Make the 'get*AlignmentFromAttr' functions into member functions within the Attributes class. Now with fix.

llvm-svn: 164370

A PHI can't create interference on its own. If two live ranges interfere
at a PHI, they must also interfere when leaving one of the PHI
predecessors.

llvm-svn: 164330

The old-fashioned many-to-one value mapping doesn't always work when
merging vector lanes. A value can map to multiple different values, and
it can even be necessary to insert new PHIs.

When a value number is defined by a copy from a value number that
required SSa update, include the live range of the copied value number
in the SSA update as well. It is not necessarily a copy of the original
value number any longer.

llvm-svn: 164329

llvm-svn: 164326

llvm-svn: 164309

llvm-svn: 164308

llvm-svn: 164297

llvm-svn: 164268

llvm-svn: 164264

A common coalescing conflict in vector code is lane insertion:

  %dst = FOO
  %src = BAR
  %dst:ssub0 = COPY %src

The live range of %src interferes with the ssub0 lane of %dst, but that
lane is never read after %src would have clobbered it. That makes it
safe to merge the live ranges and eliminate the COPY:

  %dst = FOO
  %dst:ssub0 = BAR

This patch teaches the new coalescer to resolve conflicts where dead
vector lanes would be clobbered, at least as long as the clobbered
vector lanes don't escape the basic block.

llvm-svn: 164250

llvm-svn: 164180

llvm-svn: 164154

llvm-svn: 164153

store this and use it to not emit long nops when the CPU is geode which
doesnt support them.

Fixes PR11212.

llvm-svn: 164132

llvm-svn: 164098

llvm-svn: 164090

llvm-svn: 164087

Add LIS::pruneValue() and extendToIndices(). These two functions are
used by the register coalescer when merging two live ranges requires
more than a trivial value mapping as supported by LiveInterval::join().

The pruneValue() function can remove the part of a value number that is
going to conflict in join(). Afterwards, extendToIndices can restore the
live range, using any new dominating value numbers and updating the SSA
form.

Use this complex value mapping to support merging a register into a
vector lane that has a conflicting value, but the clobbered lane is
undef.

llvm-svn: 164074

These extra operands are not needed by register allocators using
VirtRegRewriter, and RAFast don't need them any longer.

By omitting the <imp-def> operands, it becomes possible for the new
register coalescer to track which lanes are valid and which are undef.

llvm-svn: 164073

I have to work out the Target/CodeGen header dependencies
before putting this back.

llvm-svn: 164072

llvm-svn: 164065

Increase the static sizes of some SmallSets. finalizeBundle() is very frequently called for some backends, and growing into an std::set is overkill for these numbers.

llvm-svn: 164044

llvm-svn: 164043

- Preserve the original NOutVT during casting from vector to integer by
  extracting vector elements.

llvm-svn: 164042

This is used in the AMDIL and R600 backends.

llvm-svn: 164029

Disable the protection from escaped allocas in an attempt to find violating passes. This may break the buildbots. I plan to revert it in a few hours.

llvm-svn: 164024

llvm-svn: 164000

The live range of an SSA value forms a sub-tree of the dominator tree.
That means the live ranges of two values overlap if and only if the def
of one value lies within the live range of the other.

This can be used to simplify the interference checking a bit: Visit each
def in the two registers about to be joined. Check for interference
against the value that is live in the other register at the def point
only. It is not necessary to scan the set of overlapping live ranges,
this interference check can be done while computing the value mapping
required for the final live range join.

The new algorithm is prepared to handle more complicated conflict
resolution - We can allow overlapping live ranges with different values
as long as the differing lanes are undef or unused in the other
register.

The implementation in this patch doesn't do that yet, it creates code
that is nearly identical to the old algorithm's, except:

- The new stripCopies() function sees through multiple copies while
  the old RegistersDefinedFromSameValue() only can handle one.

- There are a few rare cases where the new algorithm can erase an
  IMPLICIT_DEF instuction that RegistersDefinedFromSameValue() couldn't
  handle.

llvm-svn: 163991

llvm-svn: 163974

Kill flags are removed more and more aggressively during the register
allocation passes, it is better to get information from LiveIntervals.

llvm-svn: 163972

llvm-svn: 163934

llvm-svn: 163915

llvm-svn: 163882

umulo legalization.

Fixes PR13839

llvm-svn: 163856

closer to where they're needed.

llvm-svn: 163855

- Find a legal vector type before casting and extracting element from it.
- As the new vector type may have more than 2 elements, build the final
  hi/lo pair by BFS pairing them from bottom to top.

llvm-svn: 163830

Rename the flag which protects from escaped allocas, which may come from bugs in user code or in the compiler. Also, dont assert if the protection is not enabled.

llvm-svn: 163807

by xoring the high-bit. This fails if the source operand is a vector because we need to negate
each of the elements in the vector.

Fix rdar://12281066 PR13813.

llvm-svn: 163802

llvm-svn: 163801

Stack Coloring: We have code that checks that all of the uses of allocas
are within the lifetime zone. Sometime legitimate usages of allocas are
hoisted outside of the lifetime zone. For example, GEPS may calculate the
address of a member of an allocated struct. This commit makes sure that
we only check (abort regions or assert) for instructions that read and write
memory using stack frames directly. Notice that by allowing legitimate
usages outside the lifetime zone we also stop checking for instructions
which use derivatives of allocas. We will catch less bugs in user code
and in the compiler itself.

llvm-svn: 163791