FCAs. This is essential in order to promote allocas that are used in
struct returns by frontends like Clang. The FCA load would block the
rest of the pass from firing, resulting is significant regressions with
the bullet benchmark in the nightly test suite.

Thanks to Duncan for repeated discussions about how best to do this, and
to both him and Benjamin for review.

This appears to have blocked many places where the pass tries to fire,
and so I'm expect somewhat different results with this fix added.

As with the last big patch, I'm including a change to enable the SROA by
default *temporarily*. Ben is going to remove this as soon as the LNT
bots pick up the patch. I'm just trying to get a round of LNT numbers
from the stable machines in the lab.

NOTE: Four clang tests are expected to fail in the brief window where
this is enabled. Sorry for the noise!

llvm-svn: 164119

Add a test that ensures that ASan does not allow to override the signal handlers.

llvm-svn: 164118

llvm-svn: 164117

[TSan] s/uintptr_t/intptr_t in TSan test and enforce stack size limit in one of TSan output tests that somewhy fails otherwise

llvm-svn: 164116

llvm-svn: 164115

More domain conversion; convert VFP VMOVS to NEON instructions in more cases - when we may clobber the other S-lane by converting an S to a D instruction, make an effort to work out if the S lane is clobberable or not.

llvm-svn: 164114

[Sanitizer] llvm-symbolizer: turn off symbol table lookup by default while getSymbolAddress from libObject returns wrong values

llvm-svn: 164113

[ASan] Move printing descriptions of heap addresses in error report from allocator internals to asan_report.cc.

llvm-svn: 164112

llvm-svn: 164111

[TSan] port all output tests to lit and move them to lit_tests directory. This makes 'make check-tsan' command test both unit and output TSan tests. Old custom makefiles for running TSan tests are still functional as well.

llvm-svn: 164110

Make custom operand parsing mnemonic indices use the same mnemonic table as the match table. Reorder fields in OperandMatchEntry to provide the least amount of padding for in tree targets.

llvm-svn: 164109

Use variable type for index into mnemonic table. Shrinks size of index field on in tree targets. Saving static data space.

llvm-svn: 164108

llvm-svn: 164107

llvm-svn: 164106

Now where we used to call ReInitMCSubtargetInfo, we actually recompute
the same information as InitMCSubtargetInfo instead of only setting
the feature bits.

llvm-svn: 164105

llvm-svn: 164104

llvm-svn: 164103

llvm-svn: 164102

llvm-svn: 164101

llvm-svn: 164100

llvm-svn: 164099

llvm-svn: 164098

llvm-svn: 164097

llvm-svn: 164096

TableGen subtarget emitter. Generate resolveSchedClass generated hook for resolving instruction variants.

llvm-svn: 164095

llvm-svn: 164094

llvm-svn: 164093

llvm-svn: 164092

Mark constructors, destructors, and operator new commented as 'do not implement' with LLVM_DELETED_FUNCTION instead.

llvm-svn: 164091

llvm-svn: 164090

aligned address. Based on patch by David Peixotto.

Also use vld1.64 / vst1.64 with 128-bit alignment to take advantage of alignment
hints. rdar://12090772, rdar://12238782

llvm-svn: 164089

llvm-svn: 164088

llvm-svn: 164087

llvm-svn: 164086

start of a statement or the end of a compound-statement, diagnose the comma as
a typo for a semicolon. Patch by Ahmed Bougacha! Additional test cases and
minor refactoring by me.

llvm-svn: 164085

and a conditional branch; also when removing dead cases from a switch.

llvm-svn: 164084

is no compelling argument that this is a generally useful warning,
and imposes a strong stylistic argument on code beyond what it was
intended to find warnings in.

llvm-svn: 164083

Making ClangExpression hold on to a WP to the Process instead of a SP. This fix should enable us to have per-process maps of ClangExpressions without fear of keeping the process alive forever

llvm-svn: 164082

llvm-svn: 164081

missing 'assign' attribute as it is determined by its
overridden property in primary class. // rdar://12214070 

llvm-svn: 164080