Commit Graph

1105 Commits

Author SHA1 Message Date
Daniel Dunbar a7d0231b66 clang -cc1: Rename -mcpu to -target-cpu to match other target options and not alias driver/backend option.
llvm-svn: 91671
2009-12-18 06:30:12 +00:00
Eli Friedman fa7f519ce4 Temporarily XFAIL this test.
llvm-svn: 91643
2009-12-18 00:23:19 +00:00
Mike Stump 6dc04f4067 Revert r91073.
llvm-svn: 91629
2009-12-17 22:14:41 +00:00
Nuno Lopes e9823fab83 implement PR3962: diagnose more faulty cases of usage of the restrict qualifier. this also removes a FIXME
llvm-svn: 91601
2009-12-17 11:35:26 +00:00
Daniel Dunbar 5618e98f33 Update tests to use %clang instead of 'clang', and forcibly disable use of '
clang ' or ' clang -cc1 ' or ' clang-cc ' in test lines (by substituting them to
garbage).

llvm-svn: 91460
2009-12-15 22:01:24 +00:00
Daniel Dunbar 8fbe78f6fc Update tests to use %clang_cc1 instead of 'clang-cc' or 'clang -cc1'.
- This is designed to make it obvious that %clang_cc1 is a "test variable"
   which is substituted. It is '%clang_cc1' instead of '%clang -cc1' because it
   can be useful to redefine what gets run as 'clang -cc1' (for example, to set
   a default target).

llvm-svn: 91446
2009-12-15 20:14:24 +00:00
Nate Begeman ac8183a830 Support OpenCL 1.1 odd-length vector component accessors.
For hi/odd of an odd-length vector, the last component is undefined.  Since
we shuffle with an undef vector, no CodeGen needs to change to support this.

llvm-svn: 91437
2009-12-15 18:13:04 +00:00
Mike Stump 4ec1237106 Add testcase for recent checkin.
Patch by Chip Davis.

llvm-svn: 91436
2009-12-15 18:02:45 +00:00
Fariborz Jahanian a01b67d7b0 Make tests use the new clang -cc1 flag.
llvm-svn: 91303
2009-12-14 18:00:56 +00:00
Mike Stump 18f4196792 Testcase for recent checkin.
llvm-svn: 91080
2009-12-11 00:10:15 +00:00
Mike Stump e1f6280093 Don't complain about falling off the end of a function with an asm
block, if the function is supposed to return a value as we don't know
exactly what the asm code does.

llvm-svn: 91073
2009-12-10 22:57:48 +00:00
John McCall 5677499fbf First pass at implementing C++ enum semantics: calculate (and store) an
"integer promotion" type associated with an enum decl, and use this type to
determine which type to promote to.  This type obeys C++ [conv.prom]p2 and
is therefore generally signed unless the range of the enumerators forces
it to be unsigned.

Kills off a lot of false positives from -Wsign-compare in C++, addressing
rdar://7455616

llvm-svn: 90965
2009-12-09 09:09:27 +00:00
Eli Friedman d0e8de2cd8 Move RequireCompleteType requirement for fields early into ActOnField so that
subsequent code which depends on a complete type does the right thing.

llvm-svn: 90727
2009-12-07 00:22:08 +00:00
Chris Lattner 9a152e2570 fix rdar://7446395, a crash on invalid, by fixing a broken assertion.
llvm-svn: 90647
2009-12-05 05:40:13 +00:00
John Thompson 47981226d5 Fix for PR5650 - Revised vector_size attribute handling to be done earlier before declaration is finalized.
llvm-svn: 90600
2009-12-04 21:51:28 +00:00
Eli Friedman f3da334da6 Fix for PR5447: teach Evaluate to deal with floating-point conditionals.
llvm-svn: 90521
2009-12-04 02:12:53 +00:00
Eli Friedman 5efba264cb Fix for PR5679: make __builtin_prefetch a bit more flexible in what it accepts
as a constant integer.  Also, some minor cleanup and improvements to the
diagnostics.

llvm-svn: 90504
2009-12-04 00:30:06 +00:00
Daniel Dunbar be95682389 Remove unnecessary -fblocks=0.
llvm-svn: 90070
2009-11-29 09:32:38 +00:00
Douglas Gregor 3ff3af4ff9 When the condition of a switch() statement is semantically invalid,
still parse the body of the switch to try to avoid spurious
diagnostics. Fixes PR5606.

llvm-svn: 89847
2009-11-25 06:20:02 +00:00
Fariborz Jahanian 3f21c159dc Fix a recent regression probably caused by addition of altivec-style
type-casts in the parser.

llvm-svn: 89691
2009-11-23 19:51:43 +00:00
Edward O'Callaghan 0825f09306 Fix for PR5233.
llvm-svn: 89603
2009-11-22 16:21:47 +00:00
Daniel Dunbar 32164f4bdb Driver: Use '-target-abi' 'FOO' instead of '-target-abi=FOO'.
llvm-svn: 89501
2009-11-20 22:32:30 +00:00
Daniel Dunbar 4274685b63 Pass '-mcpu' 'FOO' instead of '-mcpu=FOO'.
llvm-svn: 89498
2009-11-20 22:21:52 +00:00
Daniel Dunbar 484afa2d3b Switch -f{builtin,math-errno,rtti} and -analyzer-purge-dead to -...no... variants instead of using llvm:🆑:init(true) arguments.
llvm-svn: 89315
2009-11-19 04:55:23 +00:00
Benjamin Kramer b70e4aba9a Make test header independent so it doesn't fail on freebsd. I hope this doesn't
hurt the intention of the test.

llvm-svn: 89096
2009-11-17 14:02:16 +00:00
Daniel Dunbar 633d5b3ee2 Use clang to run tests which include headers from the system.
llvm-svn: 89085
2009-11-17 10:14:55 +00:00
Daniel Dunbar feedba68b5 Don't #include <stdio.h> when tests don't need it, or use clang instead of clang-cc when they do.
llvm-svn: 89070
2009-11-17 08:57:36 +00:00
Eli Friedman 141fbf3f36 Add constant evaluation for comma operator with floating-point operand. Fixes
PR5449.

llvm-svn: 88885
2009-11-16 04:25:37 +00:00
John McCall 5055e4cdfd Fix PR 5422: handle lvalue results when evaluating 'based' ptrtoints as part of
the -Wconversion check.

llvm-svn: 86891
2009-11-11 22:52:37 +00:00
Fariborz Jahanian b98dade25b Changed error for nested type qualifier mismatch to
warning, to match gcc. It used to be warning, so
better keep it a warning (it broke a certain project).

llvm-svn: 86597
2009-11-09 22:16:37 +00:00
Fariborz Jahanian 222c0b517e Test case for Sean Hunt's patch which I left out.
llvm-svn: 86573
2009-11-09 18:48:53 +00:00
Eli Friedman e4310c8273 Add support for cdecl attribute. (As far as I know, it doesn't affect CodeGen
unless we start implementing command-line switches which override the default
calling convention, so the effect is mostly to silence unknown attribute
warnings.)

llvm-svn: 86571
2009-11-09 18:38:53 +00:00
Anders Carlsson 2256497780 Add a triple to try to fix the buildbot error.
llvm-svn: 86563
2009-11-09 17:54:53 +00:00
Anders Carlsson 69999d9c23 __uint128_t is indeed an unsigned integer type. Fixes PR5435.
llvm-svn: 86561
2009-11-09 17:34:18 +00:00
Daniel Dunbar 8b57697954 Eliminate &&s in tests.
- 'for i in $(find . -type f); do sed -e 's#\(RUN:.*[^ ]\) *&& *$#\1#g' $i | FileUpdate $i; done', for the curious.

llvm-svn: 86430
2009-11-08 01:45:36 +00:00
John McCall b61e9d03c1 Support -Wshorten-64-to-32 for integer types only, which seems to satisfy the
core requirements.  Fixes rdar://problem/6389954

llvm-svn: 86364
2009-11-07 09:03:53 +00:00
John McCall b397956338 Improve -Wconversion by permitting binary operations on values of the target
type (or smaller) to stay "closed" within the type.

llvm-svn: 86356
2009-11-07 08:15:46 +00:00
John McCall 554e857cf4 Test case for -Wconversion.
llvm-svn: 86327
2009-11-07 03:30:38 +00:00
John McCall e46fd8531c compare.c also needs a target triple now, and improve some comments while we're
at it.

llvm-svn: 86243
2009-11-06 08:53:51 +00:00
John McCall 99ce6bfe28 Improve the -Wsign-compare heuristics:
* If the unsigned type is smaller than the signed type, never warn, because
    its value will not change when zero-extended to the larger type.
  * If we're testing for (in)equality, and the unsigned value is an integer
    constant whose sign bit is not set, never warn, because even though the
    signed value might change, it can't affect the result of the equality.

Also make the comparison test cases much more rigorous, and have them expose
the subtle differences between C and C++ here.

llvm-svn: 86242
2009-11-06 08:49:08 +00:00
Douglas Gregor 6af6c3ee56 Turn off -Wsign-compare warnings by default
llvm-svn: 86233
2009-11-06 05:24:12 +00:00
Sebastian Redl 87869bc435 Make ASTContext::getIntWidth return 1 for all boolean type variations, not just for the unqualified, unaliased bool.
llvm-svn: 86174
2009-11-05 21:10:57 +00:00
John Thompson ed4e2950bc Adding -fshort-wchar option.
llvm-svn: 86167
2009-11-05 20:14:16 +00:00
John McCall 1fa36b7cab Implement the conditional-operator part of -Wsign-compare. Turn
DiagnoseSignCompare into Sema::CheckSignCompare and call it from more places.

Add some enumerator tests.  These seem to expose some oddities in the
types we're converting C++ enumerators to;  in particular, they're converting
to unsigned before int, which seems to contradict 4.5 [conv.prom] p2.

Note to self: stop baiting Doug in my commit messages.

llvm-svn: 86128
2009-11-05 09:23:39 +00:00
John McCall 644a4181c9 Implement -Wsign-compare, or at least the actual comparison part of it.
Conditional operands are next.

Fixes part of rdar://problem/7289584.

llvm-svn: 86083
2009-11-05 00:40:04 +00:00
John McCall 4976fd4ea9 Diagnose the use of 'fastcall' on functions without prototypes or with
varargs prototypes.

llvm-svn: 86001
2009-11-04 03:36:09 +00:00
John McCall 9eff4e60ae Diagnose __builtin_offsetof on incomplete types. Fixes
rdar://problem/7222956

llvm-svn: 85999
2009-11-04 03:03:43 +00:00
John McCall 28a6aeab7e Change our basic strategy for avoiding deprecation warnings when the decl use
appears in a deprecated context.  In the new strategy, we emit the warnings
as usual unless we're currently parsing a declaration, where "declaration" is
restricted to mean a decl group or a few special cases in Objective C.  If
we *are* parsing a declaration, we queue up the deprecation warnings until
the declaration has been completely parsed, and then emit them only if the
decl is not deprecated.
We also standardize the bookkeeping for deprecation so as to avoid special cases.

llvm-svn: 85998
2009-11-04 02:18:39 +00:00
John McCall d5a36321b9 Reorganize the parsing of decl groups / function definitions so that
declarators are parsed primarily within a single function (at least for
these cases).  Remove some excess diagnostics arising during parse failures.

llvm-svn: 85924
2009-11-03 19:26:08 +00:00
Douglas Gregor bff4e7d180 Fix the type of __builtin_expect, from Ed Schouten!
llvm-svn: 85666
2009-10-31 16:04:14 +00:00