aboutsummaryrefslogtreecommitdiffstats
path: root/src/compiler/nir
Commit message (Expand)AuthorAgeFilesLines
* nir: Make nir_constant a vector rather than a matrixJason Ekstrand2019-06-193-41/+40
* nir: Use reorderable access flagConnor Abbott2019-06-191-4/+12
* nir: Add a helper to determine if an intrinsic can be reorderedConnor Abbott2019-06-193-11/+13
* nir: Add reorderable memory access enumConnor Abbott2019-06-191-1/+2
* nir/copy_prop_vars: Ignore volatile accessesConnor Abbott2019-06-191-0/+13
* glsl/nir: Propagate access qualifiersConnor Abbott2019-06-191-1/+0
* nir: Allow qualifiers on copy_deref and image instructionsConnor Abbott2019-06-196-12/+48
* nir: add a vectorization passConnor Abbott2019-06-183-0/+456
* nir/lower_tex: Add a way to lower TXS(non-0-LOD) instructionsBoris Brezillon2019-06-182-0/+52
* nir/lower_tex: Update ->sampler_dim value before calling get_texture_size()Boris Brezillon2019-06-181-2/+5
* nir/lower_tex: Actually report when projector lowering happenedBoris Brezillon2019-06-181-4/+4
* nir: detect more dynamically uniform expressionsIago Toral Quiroga2019-06-141-0/+13
* nir: Don't manually index intrinsic index enumConnor Abbott2019-06-131-20/+20
* nir: add intrinsics for AMD_shader_ballotDaniel Schürmann2019-06-133-0/+31
* nir/opt_algebraic: Fix rules for imadsh_mix16Eduardo Lima Mitev2019-06-101-2/+2
* nir: fix s/&&/||/ typoEric Engestrom2019-06-071-1/+1
* nir_algebraic: Add basic optimizations for umul_low and imadsh_mix16Eduardo Lima Mitev2019-06-072-0/+55
* nir/opcodes: Add new 'umul_low' and 'imadsh_mix16' opcodesEduardo Lima Mitev2019-06-071-1/+14
* nir/propagate_invariant: Don't add NULL vars to the hash tableJason Ekstrand2019-06-061-1/+10
* nir: Combine lower_fmod16/32 back into a single lower_fmod.Kenneth Graunke2019-06-052-5/+4
* nir: Drop lower_fmod64 option.Kenneth Graunke2019-06-052-2/+0
* nir: Don't replace the nir_shader when NIR_TEST_SERIALIZE=1Jason Ekstrand2019-06-052-10/+16
* nir: Don't replace the nir_shader when NIR_TEST_CLONE=1Jason Ekstrand2019-06-052-2/+42
* nir/algebraic: Simplify max(abs(a), 0.0) -> abs(a)Alyssa Rosenzweig2019-06-041-0/+1
* nir/vars_to_ssa: Handle UNDEF_NODE in more placesCaio Marcelo de Oliveira Filho2019-06-031-4/+8
* nir: Add functions to subtract and compare addressesCaio Marcelo de Oliveira Filho2019-06-032-0/+54
* nir: Add nir_ball_iequal() helperCaio Marcelo de Oliveira Filho2019-06-031-0/+13
* nir: copy intrinsic type when lowering load input/uniform and store outputJonathan Marek2019-06-031-0/+2
* nir: Return nir_type_invalid for non-numeric base typesCaio Marcelo de Oliveira Filho2019-05-311-2/+14
* nir: remove bool lowering from lower_int_to_floatJonathan Marek2019-05-311-71/+42
* nir: fix lower_{int,bool}_to_float for new mov opcodeJonathan Marek2019-05-312-0/+2
* nir: add lower_bitshift optionJonathan Marek2019-05-312-3/+8
* nir: fix gather_ssa_typesJonathan Marek2019-05-311-36/+52
* nir: add type information to load uniform/input and store output intrinsicsJonathan Marek2019-05-314-10/+42
* nir/instr_set: Use _mesa_set_search_or_add()Connor Abbott2019-05-311-5/+3
* nir: Rematerialize compare instructionsIan Romanick2019-05-313-0/+184
* nir: Add a shallow clone function for nir_alu_instrIan Romanick2019-05-312-0/+23
* nir: Actually propagate progress in nir_opt_move_load_ubo.Bas Nieuwenhuizen2019-05-311-1/+1
* nir/split_vars: Properly bail in the presence of complex derefsJason Ekstrand2019-05-311-9/+106
* nir/vars_to_ssa: Properly ignore variables with complex derefsJason Ekstrand2019-05-311-14/+64
* nir/vars_to_ssa: Use a non-null UNDEF_NODE pointerJason Ekstrand2019-05-311-3/+5
* nir/deref: Add a has_complex_use helperJason Ekstrand2019-05-312-0/+79
* nir/dead_cf: Call instructions aren't deadJason Ekstrand2019-05-311-1/+1
* nir: Accept nir_var_mem_global in derefs used by phisCaio Marcelo de Oliveira Filho2019-05-301-1/+2
* nir: silence three compiler warnings seen with MinGWBrian Paul2019-05-292-4/+2
* nir: Allow derefs to be used as phi sourcesCaio Marcelo de Oliveira Filho2019-05-293-2/+17
* nir/lower_non_uniform: safely iterate over blocksLionel Landwerlin2019-05-281-1/+1
* st/nir: Re-vectorize shader IOKenneth Graunke2019-05-281-0/+6
* nir: Drop imov/fmov in favor of one mov instructionJason Ekstrand2019-05-2422-50/+38
* nir/builder: Merge nir_[if]mov_alu into one nir_mov_alu helperJason Ekstrand2019-05-244-30/+12
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-04 07:30:15 +0000