Gitiles
Code Review Sign In
gerrit-public.fairphone.software / platform / external / mesa3d / cae1be954cadbe0535a3147009072c46662ab198 / src / compiler / nir
  1. 39098a2 nir/lower_memory_model: do not break with global atomic operations by Samuel Pitoiset · 4 years ago
  2. de14090 nir/lower_memory_model: return progress when visiting instructions by Samuel Pitoiset · 4 years ago
  3. ee073cb nir/load_store_vectorize: improve vectorization with identical operations by Rhys Perry · 4 years, 3 months ago
  4. a3177cc nir: Add a lowering pass to lower memcpy by Jason Ekstrand · 4 years ago
  5. b2899f7 nir: Add a new memcpy intrinsic by Jason Ekstrand · 4 years ago
  6. 09bca4c vtn/opencl: Switch some nir-sequence ops to use libclc by Jesse Natalie · 4 years, 1 month ago
  7. 93db59e nir: Add an internal flag to shader_info by Jesse Natalie · 4 years, 1 month ago
  8. 0206fb3 nir/liveness: Consider if uses in nir_ssa_defs_interfere by Jason Ekstrand · 4 years ago
  9. a18c84e nir/instr_set: hash intrinsic sources by Rhys Perry · 4 years, 1 month ago
  10. ea77958 nir: gather information about fbfetch and dual source color by Marek Olšák · 4 years ago
  11. a6abf17 nir: fix input/output info gathering for lowered IO by Marek Olšák · 4 years ago
  12. ef98c17 nir: gather fs.uses_sample_qualifier from lowered IO by Marek Olšák · 4 years ago
  13. 7b108e6 nir: set system_values_read for all intrinsics by Marek Olšák · 4 years ago
  14. abe9588 nir: gather tess.tcs_cross_invocation info from lowered IO intrinsics by Marek Olšák · 4 years ago
  15. 10be706 nir: gather indirect info from lowered IO intrinsics by Marek Olšák · 4 years ago
  16. 140f53e Revert "nir: replace lower_ffma and fuse_ffma with has_ffma" by Kenneth Graunke · 4 years ago
  17. 939ddf3 nir: replace lower_ffma and fuse_ffma with has_ffma by Marek Olšák · 4 years ago
  18. 771aad3 nir: split lower_ffma into lower_ffma16/32/64 by Marek Olšák · 4 years ago
  19. 21174de nir: split fuse_ffma into fuse_ffma16/32/64 by Marek Olšák · 4 years ago
  20. 924e276 nir_lower_system_values: Fix load_global_invocation_id to use base_work_group_id even with no base_global id by Jesse Natalie · 4 years ago
  21. 9750164 nir: Rename get_buffer_size to get_ssbo_size by Jason Ekstrand · 4 years ago
  22. f100cf0 aco: stop multiplying driver_location by 4 by Rhys Perry · 4 years ago
  23. f2b17de nir/lower_samplers: Clamp out-of-bounds access to array of samplers by Danylo Piliaiev · 4 years, 1 month ago
  24. 0ba82f7 nir/large_constants: Eliminate out-of-bounds writes to large constants by Danylo Piliaiev · 4 years, 1 month ago
  25. 66669eb nir/lower_io: Eliminate oob writes and return zero for oob reads by Danylo Piliaiev · 4 years, 1 month ago
  26. e1fc232 nir: Add a pass for lowering CL-style image ops to texture ops by Jason Ekstrand · 4 years ago
  27. 6f2b695 nir: remove ubo_r600 instrinsic since ubo_vec4 is used now by Gert Wollny · 4 years ago
  28. 2aaa156 nir/lower_io: don't reduce range if parent length is zero by Alejandro Piñeiro · 4 years ago
  29. 2c9fee9 nir: Add option lower_uniforms_to_ubo by Gert Wollny · 4 years ago
  30. 57bf4c2 nir,radeonsi: move ffma fusing to late optimizations for better codegen by Marek Olšák · 4 years ago
  31. 00914e2 nir/algebraic: fold some nested comparisons with ball and bany by Italo Nicola · 4 years ago
  32. 656d8ed nir/opt_vectorize: don't lose exact and no_*_wrap flags by Marek Olšák · 4 years ago
  33. 50d3358 nir/algebraic: add late optimizations that optimize out mediump conversions (v3) by Marek Olšák · 4 years ago
  34. b86305b nir/algebraic: collapse conversion opcodes (many patterns) by Marek Olšák · 4 years ago
  35. cdd498b nir: add new mediump opcodes f2[ui]mp, i2fmp, u2fmp by Marek Olšák · 4 years ago
  36. 385b4db nir: enforce 32-bit src type requirement for f2fmp and i2imp by Marek Olšák · 4 years ago
  37. 3d3df8d nir: remove redundant opcode u2ump by Marek Olšák · 4 years ago
  38. 26fc5e1 nir/algebraic: expand existing 32-bit patterns to all bit sizes using loops by Marek Olšák · 4 years, 1 month ago
  39. 3c8934a nir/algebraic: add flrp patterns for 16 and 64 bits by Marek Olšák · 4 years, 1 month ago
  40. 40f7afc nir: fix lower_mediump_outputs to not require variables by Marek Olšák · 4 years ago
  41. c2ae39e nir: add mediump flag to IO semantics by Marek Olšák · 4 years ago
  42. 89401e5 nir: More NIR_MAX_VEC_COMPONENTS fixes by Jesse Natalie · 4 years ago
  43. c5dd54e nir/idiv_const: Use the modern nir_src_as_* constant helpers by Jason Ekstrand · 4 years ago
  44. d86e38a nir: More NIR_MAX_VEC_COMPONENTS fixes by Jason Ekstrand · 4 years ago
  45. 7ee5da9 nir_dominance: Use uint32_t instead of int16_t for dominance counters by Jesse Natalie · 4 years ago
  46. 641d45b nir/opt_loop_unroll: fix is_access_out_of_bounds with vectors by Rhys Perry · 4 years, 1 month ago
  47. 45bcb10 nir: Add a dominance validation pass by Jason Ekstrand · 4 years, 4 months ago
  48. 6cef804 nir/opt_if: fix opt_if_merge when destination branch has a jump by Rhys Perry · 4 years ago
  49. 1ed78bd nir: Use explicit deref information to provide real UBO ranges. by Eric Anholt · 4 years ago
  50. f3b33a5 nir: Add a range_base+range to nir_intrinsic_load_ubo(). by Eric Anholt · 4 years, 1 month ago
  51. 3a93568 nir: Update the comment about nir_lower_uniforms_to_ubo()'s multiplier. by Eric Anholt · 4 years, 1 month ago
  52. e4d75c2 nir/opt_shrink_vectors: shrink image stores using the format by Rhys Perry · 4 years, 1 month ago
  53. bd42816 nir/lower_io: Fix the unknown-array-index case in get_deref_align by Jason Ekstrand · 4 years ago
  54. a7ece63 nir/algebraic: add 16-bit versions of a few 32-bit patterns by Marek Olšák · 4 years, 1 month ago
  55. 00b28a5 nir/algebraic: trivially enable existing 32-bit patterns for all bit sizes by Marek Olšák · 4 years, 1 month ago
  56. ac55b1a nir: get ffma support from NIR options for nir_lower_flrp by Marek Olšák · 4 years, 2 months ago
  57. a083560 nir/load_store_vectorizer: Add unit tests for alignment handling. by Eric Anholt · 4 years, 1 month ago
  58. c6f7219 nir/load_store_vectorizer: Use more imm helpers in the tests. by Eric Anholt · 4 years, 1 month ago
  59. 91a8a07 nir/load_store_vectorize: rework alignment calculation by Rhys Perry · 4 years, 5 months ago
  60. aaa492e nir: fix const-cast warning on MSVC by Erik Faye-Lund · 4 years ago
  61. 9641f48 nir: Allow uniform in nir_lower_vars_to_explicit_types by Jason Ekstrand · 4 years, 1 month ago
  62. 3719b69 nir: Allow var_mem_global in nir_lower_vars_to_explicit_types by Jason Ekstrand · 4 years, 1 month ago
  63. 3135984 spirv: Propagate alignments to deref chains via casts by Jason Ekstrand · 4 years, 1 month ago
  64. e7fbec0 nir/opt_deref: Remove restrictive alignment information from casts by Jason Ekstrand · 4 years, 1 month ago
  65. 99bb2a4 nir/opt_deref: Don't remove casts with alignment information by Jason Ekstrand · 4 years, 1 month ago
  66. beefd37 nir/lower_io: Apply alignments from derefs when available by Jason Ekstrand · 4 years, 1 month ago
  67. 480329c nir: Add a helper for getting the alignment of a deref by Jason Ekstrand · 4 years, 1 month ago
  68. 0654a9e nir: Handle all array stride cases in nir_deref_instr_array_stride by Jason Ekstrand · 4 years, 1 month ago
  69. 878a8da nir: Add alignment information to cast derefs by Jason Ekstrand · 4 years, 1 month ago
  70. 9414cbc nir: Don't bail too early in lower_mem_constant_vars by Jason Ekstrand · 4 years ago
  71. 38a83a3 nir/lower_indirect_derefs: Add a threshold by Jason Ekstrand · 4 years, 2 months ago
  72. 8c43edf nir: fix a bug in is_dual_slot in nir_io_add_const_offset_to_base by Marek Olšák · 4 years, 1 month ago
  73. a06955f nir/builder: Add load/store_global helpers by Jason Ekstrand · 4 years, 4 months ago
  74. 91becd8 intel/fs: Add support for a new load_reloc_const intrinsic by Jason Ekstrand · 4 years, 1 month ago
  75. 9121afe nir/clone: Add a helper for cloning most instruction types by Jason Ekstrand · 4 years, 4 months ago
  76. f25e169 nir/opt_vectorize: Add a callback for filtering of vectorizing. by Eric Anholt · 4 years, 1 month ago
  77. 479d9c9 nir: Add simplistic lowering for bany_equal/ball_inequal. by Eric Anholt · 4 years, 9 months ago
  78. c93ade9 nir/lower_explicit_io: Assert that compute address sizes match derefs by Jason Ekstrand · 4 years, 1 month ago
  79. bb8d8ba nir: Allow opt_large_constants to be run with constant_data_size > 0 by Jason Ekstrand · 4 years, 1 month ago
  80. 4360a8a nir/lower_io: Add support for nir_var_mem_constant by Jason Ekstrand · 4 years, 1 month ago
  81. ef142c6 nir/lower_io: Add a build_addr_for_var helper by Jason Ekstrand · 4 years, 1 month ago
  82. 965c268 nir/lower_io: Use the variable mode for load_scratch_base_ptr checks by Jason Ekstrand · 4 years, 1 month ago
  83. ff124e3 nir: Add a load_global_constant intrinsic by Jason Ekstrand · 4 years, 1 month ago
  84. e4f07f8 nir: Add a new nir_var_mem_constant variable mode by Jason Ekstrand · 4 years, 1 month ago
  85. b9927c8 nir/serialize: fix serialization of system values by Karol Herbst · 4 years, 1 month ago
  86. 70cbddc nir: use enum operator helper for nir_variable_mode and nir_metadata by Karol Herbst · 4 years, 1 month ago
  87. 15da983 nir: Improve the comment on num_inputs and friends by Jason Ekstrand · 4 years, 1 month ago
  88. 4d18e71 nir: Rename num_shared to shared_size by Jason Ekstrand · 4 years, 1 month ago
  89. bc123c3 nir/algebraic: mark some optimizations with fsat(NaN) as inexact by Samuel Pitoiset · 4 years, 1 month ago
  90. b778e7b nir/vtn: Convert constant samplers to variables with data by Jesse Natalie · 4 years, 5 months ago
  91. 397730e nir/vtn: Add intrinsics for CL image format/order queries by Jesse Natalie · 4 years, 4 months ago
  92. ce6f662 nir/vtn: Add type constant to image intrinsics by Jesse Natalie · 4 years, 5 months ago
  93. 865a2ad clover/nir/spirv: Use uniform rather than shader_in for kernel inputs by Jesse Natalie · 4 years, 1 month ago
  94. 73d2c6c nir: Switch the indexing of block->live_in/out arrays. by Eric Anholt · 4 years, 2 months ago
  95. 5d2b2b5 nir: Invalidate live SSA def information when making new SSA defs. by Eric Anholt · 4 years, 1 month ago
  96. ee288f2 nir: add shared/global atomics to nir_get_io_offset_src() by Italo Nicola · 4 years, 1 month ago
  97. e281ee0 nir: Look up the shader when printing a single instruction. by Eric Anholt · 4 years, 1 month ago
  98. a3a8322 nir: Fix printing of individual instructions with io semantics. by Eric Anholt · 4 years, 1 month ago
  99. ac6b8e4 nir: Take a variable remap parameter in nir_inline_function_impl by Jason Ekstrand · 4 years, 1 month ago
  100. b6f3189 nir: Use a switch in nir_inline_function_impl by Jason Ekstrand · 4 years, 1 month ago