- Added getOpcodeAfterMemoryUnfold(). It doesn't unfold an instruction, but only returns the opcode of the instruction post unfolding.
- Fix some copy+paste bugs.

llvm-svn: 43153

Add a FIXME to an assert.
Change a dyn_cast_or_null back to cast (which is more efficient).

llvm-svn: 43152

llvm-svn: 43151

llvm-svn: 43150

llvm-svn: 43149

Instead of loading small global string from memory, use
integer constant.

llvm-svn: 43148

llvm-svn: 43147

llvm-svn: 43146

llvm-svn: 43145

llvm-svn: 43144

llvm-svn: 43143

Tweak a recent fix to UsualArithmeticConversions (made by Chris - r43113). The benefit of this tweak is it guarantees the entire routine operates on unqualified types (which I believe is a bit clearer).  

llvm-svn: 43142

fixing some obviously broken code :(

llvm-svn: 43141

llvm-svn: 43140

llvm-svn: 43139

and StmtIteratorImpl (templated), which StmtIterator and
ConstStmtIterator now succintly subclass.

Implemented iteration over the initializers in DeclStmts.  This is not
thoroughly tested, so there may be bugs.

llvm-svn: 43138

directly inlining its logic.

llvm-svn: 43137

llvm-svn: 43136

llvm-svn: 43133

llvm-svn: 43132

llvm-svn: 43131

llvm-svn: 43130

llvm-svn: 43129

llvm-svn: 43128

and tblgen requires rtti.

llvm-svn: 43127

llvm-svn: 43126

llvm-svn: 43125

llvm-svn: 43124

llvm-svn: 43123

Registry<>::iterator member class.

llvm-svn: 43122

llvm-svn: 43121

llvm-svn: 43120

llvm-svn: 43119

traversing inverse register coalescing map.

llvm-svn: 43118

llvm-svn: 43117

i64 bit convert needlessly.

llvm-svn: 43116

in CodeExtractor and LoopSimplify unnecessary.

Hartmut, could you confirm that this fixes the issues you were seeing?

llvm-svn: 43115

Fix a bug in Sema::CheckConditionalOperands(). When mixing pointers and null pointer constants, we need to promote the null pointer constant (which is an integer) to the pointer type. Test case is self explanatory.

This surfaced yesterday, when compiling test/Sema/cocoa.m on Leopard. Since this has nothing to do with ObjC, it's kind of bizarre this hasn't shown up before. I imagine Cocoa.h on Leopard may have changed recently? 

Thanks to Ted for localizing the bug and giving me a useful AST dump...

llvm-svn: 43114

when comparing "float" and "const float".  This "fixes" the
issue, but may not be the right fix.  Steve, please review.

Testcase here: test/Sema/usual-float.c

llvm-svn: 43113

Fix the following bug...

unsigned char asso_values[] = { 34 };
int legal2() { 
  return asso_values[0]; 
}

The code that creates the new constant array type was operating on the original type.

As a result, the constant type being generated was "unsigned char [1][]" (which is wrong).

The fix is to operate on the element type - in this case, the correct type is "unsigned char [1]"

I added this case to array-init.c, which clearly didn't catch this bogosity...

llvm-svn: 43112