llvm-svn: 50390

We now compile test2/test3 to:

_test2:
	## InlineAsm Start
	set %xmm0, %xmm1
	## InlineAsm End
	addps	%xmm1, %xmm0
	ret
_test3:
	## InlineAsm Start
	set %xmm0, %xmm1
	## InlineAsm End
	paddd	%xmm1, %xmm0
	ret

as expected.

llvm-svn: 50389

llvm-svn: 50388

Add corresponding enum in LangOptions.

llvm-svn: 50387

towards PR2094.  It now compiles the attached .ll file to:

_sad16_sse2:
	movslq	%ecx, %rax
	## InlineAsm Start
	%ecx %rdx %rax %rax %r8d %rdx %rsi
	## InlineAsm End
	## InlineAsm Start
	set %eax
	## InlineAsm End
	ret

which is pretty decent for a 3 output, 4 input asm.

llvm-svn: 50386

e.g.
vr1024<2> extract_subreg vr1025, 2
If vr1024 do not have the same register class as vr1025, it's not safe to coalesce this away. For example, vr1024 might be a GPR32 while vr1025 might be a GPR64.

llvm-svn: 50385

llvm-svn: 50384

llvm-svn: 50383

the trip count.

llvm-svn: 50382

llvm-svn: 50380

Add a new test, and_ops_more.ll, which is XFAIL'd, to
record the parts of and_ops.ll that were affected by this
change.

llvm-svn: 50379

llvm-svn: 50377

Fix a bug in RegsForValue::getCopyToRegs() that causes cyclical scheduling units. If it's creating multiple CopyToReg nodes that are "flagged" together, it should not create a TokenFactor for it's chain outputs:

c1, f1 = CopyToReg                                                                                                                                                                                             
c2, f2 = CopyToReg                                                                                                                                                                                             
c3     = TokenFactor c1, c2                                                                                                                                                                                    
 ...                                                                                                                                                                                                                      
       = user c3, ..., f2

Now that the two CopyToReg's and the user are "flagged" together. They effectively forms a single scheduling unit. The TokenFactor is now both an operand and a successor of the Flagged nodes.

llvm-svn: 50376

Patch by Anders Johnsen!

llvm-svn: 50375

Patch by Pekka Jääskeläinen!

llvm-svn: 50373

be truncated to 32 bits. This fixes the recent Benchmarks/McCat/09-vor
regression on x86-64, among other things.

llvm-svn: 50372

llvm-svn: 50370

llvm-svn: 50369

if the zext is not legal.

llvm-svn: 50368

llvm-svn: 50367

aggregate types.

llvm-svn: 50366

reorder some of the members for clarity.

llvm-svn: 50365

std::pair<CFGBlock*, CFGBlock*> that have an 8-byte alignment for use with
ProgramPoint. This fixes a bug reported by Argiris where using std::set<> on
Windows would result in a 4-byte alignment, not an 8-byte alignment.

Fixes: <rdar://problem/5892265>
llvm-svn: 50364

llvm-svn: 50363

Bug fix in BumpPtrAllocator: don't assume that all objects have the same alignment.  "Bump" of the pointer for the next allocated object to be of the specified alignment.

llvm-svn: 50362

llvm-svn: 50361

Patch by Anders Johnsen!

llvm-svn: 50360

memcpy/memset expansion. It was a bug for the SVOffset value
to be used in the actual address calculations.

llvm-svn: 50359

ComputeMaskedBits knows about cttz, ctlz, and ctpop. Teach
SelectionDAG's ComputeMaskedBits what InstCombine's knows
about SRem. And teach them both some things about high bits
in Mul, UDiv, URem, and Sub. This allows instcombine and
dagcombine to eliminate sign-extension operations in
several new cases.

llvm-svn: 50358

sign-bit of x is known to be zero.

llvm-svn: 50357

llvm-svn: 50355

llvm-svn: 50342

llvm-svn: 50341

conversion open the door for many nasty implicit conversion issues, and
can be easily solved by initializing with (V.begin(), V.end()) when 
needed.

This patch includes many small cleanups for sdisel also.

llvm-svn: 50340

errors I introduced in my last patch.

llvm-svn: 50338

heap thrash on tiny (usually single-element) vectors.

llvm-svn: 50335

the initialization vector to have the same fixed size, just the
same element type.

llvm-svn: 50334

multiple return values.

Bill, please pull this into Tak.

llvm-svn: 50332

llvm-svn: 50331

llvm-svn: 50330