int func() {
  register int X;
  {
    int Y;

into:

define i32 @func() {
entry:
        %X = alloca i32         ; <i32*> [#uses=0]
        %Y = alloca i32         ; <i32*> [#uses=0]
        %allocapt = bitcast i32 undef to i32            ; <i32> [#uses=0]
...

llvm-svn: 39553

of one by reference, making it optional.

llvm-svn: 39552

llvm-svn: 39551

llvm-svn: 39550

We now print:
  extern void blah();
as:
  void (blah)();

Strange, but ok :)

llvm-svn: 39549

llvm-svn: 39548

llvm-svn: 39547

llvm-svn: 39546

if (11 + 42) {

to:

        %tmp = add i32 11, 42           ; <i32> [#uses=1]
        %tobool = icmp ne i32 %tmp, 0           ; <i1> [#uses=1]
        br i1 %tobool, label %ifthen, label %ifend


but this doesn't handle any of the interesting/hard stuff yet.

llvm-svn: 39545

llvm-svn: 39544

Submitted by:
Reviewed by:
After speaking with Chris, decided not to have GCC "attributes" inherit
from Decl. This will enable us to grow the attribute hierarchy over time
without effecting Decls.

llvm-svn: 39543

Submitted by:
Reviewed by:
Add implemention file for GCC attributes

llvm-svn: 39542

Submitted by:
Reviewed by:
Interface file for GCC attributes.

llvm-svn: 39541

llvm-svn: 39540

Submitted by:
Reviewed by:
Implement support for GCC __attribute__.

- Implement "TODO" in Parser::ParseAttributes. Changed the return type from
void to Parser::DeclTy. Changed all call sites to accept the return value.
- Added Action::ParseAttribute and Sema::ParseAttribute to return an
appropriate AST node. Added new node AttributeDecl to Decl.h.

Still to do...hook up to the Decl...

llvm-svn: 39539

llvm-svn: 39538

llvm-svn: 39537

llvm-svn: 39536

  a = b;
  {
    int c;
    c = a + b;
    int d;
    d++;
  }
  int e;

instead of:

  a = b;
  {
    int c;
    c = a + b;
    int d;
    d++;
  }  int e;

llvm-svn: 39535

llvm-svn: 39534

void test() {
  goto l;

l:
  if (11) {
    j: ;
  }
}

into:

define void @test() {
entry:
        br label %l

l:              ; preds = %entry
        icmp ne i32 11, 0               ; <i1>:0 [#uses=1]
        br i1 %0, label %ifthen, label %ifend

ifthen:         ; preds = %l
        br label %j

j:              ; preds = %ifthen
        br label %ifend

ifend:          ; preds = %j, %l
}

whoa... :)

llvm-svn: 39533

llvm-svn: 39532

llvm-svn: 39531

llvm-svn: 39530

llvm-svn: 39529

Submitted by:
Reviewed by:
- ParseForStatement(): Put back a test/assignment. My removal of
ParseExprStmt() was a bit over zealous:-(thanks to Chris for pointing it out)
- Add assert to VisitDeclStmt().
- Removed an out-of-date FIXME
- Added some curlies for a couple multi-line calls to Diag().

llvm-svn: 39528

Comment format changes.

llvm-svn: 39527

Submitted by:
Reviewed by:
- Many tweaks to various diagnostics.
- Fixed some location/range issues.
- Bug fix to Sema::ParseDeclStmt() - error return code is "true", not 0.

llvm-svn: 39526

- Conjugate "diagnostic" correctly for 1 diagnostic.

llvm-svn: 39525

void test1() {
  foo:
    goto foo;
    goto foo;
    goto foo;
}

void test() {
  goto l;

l:
  ;
}
into:

define void @test1() {
entry:
        br label %foo

foo:            ; preds = %0, %foo, %entry
        br label %foo
                ; No predecessors!
        br label %foo
                ; No predecessors!
}

define void @test() {
entry:
        br label %l

l:              ; preds = %entry
}

llvm-svn: 39524

Submitted by:
Reviewed by:
Unified the diagnostics for function calls. Since we have range support,
there is no need for including the argument number. Instead, I've made
the diags more expressive by including more type info.

Also improved the indentation of many calls to Diag (which can be 2-3
lines now).

llvm-svn: 39523

llvm-svn: 39522

llvm-svn: 39521

llvm-svn: 39520

cases.

llvm-svn: 39519

Submitted by:
Reviewed by:
Implement some FIXME's that stand in the way of fully typechecking "for"
statements. This involved:

- Adding a DeclStmt AST node (with statement visitor). The DeclStmt
printer is preliminary.
- Added a ParseDeclStmt action, called from Parser::ParseForStatement()
and Parser::ParseStatementOrDeclaration(). DID NOT add to
Parser::ParseIdentifierStatement()...probably could have, however didn't
really understand the context of this rule (will speak with Chris).
- Removed ParseExprStmt (and it's clients)...it was vestigial.

llvm-svn: 39518

Submitted by:
Reviewed by:
- Finished Sema::ParseReturnStmt(). Still need to tweak ranges.
- Tweaked location for function arguments (they now point at the expression directly, no parens or commas).
- Added InvalidOperands helper...was sick of looking at the same 3 lines in ~9 Check functions.
- Added a few diags and moved a group of statement diags to the proper comment/category.

llvm-svn: 39517

extern int pintFunc(int *, int *);

int test() {
  pintFunc(0,
           3);
}

We now print:

t3.c:4:13: warning: passing argument 2 makes pointer from integer without a cast
  pintFunc(0,
  ~~~~~~~~  ^

instead of:

t3.c:4:13: warning: passing argument 2 makes pointer from integer without a cast
  pintFunc(0,
  ~~~~~~~~

llvm-svn: 39516

Submitted by:
Reviewed by:
Implement type checking for ParseDoStmt, ParseWhileStmt, ParseIfStmt, and
ParseForStmt. ParseForStmt still under construction (contains a FIXME).

llvm-svn: 39515

Submitted by:
Reviewed by:
Add range support to Sema::CheckConditionalOperands().

llvm-svn: 39514