summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/MachineSink.cpp
Commit message (Expand)AuthorAgeFilesLines
* Use DomTree in MachineSink to sink over diamonds.Patrik Hagglund2014-12-041-15/+19
* Update SetVector to rely on the underlying set's insert to return a pair<iter...David Blaikie2014-11-191-1/+1
* [MachineSink] Use the real post dominator treeJingyue Wu2014-10-151-21/+14
* Access subtarget specific variables off of the MachineFunction'sEric Christopher2014-10-141-4/+2
* Revert r216862 due to a performance regressionJingyue Wu2014-10-011-9/+21
* [MachineSink+PGO] Teach MachineSink to use BlockFrequencyInfoBruno Cardoso Lopes2014-09-251-6/+23
* [MachineSinking] Conservatively clear kill flags after coalescing.Patrik Hagglund2014-09-091-0/+5
* Revert r216803 "[MachineSinking] Clear kill flag of all operands at all their...Juergen Ributzka2014-09-041-13/+3
* [MachineSink] Use the real post dominator treeJingyue Wu2014-09-011-21/+9
* [MachineSinking] Clear kill flag of all operands at all their uses.Juergen Ributzka2014-08-291-3/+13
* [MachineSink] Improve the compile time by preserving the dominance informationQuentin Colombet2014-08-111-39/+60
* Remove the TargetMachine forwards for TargetSubtargetInfo basedEric Christopher2014-08-041-2/+3
* Add TargetInstrInfo interface isAsCheapAsAMove.Jiangning Liu2014-07-291-1/+1
* [Modules] Remove potential ODR violations by sinking the DEBUG_TYPEChandler Carruth2014-04-221-1/+2
* [C++11] More 'nullptr' conversion. In some cases just using a boolean check i...Craig Topper2014-04-141-17/+17
* Disable each MachineFunctionPass for 'optnone' functions, unless thatPaul Robinson2014-03-311-0/+3
* Switch a number of loops in lib/CodeGen over to range-based for-loops, now thatOwen Anderson2014-03-171-16/+11
* Phase 2 of the great MachineRegisterInfo cleanup. This time, we're changingOwen Anderson2014-03-131-4/+4
* [C++11] Add 'override' keyword to virtual methods that override their base cl...Craig Topper2014-03-071-3/+3
* Now that we have C++11, turn simple functors into lambdas and remove a ton of...Benjamin Kramer2014-03-011-11/+6
* MachineSink: Fix and tweak critical-edge breaking heuristic.Will Dietz2013-10-141-7/+23
* Use SmallVectorImpl& instead of SmallVector to avoid repeating small vector s...Craig Topper2013-07-141-1/+1
* Use SmallVectorImpl instead of SmallVector for iterators and references to av...Craig Topper2013-07-031-3/+3
* Use the new script to sort the includes of every file under lib.Chandler Carruth2012-12-031-7/+7
* Remove unused BitVectors from getAllocatableSet().Jakob Stoklund Olesen2012-10-161-2/+0
* MachineSink: Sort the successors before trying to find SuccToSinkTo.Manman Ren2012-07-311-1/+1
* MachineSink: Sort the successors before trying to find SuccToSinkTo.Manman Ren2012-07-311-2/+15
* Codegen pass definition cleanup. No functionality.Andrew Trick2012-02-081-2/+1
* whitespaceAndrew Trick2012-02-081-5/+5
* Extract method for detecting constant unallocatable physregs.Jakob Stoklund Olesen2012-01-161-14/+1
* Do not sink instruction, if it is not profitable.Devang Patel2011-12-141-13/+76
* Fix comment.Devang Patel2011-12-091-2/+1
* Update stale comment.Devang Patel2011-12-091-4/+1
* Revert r146184. I am seeing performance regression cause by this patch in one...Devang Patel2011-12-081-10/+11
* Refactor. No intentional functionality change.Devang Patel2011-12-081-29/+41
* Filter "sink to" candidate blocks sooner. This avoids unnecessary computation...Devang Patel2011-12-081-11/+13
* Add bundle aware API for querying instruction properties and switch the codeEvan Cheng2011-12-071-1/+1
* While sinking machine instructions, sink matching DBG_VALUEs also otherwise l...Devang Patel2011-09-071-0/+31
* Fix a couple of places where changes are made but not tracked.Evan Cheng2011-04-111-1/+4
* Get rid of static constructors for pass registration. Instead, every pass ex...Owen Anderson2010-10-191-1/+3
* Begin adding static dependence information to passes, which will allow us toOwen Anderson2010-10-121-1/+6
* Now with fewer extraneous semicolons!Owen Anderson2010-10-071-1/+1
* Don't sink insert_subreg, subreg_to_reg, reg_sequence. They are meant to beEvan Cheng2010-09-231-1/+10
* Enable machine sinking critical edge splitting. e.g.Evan Cheng2010-09-201-7/+2
* Avoid splitting critical edge twice for a set of PHI uses.Evan Cheng2010-09-201-17/+23
* Fix code that break critical edges for PHI uses. Watch out for multiple PHIs ...Evan Cheng2010-09-181-71/+66
* Teach machine sink toEvan Cheng2010-09-171-68/+218
* Update debug logs.Evan Cheng2010-08-191-4/+4
* It's possible to sink a def if its local uses are PHI's.Evan Cheng2010-08-191-5/+5
* Remove disabled assertion.Evan Cheng2010-08-191-2/+0
OpenPOWER on IntegriCloud