aboutsummaryrefslogtreecommitdiffstats
path: root/lib/CodeGen/MachineLICM.cpp
Commit message (Expand)AuthorAgeFilesLines
* Add bundle aware API for querying instruction properties and switch the codeEvan Cheng2011-12-071-4/+4
* First chunk of MachineInstr bundle support.Evan Cheng2011-12-061-2/+3
* Rename MVT::untyped to MVT::Untyped to match similar nomenclature.Owen Anderson2011-11-161-1/+1
* Disable LICM speculation in high register pressure situation again now that D...Evan Cheng2011-10-261-1/+1
* As Evan suggested, loads from constant pool are safe to speculate.Devang Patel2011-10-201-5/+5
* Add a comment.Devang Patel2011-10-201-1/+3
* Constraint register class with constrainRegClass() to CSE a virtual into anot...Evan Cheng2011-10-171-3/+26
* It is safe to speculate load from GOT. This fixes performance regression caus...Devang Patel2011-10-171-1/+17
* Tabs to spaces.Nick Lewycky2011-10-131-2/+2
* Disable machine LICM speculation check (for profitability) until I have time ...Evan Cheng2011-10-121-6/+15
* Expand the check for a landing pad so that it looks at the basic block'sBill Wendling2011-10-121-5/+11
* Fix r141744.Evan Cheng2011-10-121-1/+19
* Refine r141689 with a tri-state variable.Evan Cheng2011-10-111-19/+23
* N.B. This is with the new EH scheme:Bill Wendling2011-10-111-0/+5
* Add dominance check for the instruction being hoisted.Devang Patel2011-10-111-1/+46
* Revert r141569 and r141576.Devang Patel2011-10-101-29/+0
* If loop header is also loop exiting block then it may not be safe to hoist in...Devang Patel2011-10-101-5/+4
* Add dominance check for the instruction being hoisted.Devang Patel2011-10-101-0/+30
* Teach MachineLICM reg pressure tracking code to deal with MVT::untyped. Sorry...Evan Cheng2011-09-011-27/+40
* Sink SubtargetFeature and TargetInstrItineraries (renamed MCInstrItineraries)...Evan Cheng2011-06-291-1/+1
* - Rename TargetInstrDesc, TargetOperandInfo to MCInstrDesc and MCOperandInfo andEvan Cheng2011-06-281-3/+3
* More refactoring. Move getRegClass from TargetOperandInfo to TargetInstrInfo.Evan Cheng2011-06-271-1/+1
* Look pass copies when determining whether hoisting would end up inserting mor...Evan Cheng2011-04-111-8/+17
* Move getRegPressureLimit() from TargetLoweringInfo to TargetRegisterInfo.Cameron Zwarich2011-03-071-1/+1
* Sorry, several patches in one.Evan Cheng2011-01-201-40/+12
* Simplify a bunch of isVirtualRegister() and isPhysicalRegister() logic.Jakob Stoklund Olesen2011-01-101-4/+4
* Add a FIXME comment.Dan Gohman2010-11-111-0/+2
* MachineLICM should not claim to be preserving the CFG when it can split criticalJakob Stoklund Olesen2010-11-011-1/+0
* Use instruction itinerary to determine what instructions are 'cheap'.Evan Cheng2010-10-261-4/+36
* More accurate estimate / tracking of register pressure.Evan Cheng2010-10-201-64/+121
* Make CodeGen TBAA-aware.Dan Gohman2010-10-201-1/+3
* Re-enable register pressure aware machine licm with fixes. Hoist() may haveEvan Cheng2010-10-191-77/+58
* Get rid of static constructors for pass registration. Instead, every pass ex...Owen Anderson2010-10-191-2/+6
* Revert r116781 "- Add a hook for target to determine whether an instruction defDaniel Dunbar2010-10-191-36/+52
* Fix for machine licm assert: RCCost <= RegPressure[RCId]Andrew Trick2010-10-191-2/+2
* - Add a hook for target to determine whether an instruction def isEvan Cheng2010-10-191-52/+36
* More machine LICM work. It now tracks register pressure for path from prehead...Evan Cheng2010-10-161-69/+155
* Register pressure and instruction latency aware machine LICM. Work in progress.Evan Cheng2010-10-141-26/+242
* Begin adding static dependence information to passes, which will allow us toOwen Anderson2010-10-121-1/+6
* Don't waste time unfolding simple loads. The unfolded copy won't be hoisted.Evan Cheng2010-10-081-0/+4
* Now with fewer extraneous semicolons!Owen Anderson2010-10-071-1/+1
* Reapply r110396, with fixes to appease the Linux buildbot gods.Owen Anderson2010-08-061-2/+2
* Revert r110396 to fix buildbots.Owen Anderson2010-08-061-2/+2
* Don't use PassInfo* as a type identifier for passes. Instead, use the addres...Owen Anderson2010-08-051-2/+2
* Comment typo.Dale Johannesen2010-07-291-1/+1
* Fix batch of converting RegisterPass<> to INTIALIZE_PASS().Owen Anderson2010-07-211-2/+2
* Fix test for switch statements and increaseDale Johannesen2010-07-201-2/+3
* Don't hoist things out of a large switch inside aDale Johannesen2010-07-201-2/+6
* Teach ProcessImplicitDefs to transform more COPY instructions into IMPLICIT_D...Evan Cheng2010-07-141-6/+3
* change machinelicm to use MachineInstr::isSafeToMove. NoChris Lattner2010-07-121-18/+8
generated by cgit v1.1 at 2024-07-15 16:46:33 +0000