| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | The patch fixes (base, index, offset) match. | Evgeny Stupachenko | 2017-01-04 | 1 | -9/+9 |
| * | Make the canonicalisation on shifts benifit to more case. | Zijiao Ma | 2016-12-23 | 1 | -9/+13 |
| * | Change the interface of TLI.isMultiStoresCheaperThanBitsMerge. | Wei Mi | 2016-12-22 | 1 | -2/+9 |
| * | Add extra headers that got deleted by my revert in r289916 but for which | Chandler Carruth | 2016-12-16 | 1 | -1/+2 |
| * | Revert patch series introducing the DAG combine to match a load-by-bytes | Chandler Carruth | 2016-12-16 | 1 | -283/+0 |
| * | Don't combine splats with other shuffles. | Eli Friedman | 2016-12-15 | 1 | -0/+5 |
| * | Don't combine a shuffle of two BUILD_VECTORs with duplicate elements. | Eli Friedman | 2016-12-15 | 1 | -10/+23 |
| * | [DAG] allow more select folding for targets that have 'and not' (PR31175) | Sanjay Patel | 2016-12-14 | 1 | -6/+26 |
| * | Revert "In visitSTORE, always use FindBetterChain, rather than only when UseA... | Nirav Dave | 2016-12-14 | 1 | -228/+278 |
| * | In visitSTORE, always use FindBetterChain, rather than only when UseAA is ena... | Nirav Dave | 2016-12-14 | 1 | -278/+228 |
| * | [DAGCombiner] Try to use SelectionDAG::isKnownToBeAPowerOfTwo instead of just... | Simon Pilgrim | 2016-12-14 | 1 | -28/+47 |
| * | Add a couple of assertions to the load combine code introduced by r289538 | Artur Pilipenko | 2016-12-14 | 1 | -1/+5 |
| * | Use more detailed assertion messages in the code introduced by r289538 | Artur Pilipenko | 2016-12-13 | 1 | -4/+8 |
| * | Fix a buildbot failure introduced by r289538 | Artur Pilipenko | 2016-12-13 | 1 | -2/+1 |
| * | [DAGCombiner] Match load by bytes idiom and fold it into a single load | Artur Pilipenko | 2016-12-13 | 1 | -0/+276 |
| * | Move BaseIndexOffset in DAGCombiner.cpp so it will be available for the upcom... | Artur Pilipenko | 2016-12-13 | 1 | -104/+104 |
| * | Revert "In visitSTORE, always use FindBetterChain, rather than only when UseA... | Nirav Dave | 2016-12-09 | 1 | -141/+275 |
| * | In visitSTORE, always use FindBetterChain, rather than only when UseAA is ena... | Nirav Dave | 2016-12-09 | 1 | -275/+141 |
| * | [DAGCombine] Add (sext_in_reg (zext x)) -> (sext x) combine | Simon Pilgrim | 2016-12-06 | 1 | -0/+9 |
| * | [DAGCombiner] do not fold (fmul (fadd X, 1), Y) -> (fmad X, Y, Y) by default | Nicolai Haehnle | 2016-12-02 | 1 | -5/+11 |
| * | [SelectionDAG] Rename and clarify visitFMULForFMADCombine (NFC) | Nicolai Haehnle | 2016-12-01 | 1 | -4/+6 |
| * | Test commit. Comment changes. NFC. | Warren Ristow | 2016-11-29 | 1 | -5/+5 |
| * | [DAG] clean up foldSelectCCToShiftAnd(); NFCI | Sanjay Patel | 2016-11-28 | 1 | -35/+35 |
| * | [DAG] add helper function for selectcc --> and+shift transforms; NFC | Sanjay Patel | 2016-11-28 | 1 | -42/+51 |
| * | Revert "[DAG] Improve loads-from-store forwarding to handle TokenFactor" | Nirav Dave | 2016-11-28 | 1 | -13/+2 |
| * | Use SDValue helpers instead of explicitly going via SDValue::getNode(). NFCI | Simon Pilgrim | 2016-11-25 | 1 | -7/+7 |
| * | [DAGCombine] Teach DAG combine that if both inputs of a vselect are the same,... | Craig Topper | 2016-11-24 | 1 | -0/+4 |
| * | [DAG] Improve loads-from-store forwarding to handle TokenFactor | Nirav Dave | 2016-11-23 | 1 | -2/+13 |
| * | [DAGCombiner] Fix infinite loop in vector mul/shl combining | John Brawn | 2016-11-23 | 1 | -6/+6 |
| * | Type legalization for compressstore and expandload intrinsics. | Elena Demikhovsky | 2016-11-23 | 1 | -16/+13 |
| * | Fix spelling mistakes in SelectionDAG comments. NFC. | Simon Pilgrim | 2016-11-20 | 1 | -2/+2 |
| * | DAGCombiner: fix combine of trunc and select | Asaf Badouh | 2016-11-15 | 1 | -1/+1 |
| * | [DAG Combiner] Fix the native computation of the Newton series for reciprocals | Evandro Menezes | 2016-11-10 | 1 | -28/+30 |
| * | Use common SDLoc. NFCI. | Simon Pilgrim | 2016-11-10 | 1 | -3/+3 |
| * | [DAGCombiner] Correctly extract the ConstOrConstSplat shift value for SHL nodes | Simon Pilgrim | 2016-11-10 | 1 | -3/+2 |
| * | DAGCombiner: fix use-after-free when merging consecutive stores | Nicolai Haehnle | 2016-11-03 | 1 | -18/+22 |
| * | Expandload and Compressstore intrinsics | Elena Demikhovsky | 2016-11-03 | 1 | -2/+2 |
| * | [DAG] x | x --> x | Sanjay Patel | 2016-10-30 | 1 | -0/+4 |
| * | [DAG] x & x --> x | Sanjay Patel | 2016-10-30 | 1 | -0/+4 |
| * | [DAGCombiner] Fix a crash visiting `AND` nodes. | Davide Italiano | 2016-10-28 | 1 | -1/+6 |
| * | [DAGCombiner] Enable (urem x, (shl pow2, y)) -> (and x, (add (shl pow2, y), -... | Simon Pilgrim | 2016-10-25 | 1 | -3/+3 |
| * | [DAGCombiner] Enable srem(x.y) -> urem(x,y) combine for vectors | Simon Pilgrim | 2016-10-25 | 1 | -4/+2 |
| * | [DAGCombiner] Enable sdiv(x.y) -> udiv(x,y) combine for vectors | Simon Pilgrim | 2016-10-25 | 1 | -4/+2 |
| * | [DAGCombine] Preserve shuffles when one of the vector operands is constant | Zvi Rackover | 2016-10-25 | 1 | -34/+75 |
| * | Use SDValue::getConstantOperandVal() helper. NFCI. | Simon Pilgrim | 2016-10-23 | 1 | -4/+1 |
| * | [DAG] fold negation of sign-bit | Sanjay Patel | 2016-10-21 | 1 | -11/+27 |
| * | [DAG] use SDNode flags 'nsz' to enable fadd/fsub with zero folds | Sanjay Patel | 2016-10-21 | 1 | -16/+20 |
| * | [Target] remove TargetRecip class; 2nd try | Sanjay Patel | 2016-10-20 | 1 | -11/+34 |
| * | [DAGCombiner] Add general constant vector support to (srl (shl x, c), c) -> (... | Simon Pilgrim | 2016-10-20 | 1 | -8/+8 |
| * | Merged nested ifs. NFCI. | Simon Pilgrim | 2016-10-19 | 1 | -7/+6 |
