| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Preserve fast-math flags when folding (fsub x, (fneg y)) to (fadd x, y). | Owen Anderson | 2013-07-30 | 1 | -4/+11 |
| * | Change behavior of calling bitcasted alias functions. | Matt Arsenault | 2013-07-30 | 1 | -9/+9 |
| * | Fix variable name. | Owen Anderson | 2013-07-26 | 1 | -2/+2 |
| * | When InstCombine tries to fold away (fsub x, (fneg y)) into (fadd x, y), it is | Owen Anderson | 2013-07-26 | 1 | -1/+13 |
| * | Correct case of m_UIToFp to m_UIToFP to match instruction name, add m_SIToFP ... | Stephen Lin | 2013-07-26 | 1 | -4/+4 |
| * | InstCombine: call FoldOpIntoSelect for all floating binops, not just fmul | Stephen Lin | 2013-07-20 | 2 | -3/+23 |
| * | Restore r181216, which was partially reverted in r182499. | Stephen Lin | 2013-07-17 | 2 | -43/+29 |
| * | Use llvm::array_lengthof to replace sizeof(array)/sizeof(array[0]). | Craig Topper | 2013-07-15 | 1 | -1/+2 |
| * | Use SmallVectorImpl& instead of SmallVector to avoid repeating small vector s... | Craig Topper | 2013-07-14 | 1 | -1/+1 |
| * | Add a microoptimization for urem. | Nick Lewycky | 2013-07-13 | 1 | -0/+7 |
| * | Fix a crash in EvaluateInDifferentElementOrder where it would generate an | Joey Gouly | 2013-07-12 | 1 | -1/+3 |
| * | Don't use a potentially expensive shift if all we want is one set bit. | Benjamin Kramer | 2013-07-11 | 1 | -1/+1 |
| * | InstCombine: Fix typo in comment for visitICmpInstWithInstAndIntCst | David Majnemer | 2013-07-09 | 1 | -2/+2 |
| * | InstCombine: variations on 0xffffffff - x >= 4 | David Majnemer | 2013-07-09 | 1 | -0/+12 |
| * | InstCombine: X & -C != -C -> X <= u ~C | David Majnemer | 2013-07-09 | 1 | -0/+9 |
| * | Commit r185909 was a misapplied patch, fix it | David Majnemer | 2013-07-09 | 1 | -21/+13 |
| * | InstCombine: add more transforms | David Majnemer | 2013-07-09 | 1 | -0/+42 |
| * | InstCombine: Fold X-C1 <u 2 -> (X & -2) == C1 | David Majnemer | 2013-07-08 | 1 | -0/+8 |
| * | InstCombine: (icmp eq B, 0) | (icmp ult A, B) -> (icmp ule A, B-1) | David Majnemer | 2013-07-05 | 1 | -1/+28 |
| * | InstCombine: Reimplementation of visitUDivOperand | David Majnemer | 2013-07-04 | 1 | -56/+139 |
| * | Use SmallVectorImpl::iterator/const_iterator instead of SmallVector to avoid ... | Craig Topper | 2013-07-04 | 1 | -1/+1 |
| * | Revert r185257 (InstCombine: Be more agressive optimizing 'udiv' instrs with ... | Hal Finkel | 2013-07-02 | 1 | -77/+44 |
| * | InstCombine: Also turn selects fed by an and into arithmetic when the types d... | Benjamin Kramer | 2013-06-29 | 1 | -4/+9 |
| * | InstCombine: FoldGEPICmp shouldn't change sign of base pointer comparison | David Majnemer | 2013-06-29 | 1 | -2/+1 |
| * | InstCombine: Small whitespace cleanup in FoldGEPICmp | David Majnemer | 2013-06-29 | 1 | -1/+1 |
| * | InstCombine: Be more agressive optimizing 'udiv' instrs with 'select' denoms | David Majnemer | 2013-06-29 | 1 | -44/+77 |
| * | InstCombine: Optimize (1 << X) Pred CstP2 to X Pred Log2(CstP2) | David Majnemer | 2013-06-28 | 1 | -2/+72 |
| * | Fix using arg_end() - arg_begin() instead of arg_size() | Matt Arsenault | 2013-06-28 | 1 | -3/+3 |
| * | Revert "Revert "[APFloat] Removed APFloat constructor which initialized to ei... | Michael Gottesman | 2013-06-27 | 1 | -4/+4 |
| * | Revert "[APFloat] Removed APFloat constructor which initialized to either zer... | Michael Gottesman | 2013-06-27 | 1 | -4/+4 |
| * | [APFloat] Removed APFloat constructor which initialized to either zero/NaN bu... | Michael Gottesman | 2013-06-27 | 1 | -4/+4 |
| * | In InstCombine{AddSub,MulDivRem} convert APFloat.isFiniteNonZero() && !APFloa... | Michael Gottesman | 2013-06-26 | 2 | -5/+5 |
| * | [APFloat] Converted all references to APFloat::isNormal => APFloat::isFiniteN... | Michael Gottesman | 2013-06-19 | 2 | -10/+10 |
| * | Simplify code. No functionality change. | Jakub Staszak | 2013-06-06 | 1 | -2/+1 |
| * | Re-apply "Use IRBuilder instead of ConstantInt methods." with the fixed issues. | Jakub Staszak | 2013-06-06 | 1 | -68/+55 |
| * | Revert "Use IRBuilder instead of ConstantInt methods. It simplifies code a li... | Rafael Espindola | 2013-06-06 | 1 | -56/+70 |
| * | Remove unneeded cast<>. | Jakub Staszak | 2013-06-06 | 1 | -2/+2 |
| * | Use IRBuilder instead of ConstantInt methods. | Jakub Staszak | 2013-06-06 | 1 | -27/+17 |
| * | Use IRBuilder instead of ConstantInt methods. It simplifies code a little bit. | Jakub Staszak | 2013-06-05 | 1 | -70/+56 |
| * | Delete dead safety check. | Nick Lewycky | 2013-06-03 | 1 | -6/+1 |
| * | When determining the new index for an insertelement, we may not assume that an | Nick Lewycky | 2013-06-01 | 1 | -7/+9 |
| * | Simplify multiplications by vectors whose elements are powers of 2. | Rafael Espindola | 2013-05-31 | 1 | -16/+48 |
| * | Reapply with r182909 with a fix to the calculation of the new indices for | Nick Lewycky | 2013-05-31 | 2 | -2/+257 |
| * | Revert r182909. | Evgeniy Stepanov | 2013-05-30 | 2 | -246/+0 |
| * | Swizzle vector inputs if it helps us eliminate shuffles. | Nick Lewycky | 2013-05-30 | 2 | -0/+246 |
| * | Replace Count{Leading,Trailing}Zeros_{32,64} with count{Leading,Trailing}Zeros. | Michael J. Spencer | 2013-05-24 | 1 | -1/+1 |
| * | Run clang-format over the scalarizePHI function. | Joey Gouly | 2013-05-24 | 1 | -12/+8 |
| * | scalarizePHI needs to insert the next ExtractElement in the same block | Joey Gouly | 2013-05-24 | 1 | -2/+4 |
| * | This is an update to a previous commit (r181216). | Jean-Luc Duprat | 2013-05-22 | 2 | -29/+43 |
| * | Add missing -*- C++ -*- to headers | Matt Arsenault | 2013-05-17 | 1 | -1/+1 |
