Sanjay Patel bcd538983f [SelectionDAG][x86] turn insertelement into undef with variable index into splat ... I noticed this along with the patterns in D51125, but when the index is variable, we don't convert insertelement into a build_vector. For x86, that means these get expanded at legalization time into the loading/spilling code that we see in the tests. I think it's always better to avoid going to memory on these, and we get the optimal 'broadcast' if it's available. I suspect other targets may want to look at enabling the hook. AArch64 and AMDGPU have regression tests that would be affected (although I did not check what would happen in those cases). In the most basic cases shown here, AArch64 would probably do much better with a splat. Differential Revision: https://reviews.llvm.org/D51186 llvm-svn: 340705		2018-08-26 18:20:41 +00:00
..
CMakeLists.txt	Remove trailing whitespace to trigger re-cmaking	2017-10-02 21:54:38 +00:00
DAGCombiner.cpp	[SelectionDAG][x86] turn insertelement into undef with variable index into splat	2018-08-26 18:20:41 +00:00
FastISel.cpp	[IR] Replace isa<TerminatorInst> with isTerminator().	2018-08-26 09:51:22 +00:00
FunctionLoweringInfo.cpp	DAG: Add calling convention argument to calling convention funcs	2018-07-28 13:25:19 +00:00
InstrEmitter.cpp	[MI] Change the array of MachineMemOperand pointers to be	2018-08-16 21:30:05 +00:00
InstrEmitter.h	[DebugInfo] Convert intrinsic llvm.dbg.label to MachineInstr.	2018-05-09 02:41:08 +00:00
LegalizeDAG.cpp	[ARM] Lower llvm.ctlz.i32 to a libcall when clz is not available.	2018-08-22 21:47:14 +00:00
LegalizeFloatTypes.cpp	DAG: Try to custom lower when promoting float operands	2018-08-15 20:34:54 +00:00
LegalizeIntegerTypes.cpp	[SelectionDAG][X86] Reorder the operands the MaskedStoreSDNode to put the value first.	2018-08-25 17:48:17 +00:00
LegalizeTypes.cpp	[DAG] Don't map a TableId to itself in the ReplacedValues map	2018-06-20 16:06:09 +00:00
LegalizeTypes.h	[FPEnv] Scalarize StrictFP vector operations	2018-08-14 22:13:11 +00:00
LegalizeTypesGeneric.cpp	Avoid losing Hi part when expanding VAARG nodes on big endian machines	2018-07-16 12:14:17 +00:00
LegalizeVectorOps.cpp	[FPEnv] Support constrained FREM intrinsic	2018-08-20 19:28:56 +00:00
LegalizeVectorTypes.cpp	[SelectionDAG][X86] Reorder the operands the MaskedStoreSDNode to put the value first.	2018-08-25 17:48:17 +00:00
LLVMBuild.txt
ResourcePriorityQueue.cpp	Silence a bunch of implicit fallthrough warnings	2017-12-19 22:05:25 +00:00
ScheduleDAGFast.cpp	Rename DEBUG macro to LLVM_DEBUG.	2018-05-14 12:53:11 +00:00
ScheduleDAGRRList.cpp	[ScheduleDAG] Fix unfolding of SUnits to already existent nodes.	2018-07-18 18:01:03 +00:00
ScheduleDAGSDNodes.cpp	[SDAG] Remove the reliance on MI's allocation strategy for	2018-08-14 23:30:32 +00:00
ScheduleDAGSDNodes.h	[CodeGen] Fix inconsistent declaration parameter name	2018-07-16 18:51:40 +00:00
ScheduleDAGVLIW.cpp	Rename DEBUG macro to LLVM_DEBUG.	2018-05-14 12:53:11 +00:00
SDNodeDbgValue.h	[DebugInfo] LowerDbgDeclare: Add derefs when handling CallInst users	2018-07-26 20:56:53 +00:00
SelectionDAG.cpp	[SelectionDAG][X86] Reorder the operands the MaskedStoreSDNode to put the value first.	2018-08-25 17:48:17 +00:00
SelectionDAGAddressAnalysis.cpp	[DAG] Teach findBaseOffset to interpret indexes of indexed memory operations	2018-01-26 16:51:27 +00:00
SelectionDAGBuilder.cpp	[IR] Replace isa<TerminatorInst> with isTerminator().	2018-08-26 09:51:22 +00:00
SelectionDAGBuilder.h	DAG: Add calling convention argument to calling convention funcs	2018-07-28 13:25:19 +00:00
SelectionDAGDumper.cpp	Get rid of SETCCE	2018-06-04 18:36:22 +00:00
SelectionDAGISel.cpp	[IR] Replace isa<TerminatorInst> with isTerminator().	2018-08-26 09:51:22 +00:00
SelectionDAGPrinter.cpp	Rename DEBUG macro to LLVM_DEBUG.	2018-05-14 12:53:11 +00:00
SelectionDAGTargetInfo.cpp	[CodeGen] Fix some Clang-tidy modernize and Include What You Use warnings; other minor fixes (NFC).	2017-09-13 21:15:20 +00:00
StatepointLowering.cpp	Remove trailing space	2018-07-30 19:41:25 +00:00
StatepointLowering.h	[IR][CodeGen] Remove dependency on EVT from IR/Function.cpp. Move EVT to CodeGen layer.	2018-03-29 17:21:10 +00:00
TargetLowering.cpp	[TargetLowering] Add BuildSDiv support for division by one or negone.	2018-08-21 10:20:36 +00:00