Sanjay Patel 6847ec5b33 [DAGCombiner] shrink/widen a vselect to match its condition operand size (PR14657) ... We discussed shrinking/widening of selects in IR in D26556, and I'll try to get back to that patch eventually. But I'm hoping that this transform is less iffy in the DAG where we can check legality of the select that we want to produce. A few things to note: 1. We can't wait until after legalization and do this generically because (at least in the x86 tests from PR14657), we'll have PACKSS and bitcasts in the pattern. 2. This might benefit more of the SSE codegen if we lifted the legal-or-custom requirement, but that requires a closer look to make sure we don't end up worse. 3. There's a 'vblendv' opportunity that we're missing that results in andn/and/or in some cases. That should be fixed next. 4. I'm assuming that AVX1 offers the worst of all worlds wrt uneven ISA support with multiple legal vector sizes, but if there are other targets like that, we should add more tests. 5. There's a codegen miracle in the multi-BB tests from PR14657 (the gcc auto-vectorization tests): despite IR that is terrible for the target, this patch allows us to generate the optimal loop code because something post-ISEL is hoisting the splat extends above the vector loops. Differential Revision: https://reviews.llvm.org/D32620 llvm-svn: 301781		2017-04-30 22:44:51 +00:00
..
CMakeLists.txt	[CMake] NFC. Updating CMake dependency specifications	2016-11-17 04:36:50 +00:00
DAGCombiner.cpp	[DAGCombiner] shrink/widen a vselect to match its condition operand size (PR14657)	2017-04-30 22:44:51 +00:00
FastISel.cpp	PR32382: Fix emitting complex DWARF expressions.	2017-04-18 01:21:53 +00:00
FunctionLoweringInfo.cpp	[SelectionDAG] Use KnownBits struct in DAG's computeKnownBits and simplifyDemandedBits	2017-04-28 05:31:46 +00:00
InstrEmitter.cpp	Move value type list from TargetRegisterClass to TargetRegisterInfo	2017-04-24 19:51:12 +00:00
InstrEmitter.h
LegalizeDAG.cpp	[APInt] Use inplace shift methods where possible. NFCI	2017-04-28 03:36:24 +00:00
LegalizeFloatTypes.cpp	Revert "[APInt] Fix a few places that use APInt::getRawData to operate within the normal API."	2017-04-23 12:15:30 +00:00
LegalizeIntegerTypes.cpp	Do not legalize large add with addc/adde, introduce addcarry and do it with uaddo/addcarry	2017-04-30 19:24:09 +00:00
LegalizeTypes.cpp	[MVT][SVE] Scalable vector MVTs (3/3)	2017-04-20 13:54:09 +00:00
LegalizeTypes.h	Do not legalize large add with addc/adde, introduce addcarry and do it with uaddo/addcarry	2017-04-30 19:24:09 +00:00
LegalizeTypesGeneric.cpp	[SelectionDAG] Use getBuildVector helper where possible. NFCI	2017-04-25 15:10:47 +00:00
LegalizeVectorOps.cpp	DAG: Do not scalarize fsub if fneg is legal	2017-02-15 22:02:42 +00:00
LegalizeVectorTypes.cpp	[SelectionDAG] Use getBuildVector helper where possible. NFCI	2017-04-25 15:10:47 +00:00
LLVMBuild.txt
ResourcePriorityQueue.cpp	Add iterator_range<regclass_iterator> to {Target,MC}RegisterInfo, NFC	2017-01-25 19:29:04 +00:00
ScheduleDAGFast.cpp
ScheduleDAGRRList.cpp	[ARM] ScheduleDAGRRList::DelayForLiveRegsBottomUp must consider OptionalDefs	2017-04-23 06:58:08 +00:00
ScheduleDAGSDNodes.cpp	Remove redundant call to GluedNodes.back() [NFC]	2017-02-19 16:56:18 +00:00
ScheduleDAGSDNodes.h	[Target] Fix some Clang-tidy modernize and Include What You Use warnings; other minor fixes (NFC).	2017-01-11 01:45:03 +00:00
ScheduleDAGVLIW.cpp
SDNodeDbgValue.h
SelectionDAG.cpp	Do not legalize large add with addc/adde, introduce addcarry and do it with uaddo/addcarry	2017-04-30 19:24:09 +00:00
SelectionDAGBuilder.cpp	Use Argument::hasAttribute and AttributeList::ReturnIndex more	2017-04-28 18:37:16 +00:00
SelectionDAGBuilder.h	[InlineCost] Improve the cost heuristic for Switch	2017-04-28 16:04:03 +00:00
SelectionDAGDumper.cpp	Do not legalize large add with addc/adde, introduce addcarry and do it with uaddo/addcarry	2017-04-30 19:24:09 +00:00
SelectionDAGISel.cpp	TargetLowering: Add finalizeLowering() function; NFC	2017-04-28 20:25:05 +00:00
SelectionDAGPrinter.cpp
SelectionDAGTargetInfo.cpp
StatepointLowering.cpp	Use a pointer type for target frame indices during statepoint lowering	2017-04-27 17:17:16 +00:00
StatepointLowering.h
TargetLowering.cpp	Make getParamAlignment use argument numbers	2017-04-28 20:34:27 +00:00