Gitiles
Code Review Sign In
gerrit-public.fairphone.software / toolchain / llvm-project / 81fe1fbf4abd00b24e078a80cb15a2d2c1343f11 / llvm / lib / Transforms / InstCombine / InstCombineMulDivRem.cpp
  1. 4952e66 [InstCombine] canonicalize MUL with NEG operand by Chen Zheng · 7 years ago
  2. e3605d0 Add a emitUnaryFloatFnCall version that fetches the function name from TLI by Mikael Holmen · 7 years ago
  3. 57f5d0a [IRBuilder] Fixup CreateIntrinsic to allow specifying Types to Mangle. by Neil Henning · 7 years ago
  4. 79dceb2 [InstCombine] name change: foldShuffledBinop -> foldVectorBinop; NFC by Sanjay Patel · 7 years ago
  5. 90a3634 [InstCombine] refactor mul narrowing folds; NFCI by Sanjay Patel · 7 years ago
  6. 4e63db8 [InstCombine] Fix incorrect usage of getPrimitiveSizeInBits when we should be using the element size for vectors by Craig Topper · 7 years ago
  7. a57bb61 [InstCombine] Support (mul (sext x), cst) --> (sext (mul x, cst')) and (mul (zext x), cst) --> (zext (mul x, cst')) for vectors constants. by Craig Topper · 7 years ago
  8. 6d6eab6 [InstCombine] fold udiv with common factor from muls with nuw by Sanjay Patel · 7 years ago
  9. 9d2099c [InstCombine] Corrections in comments for division transformation (NFC) by Sanjay Patel · 7 years ago
  10. 70043b7 [InstCombine] return when SimplifyAssociativeOrCommutative makes a change by Sanjay Patel · 7 years ago
  11. 9adea01 [InstCombine] simplify code for urem fold; NFCI by Sanjay Patel · 7 years ago
  12. 3575f0c [InstCombine] fold urem with sext bool divisor by Sanjay Patel · 7 years ago
  13. 7c45deb [InstCombine] fold udiv with sext bool divisor by Sanjay Patel · 7 years ago
  14. 38a86d3 [InstCombine] cleanup udiv folds; NFCI by Sanjay Patel · 7 years ago
  15. 6a96d90 [InstCombine] fold sdiv with sext bool divisor by Sanjay Patel · 7 years ago
  16. 7b0fc75 [InstCombine] simplify binops before trying other folds by Sanjay Patel · 7 years ago
  17. d894fb4 [InstCombine] Fix div handling by Serguei Katkov · 7 years ago
  18. bbc6d60 [InstCombine] call simplify before trying vector folds by Sanjay Patel · 7 years ago
  19. fbb83de [InstCombine] Moving overflow computation logic from InstCombine to ValueTracking; NFC by Omer Paparo Bivas · 7 years ago
  20. 4dfcc4a Remove @brief commands from doxygen comments, too. by Adrian Prantl · 7 years ago
  21. 5f8f34e4 Remove \brief commands from doxygen comments. by Adrian Prantl · 7 years ago
  22. 81b3b10 [InstCombine] allow more fmul folds with 'reassoc' by Sanjay Patel · 7 years ago
  23. 0e3167c [InstCombine] improve code comment; NFC by Sanjay Patel · 8 years ago
  24. 4fd4fd6 [InstCombine] distribute fmul over fadd/fsub by Sanjay Patel · 8 years ago
  25. 2455fef [InstCombine] check uses before creating instructions for fmul distribution by Sanjay Patel · 8 years ago
  26. 63b1028 [InstCombine] add nnan requirement for sqrt(x) * sqrt(y) -> sqrt(x*y) by Sanjay Patel · 8 years ago
  27. 204edec [InstCombine] fix fmul reassociation to avoid creating an extra fdiv by Sanjay Patel · 8 years ago
  28. e29375d [InstCombine] rearrange visitFMul; NFCI by Sanjay Patel · 8 years ago
  29. 2fd0acf [InstCombine] partly fix FMF for fmul+log2 fold by Sanjay Patel · 8 years ago
  30. d0cdb2f [InstCombine] allow fmul fold with less than 'fast' by Sanjay Patel · 8 years ago
  31. eb5d046 revert r326502: [InstCombine] allow fmul fold with less than 'fast' by Sanjay Patel · 8 years ago
  32. 7373ae5 [InstCombine] allow fmul fold with less than 'fast' by Sanjay Patel · 8 years ago
  33. f3b1af7 [InstCombine] simplify code for (X*Y) * X => (X*X) * Y ; NFCI by Sanjay Patel · 8 years ago
  34. eaf5a12 [InstCombine] simplify code for X * -1.0 --> -X; NFC by Sanjay Patel · 8 years ago
  35. b3f4f62 [InstCombine] move invariant call out of loop; NFC by Sanjay Patel · 8 years ago
  36. 8fdd87f [InstCombine] move constant check into foldBinOpIntoSelectOrPhi; NFCI by Sanjay Patel · 8 years ago
  37. 31a9046 [InstCombine] allow fdiv folds with less than fully 'fast' ops by Sanjay Patel · 8 years ago
  38. 2db2769 [InstCombine] simplify code for fabs(X) * fabs(X) -> X * X; NFC by Sanjay Patel · 8 years ago
  39. db53d18 [InstSimplify] sqrt(X) * sqrt(X) --> X by Sanjay Patel · 8 years ago
  40. d32104e [InstCombine] allow fmul-sqrt folds with less than full -ffast-math by Sanjay Patel · 8 years ago
  41. 6b9c7a9 [InstCombine] refactor fmul with negated op folds; NFCI by Sanjay Patel · 8 years ago
  42. 5a6f904 [InstCombine] add and use Create*FMF functions; NFC by Sanjay Patel · 8 years ago
  43. 6f716a7 [InstCombine] C / -X --> -C / X by Sanjay Patel · 8 years ago
  44. d8dd015 [InstCombine] -X / C --> X / -C for FP by Sanjay Patel · 8 years ago
  45. 7365b44 [InstCombine] remove unneeded operand swap: NFCI by Sanjay Patel · 8 years ago
  46. 29b98ae [InstCombine] remove unneeded dyn_cast to prevent unused variable warning by Sanjay Patel · 8 years ago
  47. b2d9786 [InstCombine] remove compound fdiv pattern folds by Sanjay Patel · 8 years ago
  48. 90f4c8e [InstCombine] fold fdiv with non-splat divisor to fmul: X/C --> X * (1/C) by Sanjay Patel · 8 years ago
  49. 2816560 [InstCombine] use CreateWithCopiedFlags to reduce code; NFCI by Sanjay Patel · 8 years ago
  50. 1d14779 [InstCombine] allow fdiv with constant dividend folds with less than full -ffast-math by Sanjay Patel · 8 years ago
  51. e412954 [InstCombine] refactor fdiv with constant dividend folds; NFC by Sanjay Patel · 8 years ago
  52. 08868e494 [Constant] add floating-point helpers for normal/finite-nz; NFC by Sanjay Patel · 8 years ago
  53. 91bb775 [InstCombine] clean up fdiv-with-fdiv folds; NFCI by Sanjay Patel · 8 years ago
  54. e16b0cf [InstCombine] remove redundant debug info setting; NFC by Sanjay Patel · 8 years ago
  55. 65da14d [InstCombine] reduce code duplication; NFC by Sanjay Patel · 8 years ago
  56. 1e04511 [InstCombine] use m_OneUse to reduce code; NFC by Sanjay Patel · 8 years ago
  57. 339b4d3 [InstCombine] allow sin/cos transforms with 'reassoc' by Sanjay Patel · 8 years ago
  58. 6a0f667 [InstCombine] allow X / C -> X * (1.0/C) for vector splat FP constants by Sanjay Patel · 8 years ago
  59. b39bcc0 [InstCombine] clean up fold for X / C -> X * (1.0/C); NFCI by Sanjay Patel · 8 years ago
  60. 5df4d88 [InstCombine] simplify isFMulOrFDivWithConstant(); NFCI by Sanjay Patel · 8 years ago
  61. 58dab85 [InstCombine] replace isa/cast with dyn_cast; NFC by Sanjay Patel · 8 years ago
  62. 604cb9e [InstCombine] refactor folds for mul with negated operands; NFCI by Sanjay Patel · 8 years ago
  63. 7558d86 [InstCombine] (lshr X, 31) * Y --> (ashr X, 31) & Y by Sanjay Patel · 8 years ago
  64. cb8ac00 [InstCombine] (bool X) * Y --> X ? Y : 0 by Sanjay Patel · 8 years ago
  65. be0dd72 [InstCombine] Simplify getLogBase2 case for scalar/splats. NFCI. by Simon Pilgrim · 8 years ago
  66. 4a4f35f [InstCombine] X / (X * Y) --> 1.0 / Y by Sanjay Patel · 8 years ago
  67. 1998cc6 [InstCombine] various clean-ups for div transforms; NFC by Sanjay Patel · 8 years ago
  68. 39059d2 [InstCombine] various clean-ups for commonIDivTransforms; NFC by Sanjay Patel · 8 years ago
  69. 510d647 [InstCombine] X / (X * Y) -> 1 / Y if the multiplication does not overflow by Sanjay Patel · 8 years ago
  70. 9620f4b [InstCombine] Add constant vector support for X udiv C, where C >= signbit by Simon Pilgrim · 8 years ago
  71. a54e8e4 [InstCombine] visitSRem - use m_Negative(APInt) helper. NFCI. by Simon Pilgrim · 8 years ago
  72. 1889f26 [InstCombine] Add m_Negative pattern matching by Simon Pilgrim · 8 years ago
  73. 2a90acd [InstCombine] Fix issue with X udiv (POW2_C1 << N) for non-splat constant vectors by Simon Pilgrim · 8 years ago
  74. 94cc89d [InstCombine] Fix issue with X udiv 2^C -> X >> C for non-splat constant vectors by Simon Pilgrim · 8 years ago
  75. 4039dbe Fix unused variable warning. by Simon Pilgrim · 8 years ago
  76. 0b9f391 [InstCombine] Improve mul(x, pow2) -> shl combine for vector constants by Simon Pilgrim · 8 years ago
  77. 9530f18 [InstCombine] (X << Y) / X -> 1 << Y by Sanjay Patel · 8 years ago
  78. 738e6e7 [InstCombine] Apply the fix from r322284 for sin / cos -> tan too by Benjamin Kramer · 8 years ago
  79. 44993ed [InstCombine] For cos/sin -> tan copy attributes from cos instead of the by Benjamin Kramer · 8 years ago
  80. e5fbf59 [InstCombine] Missed optimization in math expression: sin(x) / cos(x) => tan(x) by Dmitry Venikov · 8 years ago
  81. a58d8de [InstCombine] Missed optimization in math expression: squashing sqrt functions by Dmitry Venikov · 8 years ago
  82. 14adbac [InstCombine] fix miscompile of frem with 0.0 operand (PR34870) by Sanjay Patel · 8 years ago
  83. 629c411 [IR] redefine 'UnsafeAlgebra' / 'reassoc' fast-math-flags and add 'trans' fast-math-flag by Sanjay Patel · 8 years ago
  84. 7f0f9bc [Transforms] Fix some Clang-tidy modernize and Include What You Use warnings; other minor fixes (NFC). by Eugene Zelenko · 8 years ago
  85. 72d339a [InstCombine] use correct type when propagating constant condition in simplifyDivRemOfSelectWithZeroOp (PR34856) by Sanjay Patel · 8 years ago
  86. ae2e3a4 [InstCombine] rename SimplifyDivRemOfSelect to be clearer, add comments, simplify code; NFCI by Sanjay Patel · 8 years ago
  87. aa103b3 [InstCombine] Add select simplifications by Quentin Colombet · 8 years ago
  88. bb78938 [InstCombine] fix and enhance udiv/urem narrowing by Sanjay Patel · 8 years ago
  89. fde4723 [IR] Add Type::isIntOrIntVectorTy(unsigned) similar to the existing isIntegerTy(unsigned), but also works for vectors. by Craig Topper · 8 years ago
  90. bb4069e [InstCombine] Make InstCombine's IRBuilder be passed by reference everywhere by Craig Topper · 8 years ago
  91. 5fe0197 [InstCombine] Propagate nsw flag when turning mul by pow2 into shift when the constant is a vector splat or the scalar bit width is larger than 64-bits by Craig Topper · 8 years ago
  92. a420562 [InstCombine] Pass a proper context instruction to all of the calls into InstSimplify by Craig Topper · 8 years ago
  93. 73ba1c8 [InstCombine][InstSimplify] Use APInt::isNullValue/isOneValue to reduce compiled code for comparing APInts with 0 and 1. NFC by Craig Topper · 8 years ago
  94. d4039f7 [InstCombine] Add an InstCombine specific wrapper around isKnownToBeAPowerOfTwo to shorten code. NFC by Craig Topper · 8 years ago
  95. 2b1fc32 [InstCombine] Cleanup the interface for overflow checks by Craig Topper · 8 years ago
  96. 1a36b7d [ValueTracking] Replace all uses of ComputeSignBit with computeKnownBits. by Craig Topper · 8 years ago
  97. bb97372 [InstCombine] Merge duplicate functionality between InstCombine and ValueTracking by Craig Topper · 8 years ago
  98. 2c75c63 InstCombine: Use the new SimplifyQuery versions of Simplify*. Use AssumptionCache, DominatorTree, TargetLibraryInfo everywhere. by Daniel Berlin · 8 years ago
  99. bcfd2d1 [APInt] Rename getSignBit to getSignMask by Craig Topper · 8 years ago
  100. 218a359 [InstCombine] Simplify 1/X for vectors. by Craig Topper · 8 years ago