oota-llvm.git
10 years ago[AVX512] Added intrinsics for 128-, 256- and 512-bit versions of VCMPGT{BWDQ}.
Robert Khasanov [Tue, 30 Sep 2014 12:15:52 +0000 (12:15 +0000)]
[AVX512] Added intrinsics for 128-, 256- and 512-bit versions of VCMPGT{BWDQ}.
Patch by Sergey Lisitsyn <sergey.lisitsyn@intel.com>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218670 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AVX512] Added intrinsics for 128- and 256-bit versions of VCMPEQ{BWDQ}
Robert Khasanov [Tue, 30 Sep 2014 11:41:54 +0000 (11:41 +0000)]
[AVX512] Added intrinsics for 128- and 256-bit versions of VCMPEQ{BWDQ}
Fixed lowering of this intrinsics in case when mask is v2i1 and v4i1.
Now cmp intrinsics lower in the following way:
 (i8 (int_x86_avx512_mask_pcmpeq_q_128
             (v2i64 %a), (v2i64 %b), (i8 %mask))) ->
 (i8 (bitcast
   (v8i1 (insert_subvector undef,
           (v2i1 (and (PCMPEQM %a, %b),
                      (extract_subvector
                         (v8i1 (bitcast %mask)), 0))), 0))))

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218669 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AVX512] Added intrinsics for VPCMPEQB and VPCMPEQW.
Robert Khasanov [Tue, 30 Sep 2014 11:32:22 +0000 (11:32 +0000)]
[AVX512] Added intrinsics for VPCMPEQB and VPCMPEQW.
Added new operand type for intrinsics (IIT_V64)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218668 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AVX512] Enabled intrinsics for VPCMPEQD and VPCMPEQQ.
Robert Khasanov [Tue, 30 Sep 2014 11:19:50 +0000 (11:19 +0000)]
[AVX512] Enabled intrinsics for VPCMPEQD and VPCMPEQQ.
Added CMP_MASK intrinsic type

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218667 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoMake sure aggregates are properly alligned on MSP430.
Job Noorman [Tue, 30 Sep 2014 11:15:44 +0000 (11:15 +0000)]
Make sure aggregates are properly alligned on MSP430.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218665 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[IndVarSimplify] Widen loop unsigned compares.
Chad Rosier [Tue, 30 Sep 2014 03:17:42 +0000 (03:17 +0000)]
[IndVarSimplify] Widen loop unsigned compares.

This patch extends r217953 to handle unsigned comparison.
Phabricator revision: http://reviews.llvm.org/D5526

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218659 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Revert r218588, r218589, and r218600. These patches were pursuing
Chandler Carruth [Tue, 30 Sep 2014 02:52:28 +0000 (02:52 +0000)]
[x86] Revert r218588, r218589, and r218600. These patches were pursuing
a flawed direction and causing miscompiles. Read on for details.

Fundamentally, the premise of this patch series was to map
VECTOR_SHUFFLE DAG nodes into VSELECT DAG nodes for all blends because
we are going to *have* to lower to VSELECT nodes for some blends to
trigger the instruction selection patterns of variable blend
instructions. This doesn't actually work out so well.

In order to match performance with the existing VECTOR_SHUFFLE
lowering code, we would need to re-slice the blend in order to fit it
into either the integer or floating point blends available on the ISA.
When coming from VECTOR_SHUFFLE (or other vNi1 style VSELECT sources)
this works well because the X86 backend ensures that these types of
operands to VSELECT get sign extended into '-1' and '0' for true and
false, allowing us to re-slice the bits in whatever granularity without
changing semantics.

However, if the VSELECT condition comes from some other source, for
example code lowering vector comparisons, it will likely only have the
required bit set -- the high bit. We can't blindly slice up this style
of VSELECT. Reid found some code using Halide that triggers this and I'm
hopeful to eventually get a test case, but I don't need it to understand
why this is A Bad Idea.

There is another aspect that makes this approach flawed. When in
VECTOR_SHUFFLE form, we have very distilled information that represents
the *constant* blend mask. Converting back to a VSELECT form actually
can lose this information, and so I think now that it is better to treat
this as VECTOR_SHUFFLE until the very last moment and only use VSELECT
nodes for instruction selection purposes.

My plan is to:
1) Clean up and formalize the target pre-legalization DAG combine that
   converts a VSELECT with a constant condition operand into
   a VECTOR_SHUFFLE.
2) Remove any fancy lowering from VSELECT during *legalization* relying
   entirely on the DAG combine to catch cases where we can match to an
   immediate-controlled blend instruction.

One additional step that I'm not planning on but would be interested in
others' opinions on: we could add an X86ISD::VSELECT or X86ISD::BLENDV
which encodes a fully legalized VSELECT node. Then it would be easy to
write isel patterns only in terms of this to ensure VECTOR_SHUFFLE
legalization only ever forms the fully legalized construct and we can't
cycle between it and VSELECT combining.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218658 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Add some vector-register broadcast operations to the 256-bit v4
Chandler Carruth [Tue, 30 Sep 2014 02:32:36 +0000 (02:32 +0000)]
[x86] Add some vector-register broadcast operations to the 256-bit v4
tests which were missing them.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218657 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600: Fix broken check lines, missing scalar case.
Matt Arsenault [Tue, 30 Sep 2014 01:05:29 +0000 (01:05 +0000)]
R600: Fix broken check lines, missing scalar case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218655 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix missing C++ mode comment
Matt Arsenault [Tue, 30 Sep 2014 01:05:27 +0000 (01:05 +0000)]
Fix missing C++ mode comment

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218654 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[FastISel][AArch64] Fold sign-/zero-extends into the load instruction.
Juergen Ributzka [Tue, 30 Sep 2014 00:49:58 +0000 (00:49 +0000)]
[FastISel][AArch64] Fold sign-/zero-extends into the load instruction.

The sign-/zero-extension of the loaded value can be performed by the memory
instruction for free. If the result of the load has only one use and the use is
a sign-/zero-extend, then we emit the proper load instruction. The extend is
only a register copy and will be optimized away later on.

Other instructions that consume the sign-/zero-extended value are also made
aware of this fact, so they don't fold the extend too.

This fixes rdar://problem/18495928.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218653 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[FastISel][AArch64] Factor out scale factor calculation. NFC.
Juergen Ributzka [Tue, 30 Sep 2014 00:49:54 +0000 (00:49 +0000)]
[FastISel][AArch64] Factor out scale factor calculation. NFC.

Factor out the code that determines the implicit scale factor of memory
operations for a given value type.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218652 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[llvm-objdump] switch some uses of format() to format_hex() and left_justify()
Nick Kledzik [Tue, 30 Sep 2014 00:19:58 +0000 (00:19 +0000)]
[llvm-objdump] switch some uses of format() to format_hex() and left_justify()

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218649 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoSimplify conditional.
Eric Christopher [Mon, 29 Sep 2014 23:31:13 +0000 (23:31 +0000)]
Simplify conditional.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218643 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AVX512] Use X86VectorVTInfo in the masking helper classes and the FMAs
Adam Nemet [Mon, 29 Sep 2014 22:54:41 +0000 (22:54 +0000)]
[AVX512] Use X86VectorVTInfo in the masking helper classes and the FMAs

No functionality change.

Makes the code more compact (see the FMA part).

This needs a new type attribute MemOpFrag in X86VectorVTInfo.  For now I only
defined this in the simple cases.  See the commment before the attribute.

Diff of X86.td.expanded before and after is empty except for the appearance of
the new attribute.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218637 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoWinCOFFObjectWriter: optimize the string table for common suffices
Hans Wennborg [Mon, 29 Sep 2014 22:43:20 +0000 (22:43 +0000)]
WinCOFFObjectWriter: optimize the string table for common suffices

This is a follow-up from r207670 which did the same for ELF.

Differential Revision: http://reviews.llvm.org/D5530

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218636 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd soft-float to the key for the subtarget lookup in the TargetMachine
Eric Christopher [Mon, 29 Sep 2014 21:57:54 +0000 (21:57 +0000)]
Add soft-float to the key for the subtarget lookup in the TargetMachine
map, this makes sure that we can compile the same code for two different
ABIs (hard and soft float) in the same module.

Update one testcase accordingly (and fix some confusing naming) and
add a new testcase as well with the ordering swapped which would
highlight the problem.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218632 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix spelling and reflow comments.
Eric Christopher [Mon, 29 Sep 2014 21:57:52 +0000 (21:57 +0000)]
Fix spelling and reflow comments.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218631 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AArch64] Refines the Cortex-A57 Machine Model
Dave Estes [Mon, 29 Sep 2014 21:27:36 +0000 (21:27 +0000)]
[AArch64] Refines the Cortex-A57 Machine Model

Primarily refines all of the instructions with accurate latency
and micro-op information. Refinements largely focus on the NEON
instructions.

Additionally, a few advanced features are modeled, including
forwarding for MAC instructions and hazards for floating point SQRT
and DIV.

Lastly, the issue-width is reduced to three so that the scheduler
will better accommodate the narrower decode and dispatch width.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218627 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoUnit test r218187, changing RTDyldMemoryManager::getSymbolAddress's behavior favor...
David Blaikie [Mon, 29 Sep 2014 21:25:13 +0000 (21:25 +0000)]
Unit test r218187, changing RTDyldMemoryManager::getSymbolAddress's behavior favor mangled lookup over unmangled lookup.

The contract of this function seems problematic (fallback in either
direction seems like it could produce bugs in one client or another),
but here's some tests for its current behavior, at least. See the
commit/review thread of r218187 for more discussion.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218626 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFixing the build for compilers which do not yet have support for constexpr functions...
Aaron Ballman [Mon, 29 Sep 2014 20:27:01 +0000 (20:27 +0000)]
Fixing the build for compilers which do not yet have support for constexpr functions, NFC.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218622 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd getValueOr to llvm::Optional<T>.
Jordan Rose [Mon, 29 Sep 2014 18:56:08 +0000 (18:56 +0000)]
Add getValueOr to llvm::Optional<T>.

This takes a single argument convertible to T, and
- if the Optional has a value, returns the existing value,
- otherwise, constructs a T from the argument and returns that.

Inspired by std::experimental::optional from the "Library Fundamentals" C++ TS.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218618 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd "typedef T value_type;" to llvm::Optional<T>.
Jordan Rose [Mon, 29 Sep 2014 18:56:05 +0000 (18:56 +0000)]
Add "typedef T value_type;" to llvm::Optional<T>.

Inspired by std::experimental::optional from the "Library Fundamentals" C++ TS.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218617 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFixing missing C++ mode comment
Matt Arsenault [Mon, 29 Sep 2014 15:55:18 +0000 (15:55 +0000)]
Fixing missing C++ mode comment

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218612 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix include order
Matt Arsenault [Mon, 29 Sep 2014 15:53:15 +0000 (15:53 +0000)]
Fix include order

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218611 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Fix hardcoded values for modifiers.
Matt Arsenault [Mon, 29 Sep 2014 15:50:26 +0000 (15:50 +0000)]
R600/SI: Fix hardcoded values for modifiers.

Move enums to SIDefines.h

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218610 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Also fix fsub + fadd a, a to mad combines
Matt Arsenault [Mon, 29 Sep 2014 14:59:38 +0000 (14:59 +0000)]
R600/SI: Also fix fsub + fadd a, a to mad combines

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218609 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Fix using mad with multiplies by 2
Matt Arsenault [Mon, 29 Sep 2014 14:59:34 +0000 (14:59 +0000)]
R600/SI: Fix using mad with multiplies by 2

These turn into fadds, so combine them into the target
mad node.

fadd (fadd (a, a), b) -> mad 2.0, a, b

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218608 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AArch64] Improve cost model to handle sdiv by a pow-of-two.
Chad Rosier [Mon, 29 Sep 2014 13:59:31 +0000 (13:59 +0000)]
[AArch64] Improve cost model to handle sdiv by a pow-of-two.

This patch improves the target-specific cost model to better handle signed
division by a power of two. The immediate result is that this enables the SLP
vectorizer to do a better job.

http://reviews.llvm.org/D5469
PR20714

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218607 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoStore TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection.
Frederic Riss [Mon, 29 Sep 2014 13:56:39 +0000 (13:56 +0000)]
Store TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection.

There will be multiple TypeUnits in an unlinked object that will be extracted
from different sections. Now that we have DWARFUnitSection that is supposed
to represent an input section, we need a DWARFUnitSection<TypeUnit> per
input .debug_types section.

Once this is done, the interface is homogenous and we can move the Section
parsing code into DWARFUnitSection.

This is a respin of r218513 that got reverted because it broke some builders.
This new version features an explicit move constructor for the DWARFUnitSection
class to workaround compilers unable to generate correct C++11 default
constructors.

Reviewers: samsonov, dblaikie

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5482

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218606 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoUse a loop to simplify the runtime unrolling prologue.
Kevin Qin [Mon, 29 Sep 2014 11:15:00 +0000 (11:15 +0000)]
Use a loop to simplify the runtime unrolling prologue.

Runtime unrolling will create a prologue to execute the extra
iterations which is can't divided by the unroll factor. It
generates an if-then-else sequence to jump into a factor -1
times unrolled loop body, like

    extraiters = tripcount % loopfactor
    if (extraiters == 0) jump Loop:
    if (extraiters == loopfactor) jump L1
    if (extraiters == loopfactor-1) jump L2
    ...
    L1:  LoopBody;
    L2:  LoopBody;
    ...
    if tripcount < loopfactor jump End
    Loop:
    ...
    End:

It means if the unroll factor is 4, the loop body will be 7
times unrolled, 3 are in loop prologue, and 4 are in the loop.
This commit is to use a loop to execute the extra iterations
in prologue, like

        extraiters = tripcount % loopfactor
        if (extraiters == 0) jump Loop:
        else jump Prol
 Prol:  LoopBody;
        extraiters -= 1                 // Omitted if unroll factor is 2.
        if (extraiters != 0) jump Prol: // Omitted if unroll factor is 2.
        if (tripcount < loopfactor) jump End
 Loop:
 ...
 End:

Then when unroll factor is 4, the loop body will be copied by
only 5 times, 1 in the prologue loop, 4 in the original loop.
And if the unroll factor is 2, new loop won't be created, just
as the original solution.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218604 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[Thumb2] ldrexd and strexd are not defined on v7M
Oliver Stannard [Mon, 29 Sep 2014 10:57:29 +0000 (10:57 +0000)]
[Thumb2] ldrexd and strexd are not defined on v7M

The Thumb2 ldrexd and strexd instructions are not defined for
M-class architectures.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218603 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Make the new vector shuffle lowering lower blends as VSELECT
Chandler Carruth [Mon, 29 Sep 2014 09:57:07 +0000 (09:57 +0000)]
[x86] Make the new vector shuffle lowering lower blends as VSELECT
nodes, and rely exclusively on its logic. This removes a ton of
duplication from the blend lowering and centralizes it in one place.

One downside is that it requires a bunch of hacks to make this work with
the current legalization framework. We have to manually speculate one
aspect of legalizing VSELECT nodes to get everything to work nicely
because the existing legalization framework isn't *actually* bottom-up.

The other grossness is that we somewhat duplicate the analysis of
constant blends. I'm on the fence here. If reviewers thing this would
look better with VSELECT when it has constant operands dumping over tho
VECTOR_SHUFFLE, we could go that way. But it would be a substantial
change because currently all of the actual blend instructions are
matched via patterns in the TD files based around VSELECT nodes (despite
them not being perfect fits for that). Suggestions welcome, but at least
this removes the rampant duplication in the backend.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218600 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRemove dead code from DIBuilder
Jyoti Allur [Mon, 29 Sep 2014 06:32:54 +0000 (06:32 +0000)]
Remove dead code from DIBuilder

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218593 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Delete a bunch of really bad and totally unnecessary code in the
Chandler Carruth [Mon, 29 Sep 2014 02:01:20 +0000 (02:01 +0000)]
[x86] Delete a bunch of really bad and totally unnecessary code in the
X86 target-specific DAG combining that tried to convert VSELECT nodes
into VECTOR_SHUFFLE nodes that it "knew" would lower into
immediate-controlled blend nodes.

Turns out, we have perfectly good lowering of all these VSELECT nodes,
and indeed that lowering already knows how to handle lowering through
BLENDI to immediate-controlled blend nodes. The code just wasn't getting
used much because this thing forced the world to go through the vector
shuffle lowering. Yuck.

This also exposes that I was too aggressive in avoiding domain crossing
in v218588 with that lowering -- when the other option is to expand into
two 128-bit vectors, it is worth domain crossing. Restore that behavior
now that we have nice tests covering it.

The test updates here fall into two camps. One is where previously we
ended up with an unsigned encoding of the blend operand and now we get
a signed encoding. In most of those places there were elaborate comments
explaining exactly what these operands really mean. Rather than that,
just switch these tests to use the nicely decoded comments that make it
obvious that the final shuffle matches.

The other updates are just removing pointless domain crossing by
blending integers with PBLENDW rather than BLENDPS.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218589 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Refactor all of the VSELECT-as-blend lowering code to avoid domain
Chandler Carruth [Mon, 29 Sep 2014 01:32:54 +0000 (01:32 +0000)]
[x86] Refactor all of the VSELECT-as-blend lowering code to avoid domain
crossing and generally work more like the blend emission code in the new
vector shuffle lowering.

My goal is to have the new vector shuffle lowering just produce VSELECT
nodes that are either matched here to BLENDI or are legal and matched in
the .td files to specific blend instructions. That seems much cleaner as
there are other ways to produce a VSELECT anyways. =]

No *observable* functionality changed yet, mostly because this code
appears to be near-dead. The behavior of this lowering routine did
change though. This code being mostly dead and untestable will change
with my next commit which will also point some new tests at it.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218588 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Improve naming and comments for VSELECT lowering.
Chandler Carruth [Mon, 29 Sep 2014 00:51:58 +0000 (00:51 +0000)]
[x86] Improve naming and comments for VSELECT lowering.

No functionality changed.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218586 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Add the dispatch skeleton to the new vector shuffle lowering for
Chandler Carruth [Mon, 29 Sep 2014 00:37:27 +0000 (00:37 +0000)]
[x86] Add the dispatch skeleton to the new vector shuffle lowering for
AVX-512.

There is no interesting logic yet. Everything ends up eventually
delegating to the generic code to split the vector and shuffle the
halves. Interestingly, that logic does a significantly better job of
lowering all of these types than the generic vector expansion code does.
Mostly, it lets most of the cases fall back to nice AVX2 code rather
than all the way back to SSE code paths.

Step 2 of basic AVX-512 support in the new vector shuffle lowering. Next
up will be to incrementally add direct support for the basic instruction
set to each type (adding tests first).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218585 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Make the split-and-lower routine fully generic by relaxing the
Chandler Carruth [Mon, 29 Sep 2014 00:21:49 +0000 (00:21 +0000)]
[x86] Make the split-and-lower routine fully generic by relaxing the
assertion, making the name generic, and improving the documentation.

Step 1 in adding very primitive support for AVX-512. No functionality
changed yet.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218584 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Teach the new vector shuffle lowering to fall back on AVX-512
Chandler Carruth [Sun, 28 Sep 2014 23:53:10 +0000 (23:53 +0000)]
[x86] Teach the new vector shuffle lowering to fall back on AVX-512
vectors.

Someone will need to build the AVX512 lowering, which should follow
AVX1 and AVX2 *very* closely for AVX512F and AVX512BW resp. I've added
a dummy test which is a port of the v8f32 and v8i32 tests from AVX and
AVX2 to v8f64 and v8i64 tests for AVX512F and AVX512BW. Hopefully this
is enough information for someone to implement proper lowering here. If
not, I'll be happy to help, but right now the AVX-512 support isn't
a priority for me.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218583 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix the new vector shuffle lowering's use of VSELECT for AVX2
Chandler Carruth [Sun, 28 Sep 2014 23:23:55 +0000 (23:23 +0000)]
[x86] Fix the new vector shuffle lowering's use of VSELECT for AVX2
lowerings.

This was hopelessly broken. First, the x86 backend wants '-1' to be the
element value representing true in a boolean vector, and second the
operand order for VSELECT is backwards from the actual x86 instructions.
To make matters worse, the backend is just using '-1' as the true value
to get the high bit to be set. It doesn't actually symbolically map the
'-1' to anything. But on x86 this isn't quite how it works: there *only*
the high bit is relevant. As a consequence weird non-'-1' values like
0x80 actually "work" once you flip the operands to be backwards.

Anyways, thanks to Hal for helping me sort out what these *should* be.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218582 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd MachineOperand::ChangeToFPImmediate and setFPImm
Matt Arsenault [Sun, 28 Sep 2014 19:24:59 +0000 (19:24 +0000)]
Add MachineOperand::ChangeToFPImmediate and setFPImm

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218579 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix a really silly bug that I introduced fixing another bug in the
Chandler Carruth [Sun, 28 Sep 2014 06:11:04 +0000 (06:11 +0000)]
[x86] Fix a really silly bug that I introduced fixing another bug in the
new vector shuffle target DAG combines -- it helps to actually test for
the value you want rather than just using an integer in a boolean
context.

Have I mentioned that I loathe implicit conversions recently? :: sigh ::

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218576 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix yet another bug in the new vector shuffle lowering's handling
Chandler Carruth [Sun, 28 Sep 2014 03:30:25 +0000 (03:30 +0000)]
[x86] Fix yet another bug in the new vector shuffle lowering's handling
of widening masks.

We can't widen a zeroing mask unless both elements that would be merged
are either zeroed or undef. This is the only way to widen a mask if it
has a zeroed element.

Also clean up the code here by ordering the checks in a more logical way
and by using the symoblic values for undef and zero. I'm actually torn
on using the symbolic values because the existing code is littered with
the assumption that -1 is undef, and moreover that entries '< 0' are the
special entries. While that works with the values given to these
constants, using the symbolic constants actually makes it a bit more
opaque why this is the case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218575 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoWinCOFFObjectWriter.cpp: make write_uint32_le more efficient
Hans Wennborg [Sun, 28 Sep 2014 00:22:27 +0000 (00:22 +0000)]
WinCOFFObjectWriter.cpp: make write_uint32_le more efficient

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218574 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AArch64] Redundant store instructions should be removed as dead code
James Molloy [Sat, 27 Sep 2014 17:02:54 +0000 (17:02 +0000)]
[AArch64] Redundant store instructions should be removed as dead code

If there is a store followed by a store with the same value to the same location, then the store is dead/noop. It can be removed.

This problem is found in spec2006-197.parser.

For example,
  stur    w10, [x11, #-4]
  stur    w10, [x11, #-4]
Then one of the two stur instructions can be removed.

Patch by David Xu!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218569 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix llvm::huge_valf multiple initializations with Visual C++.
Yaron Keren [Sat, 27 Sep 2014 14:41:29 +0000 (14:41 +0000)]
Fix llvm::huge_valf multiple initializations with Visual C++.

llvm::huge_valf is defined in a header file, so it is initialized
multiple times in every compiled unit upon program startup.

With non-VC compilers huge_valf is set to a HUGE_VALF which the
compiler can probably optimize out.

With VC numeric_limits<float>::infinity() does not return a number
but a runtime structure member which therotically may change
between calls so the compiler does not optimize out the
initialization and it happens many times. It can be easily seen by
placing a breakpoint on the initialization line.

This patch moves llvm::huge_valf initialization to a source file
instead of the header.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218567 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix yet another issue with widening vector shuffle elements.
Chandler Carruth [Sat, 27 Sep 2014 08:40:33 +0000 (08:40 +0000)]
[x86] Fix yet another issue with widening vector shuffle elements.
I spotted this by inspection when debugging something else, so I have no
test case what-so-ever, and am not even sure it is possible to
realistically trigger the bug. But this is what was intended here.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218565 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoUpdate test case to match minor formatting change introduced in r218563.
Craig Topper [Sat, 27 Sep 2014 05:36:53 +0000 (05:36 +0000)]
Update test case to match minor formatting change introduced in r218563.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218564 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoReduce code duplication a bit.
Craig Topper [Sat, 27 Sep 2014 05:26:42 +0000 (05:26 +0000)]
Reduce code duplication a bit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218563 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix terrible bugs everywhere in the new vector shuffle lowering
Chandler Carruth [Sat, 27 Sep 2014 04:42:44 +0000 (04:42 +0000)]
[x86] Fix terrible bugs everywhere in the new vector shuffle lowering
and in the target shuffle combining when trying to widen vector
elements.

Previously only one of these was correct, and we didn't correctly
propagate zeroing target shuffle masks (which have a different sentinel
value from undef in non- target shuffle masks now). This isn't just
a missed optimization, this caused us to drop zeroing shuffles on the
floor and miscompile code. The added test case is one example of that.

There are other fixes to the test suite as a consequence of this as well
as restoring the undef elements in some of the masks that were lost when
I brought sanity to the actual *value* of the undef and zero sentinels.

I've also just cleaned up some of the PSHUFD and PSHUFLW and PSHUFHW
combining code, but that code really needs to go. It was a nice initial
attempt, but it isn't very principled and the recursive shuffle combiner
is much more powerful.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218562 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Flip the sentinel values used in the target shuffle mask decoding
Chandler Carruth [Sat, 27 Sep 2014 04:42:39 +0000 (04:42 +0000)]
[x86] Flip the sentinel values used in the target shuffle mask decoding
to significantly more sane sentinels. Notably, everywhere else in the
backend's representation of shuffles uses '-1' to represent undef. The
target shuffle masks really shouldn't diverge from that, especially as
in a few places they are manipulated by shared code.

This causes us to lose some undef lanes in various test masks. I want to
get these back, but technically it isn't invalid and there are a *lot*
of bugs here so I want to try to establish a saner baseline for fixing
some of the bugs by aligning the specific senitnel values used.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218561 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix TableGen -gen-disassembler output for bit fields with an offset.
Craig Topper [Sat, 27 Sep 2014 04:38:02 +0000 (04:38 +0000)]
Fix TableGen -gen-disassembler output for bit fields with an offset.

This fixes bit assignments like this
Inst{7-0} = Foo{9-2}

Patch by Steve King.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218560 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRefactor reciprocal and reciprocal square root estimate into target-independent funct...
Sanjay Patel [Fri, 26 Sep 2014 23:01:47 +0000 (23:01 +0000)]
Refactor reciprocal and reciprocal square root estimate into target-independent functions (part 2).

This is purely refactoring. No functional changes intended. PowerPC is the only target
that is currently using this interface.

The ultimate goal is to allow targets other than PowerPC (certainly X86 and Aarch64) to turn this:

z = y / sqrt(x)

into:

z = y * rsqrte(x)

And:

z = y / x

into:

z = y * rcpe(x)

using whatever HW magic they can use. See http://llvm.org/bugs/show_bug.cgi?id=20900 .

There is one hook in TargetLowering to get the target-specific opcode for an estimate instruction
along with the number of refinement steps needed to make the estimate usable.

Differential Revision: http://reviews.llvm.org/D5484

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218553 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd LLVM_ENABLE_MODULES flag to CMake to enable building with C++ modules.
Richard Smith [Fri, 26 Sep 2014 22:40:15 +0000 (22:40 +0000)]
Add LLVM_ENABLE_MODULES flag to CMake to enable building with C++ modules.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218551 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agollvm-vtabledump: Further simplification
David Majnemer [Fri, 26 Sep 2014 22:32:19 +0000 (22:32 +0000)]
llvm-vtabledump: Further simplification

Hoist out calls to getSection and getContents.  No functional change
intended.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218550 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoObject: BSS/virtual sections don't have contents
David Majnemer [Fri, 26 Sep 2014 22:32:16 +0000 (22:32 +0000)]
Object: BSS/virtual sections don't have contents

Users of getSectionContents shouldn't try to pass in BSS or virtual
sections.  In all instances, this is a bug in the code calling this
routine.

N.B. Some COFF implementations (like CL) will mark their BSS sections as
taking space on disk.  This would confuse COFFObjectFile into thinking
the section is larger than the file.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218549 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoclang-format of ChangeStdinToBinary & ChangeStdoutToBinary.
Yaron Keren [Fri, 26 Sep 2014 22:27:11 +0000 (22:27 +0000)]
clang-format of ChangeStdinToBinary & ChangeStdoutToBinary.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218547 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoUpdate llvm-objdump’s Mach-O symbolizer code to print the name of symbol stubs.
Kevin Enderby [Fri, 26 Sep 2014 22:20:44 +0000 (22:20 +0000)]
Update llvm-objdump’s Mach-O symbolizer code to print the name of symbol stubs.

So in fully linked images when a call is made through a stub it now gets a
comment like the following in the disassembly:

    callq 0x100000f6c             ## symbol stub for: _printf

indicating the call is to a symbol stub and which symbol it is for.  This is
done for branch reference types and seeing if the branch target is in a stub
section and if so using the indirect symbol table entry for that stub and
using that symbol table entries symbol name.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218546 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRemove definition of LLVM_VERSION_INFO; this macro is not used by any of the
Richard Smith [Fri, 26 Sep 2014 21:53:12 +0000 (21:53 +0000)]
Remove definition of LLVM_VERSION_INFO; this macro is not used by any of the
files in this directory. If it should be defined anywhere, it should be defined
when building lib/LTO/LTOCodeGenerator.cpp, but we've not had it defined there
for quite some time, so that doesn't really seem to be very important. (It also
would slow down the modules build by creating extra module variants.)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218544 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix CMake warning CMP0054: don't quote a variable name that is intended to be
Richard Smith [Fri, 26 Sep 2014 21:35:48 +0000 (21:35 +0000)]
Fix CMake warning CMP0054: don't quote a variable name that is intended to be
expanded; future versions of cmake may not expand the variable in this case.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218543 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix misinterpretation of CMake rule found by a CMake warning (related to CMP0054).
Richard Smith [Fri, 26 Sep 2014 21:33:05 +0000 (21:33 +0000)]
Fix misinterpretation of CMake rule found by a CMake warning (related to CMP0054).

lldb sets the variable SHARED_LIBRARY to 1, which breaks this conditional,
because older versions of CMake interpret

  if ("${t}" STREQUAL "SHARED_LIBRARY")

as meaning

  if ("${t}" STREQUAL "1")

in this case. Change the conditional so it does the right thing with both old
and new CMakes.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218542 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix a moderately terrifying bug in the new 128-bit shuffle logic
Chandler Carruth [Fri, 26 Sep 2014 20:41:45 +0000 (20:41 +0000)]
[x86] Fix a moderately terrifying bug in the new 128-bit shuffle logic
that managed to elude all of my fuzz testing historically. =/

Something changed to allow this code path to actually be exercised and
it was doing bad things. It is especially heavily exercised by the
patterns that emerge when doing AVX shuffles that end up lowered through
the 128-bit code path.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218540 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[IndVar] Don't widen loop compare unless IV user is sign extended.
Chad Rosier [Fri, 26 Sep 2014 20:05:35 +0000 (20:05 +0000)]
[IndVar] Don't widen loop compare unless IV user is sign extended.
PR21030

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218539 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Use break instead of continue
Matt Arsenault [Fri, 26 Sep 2014 17:55:14 +0000 (17:55 +0000)]
R600/SI: Use break instead of continue

If an instruction doesn't have src1, it doesn't have src2

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218536 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Add strict check lines to div_scale tests.
Matt Arsenault [Fri, 26 Sep 2014 17:55:11 +0000 (17:55 +0000)]
R600/SI: Add strict check lines to div_scale tests.

This has weird operand requirements so it's worthwhile
to have very strict checks for its operands.

Add different combinations of SGPR operands.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218535 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Add a note about the order of the operands to div_scale
Matt Arsenault [Fri, 26 Sep 2014 17:55:09 +0000 (17:55 +0000)]
R600/SI: Add a note about the order of the operands to div_scale

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218534 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Move finding SGPR operand to move to separate function
Matt Arsenault [Fri, 26 Sep 2014 17:55:06 +0000 (17:55 +0000)]
R600/SI: Move finding SGPR operand to move to separate function

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218533 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI Allow same SGPR to be used for multiple operands
Matt Arsenault [Fri, 26 Sep 2014 17:55:03 +0000 (17:55 +0000)]
R600/SI Allow same SGPR to be used for multiple operands

Instead of moving the first SGPR that is different than the first,
legalize the operand that requires the fewest moves if one
SGPR is used for multiple operands.

This saves extra moves and is also required for some instructions
which require that the same operand be used for multiple operands.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218532 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Partially move operand legalization to post-isel hook.
Matt Arsenault [Fri, 26 Sep 2014 17:54:59 +0000 (17:54 +0000)]
R600/SI: Partially move operand legalization to post-isel hook.

Disable the SGPR usage restriction parts of the DAG legalizeOperands.
It now should only be doing immediate folding until it can be replaced
later. The real legalization work is now done by the other
SIInstrInfo::legalizeOperands

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218531 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Implement findCommutedOpIndices
Matt Arsenault [Fri, 26 Sep 2014 17:54:54 +0000 (17:54 +0000)]
R600/SI: Implement findCommutedOpIndices

The base implementation of commuteInstruction is used
in some cases, but it turns out this has been broken for a
long time since modifiers were inserted between the real operands.

The base implementation of commuteInstruction also fails on immediates,
which also needs to be fixed.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218530 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Don't move operands that are required to be SGPRs
Matt Arsenault [Fri, 26 Sep 2014 17:54:52 +0000 (17:54 +0000)]
R600/SI: Don't move operands that are required to be SGPRs

e.g. v_cndmask_b32 requires the condition operand be an SGPR.
If one of the source operands were an SGPR, that would be considered
the one SGPR use and the condition operand would be illegally moved.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218529 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Don't assert on exotic operand types
Matt Arsenault [Fri, 26 Sep 2014 17:54:46 +0000 (17:54 +0000)]
R600/SI: Don't assert on exotic operand types

This needs a test, but I'm not sure if it is currently possible and
I originally hit it due to a bug. Right now the only global address
operands have no reason to be VALU instructions, although it
theoretically could be a problem.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218528 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Fix using wrong operand indices when commuting
Matt Arsenault [Fri, 26 Sep 2014 17:54:43 +0000 (17:54 +0000)]
R600/SI: Fix using wrong operand indices when commuting

No test since the current SIISelLowering::legalizeOperands
effectively hides this, and the general uses seem to only fire
on SALU instructions which don't have modifiers between
the operands.

When trying to use legalizeOperands immediately after
instruction selection, it now sees a lot more patterns
it did not see before which break on this.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218527 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoR600/SI: Remove apparently dead code in legalizeOperands
Matt Arsenault [Fri, 26 Sep 2014 17:54:38 +0000 (17:54 +0000)]
R600/SI: Remove apparently dead code in legalizeOperands

No tests hit this, and I don't see any way a GlobalAddress
node would survive beyond lowering on SI. It it would, the
move should probably be inserted by selection.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218526 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoIgnore annotation function calls in cost computation
David Peixotto [Fri, 26 Sep 2014 17:48:40 +0000 (17:48 +0000)]
Ignore annotation function calls in cost computation

The annotation instructions are dropped during codegen and have no
impact on size.  In some cases, the annotations were preventing the
unroller from unrolling a loop because the annotation calls were
pushing the cost over the unrolling threshold.

Differential Revision: http://reviews.llvm.org/D5335

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218525 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] The mnemonic is SHUFPS not SHUPFS. =[ I'm very bad at spelling
Chandler Carruth [Fri, 26 Sep 2014 17:27:40 +0000 (17:27 +0000)]
[x86] The mnemonic is SHUFPS not SHUPFS. =[ I'm very bad at spelling
sadly.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218524 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] In the new vector shuffle lowering, when trying to do another
Chandler Carruth [Fri, 26 Sep 2014 17:24:26 +0000 (17:24 +0000)]
[x86] In the new vector shuffle lowering, when trying to do another
layer of tie-breaking sorting, it really helps to check that you're in
a tie first. =] Otherwise the whole thing cycles infinitely. Test case
added, another one found through fuzz testing.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218523 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[x86] Fix a large collection of bugs that crept in as I fleshed out the
Chandler Carruth [Fri, 26 Sep 2014 17:11:02 +0000 (17:11 +0000)]
[x86] Fix a large collection of bugs that crept in as I fleshed out the
AVX support.

New test cases included. Note that none of the existing test cases
covered these buggy code paths. =/ Also, it is clear from this that
SHUFPS and SHUFPD are the most bug prone shuffle instructions in x86. =[

These were all detected by fuzz-testing. (I <3 fuzz testing.)

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218522 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoElide repeated register operand in Thumb1 instructions
Renato Golin [Fri, 26 Sep 2014 16:14:29 +0000 (16:14 +0000)]
Elide repeated register operand in Thumb1 instructions

This patch makes the ARM backend transform 3 operand instructions such as
'adds/subs' to the 2 operand version of the same instruction if the first
two register operands are the same.

Example: 'adds r0, r0, #1' will is transformed to 'adds r0, #1'.

Currently for some instructions such as 'adds' if you try to assemble
'adds r0, r0, #8' for thumb v6m the assembler would throw an error message
because the immediate cannot be encoded using 3 bits.

The backend should be smart enough to transform the instruction to
'adds r0, #8', which allows for larger immediate constants.

Patch by Ranjeet Singh.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218521 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[X86][SchedModel] SSE reciprocal square root instruction latencies.
Andrea Di Biagio [Fri, 26 Sep 2014 12:56:44 +0000 (12:56 +0000)]
[X86][SchedModel] SSE reciprocal square root instruction latencies.

The SSE rsqrt instruction (a fast reciprocal square root estimate) was
grouped in the same scheduling IIC_SSE_SQRT* class as the accurate (but very
slow) SSE sqrt instruction. For code which uses rsqrt (possibly with
newton-raphson iterations) this poor scheduling was affecting performances.

This patch splits off the rsqrt instruction from the sqrt instruction scheduling
classes and creates new IIC_SSE_RSQER* classes with latency values based on
Agner's table.

Differential Revision: http://reviews.llvm.org/D5370

Patch by Simon Pilgrim.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218517 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRevert "Store TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFU...
Frederic Riss [Fri, 26 Sep 2014 12:34:06 +0000 (12:34 +0000)]
Revert "Store TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection."

This reverts commit r218513.

Buildbots using libstdc++ issue an error when trying to copy
SmallVector<std::unique_ptr<>>. Revert the commit until we have a fix.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218514 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoStore TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection.
Frederic Riss [Fri, 26 Sep 2014 12:15:40 +0000 (12:15 +0000)]
Store TypeUnits in a SmallVector<DWARFUnitSection> instead of a single DWARFUnitSection.

Summary:
There will be multiple TypeUnits in an unlinked object that will be extracted
from different sections. Now that we have DWARFUnitSection that is supposed
to represent an input section, we need a DWARFUnitSection<TypeUnit> per
input .debug_types section.

Once this is done, the interface is homogenous and we can move the Section
parsing code into DWARFUnitSection.

Reviewers: samsonov, dblaikie

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5482

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218513 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix unused variable warning added in r218509
Daniel Sanders [Fri, 26 Sep 2014 10:45:26 +0000 (10:45 +0000)]
Fix unused variable warning added in r218509

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218510 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[mips] Generalize the handling of f128 return values to support f128 arguments.
Daniel Sanders [Fri, 26 Sep 2014 10:06:12 +0000 (10:06 +0000)]
[mips] Generalize the handling of f128 return values to support f128 arguments.

Summary:
This will allow us to handle f128 arguments without duplicating code from
CCState::AnalyzeFormalArguments() or CCState::AnalyzeCallOperands().

No functional change.

Reviewers: vmedic

Reviewed By: vmedic

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D5292

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218509 91177308-0d34-0410-b5e6-96231b3b80d8

10 years ago[AVX512] Added load/store from BW/VL subsets to Register2Memory opcode tables.
Robert Khasanov [Fri, 26 Sep 2014 09:48:50 +0000 (09:48 +0000)]
[AVX512] Added load/store from BW/VL subsets to Register2Memory opcode tables.
Added lowering tests for these instructions.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218508 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agollvm-vtabledump: Small cleanup
David Majnemer [Fri, 26 Sep 2014 08:01:23 +0000 (08:01 +0000)]
llvm-vtabledump: Small cleanup

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218505 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agofix a typo in doumentation index.
Jyoti Allur [Fri, 26 Sep 2014 06:59:15 +0000 (06:59 +0000)]
fix a typo in doumentation index.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218504 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agollvm-vtabledump: strip trailing NUL bytes
David Majnemer [Fri, 26 Sep 2014 05:50:45 +0000 (05:50 +0000)]
llvm-vtabledump: strip trailing NUL bytes

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218502 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoFix build breakage on MSVC 2013
David Majnemer [Fri, 26 Sep 2014 04:47:54 +0000 (04:47 +0000)]
Fix build breakage on MSVC 2013

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218499 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agollvm-vtabledump: Dump RTTI structures for the MS ABI
David Majnemer [Fri, 26 Sep 2014 04:21:51 +0000 (04:21 +0000)]
llvm-vtabledump: Dump RTTI structures for the MS ABI

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218498 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoTarget: Fix build breakage.
David Majnemer [Fri, 26 Sep 2014 02:57:05 +0000 (02:57 +0000)]
Target: Fix build breakage.

No functional change intended.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218497 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoSupport: Remove undefined behavior from &raw_ostream::operator<<
David Majnemer [Fri, 26 Sep 2014 02:48:14 +0000 (02:48 +0000)]
Support: Remove undefined behavior from &raw_ostream::operator<<

Don't negate signed integer types in &raw_ostream::operator<<(const
FormattedNumber &FN).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218496 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRevert patch of r218493, delete the test case
David Xu [Fri, 26 Sep 2014 02:40:54 +0000 (02:40 +0000)]
Revert patch of r218493, delete the test case

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218495 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRevert patch ofr218493
David Xu [Fri, 26 Sep 2014 02:28:03 +0000 (02:28 +0000)]
Revert patch ofr218493

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218494 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoRedundant store instructions should be removed as dead code
David Xu [Fri, 26 Sep 2014 02:02:09 +0000 (02:02 +0000)]
Redundant store instructions should be removed as dead code

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218493 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd the first backend support for on demand subtarget creation
Eric Christopher [Fri, 26 Sep 2014 01:44:08 +0000 (01:44 +0000)]
Add the first backend support for on demand subtarget creation
based on the Function. This is currently used to implement
mips16 support in the mips backend via the existing module
pass resetting the subtarget.

Things to note:

a) This involved running resetTargetOptions before creating a
new subtarget so that code generation options like soft-float
could be recognized when creating the new subtarget. This is
to deal with initialization code in isel lowering that only
paid attention to the initial value.

b) Many of the existing testcases weren't using the soft-float
feature correctly. I've corrected these based on the check
values assuming that was the desired behavior.

c) The mips port now pays attention to the target-cpu and
target-features strings when generating code for a particular
function. I've removed these from one function where the
requested cpu and features didn't match the check lines in
the testcase.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218492 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoAdd a FIXME to TargetMachine to remove the function specific
Eric Christopher [Fri, 26 Sep 2014 01:44:05 +0000 (01:44 +0000)]
Add a FIXME to TargetMachine to remove the function specific
code generation options from TargetMachine. This will depend
upon Function + TargetSubtargetInfo based code generation at
which point resetTargetOptions and this code can be removed.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218491 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoHave setSubtarget take a const subtarget.
Eric Christopher [Fri, 26 Sep 2014 01:28:13 +0000 (01:28 +0000)]
Have setSubtarget take a const subtarget.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218490 91177308-0d34-0410-b5e6-96231b3b80d8

10 years agoMove resetTargetOptions from taking a MachineFunction to a Function
Eric Christopher [Fri, 26 Sep 2014 01:28:10 +0000 (01:28 +0000)]
Move resetTargetOptions from taking a MachineFunction to a Function
since we are accessing the TargetMachine that we're a member
function of.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218489 91177308-0d34-0410-b5e6-96231b3b80d8