llvm-svn: 313586

Breaks build.

This reverts commit r313583 and r313584.

llvm-svn: 313585

llvm-svn: 313584

On Linux we may need preinit_array in static lib and
ubsan_standalone_initializer in shared lib.

llvm-svn: 313583

llvm-svn: 313580

NFC intended here, this only updates clang and lld's lit configs
to use some helper functionality in the lit.llvm submodule.

llvm-svn: 313579

llvm-svn: 313578

If we have an AssertZext of a truncated value that has already been AssertZext'ed, 
we can assert on the wider source op to improve the zext-y knowledge:
 assert (trunc (assert X, i8) to iN), i1 --> trunc (assert X, i1) to iN

This moves a fold from being Mips-specific to general combining, and x86 shows
improvements.

Differential Revision: https://reviews.llvm.org/D37017

llvm-svn: 313577

llvm-svn: 313576

The code responsible for these transforms has the potential to add 2 
instructions and break min/max patterns (PR33301).

llvm-svn: 313575

This is useful when debugging CMake problems.

llvm-svn: 313574

llvm-svn: 313573

llvm-svn: 313572

No time to write a test case, on to the next bug. =P

Discovered while investigating PR34659

llvm-svn: 313571

error'ed field for a template class' default ctor.

The two examples in the test would both cause a compiler assert when attempting
to calculate the exception specifier for the default constructor for the
template classes. The problem was that dependents of this function expect that
Field->getInClassInitializer (including canThrow) is not nullptr. However, if
the template's initializer has an error, exactly that situation happens.

This patch simply sets the field to be invalid.

Differential Revision: https://reviews.llvm.org/D37865

llvm-svn: 313569

llvm-svn: 313568

llvm-svn: 313567

llvm-svn: 313566

Differential Revision: https://reviews.llvm.org/D37981

llvm-svn: 313565

rL310710 allowed store merging to occur after legalization to catch stores that are created late,
but this exposes a logic hole seen in PR34217:
https://bugs.llvm.org/show_bug.cgi?id=34217

We will miss merging stores if the target lowers vector extracts into target-specific operations.
This patch allows store merging to occur both before and after legalization if the target chooses
to get maximum merging.

I don't think the potential regressions in the other tests are relevant. The tests are for
correctness of weird IR constructs rather than perf tests, and I think those are still correct.

Differential Revision: https://reviews.llvm.org/D37987

llvm-svn: 313564

The AssertZext we might see in this case is only giving information about the lower 32 bits. It isn't providing information about the upper 32 bits. So we should emit a zext.

This fixes PR28540.

Differential Revision: https://reviews.llvm.org/D37729

llvm-svn: 313563

llvm-svn: 313562

Summary:
With the recent move of `android_commands` to `sanitizer_common`, some things
have to be updated with regard to Scudo on Android.

Notably:
- `config.android` is dealt with in the common code
- `config.compile_wrapper` can be prepended to allow for the use of the android
  commands
- `SCUDO_OPTIONS` must be passed with the environment when running a test
- `preinit.cpp` fails with some API levels, not sure why, I will have to dig
  into this later.

Note that `check-scudo` is not enabled yet in the bots. It's all local testing
for now until everything looks good.

Reviewers: alekseyshl, vitalybuka

Reviewed By: vitalybuka

Subscribers: srhines, kubamracek, llvm-commits

Differential Revision: https://reviews.llvm.org/D37990

llvm-svn: 313561

llvm-svn: 313560

llvm-svn: 313559

This is similar to D37843, but for sub_8bit. This fixes all of the patterns except for the 2 that emit only an EXTRACT_SUBREG. That causes a verifier error with global isel because global isel doesn't know to issue the ABCD when doing this extract on 32-bits targets.

Differential Revision: https://reviews.llvm.org/D37890

llvm-svn: 313558

I'm pretty sure that InstrEmitter::EmitSubregNode will take care of this itself by calling ConstrainForSubReg which in turn calls TRI->getSubClassWithSubReg.

I think Jakob Stoklund Olesen alluded to this in his commit message for r141207 which added the code to EmitSubregNode.

Differential Revision: https://reviews.llvm.org/D37843

llvm-svn: 313557

"Repl" member is guranteed to have a non-null pointer. If an input
section is not merged by ICF, "Repl" points to "this". Otherwise, it
points to some other section. It must not be NULL.

llvm-svn: 313556

Refine the model of FP loads and stores.

llvm-svn: 313555

Refine the model of loads and stores using the register offset addressing
modes.

llvm-svn: 313554

Fix formatting in the predicate function AArch64InstrInfo::isExynosShiftLeftFast().

llvm-svn: 313553

r313390 taught 'allowExtraAnalysis' to check whether remarks are
enabled at all.  Use that to only do the expensive instruction printing
if they are.

llvm-svn: 313552

Summary:
1. Update ubsan_interface.inc to make the test happy.
2. Switch interface_symbols_linux and interface_symbols_darwin to C++ to import __ubsan_handle_dynamic_type_cache_miss
3. Switch interface_symbols_windows to C++ for consistency.

Reviewers: rnk, zturner

Subscribers: llvm-commits, kubamracek

Differential Revision: https://reviews.llvm.org/D37986

llvm-svn: 313551

This is not really OK in C++11, and GCc triggers a warning.
We can switch back to default arguments when C++14 will be the
minimum version of the standard supported, see:
http://www.open-std.org/jtc1/sc22/wg21/docs/cwg_defects.html#974

Ack'ed by Rafael.

llvm-svn: 313550

This should fix an issue which arises when running check-compiler-rt on
the coverage bot:
http://green.lab.llvm.org/green/job/clang-stage2-coverage-R_build/1590/

The bot doesn't build the sanitizers, but the check-compiler-rt target
always expects the profile runtime to exist.

llvm-svn: 313549

llvm-svn: 313548

As commented on D37849, AVX1 targets were missing a chance to use vmovmskps for v8f32/v8i32 results for bool vector bitcasts

llvm-svn: 313547

cl::opt<unsigned long> is not specialized and hence the option
-polly-optree-max-ops impossible to use.

Replace by supported option cl::opt<unsigned>.

Also check for an error state when computing the written value, which
happens when the quota runs out.

llvm-svn: 313546

llvm-svn: 313545

Summary:
Add test cases when float <-> pointer types conversion is triggered
in presence of load instructions.

Reviewers: Ayal, srhines, mkuper, rengolin

Reviewed By: rengolin

Subscribers: javed.absar, llvm-commits

Differential Revision: https://reviews.llvm.org/D37967

llvm-svn: 313544