summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen
Commit message (Expand)AuthorAgeFilesLines
* Fix two problems in SelectionDAGLegalize::ExpandBUILD_VECTOR's handlingChris Lattner2008-03-091-21/+38
* Teach SD some vector identities, allowing us to compile vec_set-9 into:Chris Lattner2008-03-081-1/+13
* Implement x86 support for @llvm.prefetch. It corresponds to prefetcht{0|1|2} ...Evan Cheng2008-03-083-4/+29
* Something that kills a super-register alsoBill Wendling2008-03-071-2/+1
* Fixed a register scavenger bug. If a def is re-defining part of a super regis...Evan Cheng2008-03-071-3/+8
* When setting the "unused" info, take into account something like this:Bill Wendling2008-03-061-8/+38
* 80 col violation.Evan Cheng2008-03-061-2/+4
* some more spelling changesGabor Greif2008-03-061-1/+1
* Constant fold SIGN_EXTEND_INREG with ashr not lshr.Evan Cheng2008-03-061-1/+1
* Fix a coalescer bug wrt how dead copy interval is shortened.Evan Cheng2008-03-052-13/+36
* Clarify that CALLSEQ_START..END may not be nested,Dale Johannesen2008-03-051-0/+7
* Generalize FP constant shrinking optimization to apply to any vtChris Lattner2008-03-051-26/+25
* Improve comment, pass in the original VT so that we can shrink a long double ...Chris Lattner2008-03-051-2/+4
* Codegen support for i128 UINT_TO_FP. This just fixes aDan Gohman2008-03-052-6/+2
* Add a target lowering hook to control whether it's worthwhile to compress fp ...Evan Cheng2008-03-051-1/+2
* 64bit CAS on 32bit x86.Andrew Lenharth2008-03-051-0/+11
* Codegen support for i128 SINT_TO_FP.Dan Gohman2008-03-053-21/+56
* Refactor code. Remove duplicated functions that basically do the same thing asEvan Cheng2008-03-0511-149/+102
* Some improvements related to the computation of heights, depths of SUnits.Roman Levenstein2008-03-041-21/+93
* Refactor ExpandConstantFP so it can optimize load from constpool of types lar...Evan Cheng2008-03-041-16/+19
* Did I say 'e = getNumOperands()'? I meant --e, of course.Bill Wendling2008-03-041-1/+1
* Rename isOperand() to isOperandOf() (and other similar methods). It always co...Evan Cheng2008-03-044-17/+17
* Miscellaneous clean-ups based on Evan's feedback:Bill Wendling2008-03-032-65/+79
* Misc. APInt-ification in the DAGCombiner.Dan Gohman2008-03-031-17/+20
* More APInt-ification.Dan Gohman2008-03-031-10/+6
* Yet more APInt-ification.Dan Gohman2008-03-031-9/+6
* More APInt-ification.Dan Gohman2008-03-031-16/+19
* More APInt-ification.Dan Gohman2008-03-031-3/+4
* Go through the machine instruction's operands to make sure that we're notBill Wendling2008-03-031-12/+52
* Make the register scavenger update the bookkeeping values for sub/superBill Wendling2008-03-031-3/+39
* Multiple instructions can be inserted when eliminating frame indexes. We needBill Wendling2008-03-031-7/+24
* all but CAS working on x86Andrew Lenharth2008-03-011-13/+14
* Add MVT::is128BitVector and is64BitVector. ShrinkDale Johannesen2008-03-011-16/+5
* Refactor / clean up code; remove td list scheduler special tie breaker (no re...Evan Cheng2008-03-011-78/+59
* Don't fill eh frames even though these are text sections.Evan Cheng2008-02-292-8/+9
* If we reload a virtual register that's already been assigned, we want to markBill Wendling2008-02-291-1/+2
* Fix PR2112: don't run loop aligner if target doesn't have a TargetLowering ob...Evan Cheng2008-02-291-3/+5
* No need for coalescer to update kills. Only copies are coalesced and those in...Evan Cheng2008-02-292-69/+3
* Remove redundant #include.Evan Cheng2008-02-291-1/+0
* More APInt-ification.Dan Gohman2008-02-291-107/+42
* Use the new convertFromAPInt instead of convertFromZeroExtendedInteger,Dan Gohman2008-02-291-5/+3
* Use the new APInt-enabled form of getConstant instead of convertingDan Gohman2008-02-291-1/+1
* Added option -align-loops=<true/false> to disable loop aligner pass.Evan Cheng2008-02-282-0/+7
* Interface of getByValTypeAlignment differed betweenDale Johannesen2008-02-281-2/+3
* Fix an assertion message.Dale Johannesen2008-02-281-1/+1
* Keep track how many commutes are performed by the scheduler.Evan Cheng2008-02-281-0/+4
* implement expand for ISD::DECLARE by just deleting it.Chris Lattner2008-02-281-0/+3
* Add a quick and dirty "loop aligner pass". x86 uses it to align its loops to ...Evan Cheng2008-02-286-10/+92
* Handle load/store of misaligned vectors that are the Dale Johannesen2008-02-271-19/+30
* Fix a bug in dead spill slot elimination.Evan Cheng2008-02-271-0/+2
OpenPOWER on IntegriCloud