Hal Finkel a14d6f1ea5 [LoopUnroll] Fix the partial unrolling threshold for small loop sizes ... When we compute the size of a loop, we include the branch on the backedge and the comparison feeding the conditional branch. Under normal circumstances, these don't get replicated with the rest of the loop body when we unroll. This led to the somewhat surprising behavior that really small loops would not get unrolled enough -- they could be unrolled more and the resulting loop would be below the threshold, because we were assuming they'd take (LoopSize * UnrollingFactor) instructions after unrolling, instead of (((LoopSize-2) * UnrollingFactor)+2) instructions. This fixes that computation. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@225565 91177308-0d34-0410-b5e6-96231b3b80d8		2015-01-10 00:30:55 +00:00
..
ADCE.cpp	Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>	2014-11-19 07:49:26 +00:00
AlignmentFromAssumptions.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
CMakeLists.txt	Add an AlignmentFromAssumptions Pass	2014-09-07 20:05:11 +00:00
ConstantHoisting.cpp	Remove unnecessary copying or replace it with moves in a bunch of places.	2014-10-04 16:55:56 +00:00
ConstantProp.cpp	[C++] Use 'nullptr'. Transforms edition.	2014-04-25 05:29:35 +00:00
CorrelatedValuePropagation.cpp	Make use of @llvm.assume from LazyValueInfo	2014-09-07 20:29:59 +00:00
DCE.cpp	[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE	2014-04-22 02:55:47 +00:00
DeadStoreElimination.cpp	[DSE] Remove no-data-layout-only type-based overlap checking	2014-10-17 11:56:00 +00:00
EarlyCSE.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
FlattenCFGPass.cpp	[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE	2014-04-22 02:55:47 +00:00
GVN.cpp	Re-reapply r221924: "[GVN] Perform Scalar PRE on gep indices that feed loads before	2015-01-09 19:19:56 +00:00
IndVarSimplify.cpp	Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>	2014-11-19 07:49:26 +00:00
JumpThreading.cpp	Revert r220349 to re-instate r220277 with a fix for PR21330 -- quite	2014-11-25 08:20:27 +00:00
LICM.cpp	Refine the notion of MayThrow in LICM to include a header specific version	2014-12-29 23:00:57 +00:00
LLVMBuild.txt	ScalarOpts/LLVMBuild.txt: Prune unused dependency to IPA.	2014-09-09 15:00:38 +00:00
LoadCombine.cpp	Use AA in LoadCombine	2014-11-03 23:19:16 +00:00
LoopDeletion.cpp	Use range based for loops to avoid needing to re-mention SmallPtrSet size.	2014-08-24 23:23:06 +00:00
LoopIdiomRecognize.cpp	Remove extra whitespace in function declaration. No functionality change.	2014-06-14 03:48:29 +00:00
LoopInstSimplify.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
LoopRerollPass.cpp	Reformat partially, where I touched for whitespace changes.	2014-10-28 11:54:52 +00:00
LoopRotation.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
LoopStrengthReduce.cpp	Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>	2014-11-19 07:49:26 +00:00
LoopUnrollPass.cpp	[LoopUnroll] Fix the partial unrolling threshold for small loop sizes	2015-01-10 00:30:55 +00:00
LoopUnswitch.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
LowerAtomic.cpp	IR: add "cmpxchg weak" variant to support permitted failure.	2014-06-13 14:24:07 +00:00
Makefile
MemCpyOptimizer.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
MergedLoadStoreMotion.cpp	Sink store based on alias analysis	2014-12-15 14:09:53 +00:00
PartiallyInlineLibCalls.cpp	PartiallyInlineLibCalls: Check sqrt result type before transforming it.	2014-08-01 23:21:21 +00:00
Reassociate.cpp	[Reassociate] Use dbgs() instead of errs().	2014-12-12 14:44:12 +00:00
Reg2Mem.cpp	[Modules] Fix potential ODR violations by sinking the DEBUG_TYPE	2014-04-22 02:55:47 +00:00
SampleProfile.cpp	Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>	2014-11-19 07:49:26 +00:00
Scalar.cpp	[C API] Make the 'lower switch' pass available via the C API.	2014-09-11 21:32:32 +00:00
Scalarizer.cpp	Revert "IR: MDNode => Value"	2014-11-11 21:30:22 +00:00
ScalarReplAggregates.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
SCCP.cpp	Update SetVector to rely on the underlying set's insert to return a pair<iterator, bool>	2014-11-19 07:49:26 +00:00
SeparateConstOffsetFromGEP.cpp	[SeparateConstOffsetFromGEP] Allow SeparateConstOffsetFromGEP pass to lower GEPs.	2014-11-19 06:24:44 +00:00
SimplifyCFGPass.cpp	[PM] Split the AssumptionTracker immutable pass into two separate APIs:	2015-01-04 12:03:27 +00:00
Sink.cpp	Use range based for loops to avoid needing to re-mention SmallPtrSet size.	2014-08-24 23:23:06 +00:00
SROA.cpp	Revert "Reapply: Teach SROA how to update debug info for fragmented variables."	2015-01-08 02:02:00 +00:00
StructurizeCFG.cpp	StructurizeCFG: Use LoopInfo analysis for better loop detection	2014-12-03 04:28:32 +00:00
TailRecursionElimination.cpp	Fix tail recursion elimination	2014-11-19 13:32:51 +00:00