summaryrefslogtreecommitdiffstats
path: root/llvm/lib/CodeGen/SelectionDAG/LegalizeDAG.cpp
Commit message (Expand)AuthorAgeFilesLines
...
* Migrate existing backends that care about software floating pointEric Christopher2015-05-121-1/+1
* CodeGen: Default overflow operations to expand so we don't have to assume tar...Jan Vesely2015-04-291-6/+0
* Reapply r235977 "[DebugInfo] Add debug locations to constant SD nodes"Sergey Dmitrouk2015-04-281-144/+173
* Revert "[DebugInfo] Add debug locations to constant SD nodes"Daniel Jasper2015-04-281-173/+144
* [DebugInfo] Add debug locations to constant SD nodesSergey Dmitrouk2015-04-281-144/+173
* [AArch64] Promote f16 operations to f32.Ahmed Bougacha2015-04-101-3/+52
* [CodeGen] Replace the reused stores' chain for extractelt expansion.Ahmed Bougacha2015-03-091-6/+20
* SDAG: Merge the meat of two ExpandAtomic implementations.Benjamin Kramer2015-03-051-126/+2
* [SDAG] Handle LowerOperation returning its input consistentlyHal Finkel2015-02-241-2/+2
* [X86] Teach how to custom lower double-to-half conversions under fast-math.Andrea Di Biagio2015-02-231-0/+15
* Add generic fmad DAG node.Matt Arsenault2015-02-201-0/+3
* Implement new way of expanding extloads.Matt Arsenault2015-01-141-14/+17
* [SelectionDAG] Allow targets to specify legality of extloads' resultAhmed Bougacha2015-01-081-4/+7
* Don't repeat class/function/variable names in comments. NFC.Sanjay Patel2014-11-211-47/+35
* Less space; NFCSanjay Patel2014-11-211-8/+4
* Update SetVector to rely on the underlying set's insert to return a pair<iter...David Blaikie2014-11-191-1/+1
* Fix an incorrect chain operand when expanding INSERT_VECTOR operations throug...Owen Anderson2014-11-181-1/+1
* Add minnum / maxnum codegenMatt Arsenault2014-10-211-0/+10
* Use the subtarget on the dag to get TargetFrameLowering ratherEric Christopher2014-10-091-1/+1
* Remove unnecessary copying or replace it with moves in a bunch of places.Benjamin Kramer2014-10-041-1/+2
* Replace dead links to "Hacker's Delight" with general references. NFC.Sanjay Patel2014-09-151-2/+2
* [SDAG] Re-instate r215611 with a fix to a pesky X86 DAG combine.Chandler Carruth2014-08-271-0/+2
* Revert r215611 because it caused the infinite loop in bug 20736. There is a r...Nick Lewycky2014-08-231-2/+0
* [ARM] Enable DP copy, load and store instructions for FPv4-SPOliver Stannard2014-08-211-6/+20
* Teach the AArch64 backend to handle f16Oliver Stannard2014-08-181-0/+3
* [SDAG] Fix a case where we would iteratively legalize a node duringChandler Carruth2014-08-141-0/+2
* Remove the TargetMachine forwards for TargetSubtargetInfo basedEric Christopher2014-08-041-1/+3
* [SDAG] Begin simplifying the way in which the legalizer deletes nodes.Chandler Carruth2014-08-011-41/+25
* Make sure no loads resulting from load->switch DAGCombine are marked invariantLouis Gerbarg2014-07-311-18/+24
* [SDAG] Add DEBUG logging to the legalizer, fixing a "bug" found byChandler Carruth2014-07-281-3/+19
* Add alignment value to allowsUnalignedMemoryAccessMatt Arsenault2014-07-271-8/+12
* [SDAG] Add an assert that we don't mess up the number of values whenChandler Carruth2014-07-261-0/+3
* [SDAG] Simplify the code for handling single-value nodes and addChandler Carruth2014-07-261-8/+12
* [SDAG] When performing post-legalize DAG combining, run the legalizerChandler Carruth2014-07-261-57/+93
* AA metadata refactoring (introduce AAMDNodes)Hal Finkel2014-07-241-27/+27
* CodeGen: generate single libcall for fptrunc -> f16 operations.Tim Northover2014-07-171-6/+6
* CodeGen: extend f16 conversions to permit types > float.Tim Northover2014-07-171-3/+20
* ARM: Allow __fp16 as a function arg or return type for AArch64Oliver Stannard2014-07-111-1/+1
* SelectionDAG: Factor FP_TO_SINT lower code out of DAGLegalizerJan Vesely2014-07-101-58/+3
* Make it possible for ints/floats to return different values from getBooleanCo...Daniel Sanders2014-07-101-3/+3
* [DAG] Pass the argument list to the CallLoweringInfo via move semantics. NFCI.Juergen Ributzka2014-07-011-8/+9
* SelectionDAG: Expand i64 = FP_TO_SINT i32Tom Stellard2014-06-171-0/+59
* LegalizeDAG: make sure cast is unsigned before using FP_TO_UINT.Tim Northover2014-06-151-1/+4
* IR: add "cmpxchg weak" variant to support permitted failure.Tim Northover2014-06-131-8/+29
* SelectionDAG: Expand SELECT_CC to SELECT + SETCCTom Stellard2014-06-101-1/+17
* Fix wrong setcc result type when legalizing uaddo/usuboMatt Arsenault2014-05-281-5/+11
* Target: remove old constructors for CallLoweringInfoSaleem Abdulrasool2014-05-171-45/+38
* Use a logical not when inverting SetCC. This unfortunately doesn't fire on a...Pete Cooper2014-05-121-3/+3
* Implememting named register intrinsicsRenato Golin2014-05-061-0/+7
* We already calculate WideVT above, just reuse it.Eric Christopher2014-04-281-2/+1
OpenPOWER on IntegriCloud