This is the initial checkin of the basic-block autovectorization pass along with some supporting vectorization infrastructure.
Special thanks to everyone who helped review this code over the last several months (especially Tobias Grosser).

llvm-svn: 149468

Changing arguments from being passed as fixed to varargs is unsafe, as
the ABI may require they be handled differently (stack vs. register, for
example).

Remove two tests which rely on the bitcast being folded into the direct
call, which is exactly the transformation that's unsafe.

llvm-svn: 149457

llvm-svn: 149452

Make the EarlyCSE optimizer not use recursion to do a depth first iteration.

llvm-svn: 149445

symbol from an assignment.  In this case the symbol did not have a fragment so
MCObjectWriter::IsSymbolRefDifferenceFullyResolved() should not have been
calling IsSymbolRefDifferenceFullyResolvedImpl() with a NULL fragment and should
just have returned false in that case.

llvm-svn: 149442

This new function provides a way to get the Mac OS X version number from
either generic "darwin" triples of macosx triples.

llvm-svn: 149438

Excellent suggestion from Ben Kramer.

llvm-svn: 149417

llvm-svn: 149416

llvm-svn: 149398

Add assembler dialect attribute in asm parser which lets target specific asm parser change dialect on the fly.

llvm-svn: 149396

vector. This potentially saves a resizing.

llvm-svn: 149369

llvm-svn: 149368

llvm-svn: 149367

ConstantDataArray::getString instead.

llvm-svn: 149365

with recent changes, ConstantArray is never a "string".  Remove the associated
methods and constant fold the clients to false.

llvm-svn: 149362

This removes implicit assumption about the form of MI coming into regalloc. In particular, it should be independent of ProcessImplicitDefs which will eventually become a standard part of coming out of SSA--unless we simply can eliminate IMPLICIT_DEF completely. Current unit tests expose this once I remove incidental pass ordering restrictions.

This is not a final fix. Just a temporary workaround until I figure out the right way.

llvm-svn: 149360

llvm-svn: 149357

llvm-svn: 149356

eliminate the last uses of GetConstantStringInfo from this file, I didn't realize I was that close...

llvm-svn: 149354

These are very useful for frontends and other utilities reasoning about
or selecting between triples.

llvm-svn: 149353

dramatically more efficient than GetConstantStringInfo.

llvm-svn: 149352

kicking in the big win of ConstantDataArray.  As part of this, change
the implementation of GetConstantStringInfo in ValueTracking to work
with ConstantDataArray (and not ConstantArray) making it dramatically,
amazingly, more efficient in the process and renaming it to 
getConstantStringInfo.

This keeps around a GetConstantStringInfo entrypoint that (grossly)
forwards to getConstantStringInfo and constructs the std::string 
required, but existing clients should move over to 
getConstantStringInfo instead.

llvm-svn: 149351

which is going away.

llvm-svn: 149348

CodeGen/X86/global-sections.ll to fail with CDArray

llvm-svn: 149343

llvm-svn: 149342

simplify ConstantArray handling, since they can never be empty.

llvm-svn: 149341

llvm-svn: 149340

llvm-svn: 149331

llvm-svn: 149328

over the catch information. The catch information is now tacked to the invoke
instruction.

llvm-svn: 149326

llvm-svn: 149323

llvm-svn: 149322

llvm-svn: 149318

llvm-svn: 149317

llvm-svn: 149316

Use the correct ShiftAmtTy for creating shifts after legalization.  PR11881.  Not committing a testcase because I think it will be too fragile.

llvm-svn: 149315

The eh.selector and eh.resume intrinsics aren't used anymore. Get rid of some
calls to them.

llvm-svn: 149314

llvm-svn: 149312

llvm-svn: 149307

llvm-svn: 149303