llvm-svn: 123856

Region splitting includes loop splitting as a subset, and it is more generic.
The splitting heuristics for variables that are live in more than one block are
now:

1. Try to create a region that covers multiple basic blocks.
2. Try to create a new live range for each block with multiple uses.
3. Spill.

Steps 2 and 3 are similar to what the standard spiller is doing.

llvm-svn: 123853

llvm-svn: 123842

by indvars through the scev expander.

trunc(add x, y) --> add(trunc x, y). Currently SCEV largely folds the other way
which is probably wrong, but preserved to minimize churn. Instcombine doesn't
do this fold either, demonstrating a missed optz'n opportunity on code doing
add+trunc+add.

llvm-svn: 123838

llvm-svn: 123837

llvm-svn: 123834

llvm-svn: 123832

llvm-svn: 123823

of the floating point types less than 64-bits. It's somewhat of a temporary
hack but forces more accurate modeling of register pressure and results
in fewer spills.

llvm-svn: 123811

llvm-svn: 123810

Don't forget to emit the load from indirect symbol when using movw + movt to materialize GA indirect symbols.

llvm-svn: 123809

vmrs  reg, fpexc
vmrs  reg, fpsid
vmsr  fpexc, reg
vmsr  fpsid, reg

llvm-svn: 123783

llvm-svn: 123778

llvm-svn: 123776

are pointing to the same object, one pointer is accessing the entire
object, and the other is access has a non-zero size. This prevents
TBAA from kicking in and saying NoAlias in such cases.

llvm-svn: 123775

Analyze the live range's behavior entering and leaving basic blocks. Compute an
interference pattern for each allocation candidate, and use SpillPlacement to
find an optimal region where that register can be live.

This code is still not enabled.

llvm-svn: 123774

llvm-svn: 123772

llvm.objectsize changes.

llvm-svn: 123771

llvm-svn: 123770

llvm-svn: 123769

llvm-svn: 123768

llvm-svn: 123766

llvm-svn: 123763

llvm-svn: 123760

These were not recommended by my auto-simplifier since they don't fire often enough.
However they do fire from time to time, for example they remove one subtraction from
the final bitcode for 483.xalancbmk.

llvm-svn: 123755

simplification in fully optimized code.  It occurs sporadically in the testsuite, and
many times in 403.gcc: the final bitcode has 131 fewer subtractions after this change.
The reason that the multiplies are not eliminated is the same reason that instcombine
did not catch this: they are used by other instructions (instcombine catches this with
a more general transform which in general is only profitable if the operands have only
one use).

llvm-svn: 123754

llvm-svn: 123752

SPARC backend: Modified LowerCall and LowerFormalArguments so that they use CallingConv assignments.

llvm-svn: 123749

llvm-svn: 123748

llvm-svn: 123747

llvm-svn: 123746

llvm-svn: 123745

llvm-svn: 123744

llvm-svn: 123743

llvm-svn: 123740

llvm-svn: 123739

McARM: Always keep an offset expression, if used (instead of assuming == 0 if used but not present), and simplify logic.

Also, clean up various non-sensicalisms in isMemModeRegThumb() and isMemModeImmThumb().

llvm-svn: 123738

llvm-svn: 123737

llvm-svn: 123736

llvm-svn: 123732