the sets of available conversions for the first and second arguments
separate. This is apparently the indent of C++ [over.built], and
reduces the number of overload candidates generated, eliminating some
ambiguities. Fixes PR8477.
llvm-svn: 118178
value type, so there is no point in passing it around using
an EVT. Use the simpler MVT everywhere. Rather than trying
to propagate this information maximally in all the code that
using the calling convention stuff, I chose to do a mainly
low impact change instead.
llvm-svn: 118167
1. For statement: const C& c = C(0) ?: C(1) destructors generated for condition will not differ from those generated for case without prolonged lifetime of temporary,
2. There will be no destructor for constant reference member bound to temporary at the exit from constructor.
llvm-svn: 118158
distros listed by running
gcc main.o -o main
g++ main.o -o main
gcc main.o -o main -static
g++ main.o -o main -static
gcc f.o -o f.so -shared
g++ f.o -o f.so -shared
and comparing the ld line with the one created by clang. I also added
-m32/m64 in distros that support it.
While I tested many distros, there will always be more. If you are hit by this
it should be somewhat easy to add your distro. If you are in a hurry, do
revert this, but please inform how to detect you distro and the ld command
lines produced by the above gcc invocations. Most distros have some patches
on gcc :-(
llvm-svn: 118149
the end of the list. We had an issue in the MacOSX dynamic loader where if
we had shlibs:
1 - a.out
2 - a.dylib
3 - b.dylib
And then a.dylib got unloaded, we would unload b.dylib due to the assumption
that only shared libraries could come off the end of the list. We now properly
search and find which ones get loaded.
Added a new internal logging category for the "lldb" log channel named "dyld".
This should allow all dynamic loaders to use this as a generic log channel so
we can track shared library loads and unloads in the logs without having to
have each plug-in make up its own logging channel.
llvm-svn: 118147
vldr.64 d1, [r0, #-32]
The problem was with how the addressing mode 5 encodes the offsets. This change
makes sure that the way offsets are handled in addressing mode 5 is consistent
throughout the MC code. It involves re-refactoring the "getAddrModeImmOpValue"
method into an "Imm12" and "addressing mode 5" version. But not to worry! The
majority of the duplicated code has been unified.
llvm-svn: 118144
set breakpoints at the different locations where
an exception could be thrown, so that exceptions
thrown by expressions are properly caught.
llvm-svn: 118142
1. Fix pre-ra scheduler so it doesn't try to push instructions above calls to
"optimize for latency". Call instructions don't have the right latency and
this is more likely to use introduce spills.
2. Fix if-converter cost function. For ARM, it should use instruction latencies,
not # of micro-ops since multi-latency instructions is completely executed
even when the predicate is false. Also, some instruction will be "slower"
when they are predicated due to the register def becoming implicit input.
rdar://8598427
llvm-svn: 118135
ensuring that they cover all of their child nodes. There's still a
clang_getCursor()-related issue with CXXFunctionalCastExprs with
CXXConstructExprs as children (see FIXME in the test case); I'll look
at that separately.
llvm-svn: 118132
ins/outs list that isn't specified by their asmstring. Previously
the asmmatcher would just force a 0 register into it, which clearly
isn't right. Mark a bunch of ARM instructions that use this as
isCodeGenOnly. Some of them are clearly pseudo instructions (like
t2TBB) others use a weird hasExtraSrcRegAllocReq thing that will
either need to be removed or the asmmatcher will need to be taught
about it (someday).
llvm-svn: 118119
Douglas Gregor