Commit Graph

102954 Commits

Author SHA1 Message Date
Benjamin Kramer
d9ced7112e X86TTI: i16/i32 vector div with a constant (splat) divisor are reasonably cheap now.
Turn vectorization back on.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207320 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 14:53:05 +00:00
Benjamin Kramer
9f2c21871c X86: Lower SMUL_LOHI of v4i32 to pmuldq when SSE4.1 is available.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207318 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 14:12:19 +00:00
Benjamin Kramer
fb625eadf9 X86: Add patterns for MULHU/MULHS of v8i16 and v16i16.
This gets us pretty code for divs of i16 vectors. Turn the existing
intrinsics into the corresponding nodes.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207317 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 13:01:03 +00:00
Benjamin Kramer
75125c127d Rip out X86-specific vector SDIV lowering, make the corresponding DAGCombiner transform work on vectors.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207316 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 13:00:53 +00:00
Benjamin Kramer
aab6231cd9 DAGCombiner: Turn divs of vector splats into vectorized multiplications.
Otherwise the legalizer would just scalarize everything. Support for
mulhi in the targets isn't that great yet so on most targets we get
exactly the same scalarized output. Add a test for x86 vector udiv.

I had to disable the mulhi nodes on ARM because there aren't any patterns
for it. As far as I know ARM has instructions for getting the high part of
a multiply so this should be fixed.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207315 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 12:06:28 +00:00
Benjamin Kramer
05e00b6e65 X86: Custom lower v4i32 UMUL_LOHI into 2 pmuludqs.
Test will follow soon.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207314 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 12:06:11 +00:00
Michael Zolotukhin
abd7ca0706 Revert r206749 till a final decision about the intrinsics is made.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207313 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 09:56:41 +00:00
Chandler Carruth
9a1fab37c7 [LCG] Rather than removing nodes from the SCC entry set when we process
them, just skip over any DFS-numbered nodes when finding the next root
of a DFS. This allows the entry set to just be a vector as we populate
it from a uniqued source. It also removes the possibility for a linear
scan of the entry set to actually do the removal which can make things
go quadratic if we get unlucky.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207312 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 09:45:55 +00:00
Chandler Carruth
797bbced53 [LCG] Rotate the full SCC finding algorithm to avoid round-trips through
the DFS stack for leaves in the call graph. As mentioned in my previous
commit, this is particularly interesting for graphs which have high fan
out but low connectivity resulting in many leaves. For such graphs, this
can remove a large % of the DFS stack traffic even though it doesn't
make the stack much smaller.

It's a bit easier to formulate this for the full algorithm because that
one stops completely for each SCC. For example, I was able to directly
eliminate the "Recurse" boolean used to continue an outer loop from the
inner loop.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207311 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 09:28:00 +00:00
Chandler Carruth
8495669112 [LCG] Hoist the main DFS loop out of the edge removal function. This
makes working through the worklist much cleaner, and makes it possible
to avoid the 'bool-to-continue-the-outer-loop' hack. Not a huge
difference, but I think this is approaching as polished as I can make
it.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207310 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 09:06:53 +00:00
Gerolf Hoflehner
b79f1fe084 RecursivelyDeleteTriviallyDeadInstructions() could remove
more than 1 instruction. The caller need to be aware of this
and adjust instruction iterators accordingly.

rdar://16679376

Repaired r207302.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207309 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 05:58:11 +00:00
Gerolf Hoflehner
67a1d85141 Restore CloneFunction.cpp which got accidently
overwritten by previous backout of r207303


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207308 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 05:43:41 +00:00
Chandler Carruth
dec9a2ca23 [LCG] In the incremental SCC re-formation, lift the node currently being
processed in the DFS out of the stack completely. Keep it exclusively in
a variable. Re-shuffle some code structure to make this easier. This can
have a very dramatic effect in some cases because call graphs tend to
look like a high fan-out spanning tree. As a consequence, there are
a large number of leaf nodes in the graph, and this technique causes
leaf nodes to never even go into the stack. While this only reduces the
max depth by 1, it may cause the total number of round trips through the
stack to drop by a lot.

Now, most of this isn't really relevant for the incremental version. =]
But I wanted to prototype it first here as this variant is in ways more
complex. As long as I can get the code factored well here, I'll next
make the primary walk look the same. There are several refactorings this
exposes I think.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207306 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 03:36:42 +00:00
Chandler Carruth
0c8f0bfce2 [LCG] Special case the removal of self edges. These don't impact the SCC
graph in any way because we don't track edges in the SCC graph, just
nodes. This also lets us add a nice assert about the invariant that
we're working on at least a certain number of nodes within the SCC.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207305 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 03:36:37 +00:00
Juergen Ributzka
d10a9fb25a [DAG] During DAG legalization keep opaque constants even after expanding.
The included test case would return the incorrect results, because the expansion
of an shift with a constant shift amount of 0 would generate undefined behavior.

This is because ExpandShiftByConstant assumes that all shifts by constants with
a value of 0 have already been optimized away. This doesn't happen for opaque
constants and usually this isn't a problem, because opaque constants won't take
this code path - they are not supposed to. In the case that the opaque constant
has to be expanded by the legalizer, the legalizer would drop the opaque flag.
In this case we hit the limitations of ExpandShiftByConstant and create incorrect
code.

This commit fixes the legalizer by not dropping the opaque flag when expanding
opaque constants and adding an assertion to ExpandShiftByConstant to catch this
not supported case in the future.

This fixes <rdar://problem/16718472>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207304 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 02:58:04 +00:00
Gerolf Hoflehner
9d4048578c Revert commit r207302 since build failures
have been reported.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207303 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 02:03:17 +00:00
Gerolf Hoflehner
4c9277bb9f RecursivelyDeleteTriviallyDeadInstructions() could remove
more than 1 instruction. The caller need to be aware of this
and adjust instruction iterators accordingly.

rdar://16679376



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207302 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 01:19:16 +00:00
Quentin Colombet
9e93e47b7f [X86] Implement TargetLowering::getScalingFactorCost hook.
Scaling factors are not free on X86 because every "complex" addressing mode
breaks the related instruction into 2 allocations instead of 1.

<rdar://problem/16730541>


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207301 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 01:11:26 +00:00
Chandler Carruth
64e1be4bf1 [LCG] Refactor the duplicated code I added in my last commit here into
a helper function. Also factor the other two places where we did the
same thing into the helper function. =] Much cleaner this way. NFC.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207300 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 01:03:46 +00:00
Andrea Di Biagio
96db9b8ed8 [InstCombine][X86] Teach how to fold calls to SSE2/AVX2 packed logical shift
right intrinsics.

A packed logical shift right with a shift count bigger than or equal to the
element size always produces a zero vector. In all other cases, it can be
safely replaced by a 'lshr' instruction.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207299 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 01:03:22 +00:00
Richard Smith
f3a9eb107c Add missing include guards and missing #include, found by modules build.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207298 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 00:53:26 +00:00
Filipe Cabecinhas
31e75e673c Appease the almighty buildbots.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207295 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-26 00:02:37 +00:00
Filipe Cabecinhas
3c02165172 Optimization for certain shufflevector by using insertps.
Summary:
If we're doing a v4f32/v4i32 shuffle on x86 with SSE4.1, we can lower
certain shufflevectors to an insertps instruction:
When most of the shufflevector result's elements come from one vector (and
keep their index), and one element comes from another vector or a memory
operand.

Added tests for insertps optimizations on shufflevector.
Added support and tests for v4i32 vector optimization.

Reviewers: nadav

Subscribers: llvm-commits

Differential Revision: http://reviews.llvm.org/D3475

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207291 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 23:51:17 +00:00
Duncan P. N. Exon Smith
cee7abfb2c Revert "blockfreq: Approximate irreducible control flow"
This reverts commit r207286.  It causes an ICE on the
cmake-llvm-x86_64-linux buildbot [1]:

    llvm/lib/Analysis/BlockFrequencyInfo.cpp: In lambda function:
    llvm/lib/Analysis/BlockFrequencyInfo.cpp:182:1: internal compiler error: in get_expr_operands, at tree-ssa-operands.c:1035

[1]: http://bb.pgr.jp/builders/cmake-llvm-x86_64-linux/builds/12093/steps/build_llvm/logs/stdio

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207287 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 23:16:58 +00:00
Duncan P. N. Exon Smith
d905bba691 blockfreq: Approximate irreducible control flow
Previously, irreducible backedges were ignored.  With this commit,
irreducible SCCs are discovered on the fly, and modelled as loops with
multiple headers.

This approximation specifies the headers of irreducible sub-SCCs as its
entry blocks and all nodes that are targets of a backedge within it
(excluding backedges within true sub-loops).  Block frequency
calculations act as if we insert a new block that intercepts all the
edges to the headers.  All backedges and entries to the irreducible SCC
point to this imaginary block.  This imaginary block has an edge (with
even probability) to each header block.

The result is now reasonable enough that I've added a number of
testcases for irreducible control flow.  I've outlined in
`BlockFrequencyInfoImpl.h` ways to improve the approximation.

<rdar://problem/14292693>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207286 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 23:08:57 +00:00
Adrian Prantl
2bfbbd5d4d Unbreak the gdb buildbot by not lowering dbg.declare intrinsics for arrays.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207284 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 23:00:25 +00:00
Eric Christopher
eed2620611 Make sure that rangelists are also relative to the compile unit
low_pc similar to location lists.

Fixes PR19563

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207283 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 22:23:54 +00:00
Matt Arsenault
d1f361aa39 R600: Fix function name printing in LowerCall
v2: Check both ExternalSymbol and GlobalAddress

Patch by: Jan Vesely <jan.vesely@rutgers.edu>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207282 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 22:22:01 +00:00
David Blaikie
82a35bf01a DwarfAccelTable: Store the string symbol in the accelerator table to avoid duplicate lookup.
This also avoids the need for subtly side-effecting calls to manifest
strings in the string table at the point where items are added to the
accelerator tables.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207281 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 22:21:35 +00:00
Tom Roeder
817f5e2fa1 Add an -mattr option to the gold plugin to support subtarget features in LTO
This adds support for an -mattr option to the gold plugin and to llvm-lto. This
allows the caller to specify details of the subtarget architecture, like +aes,
or +ssse3 on x86.  Note that this requires a change to the include/llvm-c/lto.h
interface: it adds a function lto_codegen_set_attr and it increments the
version of the interface.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207279 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:46:51 +00:00
Alexey Samsonov
c744a37153 Fix missing include
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207278 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:42:35 +00:00
David Blaikie
891481f89d Encapsulate the DWARF string pool in a separate type.
Pulls out some more code from some of the rather monolithic DWARF
classes. Unlike the address table, the string table won't move up into
DwarfDebug - each DWARF file has its own string table (but there can be
only one address table).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207277 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:34:35 +00:00
Alexey Samsonov
c87722ce4b [DWARF parser] Cleanup code in DWARFDebugAranges.
No functionality change.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207276 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:30:03 +00:00
Alexey Samsonov
bfd66f57da [DWARF parser] Cleanup code in DWARFDebugAbbrev.
No functionality change.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207274 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:10:56 +00:00
Adam Nemet
d761cc1dfa [LoopStrengthReduce] Don't trim formula that uses a subset of required registers
Consider this use from the new testcase:

  LSR Use: Kind=ICmpZero, Offsets={0}, widest fixup type: i32
    reg({1000,+,-1}<nw><%for.body>)
    -3003 + reg({3,+,3}<nw><%for.body>)
    -1001 + reg({1,+,1}<nuw><nsw><%for.body>)
    -1000 + reg({0,+,1}<nw><%for.body>)
    -3000 + reg({0,+,3}<nuw><%for.body>)
    reg({-1000,+,1}<nw><%for.body>)
    reg({-3000,+,3}<nsw><%for.body>)

This is the last use we consider for a solution in SolveRecurse, so CurRegs is
a large set.  (CurRegs is the set of registers that are needed by the
previously visited uses in the in-progress solution.)

ReqRegs is {
  {3,+,3}<nw><%for.body>,
  {1,+,1}<nuw><nsw><%for.body>
}

This is the intersection of the regs used by any of the formulas for the
current use and CurRegs.

Now, the code requires a formula to contain *all* these regs (the comment is
simply wrong), otherwise the formula is immediately disqualified.  Obviously,
no formula for this use contains two regs so they will all get disqualified.

The fix modifies the check to allow the formula in this case.  The idea is
that neither of these formulae is introducing any new registers which is the
point of this early pruning as far as I understand.

In terms of set arithmetic, we now allow formulas whose used regs are a subset
of the required regs not just the other way around.

There are few more loops in the test-suite that are now successfully LSRed.  I
have benchmarked those and found very minimal change.

Fixes <rdar://problem/13965777>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207271 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 21:02:21 +00:00
Duncan P. N. Exon Smith
d9dc95709e SCC: Use the reference typedef
Actually use the `reference` typedef, and remove the private
redefinition of `pointer` since it has no users.

Using `reference` exposes a problem with r207257, which specified the
wrong `value_type` to `iterator_facade_base` (fixed that too).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207270 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:52:08 +00:00
Adrian Prantl
988b78a846 This reapplies r207235 with an additional bugfixes caught by the msan
buildbot - do not insert debug intrinsics before phi nodes.

Debug info for optimized code: Support variables that are on the stack and
described by DBG_VALUEs during their lifetime.

Previously, when a variable was at a FrameIndex for any part of its
lifetime, this would shadow all other DBG_VALUEs and only a single
fbreg location would be emitted, which in fact is only valid for a small
range and not the entire lexical scope of the variable. The included
dbg-value-const-byref testcase demonstrates this.

This patch fixes this by
Local
- emitting dbg.value intrinsics for allocas that are passed by reference
- dropping all dbg.declares (they are now fully lowered to dbg.values)
SelectionDAG
- renamed constructors for SDDbgValue for better readability.
- fix UserValue::match() to handle indirect values correctly
- not inserting an MMI table entries for dbg.values that describe allocas.
- lowering dbg.values that describe allocas into *indirect* DBG_VALUEs.
CodeGenPrepare
- leaving dbg.values for an alloca were they are (see comment)
Other
- regenerated/updated instcombine.ll testcase and included source

rdar://problem/16679879
http://reviews.llvm.org/D3374

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207269 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:49:25 +00:00
David Blaikie
31494cb6c4 MCAssembler: Simplify implementation of const variants of getSymbolData by calling one implementation from the other.
Code review feedback by Rafael Espindola on r207124.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207266 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:19:11 +00:00
David Blaikie
5ed33e08f3 BugPoint: Fix some memory leaks.
Patch by Kostya Serebryany.

unique_ptr would be nice, but it's a bit too much work for an area I'm
not familiar with, nor invested in, unfortunately.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207265 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:15:16 +00:00
David Blaikie
9c6a820aa7 DwarfUnit: Remove unused function
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207264 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:02:24 +00:00
David Blaikie
12d5224df6 DIE: Pass ownership of children via std::unique_ptr rather than raw pointer.
This should reduce the chance of memory leaks like those fixed in
r207240.

There's still some unclear ownership of DIEs happening in DwarfDebug.
Pushing unique_ptr and references through more APIs should help expose
the cases where ownership is a bit fuzzy.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207263 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 20:00:34 +00:00
David Blaikie
172515f0be DIEEntry: Refer to the specified DIE via reference rather than pointer.
Makes some more cases (the unit tests, specifically), lexically
compatible with a change to unique_ptr.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207261 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 19:33:43 +00:00
David Blaikie
d48f5efa9d DwarfUnit: return by reference from createAndAddDIE
Since this doesn't return ownership (the DIE has been added to the
specified parent already) nor return null, just return by reference.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207259 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:52:29 +00:00
Duncan P. N. Exon Smith
2d18167483 blockfreq: Further shift logic to LoopData
Move a lot of the loop-related logic that was sprinkled around the code
into `LoopData`.

<rdar://problem/14292693>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207258 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:47:04 +00:00
Duncan P. N. Exon Smith
eae0809a60 SCC: Provide operator->() through iterator_facade_base
Use the fancy new `iterator_facade_base` to add
`scc_iterator::operator->()`.  Remove other definitions where
`iterator_facade_base` does the right thing.

<rdar://problem/14292693>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207257 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:43:41 +00:00
Reed Kotler
4870dae19f enable fast isel tablegen files for Mips
Reviewers: dsanders

Reviewed By: dsanders

Differential Revision: http://reviews.llvm.org/D3498

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207256 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:36:38 +00:00
David Blaikie
5410b5acda Return DIE by reference instead of pointer from DwarfUnit::getUnitDie
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207255 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:35:57 +00:00
Duncan P. N. Exon Smith
d86dbccfef SCC: Remove non-const operator*()
<rdar://problem/14292693>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207254 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:26:45 +00:00
David Blaikie
f6e00376e7 DwarfUnit: Suddently, DIE references, everywhere.
This'll make changing to unique_ptr ownership of DIEs easier since the
usages will now have '*' on them making them textually compatible
between unique_ptr and raw pointer.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207253 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:26:14 +00:00
Duncan P. N. Exon Smith
db8c1ae04e SCC: Change clients to use const, NFC
It's fishy to be changing the `std::vector<>` owned by the iterator, and
no one actual does it, so I'm going to remove the ability in a
subsequent commit.  First, update the users.

<rdar://problem/14292693>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207252 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-25 18:24:50 +00:00