Philip Reames 0adbb19409 [EarlyCSE] Exploit open ended invariant.start scopes ... If we have an invariant.start with no corresponding invariant.end, then the memory location becomes invariant indefinitely after the invariant.start. As a result, anything dominated by the start is guaranteed to see the value the memory location had when the invariant.start executed. This patch adds an AvailableInvariants table which tracks the generation a particular memory location became invariant and then uses that information to allow value forwarding that would otherwise be disallowed by potentially aliasing stores. (Reminder: In EarlyCSE everything clobbers everything by default.) This should be compatible with the MemorySSA variant, but design is generational. We can and should add first class support for invariant.start within MemorySSA at a later time. I took a quick look at doing so, but probably need some input from a MemorySSA expert. Differential Revision: https://reviews.llvm.org/D43716 llvm-svn: 327577		2018-03-14 21:35:06 +00:00
..
ADCE	…
AddDiscriminators	Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)	2018-01-19 17:13:12 +00:00
AggressiveInstCombine	[AggressiveInstCombine] Fixed TruncCombine class to handle TruncInst leaf node correctly.	2018-01-31 22:39:05 +00:00
AlignmentFromAssumptions	[AlignmentFromAssumptions] Set source and dest alignments of memory intrinsiscs separately	2018-02-22 18:55:59 +00:00
ArgumentPromotion	[ArgumentPromotion] don't break musttail invariant PR36543	2018-03-02 00:59:27 +00:00
AtomicExpand	…
BDCE	[BDCE] Salvage debug info from dying insts	2018-02-21 01:55:33 +00:00
BlockExtractor	BlockExtractor: Don’t delete functions directly	2018-03-12 22:28:18 +00:00
BranchFolding	…
CallSiteSplitting	[CallSiteSplitting] Do not crash when BB's terminator changes.	2018-03-06 14:00:58 +00:00
CalledValuePropagation	Add CalledValuePropagation pass	2017-10-25 13:40:08 +00:00
CodeExtractor	[PartialInlining] Use isInlineViable to detect constructs preventing inlining.	2018-03-10 14:53:44 +00:00
CodeGenPrepare	[CGP] Fix the remove of matched phis in complex addressing mode	2018-03-12 03:50:07 +00:00
ConstProp	[TargetLibraryInfo] fix finite mathlib function availability	2018-01-08 17:38:09 +00:00
ConstantHoisting	Fix out-of-order stepping behavior in programs with hoisted constants.	2017-11-09 20:01:31 +00:00
ConstantMerge	…
Coroutines	[Coroutines] Don't move stores for allocator args	2018-02-15 19:31:45 +00:00
CorrelatedValuePropagation	Back out "Re-land: Teach CorrelatedValuePropagation to reduce the width of udiv/urem instructions."	2018-03-12 09:26:09 +00:00
CrossDSOCFI	…
DCE	[DCE] Salvage debug info from dead insts	2018-02-15 22:26:18 +00:00
DeadArgElim	[DAE] don't remove args of musttail target/caller	2018-03-01 00:09:35 +00:00
DeadStoreElimination	[DSE] Don't DSE stores that subsequent memmove calls read from	2018-02-20 23:19:34 +00:00
DivRemPairs	[DivRemPairs] split tests per target to account for bots that don't build for all targets	2017-09-09 14:10:59 +00:00
EarlyCSE	[EarlyCSE] Exploit open ended invariant.start scopes	2018-03-14 21:35:06 +00:00
EliminateAvailableExternally	…
EntryExitInstrumenter	EntryExitInstrumenter: set DebugLocs on the inserted call instructions (PR35412)	2017-11-28 18:44:26 +00:00
ExpandMemCmp/X86	[x86, MemCmpExpansion] allow 2 pairs of loads per block (PR33325)	2018-01-06 16:16:04 +00:00
Float2Int	…
ForcedFunctionAttrs	…
FunctionAttrs	[FunctionAttrs][ArgumentPromotion][GlobalOpt] Disable some optimisations passes for naked functions	2018-02-22 14:42:08 +00:00
FunctionImport	Reland r327041: [ThinLTO] Keep available_externally symbols live	2018-03-13 05:08:48 +00:00
GCOVProfiling	…
GVN	Mark MergedLoadStoreMotion as not preserving MemDep results	2018-02-23 10:41:57 +00:00
GVNHoist	[GVNHoist] Fix: PR35222 gvn-hoist incorrectly erases load in case of a loop	2018-01-04 07:47:24 +00:00
GVNSink	Add an @llvm.sideeffect intrinsic	2017-11-08 21:59:51 +00:00
GlobalDCE	…
GlobalMerge	…
GlobalOpt	[Evaluator] Evaluate load/store with bitcast	2018-03-13 10:19:50 +00:00
GlobalSplit	…
GuardWidening	…
IPConstantProp	[IPSCCP] do not break musttail invariant (PR36485)	2018-03-01 01:19:18 +00:00
IRCE	[SCEV] Smart range calculation for SCEVUnknown Phis	2018-03-01 06:56:48 +00:00
IndVarSimplify	Revert [SCEV] Fix isKnownPredicate	2018-03-13 06:36:00 +00:00
IndirectBrExpand	Introduce the "retpoline" x86 mitigation technique for variant #2 of the speculative execution vulnerabilities disclosed today, specifically identified by CVE-2017-5715, "Branch Target Injection", and is one of the two halves to Spectre..	2018-01-22 22:05:25 +00:00
InferAddressSpaces	[AMDGPU] Switch to the new addr space mapping by default	2018-02-02 16:07:16 +00:00
InferFunctionAttrs	…
Inline	[NFC] fix trivial typos in comments and documents	2018-01-29 05:17:03 +00:00
InstCombine	[InstCombine] [NFC] Add tests for peeking through unsigned FP casts for zero-equality compares (PR36682)	2018-03-14 17:31:03 +00:00
InstMerge	…
InstNamer	…
InstSimplify	[InstSimplify] fix folds for (0.0 - X) + X --> 0 (PR27151)	2018-03-14 21:23:27 +00:00
InterleavedAccess	[X86][LLVM]Expanding Supports lowerInterleaved{store|load}() in X86InterleavedAccess (VF64 stride 3-4)	2017-10-02 07:35:25 +00:00
Internalize	…
JumpThreading	[LazyValueInfo] PR33357 prevent infinite recursion on BinaryOperator	2018-03-13 18:14:10 +00:00
LCSSA	[Test] Fix the test to output to /dev/null instead of redirecting.	2018-02-23 19:03:04 +00:00
LICM	[LICM] update BlockColors after splitting predecessors	2018-02-12 17:56:55 +00:00
LoadStoreVectorizer	[AMDGPU] Supported ds_read_b128 generation; Widened vector length for local address-space.	2018-03-09 17:41:39 +00:00
LoopDataPrefetch	…
LoopDeletion	[LoopDeletion] Handle users in unreachable block	2018-01-12 07:24:43 +00:00
LoopDistribute	…
LoopIdiom	Adding a width of the GEP index to the Data Layout.	2018-02-14 06:58:08 +00:00
LoopInterchange	DA: remove uses of GEP, only ask SCEV	2018-03-06 21:55:59 +00:00
LoopLoadElim	…
LoopPredication	[Loop Predication] Teach LP about reverse loops with uge and sge latch conditions	2018-02-08 10:34:08 +00:00
LoopReroll	…
LoopRotate	[LoopRotate] Detect loops with indirect branches better (we're giving up on them).	2018-01-09 23:54:35 +00:00
LoopSimplify	[BasicBlockUtils] Check for unreachable preds before updating LI in UpdateAnalysisInformation	2018-01-02 16:25:50 +00:00
LoopSimplifyCFG	…
LoopStrengthReduce	Revert "[PowerPC] LSR tunings for PowerPC"	2018-03-09 16:08:55 +00:00
LoopUnroll	LoopUnroll: respect pragma unroll when AllowRemainder is disabled	2018-03-02 16:22:32 +00:00
LoopUnswitch	[SimplifyCFG] Re-apply Relax restriction for folding unconditional branches	2018-02-08 07:16:29 +00:00
LoopVectorize	[LV] Adding test for r327109	2018-03-09 18:02:36 +00:00
LoopVersioning	…
LoopVersioningLICM	…
LowerAtomic	…
LowerExpectIntrinsic	…
LowerGuardIntrinsic	…
LowerInvoke	…
LowerSwitch	…
LowerTypeTests	Use branch funnels for virtual calls when retpoline mitigation is enabled.	2018-03-09 19:11:44 +00:00
Mem2Reg	[Debugify] Add a pass to test debug info preservation	2017-12-08 21:57:28 +00:00
MemCpyOpt	Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)	2018-01-19 17:13:12 +00:00
MergeFunc	Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)	2018-01-19 17:13:12 +00:00
MergeICmps	[MergeICmps] Make sure that the comparison only has one use.	2018-03-13 07:05:55 +00:00
MetaRenamer	Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)	2018-01-19 17:13:12 +00:00
NameAnonGlobals	…
NaryReassociate	Add early exit on reassociation of 0 expression.	2018-03-07 02:17:08 +00:00
NewGVN	[InstCombine, NewGVN] remove FP undef from tests	2018-03-08 14:57:08 +00:00
ObjCARC	ObjCARC: teach the cloner about funclets	2018-03-12 21:46:09 +00:00
PGOProfile	[ThinLTO] Recommit of import global variables	2018-03-12 10:30:50 +00:00
PartiallyInlineLibCalls	[PartiallyInlineLibCalls][x86] add TTI hook to allow sqrt inlining to depend on arg rather than result	2017-11-27 21:15:43 +00:00
PhaseOrdering	Adding a width of the GEP index to the Data Layout.	2018-02-14 06:58:08 +00:00
PlaceSafepoints	Remove alignment argument from memcpy/memmove/memset in favour of alignment attributes (Step 1)	2018-01-19 17:13:12 +00:00
PreISelIntrinsicLowering	…
PruneEH	…
Reassociate	[Reassociate] fix test to be independent of FP undef	2018-03-08 22:05:27 +00:00
Reg2Mem	…
RewriteStatepointsForGC	[RewriteStatepoints] Fix stale parse points	2018-03-05 22:27:30 +00:00
SCCP	[IPSCCP] Add getCompare which returns either true, false, undef or null.	2018-03-05 17:33:50 +00:00
SLPVectorizer	[SLP] Additional tests for stores vectorization, NFC.	2018-03-05 20:20:12 +00:00
SROA	[SROA] Take advantage of separate alignments for memcpy source and destination	2018-03-13 14:25:33 +00:00
SafeStack	[SafeStack] Use updated CreateMemCpy API to set more accurate source and destination alignments.	2018-02-12 22:39:47 +00:00
SampleProfile	Profiling tests: Endianess XFAIL for powerpc- (32-bit)	2018-01-09 20:09:23 +00:00
Scalarizer	…
SeparateConstOffsetFromGEP	[AMDGPU] Change constant addr space to 4	2018-02-13 18:00:25 +00:00
SimpleLoopUnswitch	[PM/Unswitch] Teach SimpleLoopUnswitch to do non-trivial unswitching,	2017-11-17 19:58:36 +00:00
SimplifyCFG	Revert "[Debug] Retain both sets of debug intrinsics in HoistThenElseCodeToIf"	2018-03-09 22:00:10 +00:00
Sink	[Sink] Really really fix predicate in legality check	2018-01-11 21:28:57 +00:00
SpeculateAroundPHIs	Add a new pass to speculate around PHI nodes with constant (integer) operands when profitable.	2017-11-28 11:32:31 +00:00
SpeculativeExecution	…
StraightLineStrengthReduce	…
StripDeadPrototypes	…
StripSymbols	…
StructurizeCFG	[StructurizeCFG] fix test to be independent of FP undef	2018-03-08 17:13:57 +00:00
SyntheticCountsPropagation	Add a pass to generate synthetic function entry counts.	2018-01-09 19:39:35 +00:00
TailCallElim	Remove this test	2017-11-28 22:39:38 +00:00
ThinLTOBitcodeWriter	[ThinLTO] fix test failure without x86 backend	2018-02-06 07:03:09 +00:00
Util	LowerDbgDeclare: ignore dbg.declares for allocas with volatile access	2018-03-09 00:45:04 +00:00
WholeProgramDevirt	Use branch funnels for virtual calls when retpoline mitigation is enabled.	2018-03-09 19:11:44 +00:00