Calling RemoveOperand is very expensive on huge PHI instructions. This makes
early tail duplication run twice as fast on the Firefox JavaScript
interpreter.

llvm-svn: 95832

into TargetOpcodes.h.  #include the new TargetOpcodes.h
into MachineInstr.  Add new inline accessors (like isPHI())
to MachineInstr, and start using them throughout the 
codebase.

llvm-svn: 95687

not during the later post-alloc tail duplication.

llvm-svn: 93600

llvm-svn: 93540

The pre-regalloc pass caused some regressions in both compile time and
performance of the generated code, and it did not improve performance, except
for indirect branches.  I also moved the check for single-block loops to speed
up the common case when running the taildup pass before reg allocation.

llvm-svn: 93505

Some instructions refer to unique labels, and so cannot be trivially cloned
with CloneMachineInstr.

llvm-svn: 92873

llvm-svn: 92582

Tail duplication should zap a copy it inserted for SSA update if the copy is the only use of its source.

llvm-svn: 91390

llvm-svn: 90804

llvm-svn: 90759

llvm-svn: 90575

llvm-svn: 90567

llvm-svn: 90432

llvm-svn: 90326

branches even when optimizing for code size.  Unless we find evidence to the
contrary in the future, the special treatment for indirect branches does not
have a significant effect on code size, and performance still matters with -Os.

llvm-svn: 90147

for all the processors where I have tried it, and even when it might not help
performance, the cost is quite low.  The opportunities for duplicating
indirect branches are limited by other factors so code size does not change
much due to tail duplicating indirect branches aggressively.

llvm-svn: 90144

llvm-svn: 89968

running tail duplication when doing branch folding for if-conversion, and
we also want to be able to run tail duplication earlier to fix some
reg alloc problems.  Move the CanFallThrough function from BranchFolding
to MachineBasicBlock so that it can be shared by TailDuplication.

llvm-svn: 89904