As discussed in D11760, this patch moves the (V)PSRA(WD) arithmetic shift-by-constant folding to InstCombine to match the logical shift implementations.
Differential Revision: http://reviews.llvm.org/D11886
llvm-svn: 244495
This patch moves the verification of fast-math to just before vectorization is done. This way we can tell clang to append the command line options would that allow floating-point commutativity. Specifically those are enableing fast-math or specifying a loop hint.
llvm-svn: 244489
Sometimes interleaving is not beneficial, as determined by the cost-model and sometimes it is disabled by a loop hint (by the user). This patch modifies the diagnostic messages to make it clear why interleaving wasn't done.
llvm-svn: 244485
The LDD/STD instructions can load/store a 64bit quantity from/to
memory to/from a consecutive even/odd pair of (32-bit) registers. They
are part of SparcV8, and also present in SparcV9. (Although deprecated
there, as you can store 64bits in one register).
As recommended on llvmdev in the thread "How to enable use of 64bit
load/store for 32bit architecture" from Apr 2015, I've modeled the
64-bit load/store operations as working on a v2i32 type, rather than
making i64 a legal type, but with few legal operations. The latter
does not (currently) work, as there is much code in llvm which assumes
that if i64 is legal, operations like "add" will actually work on it.
The same assumption does not hold for v2i32 -- for vector types, it is
workable to support only load/store, and expand everything else.
This patch:
- Adds a new register class, IntPair, for even/odd pairs of registers.
- Modifies the list of reserved registers, the stack spilling code,
and register copying code to support the IntPair register class.
- Adds support in AsmParser. (note that in asm text, you write the
name of the first register of the pair only. So the parser has to
morph the single register into the equivalent paired register).
- Adds the new instructions themselves (LDD/STD/LDDA/STDA).
- Hooks up the instructions and registers as a vector type v2i32. Adds
custom legalizer to transform i64 load/stores into v2i32 load/stores
and bitcasts, so that the new instructions can actually be
generated, and marks all operations other than load/store on v2i32
as needing to be expanded.
- Copies the unfortunate SelectInlineAsm hack from ARMISelDAGToDAG.
This hack undoes the transformation of i64 operands into two
arbitrarily-allocated separate i32 registers in
SelectionDAGBuilder. and instead passes them in a single
IntPair. (Arbitrarily allocated registers are not useful, asm code
expects to be receiving a pair, which can be passed to ldd/std.)
Also adds a bunch of test cases covering all the bugs I've added along
the way.
Differential Revision: http://reviews.llvm.org/D8713
llvm-svn: 244484
I looked into adding a warning / error for this to FileCheck, but there doesn't
seem to be a good way to avoid it triggering on the instances of it in RUN lines.
llvm-svn: 244481
This change adds the unroll metadata "llvm.loop.unroll.enable" which directs
the optimizer to unroll a loop fully if the trip count is known at compile time, and
unroll partially if the trip count is not known at compile time. This differs from
"llvm.loop.unroll.full" which explicitly does not unroll a loop if the trip count is not
known at compile time.
The "llvm.loop.unroll.enable" is intended to be added for loops annotated with
"#pragma unroll".
llvm-svn: 244466
Summary:
This adds a hook to TTI which enables us to selectively turn on by default
interleaved access vectorization for targets on which we have have performed
the required benchmarking.
Reviewers: rengolin
Subscribers: rengolin, llvm-commits
Differential Revision: http://reviews.llvm.org/D11901
llvm-svn: 244449
The scalarizer can cache incorrect entries when walking up a chain of
insertelement instructions. This occurs when it encounters more than one
instruction that it is not actively searching for, as it unconditionally caches
every element it finds. The fix is to only cache the first element that it
isn't searching for so we don't overwrite correct entries.
Reviewers: hfinkel
Differential Revision: http://reviews.llvm.org/D11559
llvm-svn: 244448
Summary:
Analogously to Function::viewCFG(), RegionInfo::view() and RegionInfo::viewOnly() are meant to be called in debugging sessions. They open a viewer to show how RegionInfo currently understands the region hierarchy.
The functions viewRegion(Function*) and viewRegionOnly(Function*) invoke a fresh region analysis of the function in contrast to viewRegion(RegionInfo*) and viewRegionOnly(RegionInfo*) which show the current analysis result.
Reviewers: grosser
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11875
llvm-svn: 244444
This allows printing region graphs when only the RegionInfo (e.g. Region::getRegionInfo()), but no RegionInfoPass object is available.
Specifically, we will use this to print RegionInfo graphs in the debugger.
Differential version: http://reviews.llvm.org/D11874
Reviewed-by: grosser
llvm-svn: 244442
PR24139 contains an analysis of poor register allocation. One of the findings
was that when calculating the spill weight, a rematerializable interval once
split is no longer rematerializable. This is because the isRematerializable
check in CalcSpillWeights.cpp does not follow the copies introduced by live
range splitting (after splitting, the live interval register definition is a
copy which is not rematerializable).
Reviewers: qcolombet
Differential Revision: http://reviews.llvm.org/D11686
llvm-svn: 244439
The SP was always unconditionally assigned to later, but initialised early.
This delays the initialisation, and avoids the dead store. Identified by
clang static analysis. No functional change intended.
llvm-svn: 244423
We can only PHI translate instructions. In our attempt to PHI translate
a bitcast, we attempt to translate its operand; however, the operand
might be an argument or a global instead of an instruction. Benignly
bail out when this happens.
This fixes PR24397.
Differential Revision: http://reviews.llvm.org/D11879
llvm-svn: 244418
Apparently if you make a typo in the argument to CMAKE_BUILD_TYPE,
cmake silently accepts this but doesn't apply any particular build
type to your build. This means you get a build that doesn't really
make any sense - it's sort of a debug build with asserts disabled.
Error out instead.
llvm-svn: 244406
Seq.emplace_back(Seq.back());
does not work as planned, since Seq.back() may become a dangling reference
when emplace_back is called and possibly reallocates vector. To avoid this,
the vector allocation should be reserved first and only then used.
This broke test/tools/dsymutil/X86/custom-line-table.test with Visual C++ 2013.
llvm-svn: 244405
The pass adds new kernel arguments for image attributes, and
resolves calls to dummy attribute and resource id getter functions.
Patch by: Zoltan Gilian
llvm-svn: 244372
This is unused after filtering checks was moved to the clients.
As a result, we can just return the number of the checks in the
precomputed set.
llvm-svn: 244369
This is the full set of checks that clients can further filter. IOW,
it's client-agnostic. This makes LAA complete in the sense that it now
provides the two main results of its analysis precomputed:
1. memory dependences via getDepChecker().getInsterestingDependences()
2. run-time checks via getRuntimePointerCheck().getChecks()
However, as a consequence we now compute this information pro-actively.
Thus if the client decides to skip the loop based on the dependences
we've computed the checks unnecessarily. In order to see whether this
was a significant overhead I checked compile time on SPEC2k6 LTO bitcode
files. The change was in the noise.
The checks are generated in canCheckPtrAtRT, at the same place where we
used to call groupChecks to merge checks.
llvm-svn: 244368
At this point the given Opc must be valid, otherwise we should
not look for a matching pair to form paired load or store.
Thanks to Chad to point out this piece of code!
llvm-svn: 244366
Summary:
With InstAlias, we don't need to print the _e32 portion of the mnemonic
when we print the $dst operand. This change makes it possible to
include vcc in the asm string when we switch VOPC over to having
implicit vcc defs.
Reviewers: arsenm
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11813
llvm-svn: 244362
This commit extract the code that parses the 64-bit offset from the method
'parseOperandsOffset' to a new method 'parseOffset' so that we can reuse it
when parsing the offset for the machine memory operands.
llvm-svn: 244355
Summary: llvm::ConstantFoldTerminator function can convert SwitchInst with single case (and default) to a conditional BranchInst. This patch adds support to preserve make.implicit metadata on this conversion.
Reviewers: sanjoy, weimingz, chenli
Subscribers: mcrosier, llvm-commits
Differential Revision: http://reviews.llvm.org/D11841
llvm-svn: 244348
This patch fixes the sse2/avx2 vector shift by constant instcombine call to correctly deal with the fact that the shift amount is formed from the entire lower 64-bit and not just the lowest element as it currently assumes.
e.g.
%1 = tail call <4 x i32> @llvm.x86.sse2.psrl.d(<4 x i32> %v, <4 x i32> <i32 15, i32 15, i32 15, i32 15>)
In this case, (V)PSRLD doesn't perform a lshr by 15 but in fact attempts to shift by 64424509455 ((15 << 32) | 15) - giving a zero result.
In addition, this review also recognizes shift-by-zero from a ConstantAggregateZero type (PR23821).
Differential Revision: http://reviews.llvm.org/D11760
llvm-svn: 244341
PrettyStackTraceHead is a LLVM_THREAD_LOCAL, which means it's just a global
in LLVM_ENABLE_THREADS=NO builds. If a CrashRecoveryContext is used with
code that uses PrettyStackEntries, and a crash happens, PrettyStackTraceHead is
currently not reset to its pre-crash value. These functions make it possible
to add a cleanup to such code that does this.
(Not reseting the value then causes the assert in ~PrettyStackTraceEntry() to
fire if the code outside of the CrashRecoveryContext also uses
PrettyStackEntries -- for example, clang when building a module.)
Part of PR11974.
llvm-svn: 244338
Summary: We were using the SI encoding for VI.
Reviewers: arsenm
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11812
llvm-svn: 244332
build so check and turn on -Wmissing-field-initializers. While there,
reorganize the conditional warning code based on compiler to be a bit
more obvious and inside a switch statement.
llvm-svn: 244330
In tree they are only used by llvm-readobj, but it is also used by
https://github.com/mono/CppSharp.
While at it, add some missing error checking.
llvm-svn: 244320
llvm-dsymutil has to be able to process debug info produced by other compilers
which use different line table settings. The testcase wasn't generated by
another compiler, but by a modified clang.
llvm-svn: 244319
NFC patch for current users, but llvm-dsymutil will use the new
functionality to adapt to the input linetable.
Based on a patch by Adrian Prantl.
llvm-svn: 244318
Summary:
Port the ReconstructShuffle function from AArch64 to ARM
to handle mismatched incoming types in the BUILD_VECTOR
node.
This fixes an outstanding FIXME in the ReconstructShuffle
code.
Reviewers: t.p.northover, rengolin
Subscribers: aemerson, llvm-commits, rengolin
Differential Revision: http://reviews.llvm.org/D11720
llvm-svn: 244314
Summary: WebAssembly's tablegen instructions have the names WebAssembly expects, but by LLVM convention they're uppercase and suffixed with their type after an underscore. Leave the C++ code that way, but print outt he names WebAssembly expects (lowercase, no type). We could teach tablegen to do this later, maybe by using `!cast<string>(node)` in the .td files.
Reviewers: sunfish
Subscribers: jfb, llvm-commits
Differential Revision: http://reviews.llvm.org/D11776
llvm-svn: 244305
As a follow-up to r244181, resolve uniquing cycles underneath distinct
nodes on the fly. This prevents uniquing cycles in early operands from
affecting later operands. It also removes an iteration through distinct
nodes' operands.
No real functional change here, just more prompt resolution of temporary
nodes.
llvm-svn: 244302
The block address machine operands can reference IR blocks in other functions.
This commit fixes a bug where the references to unnamed IR blocks in other
functions weren't serialized correctly.
llvm-svn: 244299
This commit removes the 'StringOffset' and 'HasStringValue' fields from the
MIToken struct and simplifies the 'stringValue' method which now returns
the new 'StringValue' field.
This commit also adopts a different way of initializing the lexed tokens -
instead of constructing a new MIToken instance, the lexer resets the old token
using the new 'reset' method and sets its attributes using the new
'setStringValue', 'setOwnedStringValue', and 'setIntegerValue' methods.
Reviewers: Sean Silva
Differential Revision: http://reviews.llvm.org/D11792
llvm-svn: 244295
When we are not emitting the condition for the branch, because the condition is
in another BB or SDAG did the selection for us, then we have to mask the flag in
the register with AND.
This is required when the condition comes from a truncate, because SDAG only
truncates down to a legal size of i32.
This fixes rdar://problem/22161062.
llvm-svn: 244291
This reverts commit r243198 and 243304.
Turns out this wasn't the correct fix for this problem. It works only within
FastISel, but fails when the truncate is selected by SDAG.
llvm-svn: 244287
lld might end up using a small part of this, but it will be in a much
refactored form. For now this unblocks avoiding the full section scan in the
ELFFile constructor.
This also has a (very small) error handling improvement.
llvm-svn: 244282
Summary:
This adds somewhat basic preparation functionality including:
- Formation of funclets via coloring basic blocks.
- Cloning of polychromatic blocks to ensure that funclets have unique
program counters.
- Demotion of values used between different funclets.
- Some amount of cleanup once we have removed predecessors from basic
blocks.
- Verification that we are left with a CFG that makes some amount of
sense.
N.B. Arguments and numbering still need to be done.
Reviewers: rnk, JosephTremoulet
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11750
llvm-svn: 244272
A dSYM bundle is a file hierarchy that looks slike this:
<bundle name>.dSYM/
Contents/
Info.plist
Resources/
DWARF/
<DWARF file(s)>
This is the default output mode of dsymutil.
llvm-svn: 244270
dsymutil should by default generate dSYM bundles which are filesystem
hierarchies containing the debug info and an additional Info.plist.
Currently llvm-dsymutil emits raw binaries containing the debug info.
This is what we call the 'flat mode'. Add a -f/-flat option that is
supposed to enable that flat mode, but don't wire it for now, only
pass it to the tests that will need it to stay functional once we
do bundle generation by default.
This basically makes this commit NFC and removes the noise from the
actual commit that adds support for bundle generation.
llvm-svn: 244269
This adds documentation on how to use the new EH instructions added in
r243766.
Reviewers: majnemer, reames
Differential Revision: http://reviews.llvm.org/D11565
llvm-svn: 244267
After r244074, we now have a successors() method to iterate over
all the successors of a TerminatorInst. This commit changes a bunch
of eligible loops to use it.
llvm-svn: 244260
Summary: This allows us to consolidate several of the TableGen patterns.
Reviewers: arsenm
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11602
llvm-svn: 244253
libclang uses a CrashRecoveryContext, and building a module does too. If a
module gets built through libclang, nested CrashRecoveryContexts are used. They
work fine with threads as things are stored in ThreadLocal variables, but in
LLVM_ENABLE_THREADS=OFF builds the two recovery contexts would write to the
same globals.
To fix, keep active CrashRecoveryContextImpls in a list and have the global
point to the innermost one, and do something similar for
tlIsRecoveringFromCrash.
Necessary (but not sufficient) for PR11974 and PR20325
http://reviews.llvm.org/D11770
llvm-svn: 244251
points.
There is an infinite loop that can occur in Shrink Wrapping while searching
for the Save/Restore points.
Part of this search checks whether the save/restore points are located in
different loop nests and if so, uses the (post) dominator trees to find the
immediate (post) dominator blocks. However, if the current block does not have
any immediate (post) dominators then this search will result in an infinite
loop. This can occur in code containing an infinite loop.
The modification checks whether the immediate (post) dominator is different from
the current save/restore block. If it is not, then the search terminates and the
current location is not considered as a valid save/restore point for shrink wrapping.
Phabricator: http://reviews.llvm.org/D11607
llvm-svn: 244247
iisUnmovableInstruction() had a list of instructions hardcoded which are
considered unmovable. The list lacked (at least) an entry for the va_arg
and cmpxchg instructions.
Fix this by introducing a new Instruction::mayBeMemoryDependent()
instead of maintaining another instruction list.
Patch by Matthias Braun <matze@braunis.de>.
Differential Revision: http://reviews.llvm.org/D11577
rdar://problem/22118647
llvm-svn: 244244
It adds a new constructor, which takes a std::function predicate function that
is run at the beginning of shrink wrapping to determine whether the optimization
should run on the given machine function. The std::function can be overridden by
each target, allowing target-specific decisions to be made on each machine
function.
This is necessary for PowerPC, as the decision to run shrink wrapping is
partially based on the ABI. Futhermore, this operates nicely with the GCC iFunc
capability, which allows option overrides on a per-function basis.
Phabricator: http://reviews.llvm.org/D11421
llvm-svn: 244235
Summary: Divide the primitive size in bits by eight so the initial load's alignment is in bytes as expected. Tested with the included unit test.
Reviewers: rengolin, jfb
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11804
llvm-svn: 244229
This change improves EmitLoweredSelect() so that multiple contiguous CMOV pseudo
instructions with the same (or exactly opposite) conditions get lowered using a single
new basic-block. This eliminates unnecessary extra basic-blocks (and CFG merge points)
when contiguous CMOVs are being lowered.
Patch by: kevin.b.smith@intel.com
Differential Revision: http://reviews.llvm.org/D11428
llvm-svn: 244202
'llvm::TrailingObjects<`anonymous-namespace'::Class1,short,llvm::NoTrailingTypeArg>::additionalSizeToAlloc' :
cannot access protected member declared in class
'llvm::TrailingObjects<`anonymous-namespace'::Class1,short,llvm::NoTrailingTypeArg>'
I'm not sure how this compiles with gcc.
Aren't protecteded members accessible only with protected or public inheritance?
llvm-svn: 244199
This is the first mechanical step in preparation for making this and all
the other alias analysis passes available to the new pass manager. I'm
factoring out all the totally boring changes I can so I'm moving code
around here with no other changes. I've even minimized the formatting
churn.
I'll reformat and freshen comments on the interface now that its located
in the right place so that the substantive changes don't triger this.
llvm-svn: 244197
The COFFSymbolRef::isFunctionDefinition() function tests for several conditions
that are not related to whether a symbol is a function, but rather whether
the symbol meets the requirements for a function definition auxiliary record,
which excludes certain symbols such as internal functions and undefined
references. The test we need to determine the symbol type is much simpler:
we only need to compare the complex type against IMAGE_SYM_DTYPE_FUNCTION.
llvm-svn: 244195
around a DataLayout interface in favor of directly querying DataLayout.
This wrapper specifically helped handle the case where this no
DataLayout, but LLVM now requires it simplifynig all of this. I've
updated callers to directly query DataLayout. This in turn exposed
a bunch of places where we should have DataLayout readily available but
don't which I've fixed. This then in turn exposed that we were passing
DataLayout around in a bunch of arguments rather than making it readily
available so I've also fixed that.
No functionality changed.
llvm-svn: 244189
This commit implements the initial serialization of the machine operand target
flags. It extends the 'TargetInstrInfo' class to add two new methods that help
to provide text based serialization for the target flags.
This commit can serialize only the X86 target flags, and the target flags for
the other targets will be serialized in the follow-up commits.
Reviewers: Duncan P. N. Exon Smith
llvm-svn: 244185
This reverts commit r244163. The workaround shouldn't be necessary
after r244172, and moreover the commit was slightly buggy as it
dis a simple mkdir without removing the directory first, which could
cause 'File exists' errors.
llvm-svn: 244182
Rotate the algorithm for remapping distinct nodes in order to simplify
how uniquing cycles get resolved. This removes some of the recursion,
and, most importantly, exposes all uniquing cycles at the top-level.
Besides being a little more efficient -- temporary MDNodes won't live as
long -- the clearer logic should help protect against bugs like those
fixed in r243961 and r243976.
What are uniquing cycles? Why do they present challenges when remapping
metadata?
!0 = !{!1}
!1 = !{!0}
!0 and !1 form a simple uniquing cycle. When remapping from one
metadata graph to another, every uniquing cycle gets "duplicated"
through a dance:
!0-temp = !{!1?} ; map(!0): clone !0, VM[!0] = !0-temp
!1-temp = !{!0?} ; ..map(!1): clone !1, VM[!1] = !1-temp
!1-temp = !{!0-temp} ; ..map(!1): remap !1's operands
!2 = !{!0-temp} ; ..map(!1): uniquify: !1-temp => !2
!0-temp = !{!2} ; map(!0): remap !0's operands
!3 = !{!2} ; map(!0): uniquify: !0-temp => !3
; Result
!2 = !{!3}
!3 = !{!2}
(In the two "uniquify" steps above, the operands of !X-temp are compared
to the operands of !X. If they're the same, then !X-temp gets RAUW'ed
to !X; if they're different, then !X-temp is promoted to a new unique
node. The latter case always hits in for uniquing cycles, so we
duplicate all the nodes involved.)
Why is this a problem? Uniquable Metadata nodes that have temporary
node as transitive operands keep RAUW support until the temporary nodes
get finalized. With non-cycles, this happens automatically: when a
uniquable node's count of unresolved operands drops to zero, it
immediately sheds its own RAUW support (possibly triggering the same in
any node that references it). However, uniquing cycles create a
reference cycle, and uniqued nodes that transitively reference a
uniquing cycle are "stuck" in an unresolved state until someone calls
`MDNode::resolveCycles()` on a node in the unresolved subgraph.
Distinct nodes should help here (and mostly do): since they aren't
uniqued anywhere, they are guaranteed not to be RAUW'ed. They
effectively form a barrier between uniqued nodes, breaking some uniquing
cycles, and shielding uniqued nodes from uniquing cycles.
Unfortunately, with this barrier in place, the unresolved subgraph(s)
can be disjoint from the top-level node. The mapping algorithm needs to
find at least one representative from each disjoint subgraph. But which
nodes are *stuck*, and which will get resolved automatically? And which
nodes are in the unresolved subgraph? The old logic was conservative.
This commit rotates the logic for distinct nodes, so that we have access
to unresolved nodes at the top-level call to `llvm::MapMetadata()`.
Each time we return to the top-level, we know that all temporaries have
been RAUW'ed away. Here, it's safe (and necessary) to call
`resolveCycles()` immediately on unresolved operands.
This should also perform better than the old algorithm. The recursion
stack is shorter, temporary nodes don't live as long, and there are
fewer tracking references to unresolved nodes. As the debug info graph
introduces more 'distinct' nodes, remapping should incrementally get
cheaper and cheaper.
Aside from possible performance improvements (and reduced cruft in the
`LLVMContext`), there should be no functionality change here.
llvm-svn: 244181
The files were never written to and then deleted, but they were created
nonetheless. To prevent that, create a wrapper around the 2 variants of
createUniqueFile and use the one that only does an access(Exists) call
to check for name unicity in -no-output mode.
llvm-svn: 244172
Rename `remap()` to `remapOperands()`, and restrict its contract to
remapping operands. Previously, it also called `mapToMetadata()`, but
this logic is hard to reason about externally. In particular, this
refactors `mapUniquedNode()` to avoid redundant mapping calls, taking
advantage of the RAUWs that are already in place.
llvm-svn: 244168
Summary: The casts from String to PatFrag weren't needed if we instead provided an SDNode. This fix was suggested by @pete in D11382.
Subscribers: pete, llvm-commits
Differential Revision: http://reviews.llvm.org/D11788
llvm-svn: 244167
More specifically, make NVPTXISelDAGToDAG able to emit cached loads (LDG) for pointer induction variables.
Also fix latent bug where LDG was not restricted to kernel functions. I believe that this could not be triggered so far since we do not currently infer that a pointer is global outside a kernel function, and only loads of global pointers are considered for cached loads.
llvm-svn: 244166
This is intended to help support the idiom of a class that has some
other objects (or multiple arrays of different types of objects)
appended on the end, which is used quite heavily in clang.
Differential Revision: http://reviews.llvm.org/D11272
llvm-svn: 244164
This option allows to select a subset of the architectures when
performing a universal binary link. The filter is done completely
in the mach-o specific part of the code.
llvm-svn: 244160
Summary:
Emit both DWARF and CodeView if "CodeView" and "Dwarf Version" module
flags are set.
Reviewers: majnemer
Subscribers: llvm-commits
Differential Revision: http://reviews.llvm.org/D11756
llvm-svn: 244158
This commit serializes the offset for the following operands: target index,
global address, external symbol, constant pool index, and block address.
llvm-svn: 244157
1. Create a utility function normalizeEdgeWeights() in MachineBranchProbabilityInfo that normalizes a list of edge weights so that the sum of then can fit in uint32_t.
2. Provide an interface in MachineBasicBlock to normalize its successors' weights.
3. Add a flag in MachineBasicBlock that tracks whether its successors' weights are normalized.
4. Provide an overload of getSumForBlock that accepts a non-const pointer to a MBB so that it can force normalizing this MBB's successors' weights.
5. Update several uses of getSumForBlock() by eliminating the once needed weight scale.
Differential Revision: http://reviews.llvm.org/D11442
llvm-svn: 244154
Simon Pilgrim