summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/InstCombine/InstCombineMulDivRem.cpp
Commit message (Expand)AuthorAgeFilesLines
* [InstCombine] fold udiv with common factor from muls with nuwSanjay Patel2018-07-261-0/+15
* [InstCombine] Corrections in comments for division transformation (NFC)Sanjay Patel2018-07-151-3/+3
* [InstCombine] return when SimplifyAssociativeOrCommutative makes a changeSanjay Patel2018-07-131-3/+8
* [InstCombine] simplify code for urem fold; NFCISanjay Patel2018-06-261-5/+2
* [InstCombine] fold urem with sext bool divisorSanjay Patel2018-06-261-2/+13
* [InstCombine] fold udiv with sext bool divisorSanjay Patel2018-06-261-1/+7
* [InstCombine] cleanup udiv folds; NFCISanjay Patel2018-06-251-30/+20
* [InstCombine] fold sdiv with sext bool divisorSanjay Patel2018-06-251-4/+7
* [InstCombine] simplify binops before trying other foldsSanjay Patel2018-06-211-18/+25
* [InstCombine] Fix div handlingSerguei Katkov2018-06-041-2/+2
* [InstCombine] call simplify before trying vector foldsSanjay Patel2018-06-021-32/+24
* [InstCombine] Moving overflow computation logic from InstCombine to ValueTrac...Omer Paparo Bivas2018-05-101-41/+0
* Remove @brief commands from doxygen comments, too.Adrian Prantl2018-05-011-2/+2
* Remove \brief commands from doxygen comments.Adrian Prantl2018-05-011-4/+4
* [InstCombine] allow more fmul folds with 'reassoc'Sanjay Patel2018-04-031-64/+64
* [InstCombine] improve code comment; NFCSanjay Patel2018-03-261-2/+2
* [InstCombine] distribute fmul over fadd/fsubSanjay Patel2018-03-261-98/+15
* [InstCombine] check uses before creating instructions for fmul distributionSanjay Patel2018-03-261-1/+1
* [InstCombine] add nnan requirement for sqrt(x) * sqrt(y) -> sqrt(x*y)Sanjay Patel2018-03-181-1/+3
* [InstCombine] fix fmul reassociation to avoid creating an extra fdivSanjay Patel2018-03-131-6/+20
* [InstCombine] rearrange visitFMul; NFCISanjay Patel2018-03-021-73/+69
* [InstCombine] partly fix FMF for fmul+log2 foldSanjay Patel2018-03-021-52/+17
* [InstCombine] allow fmul fold with less than 'fast'Sanjay Patel2018-03-021-1/+1
* revert r326502: [InstCombine] allow fmul fold with less than 'fast'Sanjay Patel2018-03-011-1/+1
* [InstCombine] allow fmul fold with less than 'fast'Sanjay Patel2018-03-011-1/+1
* [InstCombine] simplify code for (X*Y) * X => (X*X) * Y ; NFCISanjay Patel2018-03-011-35/+17
* [InstCombine] simplify code for X * -1.0 --> -X; NFCSanjay Patel2018-02-281-7/+3
* [InstCombine] move invariant call out of loop; NFCSanjay Patel2018-02-281-4/+4
* [InstCombine] move constant check into foldBinOpIntoSelectOrPhi; NFCISanjay Patel2018-02-281-17/+15
* [InstCombine] allow fdiv folds with less than fully 'fast' opsSanjay Patel2018-02-261-13/+3
* [InstCombine] simplify code for fabs(X) * fabs(X) -> X * X; NFCSanjay Patel2018-02-231-13/+4
* [InstSimplify] sqrt(X) * sqrt(X) --> XSanjay Patel2018-02-231-4/+0
* [InstCombine] allow fmul-sqrt folds with less than full -ffast-mathSanjay Patel2018-02-231-15/+8
* [InstCombine] refactor fmul with negated op folds; NFCISanjay Patel2018-02-231-24/+18
* [InstCombine] add and use Create*FMF functions; NFCSanjay Patel2018-02-211-15/+7
* [InstCombine] C / -X --> -C / XSanjay Patel2018-02-211-8/+17
* [InstCombine] -X / C --> X / -C for FPSanjay Patel2018-02-201-5/+12
* [InstCombine] remove unneeded operand swap: NFCISanjay Patel2018-02-201-3/+0
* [InstCombine] remove unneeded dyn_cast to prevent unused variable warningSanjay Patel2018-02-201-2/+1
* [InstCombine] remove compound fdiv pattern foldsSanjay Patel2018-02-201-27/+1
* [InstCombine] fold fdiv with non-splat divisor to fmul: X/C --> X * (1/C)Sanjay Patel2018-02-201-21/+16
* [InstCombine] use CreateWithCopiedFlags to reduce code; NFCISanjay Patel2018-02-191-7/+6
* [InstCombine] allow fdiv with constant dividend folds with less than full -ff...Sanjay Patel2018-02-191-2/+3
* [InstCombine] refactor fdiv with constant dividend folds; NFCSanjay Patel2018-02-191-26/+27
* [Constant] add floating-point helpers for normal/finite-nz; NFCSanjay Patel2018-02-161-42/+13
* [InstCombine] clean up fdiv-with-fdiv folds; NFCISanjay Patel2018-02-161-28/+23
* [InstCombine] remove redundant debug info setting; NFCSanjay Patel2018-02-161-2/+0
* [InstCombine] reduce code duplication; NFCSanjay Patel2018-02-161-31/+19
* [InstCombine] use m_OneUse to reduce code; NFCSanjay Patel2018-02-151-2/+2
* [InstCombine] allow sin/cos transforms with 'reassoc'Sanjay Patel2018-02-151-2/+1
OpenPOWER on IntegriCloud