summaryrefslogtreecommitdiff
path: root/lib/Target/X86/X86ISelDAGToDAG.cpp
Commit message (Expand)AuthorAge
* Simplify and generalize X86DAGToDAGISel::CanBeFoldedBy, and drawDan Gohman2008-09-17
* Reverting r56249. On further investigation, this functionality isn't needed.Bill Wendling2008-09-16
* - Change "ExternalSymbolSDNode" to "SymbolSDNode".Bill Wendling2008-09-16
* Rename ConstantSDNode::getValue to getZExtValue, for consistencyDan Gohman2008-09-12
* fix a bunch of 80-col violationsGabor Greif2008-08-31
* erect abstraction boundaries for accessing SDValue members, rename Val -> Nod...Gabor Greif2008-08-28
* disallow direct access to SDValue::ResNo, provide a getter insteadGabor Greif2008-08-26
* Try approach to moving call address load inside of callseq_start. Now it's do...Evan Cheng2008-08-25
* Move the point at which FastISel taps into the SelectionDAGISelDan Gohman2008-08-23
* Simplify SelectRoot's interface, and factor out some common codeDan Gohman2008-08-21
* Move the handling of ANY_EXTEND, SIGN_EXTEND_INREG, and TRUNCATEDan Gohman2008-08-20
* Fix a (u)comiss intrinsic lowering bug. It was using anyext which can return ...Evan Cheng2008-08-17
* Oops, check in these files too, for the FastISel -> Fast rename.Dan Gohman2008-08-13
* Some fixes for x86-64 JIT. Make it use small codeDale Johannesen2008-08-11
* Rename SDOperand to SDValue.Dan Gohman2008-07-27
* Tidy SDNode::use_iterator, and complete the transition to have itDan Gohman2008-07-27
* Add titles to the various SelectionDAG viewGraph callsDan Gohman2008-07-21
* Add a new function, ReplaceAllUsesOfValuesWith, which handles bulkDan Gohman2008-07-17
* Fix the result type of X86's truncate to i8.Dan Gohman2008-07-16
* Do not use computationally expensive scheduling heuristics with -fast.Evan Cheng2008-07-01
* Split scheduling from instruction selection.Evan Cheng2008-06-30
* Unbreak DECLARE isel in pic mode.Evan Cheng2008-06-18
* Rather than avoiding to wrap ISD::DECLARE GV operand in X86ISD::Wrapper, simp...Evan Cheng2008-06-17
* Wrap MVT::ValueType in a struct to get type safetyDuncan Sands2008-06-06
* Fix a tblgen problem handling variable_ops in tblgen instructionDan Gohman2008-05-29
* Use movlps / movhps to modify low / high half of 16-byet memory location.Evan Cheng2008-05-23
* Handle a few more cases of folding load i64 into xmm and zero top bits.Evan Cheng2008-05-09
* Handle vector move / load which zero the destination register top bits (i.e. ...Evan Cheng2008-05-08
* Not checking for intrinsics which do not have a chain operand.Evan Cheng2008-04-25
* - Switch from std::set to SmallPtrSet.Evan Cheng2008-04-25
* Loosen up an assertion to allow intrinsics. I really have noChris Lattner2008-04-25
* Re-commit of the r48822, where the infinite looping problem discoveredRoman Levenstein2008-04-07
* CosmeticEvan Cheng2008-04-03
* Backing out 48222 temporarily.Evan Cheng2008-04-03
* Use a linked data structure for the uses lists of an SDNode, just like Roman Levenstein2008-03-26
* remove Evan's "ugly hack" that sorta attempted to get Chris Lattner2008-03-21
* Make insert_subreg a two-address instruction, vastly simplifying LowerSubregs...Christopher Lamb2008-03-16
* Get rid of a pseudo instruction and replace it with subreg based operation on...Christopher Lamb2008-03-13
* Recommitting parts of r48130. These do not appear to cause the observed failu...Christopher Lamb2008-03-11
* Change the model for FP Stack return to use fp operands on the Chris Lattner2008-03-11
* Don't emit FP_REG_KILL into a block that just returns. NothingChris Lattner2008-03-10
* Revert 48125, 48126, and 48130 for now to unbreak some x86-64 tests.Evan Cheng2008-03-10
* Allow insert_subreg into implicit, target-specific values. Christopher Lamb2008-03-10
* rename FpGETRESULT32 -> FpGET_ST0_32 etc. Add support forChris Lattner2008-03-09
* Remove -always-fold-and-in-test.Evan Cheng2008-03-04
* Set to default: x86 no longer fold and into test if it has more than one use.Evan Cheng2008-02-28
* Revert the assert for MUL_LOHI with an unused high result; ChrisDan Gohman2008-02-25
* Add an assert to verify that we don't see anDan Gohman2008-02-25
* Remove the hack that turned an {S,U}MUL_LOHI with an unused highDan Gohman2008-02-25
* Convert MaskedValueIsZero and all its users to use APInt. Also addDan Gohman2008-02-25