Owen Anderson 956afdd1f2 Relax the "don't unroll loops containing calls" rule. Instead, when a loop contains a call, lower the ...

unrolling threshold to the optimize-for-size threshold.  Basically, for loops containing calls, unrolling
can still be profitable as long as the loop is REALLY small.

llvm-svn: 113439

2010-09-08 23:10:07 +00:00

..

ADCE.cpp

…

BasicBlockPlacement.cpp

…

CMakeLists.txt

…

CodeGenPrepare.cpp

…

ConstantProp.cpp

…

CorrelatedValuePropagation.cpp

Propagate non-local comparisons. Fixes PR1757.

2010-09-03 22:47:08 +00:00

DCE.cpp

…

DeadStoreElimination.cpp

…

GEPSplitter.cpp

…

GVN.cpp

zap dead code.

2010-09-04 18:12:00 +00:00

IndVarSimplify.cpp

…

JumpThreading.cpp

Change lower atomic pass to use IntrinsicInst to simplify it a bit.

2010-09-05 20:10:47 +00:00

LICM.cpp

fix PR8067, an over-aggressive assertion in LICM.

2010-09-06 05:11:24 +00:00

LoopDeletion.cpp

…

LoopIndexSplit.cpp

…

LoopRotation.cpp

Teach loop rotate to hoist trivially invariant instructions

2010-09-06 01:10:22 +00:00

LoopStrengthReduce.cpp

…

LoopUnrollPass.cpp

Relax the "don't unroll loops containing calls" rule. Instead, when a loop contains a call, lower the

2010-09-08 23:10:07 +00:00

LoopUnswitch.cpp

…

LowerAtomic.cpp

more cleanups

2010-09-05 20:13:07 +00:00

Makefile

…

MemCpyOptimizer.cpp

…

Reassociate.cpp

…

Reg2Mem.cpp

…

Scalar.cpp

…

ScalarReplAggregates.cpp

…

SCCP.cpp

…

SimplifyCFGPass.cpp

…

SimplifyHalfPowrLibCalls.cpp

…

SimplifyLibCalls.cpp

…

Sink.cpp

…

TailDuplication.cpp

…

TailRecursionElimination.cpp

…