Previously, only regular AArch64 instructions were annotated with SchedRW lists.
This patch does the same for NEON enabling these instructions to be scheduled by
the MIScheduler. Additionally, store operations are now modeled and a few
SchedRW lists were updated for bug fixes (e.g. multiple def operands).

Reviewers: apazos, mcrosier, atrick
Patch by Dave Estes <cestes@codeaurora.org>!

llvm-svn: 204505

Suppress SIGSTOP under Linux and don't explicitly call SetResumeSignal() in POSIXThread, instead just let StopInfo handle it.

llvm-svn: 204504

llvm-svn: 204503

llvm-svn: 204502

llvm-svn: 204501

<rdar://problem/15943240>

llvm-svn: 204500

Write __llvm_profile_write_buffer(), which uses the same logic as
__llvm_profile_write_file(), but writes directly to a provided `char*`
buffer instead.

<rdar://problem/15943240>

llvm-svn: 204499

It was misguided to plan to rely on __llvm_profile_write_buffer() in
__llvm_profile_write_file().  It's less complex to duplicate the writing
logic than to mmap the file.

Since it's here to stay, move `FILE*`-based writing logic into
InstrProfilingFile.c.

<rdar://problem/15943240>

llvm-svn: 204498

Move functions around to prepare for some other changes.

  - Merge InstrProfilingExtras.h with InstrProfiling.h.  There's no
    benefit to having these split.

  - Rename InstrProfilingExtras.c to InstrProfilingFile.c.

  - Split actual buffer writing code out of InstrProfiling.c into
    InstrProfilingBuffer.c.

  - Drive-by corrections of a couple of header comments.

<rdar://problem/15943240>

llvm-svn: 204497

Read a raw binary profile that corresponds to a memory dump from the
runtime profile.

The test is a binary file generated from
cfe/trunk/test/Profile/c-general.c with the new compiler-rt runtime and
the matching text version of the input.  It includes instructions on how
to regenerate.

<rdar://problem/15950346>

llvm-svn: 204496

Write a raw binary profile from the runtime.

<rdar://problem/15950346>

llvm-svn: 204495

llvm-svn: 204494

and substitute fully qualified path names pointing to the build
directory.  This ensures we're testing the just-built tools.

llvm-svn: 204493

Some of them also had the pattern on both, so this removes the
duplication.

llvm-svn: 204492

This is tested from MC already.

llvm-svn: 204491

llvm-svn: 204490

This isn't a format we'll want to write out in practice, but moving it
to the writer library simplifies llvm-profdata and isolates it from
further changes to the format.

This also allows us to update the tests to not rely on the text output
format.

llvm-svn: 204489

An unnamed global in llvm still produces a regular symbol.

llvm-svn: 204488

llvm-svn: 204487

llvm-svn: 204486

The `llvm-profdata show` command summarizes a profdata file's contents
in a human readable format.

llvm-svn: 204485

Use new(allocator_for_flags) instead of allocator_for_flags.Allocate()
Fix the description output format a bit.

llvm-svn: 204484

The production of the .eh symbols is done from MC now and we already have tests
for it.

llvm-svn: 204483

This introduces the ProfileData library and updates llvm-profdata to
use this library for reading profiles. InstrProfReader is an abstract
base class that will be subclassed for both the raw instrprof data
from compiler-rt and the efficient instrprof format that will be used
for PGO.

llvm-svn: 204482

llvm-svn: 204481

Summary:
VECTOR_SHUFFLE concatenates the vectors in an vectorwise fashion.
  <0b00, 0b01> + <0b10, 0b11> -> <0b00, 0b01, 0b10, 0b11>
VSHF concatenates the vectors in a bitwise fashion:
  <0b00, 0b01> + <0b10, 0b11> ->
  0b0100       + 0b1110       -> 0b01001110
                                 <0b10, 0b11, 0b00, 0b01>
We must therefore swap the operands to get the correct result.

The test case that discovered the issue was MultiSource/Benchmarks/nbench.

Reviewers: matheusalmeida

Reviewed By: matheusalmeida

Differential Revision: http://llvm-reviews.chandlerc.com/D3142

llvm-svn: 204480

llvm-svn: 204479

Patch by: Jeroen Ketema

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 204478

Patch by: Jeroen Ketema

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
llvm-svn: 204477

llvm-svn: 204476

llvm-svn: 204475

The SReg_(32|64) register classes contain special registers in addition
to the numbered SGPRs.  This can lead to machine verifier errors when
these register classes are used as sub-registers for SReg_128, since
SReg_128 only uses the numbered SGPRs.

Replacing SReg_(32|64) with SGPR_(32|64) fixes this problem, since
the SGPR_(32|64) register classes contain only numbered SGPRs.

Tests cases for this are comming in a later commit.

llvm-svn: 204474

CodeGen treats allocas outside the entry block as dynamically sized
stack objects.

llvm-svn: 204473

llvm-svn: 204472

Fixing code that doesn't compile in MSVC 2012 (but does in MSVC 2013) from r204417 and related commits.

llvm-svn: 204471

For complex examples it may happen that we do not compute dependences. In this
case we do not want to crash, but just not detect parallel loops.

llvm-svn: 204470

The release_capability, release_shared_capability and release_generic_capability functions are now functionally distinct for capability analysis. The unlock_function attribute maps directly to release_generic_capability.

llvm-svn: 204469

llvm-svn: 204468

This unbreaks polly-formatting-tests and we can make a decision for
LLVM style independently.

llvm-svn: 204467

llvm-svn: 204466