1. c63c391 specs: Remove GLES profile interaction text from GLX_MESA_query_renderer by Adam Jackson · 6 years ago
  2. 5820e63 freedreno/ir3: Make imageStore use num components from image format by Eduardo Lima Mitev · 6 years ago
  3. 5dad1ab nir/dead_write_vars: Get modes directly from derefs by Jason Ekstrand · 6 years ago
  4. fa40a58 nir/copy_prop_vars: Get modes directly from derefs by Jason Ekstrand · 6 years ago
  5. cf7fb39 nir/lower_wpos_center: Look at derefs for modes by Jason Ekstrand · 6 years ago
  6. 867fe35 nir/lower_io_to_scalar: Look at derefs for modes by Jason Ekstrand · 6 years ago
  7. 3fe0363 nir/lower_io_arrays_to_elements: Look at derefs for modes by Jason Ekstrand · 6 years ago
  8. 8cc0f92 nir/linking_helpers: Look at derefs for modes by Jason Ekstrand · 6 years ago
  9. 8410cf6 nir/propagate_invariant: Skip unknown vars by Jason Ekstrand · 6 years ago
  10. 29e4b94 Revert "nir/lower_indirect: Bail early if modes == 0" by Ian Romanick · 6 years ago
  11. 433ca31 st/dri: replace format conversion functions with single mapping table by Lucas Stach · 7 years ago
  12. 67174d4 st/dri: allow both render and sampler compatible dma-buf formats by Lucas Stach · 7 years ago
  13. a3e592e etnaviv: use surface format directly by Lucas Stach · 6 years ago
  14. 7a90886 meson: Add toggle for glx-direct by Dylan Baker · 6 years ago
  15. 8c77f4c meson: Add support for gnu hurd by Dylan Baker · 6 years ago
  16. 6cf5f25 meson: remove duplicate definition by Dylan Baker · 6 years ago
  17. e430a03 meson: Fix ppc64 little endian detection by Dylan Baker · 6 years ago
  18. 3feda3c anv: Bump the patch version to 96 by Jason Ekstrand · 6 years ago
  19. 3c71ba3 i965: Don't override subslice count to 4 on Gen11. by Kenneth Graunke · 6 years ago
  20. af07141 intel/compiler: More peephole_select for pre-Gen6 by Ian Romanick · 7 years ago
  21. 378f996 nir/opt_peephole_select: Don't peephole_select expensive math instructions by Ian Romanick · 7 years ago
  22. 8fb8ebf intel/compiler: More peephole select by Ian Romanick · 7 years ago
  23. 09b7e1d nir/opt_peephole_select: Don't try to remove flow control around indirect loads by Ian Romanick · 7 years ago
  24. 4cd1a0b i965/vec4: Propagate conditional modifiers from more compares to other compares by Ian Romanick · 7 years ago
  25. 9a83c3d i965/fs: Eliminate unary op on operand of compare-with-zero by Ian Romanick · 7 years ago
  26. 440c051 i965/vec4/dce: Don't narrow the write mask if the flags are used by Ian Romanick · 7 years ago
  27. 111bcc8 i965/vec4: Silence unused parameter warnings in vec4 compiler tests by Ian Romanick · 7 years ago
  28. f67dea5 radv: Fix multiview depth clears by Bas Nieuwenhuizen · 6 years ago
  29. 9add63a radv: Remove redundant format check. by Bas Nieuwenhuizen · 7 years ago
  30. 708d8f4 nir: Fix clamping of uints for image store lowering. by Eric Anholt · 6 years ago
  31. 00e2cbc v3d: Fix the argument type for vir_BRANCH(). by Eric Anholt · 6 years ago
  32. 376054f vc4: Reuse nir_format_convert.h in our blend lowering. by Eric Anholt · 6 years ago
  33. 445867c radv: report Vulkan version 1.1.90 for real by Samuel Pitoiset · 6 years ago
  34. cae3731 anv,radv: Re-enable VK_EXT_pci_bus_info by Jason Ekstrand · 6 years ago
  35. e5b59fe vulkan: Update the XML and headers to 1.1.96 by Jason Ekstrand · 6 years ago
  36. ef198e8 radv: switch from nir_bcsel to nir_b32csel by Rhys Perry · 6 years ago
  37. bba94a3 radv: don't set surf_index for stencil-only images by Rhys Perry · 6 years ago
  38. 9dc135e nir: Release per-block metadata in nir_sweep by Ian Romanick · 6 years ago
  39. 7adafd6 nir: Fix holes in nir_instr by Ian Romanick · 6 years ago
  40. 8161a87 nir/phi_builder: Use per-value hash table to store [block] -> def mapping by Ian Romanick · 6 years ago
  41. e3043e1 util/hash_table: Add _mesa_hash_table_init function by Ian Romanick · 6 years ago
  42. db197fd st/nir: Use nir_src_as_uint for tokens by Jason Ekstrand · 6 years ago
  43. 47e1e06 radv: Fix a stupid if in gather_intrinsic_info by Jason Ekstrand · 6 years ago
  44. 6bcd2af nir/algebraic: Add some optimizations for D3D-style Booleans by Jason Ekstrand · 6 years ago
  45. 3b30814 nir/algebraic: Optimize 1-bit Booleans by Jason Ekstrand · 6 years ago
  46. 4422745 nir: Switch to using 1-bit Booleans for almost everything by Jason Ekstrand · 6 years ago
  47. 11dc130 nir: Add a bool to int32 lowering pass by Jason Ekstrand · 6 years ago
  48. 191a1dc nir: Add 1-bit Boolean opcodes by Jason Ekstrand · 6 years ago
  49. 615cc26 nir/algebraic: Generalize an optimization by Jason Ekstrand · 6 years ago
  50. 487514a nir/large_constants: Properly handle 1-bit bools by Jason Ekstrand · 6 years ago
  51. 3191a82 nir: Add support for 1-bit data types by Jason Ekstrand · 6 years ago
  52. 2fe8708 nir/constant_expressions: Rework Boolean handling by Jason Ekstrand · 6 years ago
  53. 80e8dfe nir: Rename Boolean-related opcodes to include 32 in the name by Jason Ekstrand · 6 years ago
  54. b569093 nir/algebraic: Make an optimization more specific by Jason Ekstrand · 6 years ago
  55. 5170998 nir: Drop support for lower_b2f by Jason Ekstrand · 6 years ago
  56. 4bb1a34 nir/algebraic: Optimize x2b(xneg(a)) -> a by Jason Ekstrand · 6 years ago
  57. 3595a0a nir/constant_folding: Fix source bit size logic by Jason Ekstrand · 6 years ago
  58. 9f7bd84 nir/tgsi: Use nir_bany in ttn_kill_if by Jason Ekstrand · 6 years ago
  59. e174260 nir/lower_idiv: Use ilt instead of bit twiddling by Jason Ekstrand · 6 years ago
  60. 2977c77 v3d: Use the original bit size when scalarizing uniform loads. by Eric Anholt · 6 years ago
  61. 91a0251 vc4: Use the original bit size when scalarizing uniform loads. by Eric Anholt · 6 years ago
  62. bde9f48 ac: split 16-bit ssbo loads that may not be dword aligned by Rhys Perry · 6 years ago
  63. 12dc7cb ac: refactor visit_load_buffer by Rhys Perry · 6 years ago
  64. ed4020f nir: fix constness in nir_intrinsic_align() by Rhys Perry · 6 years ago
  65. e4f9a37 clover: Fix build after clang r348827 by Jan Vesely · 6 years ago
  66. d512b35 glx: Fix compilation with GLX_USE_WINDOWSGL by Jon Turney · 6 years ago
  67. 29927e7 v3d: Drop in a bunch of notes about performance improvement opportunities. by Eric Anholt · 6 years ago
  68. 248a7fb v3d: Do uniform pretty-printing in the QPU dump. by Eric Anholt · 6 years ago
  69. a370ed7 v3d: Use the uniform pretty-printer in v3d_write_uniforms()'s debug code. by Eric Anholt · 6 years ago
  70. 532b6c5 v3d: Move uniform pretty-printing to its own helper function. by Eric Anholt · 6 years ago
  71. 78ef05b v3d: Move uinfo->data[] dereference to the top of v3d_write_uniforms(). by Eric Anholt · 6 years ago
  72. a7e15a5 v3d: Avoid assertion failures when removing end-of-shader instructions. by Eric Anholt · 6 years ago
  73. 5b2cc03 v3d: Add support for draw indirect for GLES3.1. by Eric Anholt · 6 years ago
  74. ff80e58 v3d: Add missing flagging of SYNCB as a TSY op. by Eric Anholt · 6 years ago
  75. 3f9bcf9 v3d: Make sure that a thrsw doesn't split a multop from its umul24. by Eric Anholt · 6 years ago
  76. 332a5cf v3d: Add safety checks for resource_create(). by Eric Anholt · 6 years ago
  77. 6ad9e86 v3d: Add support for texturing from linear. by Eric Anholt · 6 years ago
  78. 976ea90 v3d: Add support for using the TFU to do some blits. by Eric Anholt · 6 years ago
  79. e5b4d1f v3d: Don't forget to bump the number of writes when doing TFU ops. by Eric Anholt · 6 years ago
  80. 485df25 v3d: Set up the right stride for raster TFU. by Eric Anholt · 6 years ago
  81. e731d53 v3d: Don't forget to wait for our TFU job before rendering from it. by Eric Anholt · 6 years ago
  82. 153d3fc nvc0: always keep TSC slot 0 bound to fix TXF by Ilia Mirkin · 6 years ago
  83. 4aeaf89 nvc0: replace use of explicit default_tsc with entry 0 by Ilia Mirkin · 6 years ago
  84. 5f90856 freedreno/a6xx: fix corrupted uniforms by Rob Clark · 6 years ago
  85. 4db4b34 pci_ids: add new vega20 pci id by Alex Deucher · 6 years ago
  86. 56cf25a pci_ids: add new vega10 pci ids by Alex Deucher · 6 years ago
  87. 5c45466 i965/gen9: Add workarounds for object preemption. by Rafael Antognolli · 6 years ago
  88. d8b50e1 i965/gen10+: Enable object level preemption. by Rafael Antognolli · 6 years ago
  89. 019a92f intel/genxml: Add register for object preemption. by Rafael Antognolli · 6 years ago
  90. a6b7d11 util/slab: Rename slab_mempool typed parameters to mempool by Ian Romanick · 6 years ago
  91. ba5402e nir/phi_builder: Internal users should use nir_phi_builder_value_set_block_def too by Ian Romanick · 6 years ago
  92. 489ffaf etnaviv: drop redundant ctx function parameter by Christian Gmeiner · 6 years ago
  93. 0b44644 genxml: Consistently use a numeric "MOCS" field by Kenneth Graunke · 6 years ago
  94. a2ec788 nir: fix opt_if_loop_last_continue() by Timothy Arceri · 6 years ago
  95. 0ac5aca freedreno/a6xx: fix resource_copy_region() by Rob Clark · 6 years ago
  96. 4ec2f61 freedreno: move fd_resource_copy_region() by Rob Clark · 6 years ago
  97. 57b76ee freedreno/a6xx: more blitter fixes by Rob Clark · 6 years ago
  98. d15fc78 freedreno: update generated headers by Rob Clark · 6 years ago
  99. 532f8c0 gallium/aux: add is_unorm() helper by Rob Clark · 6 years ago
  100. 85cd4df freedreno/a6xx: fix blitter crash by Rob Clark · 6 years ago