| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Fix all the remaining lost-fast-math-flags bugs I've been able to find. The ... | Owen Anderson | 2014-01-20 | 1 | -0/+10 |
| * | InstCombine: Teach most integer add/sub/mul/div combines how to deal with vec... | Benjamin Kramer | 2014-01-19 | 1 | -21/+22 |
| * | InstCombine: Refactor fmul/fdiv combines to handle vectors. | Benjamin Kramer | 2014-01-19 | 1 | -64/+77 |
| * | InstCombine: Make the (fmul X, -1.0) -> (fsub -0.0, X) transform handle vecto... | Benjamin Kramer | 2014-01-18 | 1 | -6/+4 |
| * | Fix an instance where we would drop fast math flags when performing an fdiv t... | Owen Anderson | 2014-01-16 | 1 | -1/+3 |
| * | Fix a bug in InstCombine where we failed to preserve fast math flags when opt... | Owen Anderson | 2014-01-16 | 1 | -2/+5 |
| * | Teach InstCombine that (fmul X, -1.0) can be simplified to (fneg X), which LL... | Owen Anderson | 2014-01-16 | 1 | -0/+10 |
| * | InstCombine: Replace manual fast math flag copying with the new IRBuilder RAI... | Benjamin Kramer | 2013-09-30 | 1 | -22/+20 |
| * | Fix a bug in InstCombine where it attempted to cast a Value* to an Instruction* | Joey Gouly | 2013-09-30 | 1 | -2/+2 |
| * | [Fast-math] Disable "(C1/X)*C2 => (C1*C2)/X" if C1/X has multiple uses. | Shuxin Yang | 2013-09-19 | 1 | -3/+6 |
| * | 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 | 1 | -0/+9 |
| * | Restore r181216, which was partially reverted in r182499. | Stephen Lin | 2013-07-17 | 1 | -0/+29 |
| * | Add a microoptimization for urem. | Nick Lewycky | 2013-07-13 | 1 | -0/+7 |
| * | InstCombine: Reimplementation of visitUDivOperand | David Majnemer | 2013-07-04 | 1 | -56/+139 |
| * | Revert r185257 (InstCombine: Be more agressive optimizing 'udiv' instrs with ... | Hal Finkel | 2013-07-02 | 1 | -77/+44 |
| * | InstCombine: Be more agressive optimizing 'udiv' instrs with 'select' denoms | David Majnemer | 2013-06-29 | 1 | -44/+77 |
| * | In InstCombine{AddSub,MulDivRem} convert APFloat.isFiniteNonZero() && !APFloa... | Michael Gottesman | 2013-06-26 | 1 | -4/+4 |
| * | [APFloat] Converted all references to APFloat::isNormal => APFloat::isFiniteN... | Michael Gottesman | 2013-06-19 | 1 | -9/+9 |
| * | Simplify code. No functionality change. | Jakub Staszak | 2013-06-06 | 1 | -2/+1 |
| * | Simplify multiplications by vectors whose elements are powers of 2. | Rafael Espindola | 2013-05-31 | 1 | -16/+48 |
| * | This is an update to a previous commit (r181216). | Jean-Luc Duprat | 2013-05-22 | 1 | -29/+0 |
| * | Fix two typo | Sylvestre Ledru | 2013-05-14 | 1 | -1/+1 |
| * | InstCombine: Flip the order of two urem transforms | David Majnemer | 2013-05-12 | 1 | -6/+6 |
| * | InstCombine: Turn urem to bitwise-and more often | David Majnemer | 2013-05-11 | 1 | -20/+2 |
| * | InstCombine: Verify the type before transforming uitofp into select. | Benjamin Kramer | 2013-05-10 | 1 | -22/+23 |
| * | Provide InstCombines for the following 3 cases: | Jean-Luc Duprat | 2013-05-06 | 1 | -0/+28 |
| * | Tidy up a bit. No functional change. | Jim Grosbach | 2013-04-05 | 1 | -56/+56 |
| * | Fix a bug in instcombine for fmul in fast math mode. | Quentin Colombet | 2013-02-28 | 1 | -3/+3 |
| * | 1. Hoist minus sign as high as possible in an attempt to reveal | Shuxin Yang | 2013-01-15 | 1 | -31/+60 |
| * | This change is to implement following rules under the condition C_A and/or C_R | Shuxin Yang | 2013-01-14 | 1 | -8/+127 |
| * | Cosmetical changne in order to conform to coding std. | Shuxin Yang | 2013-01-07 | 1 | -5/+6 |
| * | This change is to implement following rules: | Shuxin Yang | 2013-01-07 | 1 | -0/+127 |
| * | Move all of the header files which are involved in modelling the LLVM IR | Chandler Carruth | 2013-01-02 | 1 | -1/+1 |
| * | rdar://12753946 | Shuxin Yang | 2012-12-14 | 1 | -0/+32 |
| * | Rename isPowerOfTwo to isKnownToBeAPowerOfTwo. | Rafael Espindola | 2012-12-13 | 1 | -2/+2 |
| * | The TargetData is not used for the isPowerOfTwo determination. It has never | Rafael Espindola | 2012-12-12 | 1 | -3/+2 |
| * | Remove redunant optimizations from InstCombine, instead call the appropriate ... | Michael Ilseman | 2012-12-12 | 1 | -13/+4 |
| * | Use the new script to sort the includes of every file under lib. | Chandler Carruth | 2012-12-03 | 1 | -1/+1 |
| * | reversed the logic of the log2 detection routine to reduce the number of nest... | Pedro Artigas | 2012-11-30 | 1 | -25/+29 |
| * | Addresses many style issues with prior checkin (r169025) | Pedro Artigas | 2012-11-30 | 1 | -58/+44 |
| * | Add fast math inst combine X*log2(Y*0.5)-->X*log2(Y)-X | Pedro Artigas | 2012-11-30 | 1 | -0/+77 |
| * | Move TargetData to DataLayout. | Micah Villmow | 2012-10-08 | 1 | -2/+2 |
| * | Revert 'Fix a typo 'iff' => 'if''. iff is an abreviation of if and only if. S... | Sylvestre Ledru | 2012-09-27 | 1 | -2/+2 |
| * | Fix a typo 'iff' => 'if' | Sylvestre Ledru | 2012-09-27 | 1 | -2/+2 |
| * | InstCombine: Make sure we use the pre-zext type when creating a constant of a... | Benjamin Kramer | 2012-09-21 | 1 | -1/+2 |
| * | InstCombine: Fix comment to reflect the code. | Benjamin Kramer | 2012-08-30 | 1 | -1/+1 |
| * | It is illegal to transform (sdiv (ashr X c1) c2) -> (sdiv x (2^c1 * c2)), | Nadav Rotem | 2012-08-30 | 1 | -10/+0 |
| * | InstCombine: Defensively avoid undefined shifts by limiting the amount to the... | Benjamin Kramer | 2012-08-28 | 1 | -2/+2 |
| * | InstCombine: Guard the transform introduced in r162743 against large ints and... | Benjamin Kramer | 2012-08-28 | 1 | -10/+10 |
