 years ago
5c3467e
radv: Run the new ycbcr lowering pass.
by Bas Nieuwenhuizen
· 5 years ago
b3e3440
radv: add VK_NV_compute_shader_derivates support
by Samuel Pitoiset
· 5 years ago
9cf55b0
radv: add VK_KHR_shader_atomic_int64 but disable it for now
by Samuel Pitoiset
· 5 years ago
ecbe6cb
radv: sort the shader capabilities alphabetically
by Samuel Pitoiset
· 5 years ago
14f0397
radv: enable VK_KHR_shader_float16_int8
by Samuel Pitoiset
· 5 years ago
e30804c
nir/radv: remove restrictions on opt_if_loop_last_continue()
by Timothy Arceri
· 5 years ago
c25f638
radv: partially enable VK_KHR_shader_float16_int8
by Samuel Pitoiset
· 5 years ago
0af95f0
radv: lower 16-bit flrp
by Rhys Perry
· 6 years ago
8a6e61c
radv: do not lower frexp_exp and frexp_sig
by Samuel Pitoiset
· 6 years ago
23d30f4
spirv,nir: lower frexp_exp/frexp_sig inside a new NIR pass
by Samuel Pitoiset
· 6 years ago
037f11d
radv: enable VK_KHR_8bit_storage
by Rhys Perry
· 6 years ago
08f804e
anv,radv,turnip: Lower TG4 offsets with nir_lower_tex
by Jason Ekstrand
· 6 years ago
71ffa00
radv: enable lower_mul_2x32_64
by Samuel Pitoiset
· 6 years ago
Next »