Commit Graph

43 Commits

Author SHA1 Message Date
Matt Arsenault
4598bd53ab Use type helper functions.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@190113 91177308-0d34-0410-b5e6-96231b3b80d8
2013-09-06 00:37:24 +00:00
Matt Arsenault
b70d79e7e9 Fix typo.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@189524 91177308-0d34-0410-b5e6-96231b3b80d8
2013-08-28 22:17:26 +00:00
Joey Gouly
ebe1147722 Fix a crash in EvaluateInDifferentElementOrder where it would generate an
undef vector of the wrong type.

LGTM'd by Nick Lewycky on IRC.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@186224 91177308-0d34-0410-b5e6-96231b3b80d8
2013-07-12 23:08:06 +00:00
Nick Lewycky
4526d1cd4a Delete dead safety check.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183167 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-03 23:15:20 +00:00
Nick Lewycky
e4546cb71e When determining the new index for an insertelement, we may not assume that an
index greater than the size of the vector is invalid. The shuffle may be
shrinking the size of the vector. Fixes a crash!

Also drop the maximum recursion depth of the safety check for this
optimization to five.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@183080 91177308-0d34-0410-b5e6-96231b3b80d8
2013-06-01 20:51:31 +00:00
Nick Lewycky
903f26d904 Reapply with r182909 with a fix to the calculation of the new indices for
insertelement instructions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182976 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-31 00:59:42 +00:00
Evgeniy Stepanov
ccb7bd9d84 Revert r182909.
PR/16177


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182919 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-30 09:40:17 +00:00
Nick Lewycky
e97b102e2b Swizzle vector inputs if it helps us eliminate shuffles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182909 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-30 04:33:38 +00:00
Joey Gouly
7ab9fb02f8 Run clang-format over the scalarizePHI function.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182640 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-24 12:33:28 +00:00
Joey Gouly
4a941316cd scalarizePHI needs to insert the next ExtractElement in the same block
as the BinaryOperator, *not* in the block where the IRBuilder is currently
inserting into. Fixes a bug where scalarizePHI would create instructions
that would not dominate all uses.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@182639 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-24 12:29:54 +00:00
Nick Lewycky
cd4e5e9b34 Tabs to spaces. No functionality change.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@181082 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-04 01:08:15 +00:00
Jim Grosbach
10cc563bfe Revert "InstCombine: Fold more shuffles of shuffles."
This reverts commit r180802

There's ongoing discussion about whether this is the right place to make
this transformation. Reverting for now while we figure it out.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180834 91177308-0d34-0410-b5e6-96231b3b80d8
2013-05-01 00:25:27 +00:00
Jim Grosbach
6548096a2e InstCombine: Fold more shuffles of shuffles.
Always fold a shuffle-of-shuffle into a single shuffle when there's only one
input vector in the first place. Continue to be more conservative when there's
multiple inputs.

rdar://13402653
PR15866

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180802 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-30 20:43:52 +00:00
Anat Shemer
c9090b0723 Changed back (relative to commit 179786) the operations executed when extract(cast) is transformed to cast(extract). It uses the Builder class as before. In addition the result node is added to the Worklist, so all the previous extract users will become the new scalar cast users.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@180045 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-22 20:51:10 +00:00
Anat Shemer
86dc3f3739 In the function InstCombiner::visitExtractElementInst() removed the limitation that extract is promoted over a cast only if the cast has only one use.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179786 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-18 19:56:44 +00:00
Anat Shemer
77e95d04c4 Added a function scalarizePHI() that sclarizes a vector phi instruction if it has only 2 uses: one to promote the vector phi in a loop and the other use is an extract operation of one element at a constant location.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179783 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-18 19:35:39 +00:00
Benjamin Kramer
c37cb66e6e Fix for wrong instcombine on vector insert/extract
When trying to collapse sequences of insertelement/extractelement
instructions into single shuffle instructions, there is one specific
case where the Instruction Combiner wrongly updates the resulting
Mask of shuffle indexes.

The problem is in function CollectShuffleElments.

If we have a sequence of insert/extract element instructions
like the one below:

  %tmp1 = extractelement <4 x float> %LHS, i32 0
  %tmp2 = insertelement <4 x float> %RHS, float %tmp1, i32 1
  %tmp3 = extractelement <4 x float> %RHS, i32 2
  %tmp4 = insertelement <4 x float> %tmp2, float %tmp3, i32 3

Where:
  . %RHS will have a mask of [4,5,6,7]
  . %LHS will have a mask of [0,1,2,3]

The Mask of shuffle indexes is wrongly computed to [4,1,6,7]
instead of [4,0,6,7].
When analyzing %tmp2 in order to compute the Mask for the
resulting shuffle instruction, the algorithm forgets to update
the mask index at position 1 with the index associated to the
element extracted from %LHS by instruction %tmp1.

Patch by Andrea DiBiagio!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@179291 91177308-0d34-0410-b5e6-96231b3b80d8
2013-04-11 15:10:09 +00:00
Craig Topper
081c29b256 Check for less than 0 in shuffle mask instead of -1. It's more consistent with other code related to shuffles and easier to implement in compiled code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172788 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-18 05:30:07 +00:00
Craig Topper
37d093f0b0 Remove trailing whitespace. Remove new lines between closing brace and 'else'
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172784 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-18 05:09:16 +00:00
Nadav Rotem
83d5853833 Teach InstCombine to optimize extract of a value from a vector add operation with a constant zero.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@172576 91177308-0d34-0410-b5e6-96231b3b80d8
2013-01-15 23:43:14 +00:00
Michael Gottesman
4932bbe20c [InstCombine] Teach InstCombine how to handle an obfuscated splat.
An obfuscated splat is where the frontend poorly generates code for a splat
using several different shuffles to create the splat, i.e.,

  %A = load <4 x float>* %in_ptr, align 16
  %B = shufflevector <4 x float> %A, <4 x float> undef, <4 x i32> <i32 0, i32 0, i32 undef, i32 undef>
  %C = shufflevector <4 x float> %B, <4 x float> %A, <4 x i32> <i32 0, i32 1, i32 4, i32 undef>
  %D = shufflevector <4 x float> %C, <4 x float> %A, <4 x i32> <i32 0, i32 1, i32 2, i32 4>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@166061 91177308-0d34-0410-b5e6-96231b3b80d8
2012-10-16 21:29:38 +00:00
Chris Lattner
a78fa8cc2d continue making the world safe for ConstantDataVector. At this point,
we should (theoretically optimize and codegen ConstantDataVector as well
as ConstantVector.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149116 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-27 03:08:05 +00:00
Chris Lattner
230cdab220 some general cleanup, using new methods and tidying up old code.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@149006 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-26 00:42:34 +00:00
Chris Lattner
bec2d03c4d basic instcombine support for CDS.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@148806 91177308-0d34-0410-b5e6-96231b3b80d8
2012-01-24 14:31:22 +00:00
Eli Friedman
8d992f5c2c Minor simplification: use ShuffleVectorInst::getMaskValue instead of a more expensive helper.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142672 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 19:11:34 +00:00
Eli Friedman
d2822e7572 Extend instcombine's shufflevector simplification to handle more cases where the input and output vectors have different sizes. Patch by Xiaoyi Guo.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@142671 91177308-0d34-0410-b5e6-96231b3b80d8
2011-10-21 19:06:29 +00:00
Chris Lattner
db125cfaf5 land David Blaikie's patch to de-constify Type, with a few tweaks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@135375 91177308-0d34-0410-b5e6-96231b3b80d8
2011-07-18 04:54:35 +00:00
Nadav Rotem
0ff8a4fa35 Instcombile optimization: extractelement(cast) -> cast(extractelement)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@128683 91177308-0d34-0410-b5e6-96231b3b80d8
2011-03-31 22:57:29 +00:00
Eli Friedman
1347623aaf PR9218: SimplifyDemandedVectorElts can return a non-null value that is not
the instruction passed in.  Make sure to account for this correctly, instead
of looping infinitely.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126058 91177308-0d34-0410-b5e6-96231b3b80d8
2011-02-19 22:42:40 +00:00
Jay Foad
7a874ddda0 PR5207: Rename overloaded APInt methods set(), clear(), flip() to
setAllBits(), setBit(unsigned), etc.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@120564 91177308-0d34-0410-b5e6-96231b3b80d8
2010-12-01 08:53:58 +00:00
Bob Wilson
db1da8ed42 Clean up indentation and other whitespace.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117728 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-29 22:20:45 +00:00
Bob Wilson
09fd64644d Remove trailing whitespace.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117727 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-29 22:20:43 +00:00
Bob Wilson
f0b48f836e Fix 80-column violation.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117722 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-29 22:03:07 +00:00
Bob Wilson
822cb58d08 Change instcombine's getShuffleMask to represent undef with negative values.
This code had previously used 2*N, where N is the mask length, to represent
undef.  That is not safe because the shufflevector operands may have more
than N elements -- they don't have to match the result type.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117721 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-29 22:03:05 +00:00
Bob Wilson
4cac5facc3 Make instcombine a little more aggressive in combining vector shuffles.
Allow splats even if they don't match either of the original shuffles,
possibly due to undef entries in the shuffles masks.  Radar 8597790.
Also fix some 80-column violations.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@117719 91177308-0d34-0410-b5e6-96231b3b80d8
2010-10-29 22:02:50 +00:00
Eric Christopher
68c23f8616 Temporarily revert r110987 as it's causing some miscompares in
vector heavy code.  I'll re-enable when we've tracked down the problem.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@111318 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-17 22:55:27 +00:00
Nate Begeman
7f1f4089a1 Reapply this transformation now that it is passing the external test which it previously failed.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110987 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-13 00:17:53 +00:00
Eric Christopher
7486278900 Temporarily revert 110737 and 110734, they were causing failures
in an external testsuite.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110905 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-12 07:01:22 +00:00
Nate Begeman
95743d8748 Add the minimal amount of smarts necessary to instcombine of shufflevectors to recognize
patterns generated by clang for transpose of a matrix in generic vectors.  This is made
of two parts:

1) Propagating vector extracts of hi/lo half into their users
2) Recognizing an insertion of even elements followed by the odd elements as an unpack.

Testcase to come, but this shrinks the # of shuffle instructions generated on x86 from ~40 to the minimal 8.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@110734 91177308-0d34-0410-b5e6-96231b3b80d8
2010-08-10 21:38:12 +00:00
Duncan Sands
1df9859c40 There are two ways of checking for a given type, for example isa<PointerType>(T)
and T->isPointerTy().  Convert most instances of the first form to the second form.
Requested by Chris.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@96344 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-16 11:11:14 +00:00
Chris Lattner
8609fda0f7 fix some problems handling large vectors reported in PR6230
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@95616 91177308-0d34-0410-b5e6-96231b3b80d8
2010-02-08 23:56:03 +00:00
Chris Lattner
d5da271863 reduce indentation
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@92684 91177308-0d34-0410-b5e6-96231b3b80d8
2010-01-05 05:42:08 +00:00
Chris Lattner
b8a5cecd6b split vector stuff out to InstCombineVectorOps.cpp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@92683 91177308-0d34-0410-b5e6-96231b3b80d8
2010-01-05 05:36:20 +00:00