Google Git
Sign in
llvm / llvm-project / libclc / HEAD
  1. 68835a2 amdgcn/fmin: Fix typos that reduced precision by Jan Vesely · 6 years ago
  2. b76b23f exp10: Port from amd builtins by Jan Vesely · 6 years ago
  3. 415f069 hypot: Port from amd builtins by Jan Vesely · 6 years ago
  4. ba67583 select: simplify implementation and fix fp16 by Jan Vesely · 6 years ago
  5. adef60a fmod: Port from amd_builtins by Jan Vesely · 6 years ago
  6. ae46331 r600: Update datalayout after LLVM r328656 by Jan Vesely · 6 years ago
  7. 46ef35f amdgcn: Update datalayout after LLVM r328656 by Jan Vesely · 6 years ago
  8. ddf7cb5 remainder: Port from amd builtins by Jan Vesely · 6 years ago
  9. 9d6d4aa nan: Implement by Jan Vesely · 6 years ago
  10. 38e29d6 travis: Add build using llvm-6 by Jan Vesely · 6 years ago
  11. d5f47dc amdgcn/fmax: fcanonicalize operands by Jan Vesely · 6 years ago
  12. a81d39f amdgcn/fmin: fcanonicalize operands by Jan Vesely · 6 years ago
  13. 864a28f amdgcn,popcount: Workaround broken llvm.ctpop intrinsic on some GCN ASICs by Jan Vesely · 6 years ago
  14. 26b8288 integer/gentype: Add __CLC_VECSIZE macro by Jan Vesely · 6 years ago
  15. 1e2caf9 popcount: Provide function implementation rather than intrinsic redirect by Jan Vesely · 6 years ago
  16. 9adc84b lgamma_r: Move code from .inc to .cl file by Jan Vesely · 6 years ago
  17. c2c64d2 frexp: Reuse types provided by gentype.inc by Jan Vesely · 6 years ago
  18. edf8418 select: Add vector implementation by Jan Vesely · 6 years ago
  19. 5fc4e80 minmag: Condition variable needs to be the same bitwidth as operands by Jan Vesely · 6 years ago
  20. bff5139 maxmag: Condition variable needs to be the same bitwidth as operands by Jan Vesely · 6 years ago
  21. b0d41f5 Move cl_khr_fp64 exntension enablement to gentype include lists by Jan Vesely · 6 years ago
  22. 386115c utils: Adapt to llvm r325155 by Jan Vesely · 6 years ago
  23. 756ab56 amdgcn: Fix build after GDS/const AS swap in r325030 by Jan Vesely · 6 years ago
  24. 62d3ed7 amdgcn: Fix datalayout after addition of 32bit const AS in r324747 by Jan Vesely · 6 years ago
  25. 4125cc8 r600: Fix datalayout after clang r324101 by Jan Vesely · 6 years ago
  26. 269db58 amdgcn: Fix datalayout after clang r324101 by Jan Vesely · 6 years ago
  27. 4ad54e2 amdgpu/half_recip: Switch implementation to native_recip by Jan Vesely · 6 years ago
  28. 19012e3 amdgpu/half_log2: Switch implementation to native_log2 by Jan Vesely · 6 years ago
  29. 9f8ac5a amdgpu/half_log10: Switch implementation to native_log10 by Jan Vesely · 6 years ago
  30. 293ed80 amdgpu/half_log: Switch implementation to native_log by Jan Vesely · 6 years ago
  31. 10b8c26 amdgpu/half_exp2: Switch implementation to native_exp2 by Jan Vesely · 6 years ago
  32. 7fd39ca amdgpu/half_exp10: Switch implementation to native_exp10 by Jan Vesely · 6 years ago
  33. 5542612 amdgpu/half_exp: Switch implementation to native_exp by Jan Vesely · 6 years ago
  34. 3ecaac7 amdgpu/half_sqrt: Switch implementation to native_sqrt by Jan Vesely · 6 years ago
  35. 78cbd88 amdgpu/half_rsqrt: Switch implementation to native_rsqrt by Jan Vesely · 6 years ago
  36. 6f7c4a3 Add vstore_half_rte implementation by Jan Vesely · 6 years ago
  37. 0bc21a0 Add vstore_half_rtp implementation by Jan Vesely · 6 years ago
  38. 36af339 Add vstore_half_rtn implementation by Jan Vesely · 6 years ago
  39. b266f7c Add vstore_half_rtz implementation by Jan Vesely · 6 years ago
  40. 4232518 vstore_half: Consolidate declarations by Jan Vesely · 6 years ago
  41. ec8ebba vstore_half: Add support for custom rounding functions by Jan Vesely · 6 years ago
  42. 0eefe58 vstore_half: Make sure the helper function is always inline by Jan Vesely · 6 years ago
  43. 8c3f2e9 half_powr: Implement using powr by Jan Vesely · 6 years ago
  44. 789a234 math.h: Use logical operations instead of bit operations for readability by Jan Vesely · 6 years ago
  45. 367a161 math.h: Set HAVE_HW_FMA32 based on compiler provided macro by Jan Vesely · 6 years ago
  46. cc62e5d tanpi: Port from amd_builtins by Jan Vesely · 6 years ago
  47. 50100b7 tan: Port from amd_builtins by Jan Vesely · 6 years ago
  48. 5923ec2 half_divide: Implement using x/y by Jan Vesely · 6 years ago
  49. 94dd601 half_tan: Implement using tan by Jan Vesely · 6 years ago
  50. 423c4c8 half_sin: Implement using sin by Jan Vesely · 6 years ago
  51. 8a5a034 half_recip: Implement using 1/x by Jan Vesely · 6 years ago
  52. c4f0b1c half_log2: Implement using log2 by Jan Vesely · 6 years ago
  53. 72b17bc half_log10: Implement using log10 by Jan Vesely · 6 years ago
  54. f9d4d49 half_log: Implement using log by Jan Vesely · 6 years ago
  55. ae3339e half_exp10: Implement using exp10 by Jan Vesely · 6 years ago
  56. 1fd1ef8 half_exp2: Implement using exp2 by Jan Vesely · 6 years ago
  57. ca7a8ec half_exp: Implement using exp by Jan Vesely · 6 years ago
  58. a275161 half_cos: Implement using cos by Jan Vesely · 6 years ago
  59. 955e738 half_sqrt: Cleanup implementation by Jan Vesely · 6 years ago
  60. c9c6015 half_rsqrt: Cleanup implementation by Jan Vesely · 6 years ago
  61. 77cd945 rootn: Port from amd_builtins by Jan Vesely · 6 years ago
  62. 224fdeb powr: Port from amd_builtins by Jan Vesely · 6 years ago
  63. 85df2d4 pown: Port from amd_builtins by Jan Vesely · 6 years ago
  64. 8ba16e1 pow: Port from amd_builtins by Jan Vesely · 6 years ago
  65. 8362c0b configure.py: Add gfx900 (Vega, Raven) by Vedran Miletic · 6 years ago
  66. 54102ad math: Implement minmag by Jan Vesely · 6 years ago
  67. f4dfdf3 math: Implement maxmag by Jan Vesely · 6 years ago
  68. 690a12a native_powr: Switch implementation to native_exp2 and native_log2 by Jan Vesely · 6 years ago
  69. 5865fc6 native_divide: provide function implementation instead of macro by Jan Vesely · 6 years ago
  70. aa1665c native_recip: provide function implementation instead of macro by Jan Vesely · 6 years ago
  71. 1ec8b9b native_rsqrt: Switch implementation to 1 / native_sqrt by Jan Vesely · 6 years ago
  72. 5de9a9e native_tan: Switch implementation to use native_sin/native_cos by Jan Vesely · 6 years ago
  73. 1d20f64 math: Use precomputed constant for log2(10.0) by Jan Vesely · 6 years ago
  74. 0b65532 native_exp10: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  75. 0aedf0e native_sqrt: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  76. d92e214 native_sin: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  77. 696b488 native_cos: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  78. b0cce88 native_exp2: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  79. ad32ecc native_exp: Switch implementation to llvm intrinsic by Jan Vesely · 6 years ago
  80. 725288d amdgpu: Add workaround for unimplemented llvm.exp intrinsic by Jan Vesely · 6 years ago
  81. 02eb831 native_log10: Switch to generic native intrinsic inc file by Jan Vesely · 6 years ago
  82. 2a509d7 native_log: Switch to generic native intrinsic inc file by Jan Vesely · 6 years ago
  83. a7a8df9 native_log2: Switch to generic native intrinsic inc file by Jan Vesely · 6 years ago
  84. f9e9a1a tgamma: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  85. 506de3b tanh: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  86. 51a4cc6 tan: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  87. e2eff59 sqrt: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  88. 14c1818 sinpi: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  89. 77ede0a sinh: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  90. bfdd610 sin: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  91. 36d527a native_log: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  92. e7eb6f7 native_log2: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  93. 91318a1 native_log10: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  94. 165ab8c log: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  95. 3ddc6f5 logb: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  96. 41c9bf9 log2: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  97. adbcf1b log1p: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  98. 5f65981 lgamma: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  99. 5863d8c exp2: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago
  100. 99c27ae cospi: Use unary_decl instead of custom inc file by Jan Vesely · 6 years ago