Chris Lattner 37ac608623 Turn a memcpy from a double* into a load/store of double instead of ... a load/store of i64. The later prevents promotion/scalarrepl of the source and dest in many cases. This fixes the 300% performance regression of the byval stuff on stepanov_v1p2. git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@45945 91177308-0d34-0410-b5e6-96231b3b80d8		2008-01-14 00:28:35 +00:00
..
ADCE
ArgumentPromotion	Teach argpromote to ruthlessly hack small byval structs when it can	2008-01-11 22:31:41 +00:00
BlockPlacement
BranchFolding
CodeExtractor
CondProp
ConstantMerge
ConstProp
CorrelatedExprs
DeadArgElim	When DAE drops the varargs part of a function, ensure any	2008-01-11 23:13:45 +00:00
DeadStoreElimination
DecomposeMultiDimRefs
GCSE
GlobalDCE
GlobalOpt	Fix PR1896	2008-01-04 05:04:53 +00:00
GVN
GVNPRE
IndVarsSimplify	Add new SCEV, SCEVSMax. This allows LLVM to analyze do-while loops.	2007-11-25 22:41:31 +00:00
Inline	we don't have to make an explicit copy of a byval argument when	2008-01-12 18:54:29 +00:00
InstCombine	Turn a memcpy from a double* into a load/store of double instead of	2008-01-14 00:28:35 +00:00
IPConstantProp
LCSSA
LICM	Update this testcase. The output needs to be disabled to pass.	2008-01-01 01:34:36 +00:00
LoopIndexSplit	If ExitValue operand is also defined in Loop header then	2007-12-03 19:17:21 +00:00
LoopRotate
LoopSimplify
LoopStrengthReduce
LoopUnroll
LoopUnswitch
LowerInvoke
LowerSetJmp
LowerSwitch
Mem2Reg
PredicateSimplifier
PruneEH	Make PruneEH update the nounwind/noreturn attributes	2007-12-10 19:09:40 +00:00
RaiseAllocations
Reassociate
ScalarRepl
SCCP
SimplifyCFG	don't hoist FP additions into unconditional adds + selects. This	2008-01-03 07:25:26 +00:00
SimplifyLibCalls
TailCallElim
TailDup