Re-apply 133010, with fixes for inline assembler.
Original commit message:
"When an assembler local symbol is used but not defined in a module, a
Darwin assembler wants to issue a diagnostic to that effect."
Added fix to only perform the check when finalizing, as otherwise we're not
done and undefined symbols may simply not have been encountered yet.
Passes "make check" and a self-host check on Darwin.
llvm-svn: 133071
Note that this actually changes code generation, and someone who
understands this target better should check the changes.
- R12Q is now allocatable. I think it was omitted from the allocation
order by mistake since it isn't reserved. It as apparently used as a
GOT pointer sometimes, and it should probably be reserved if that is
the case.
- The GR64 registers are allocated in a different order now. The
register allocator will automatically put the CSRs last. There were
other changes to the order that may have been significant.
The test fix is because r0 and r1 swapped places in the allocation order.
llvm-svn: 133067
- llvm.dbg.declare already receives line number information from ParmDecl
- Additional extra stoppoint messes up gdb's understanding of where function body starts.
llvm-svn: 133065
were just punting on template argument deduction for a number of type
nodes. Most of them, obviously, didn't matter.
As a consequence of this, make extended vector types (via the
ext_vector_type attribute) actually work properly for several
important cases:
- If the attribute appears in a type-id (i.e, not attached to a
typedef), actually build a proper vector type
- Build ExtVectorType whenever the size is constant; previously, we
were building DependentSizedExtVectorType when the size was constant
but the type was dependent, which makes no sense at all.
- Teach template argument deduction to handle
ExtVectorType/DependentSizedExtVectorType.
llvm-svn: 133060
before the template parameters have acquired a proper context (e.g.,
because the enclosing context has yet to be built), provide empty
parameter lists for all outer template parameter scopes to inhibit any
substitution for those template parameters. Fixes PR9643 /
<rdar://problem/9251019>.
llvm-svn: 133055
GetDemandBits (which must operate on the vector element type).
Fix the a usage of getZeroExtendInReg which must also be done on scalar types.
llvm-svn: 133052
At the time I wrote this code (circa 2007), TargetRegisterInfo was using a std::set to perform these queries. Switching to the static hashtables was an obvious improvement, but in reality there's no reason to do anything other than scan.
With this change, total LLC time on a whole-program 403.gcc is reduced by approximately 1.5%, almost all of which comes from a 15% reduction in LiveVariables time. It also reduces the binary size of LLC by 86KB, thanks to eliminating a bunch of very large static tables.
llvm-svn: 133051
Unfortunately we can't follow what the rest of the language does (wrapping it
in double-quotes) because that would cause an ambiguity with metadata strings,
so instead we escape any unusual characters with \xx escaping.
llvm-svn: 133050
- (bounded copies) Be more conservative about how much is being copied.
- (str(n)cat) If we can't compute the exact final length of an append operation, we can still lower-bound it.
- (stpcpy) Fix the conjured return value at the end to actually be returned.
This requires these supporting changes:
- C string metadata symbols are still live even when buried in a SymExpr.
- "Hypothetical" C string lengths, to represent a value that /will/ be passed to setCStringLength() if all goes well. (The idea is to allow for temporary constrainable symbols that may end up becoming permanent.)
- The 'checkAdditionOverflow' helper makes sure that the two strings being appended in a strcat don't overflow size_t. This should never *actually* happen; the real effect is to keep the final string length from "wrapping around" in the constraint manager.
This doesn't actually test the "bounded" operations (strncpy and strncat) because they can leave strings unterminated. Next on the list!
llvm-svn: 133046
This prepares tablegen to compute register lists from set theoretic dag
expressions. This doesn't really make any difference as long as
Target.td still declares RegisterClass::MemberList as [Register].
llvm-svn: 133043
There's no associated test for this because fully-constrained symbolic values are evaluated ahead of time in normal expressions. This can only come up in checker-constructed expressions (like the ones in an upcoming patch to CStringChecker).
llvm-svn: 133041
Make the Elements vector private and expose an ArrayRef through
getOrder() instead. getOrder will eventually provide multiple
user-specified allocation orders.
Use the sorted member set for member and subclass tests. Clean up a lot
of ad hoc searches.
llvm-svn: 133040
the bits being cleared by the AND are not demanded by the BFI.
The previous BFI dag combine rule was actually incorrect (or used to be
correct until BFI representation changed).
rdar://9609030
llvm-svn: 133034
Change the output for -Wshift-overflow and
-Wshift-sign-overflow to an unsigned hexadecimal. It makes
more sense for looking at bits than a signed decimal does.
Also, change the diagnostic's wording from "overrides"
to "sets".
This uses a new optional argument in APInt::toString()
that adds the '0x' prefix to hexademical numbers.
This fixes PR 9651.
Patch by nobled@dreamwidth.org!
llvm-svn: 133033
toString() now takes an optional bool argument that,
depending on the radix, adds the appropriate prefix
to the integer's string representation that makes it into a
meaningful C literal, e.g.:
hexademical: '-f' becomes '-0xf'
octal: '77' becomes '077'
binary: '110' becomes '0b110'
Patch by nobled@dreamwidth.org!
llvm-svn: 133032
converted to add x,x if x is a undef. add undef, undef does not guarantee
that the resulting low order bit is zero.
Fixes <rdar://problem/9453156> and <rdar://problem/9487392>.
llvm-svn: 133022
Jim Grosbach