Prune some includes
[oota-llvm.git] / lib / Target / X86 / X86ISelDAGToDAG.cpp
2012-03-27 Craig TopperPrune some includes
2012-03-27 Craig TopperRemove unnecessary llvm:: qualifications
2012-03-17 Craig TopperReorder includes in Target backends to following coding...
2012-03-09 Craig TopperUse uint16_t to store opcodes in static tables in X86...
2012-02-22 Craig TopperDeclare register classes as const. Fix a couple pointer...
2012-02-16 Jakob Stoklund OlesenUse the same CALL instructions for Windows as for every...
2012-02-15 Pete CooperStop custom lowering forr x86 DEC64m from happening...
2012-02-13 Pete CooperFixed bug when custom lowering DEC64m on x86.
2012-01-20 David BlaikieMore dead code removal (using -Wunreachable-code)
2012-01-12 Chandler CarruthSwitch all of the uses of my InsertDAGNode helper to...
2012-01-11 Chandler CarruthRevert r147945 which disabled an addressing mode transf...
2012-01-11 Chandler CarruthDisable the transformation I added in r147936 to see...
2012-01-11 Chandler CarruthHoist a really redundant code pattern into a helper...
2012-01-11 Chandler CarruthSimplify the AND-rooted mask+shift checking code to...
2012-01-11 Chandler CarruthUnify the interface of the three mask+shift transform...
2012-01-11 Chandler CarruthClarify and make explicit some of the requirements...
2012-01-11 Chandler CarruthHoist the logic to transform shift+mask combinations...
2012-01-11 Chandler CarruthTeach the X86 instruction selection to do some heroic...
2012-01-09 Chandler CarruthDon't rely on the fact that shift values are never...
2011-11-16 Pete CooperAdded missing comment about new custom lowering of...
2011-11-15 Pete CooperAdded custom lowering for load->dec->store sequence...
2011-11-03 Dan GohmanReapply r143206, with fixes. Disallow physical register...
2011-10-29 Dan GohmanRevert r143206, as there are still some failing tests.
2011-10-28 Dan GohmanReapply r143177 and r143179 (reverting r143188), with...
2011-10-28 Duncan SandsSpeculatively disable Dan's commits 143177 and 143179...
2011-10-28 Dan GohmanEliminate LegalizeOps' LegalizedNodes map and have...
2011-10-08 Jakob Stoklund OlesenAdd TEST8ri_NOREX pseudo to constrain sub_8bit_hi copies.
2011-08-01 Bruno Cardoso LopesTeach PreprocessISelDAG to be aware of vector types...
2011-07-13 Eli FriedmanMake sure we don't combine a large displacement and...
2011-07-13 Eli FriedmanRefactor out checking for displacements on x86-64 addre...
2011-07-01 Eric ChristopherTargetConstant immediates won't be placed into register...
2011-06-30 Eric ChristopherFix a small thinko for constant i64 lock/orq optimizati...
2011-05-20 Stuart HastingsRe-commit 131641 with fixes; de-pseudoize MOVSX16rr8...
2011-05-17 Eric ChristopherUpdate comment.
2011-05-17 Eric ChristopherSupport XOR and AND optimization with no return value.
2011-05-17 Eric ChristopherCouple less magic numbers.
2011-05-17 Eric ChristopherMake this code a little less magic number laden.
2011-05-11 Eric ChristopherTurn this into a table, this will make more sense shortly.
2011-05-10 Eric ChristopherOptimize atomic lock or that doesn't use the result...
2011-04-23 Benjamin KramerSilence an overzealous uninitialized variable warning...
2011-04-22 Benjamin KramerX86: Try to use a smaller encoding by transforming...
2011-02-16 Stuart HastingsSwap VT and DebugLoc operands of getExtLoad() for consi...
2011-02-13 Chris LattnerEnhance ComputeMaskedBits to know that aligned frameindexes
2011-01-27 NAKAMURA Takumilib/Target/X86/X86ISelDAGToDAG.cpp: __main should be...
2011-01-16 Chris Lattnerfix PR8514, a bug where the "heroic" transformation...
2011-01-14 Ted Kremenek'HiReg' is written but never read. Nuke its
2011-01-06 Bill WendlingPR8918 - When used with MinGW64, LLVM generates a ...
2010-12-21 Chris Lattnerrename MVT::Flag to MVT::Glue. "Flag" is a terrible...
2010-12-05 Chris Lattnerit turns out that when ".with.overflow" intrinsics...
2010-10-26 Dale JohannesenUse a MemIntrinsicSDNode for ISD::PREFETCH, which touches
2010-10-05 Chris LattnerUse #NAME# to have the CMOV multiclass define things...
2010-10-05 Chris Lattnerswitch CMOVBE to the multipattern:
2010-09-22 Eric ChristopherTemporarily work around new address lowering while...
2010-09-22 Chris Lattnerreimplement elf TLS support in terms of addressing...
2010-09-22 Chris Lattnerconvert the last 4 X86ISD nodes that should have memope...
2010-09-22 Chris Lattnergive X86ISD::FNSTCW16m a memoperand, since it touches...
2010-09-22 Chris Lattnergive FP_TO_INT16_IN_MEM and friends a memoperand. ...
2010-09-22 Chris Lattnergive VZEXT_LOAD a memory operand, it now works with...
2010-09-22 Chris Lattnerrevert r114386 now that address modes work correctly...
2010-09-21 Chris Lattnergive LCMPXCHG_DAG[8] a memory operand, allowing it...
2010-09-21 Chris Lattnerreimplement support for GS and FS relative address...
2010-09-21 Chris Lattnerfix a long standing wart: all the ComplexPattern's...
2010-09-21 Chris Lattnereven though I'm about to rip it out, simplify the addre...
2010-09-21 Chris Lattnerpropagate MachinePointerInfo through various uses of...
2010-09-21 Chris Lattnerfix rdar://8453210, a crash handling a call through...
2010-09-04 Chris Lattnerzap dead code.
2010-09-03 Jakob Stoklund OlesenDon't call Predicate_* from X86 target.
2010-08-25 Benjamin KramerRemove dead recursive function. Yay for clang -Wunused...
2010-08-04 Eli FriedmanPR7814: Truncates cannot be ignored for signed comparisons.
2010-07-08 Chris LattnerChange LEA to have 5 operands for its memory operand...
2010-07-07 Evan ChengMove getExtLoad() and (some) getLoad() DebugLoc argumen...
2010-07-06 Devang PatelPropagate debug loc.
2010-06-26 Jakob Stoklund OlesenWhen creating X86 MUL8 and DIV8 instructions, make...
2010-06-18 Dan GohmanChange UpdateNodeOperands' operand and return value...
2010-06-18 Dan GohmanDon't maintain a set of deleted nodes; instead, use...
2010-06-03 Eric ChristopherAdd first pass at darwin tls compiler support.
2010-05-24 Jakob Stoklund OlesenRename X86 subregister indices to something shorter.
2010-04-29 Dan GohmanDon't leave Base.FrameIndex uninitialized, so that...
2010-04-28 Evan ChengEnable i16 to i32 promotion by default.
2010-04-20 Chris Lattnerteach the x86 address matching stuff to handle
2010-04-17 Dan GohmanUse const qualifiers with TargetLowering. This eliminat...
2010-04-15 Dan GohmanAdd const qualifiers to CodeGen's use of LLVM IR constr...
2010-04-14 Dan GohmanDelete unneeeded arguments.
2010-04-02 Chris Lattneruse DebugLoc default ctor instead of DebugLoc::getUnkno...
2010-03-17 Evan ChengX86 address mode matching code MatchAddressRecursively...
2010-03-14 Evan ChengDo not force indirect tailcall through fixed registers...
2010-03-04 Chris Lattneradd a comment.
2010-03-03 Chris Lattnerfactor the 'sign extended from 8 bit' patterns better so
2010-03-02 Chris Lattnermerge two loops over all nodes in the graph into one.
2010-03-02 Chris Lattnereliminate PreprocessForRMW now that isel handles it.
2010-03-02 Chris LattnerFix some issues in WalkChainUsers dealing with
2010-03-02 Chris LattnerSink InstructionSelect() out of each target into SDISel...
2010-03-01 Chris Lattnerremove a little hack I did for the old isel, not needed
2010-03-01 Chris Lattnerremove a terrible hack that disabled assertions from...
2010-02-23 Chris Lattnerno need to override IsLegalToFold, the base implementation
2010-02-21 Chris Lattnerfix and un-xfail X86/vec_ss_load_fold.ll
2010-02-21 Chris Lattnerrename SelectScalarSSELoad -> SelectScalarSSELoadXXX...
2010-02-17 Chris Lattnerrename and document some arguments so I don't have...
2010-02-16 Chris Lattnerfix rdar://7653908, a crash on a case where we would...
2010-02-15 Evan ChengSplit SelectionDAGISel::IsLegalAndProfitableToFold to
next