Commit Graph

149 Commits

Author SHA1 Message Date
Chandler Carruth
ffc97a6ae1 [slp] Fix a nasty bug in the SLP vectorizer that Joerg pointed out.
Apparently some code finally started to tickle this after my
canonicalization changes to instcombine.

The bug stems from trying to form a vector type out of scalars that
aren't compatible at all. In this example, from x86_mmx values. The code
in the vectorizer that checks for reasonable types whas checking for
aggregates or vectors, but there are lots of other types that should
just never reach the vectorizer.

Debugging this was made more confusing by the lie in an assert in
VectorType::get() -- it isn't that the types are *primitive*. The types
must be integer, pointer, or floating point types. No other types are
allowed.

I've improved the assert and added a helper to the vectorizer to handle
the element type validity checks. It now re-uses the VectorType static
function and then further excludes weird target-specific types that we
probably shouldn't be touching here (x86_fp80 and ppc_fp128). Neither of
these are really reachable anyways (neither 80-bit nor 128-bit things
will get vectorized) but it seems better to just eagerly exclude such
nonesense.

I've added a test case, but while it definitely covers two of the paths
through this code there may be more paths that would benefit from test
coverage. I'm not familiar enough with the SLP vectorizer to synthesize
test cases for all of these, but was able to update the code itself by
inspection.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228899 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-12 02:30:56 +00:00
Erik Eckstein
40d542097a Fix: SLPVectorizer crashes with assertion when vectorizing a cmp instruction.
The commit r225977 uncovered this bug. The problem was that the vectorizer tried to
read the second operand of an already deleted instruction.
The bug didn't show up before r225977 because the freed memory still contained a non-null pointer.
With r225977 deletion of instructions is delayed and the read operand pointer is always null.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227800 91177308-0d34-0410-b5e6-96231b3b80d8
2015-02-02 12:45:34 +00:00
Erik Eckstein
8f6e8cb4f6 SLPVectorizer: fix wrong scheduling of atomic load/stores.
This fixes PR22306.




git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@227077 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-26 09:07:04 +00:00
Karthik Bhat
7e9f120130 Fix Operandreorder logic in SLPVectorizer to generate longer vectorizable chain.
This patch fixes 2 issues in reorderInputsAccordingToOpcode
1) AllSameOpcodeLeft and AllSameOpcodeRight was being calculated incorrectly resulting in code not being vectorized in few cases.
2) Adds logic to reorder operands if we get longer chain of consecutive loads enabling vectorization. Handled the same for cases were we have AltOpcode.
Thanks Michael for inputs and review.
Review: http://reviews.llvm.org/D6677



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226547 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-20 06:11:00 +00:00
Duncan P. N. Exon Smith
37ac8d3622 IR: Move MDLocation into place
This commit moves `MDLocation`, finishing off PR21433.  There's an
accompanying clang commit for frontend testcases.  I'll attach the
testcase upgrade script I used to PR21433 to help out-of-tree
frontends/backends.

This changes the schema for `DebugLoc` and `DILocation` from:

    !{i32 3, i32 7, !7, !8}

to:

    !MDLocation(line: 3, column: 7, scope: !7, inlinedAt: !8)

Note that empty fields (line/column: 0 and inlinedAt: null) don't get
printed by the assembly writer.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226048 91177308-0d34-0410-b5e6-96231b3b80d8
2015-01-14 22:27:36 +00:00
Suyog Sarda
4bfc4f2e8c Revert 224119 "This patch recognizes (+ (+ v0, v1) (+ v2, v3)), reorders them for bundling into vector of loads,
and vectorizes it." 

This was re-ordering floating point data types resulting in mismatch in output.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224424 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-17 10:34:27 +00:00
Duncan P. N. Exon Smith
1ef70ff39b IR: Make metadata typeless in assembly
Now that `Metadata` is typeless, reflect that in the assembly.  These
are the matching assembly changes for the metadata/value split in
r223802.

  - Only use the `metadata` type when referencing metadata from a call
    intrinsic -- i.e., only when it's used as a `Value`.

  - Stop pretending that `ValueAsMetadata` is wrapped in an `MDNode`
    when referencing it from call intrinsics.

So, assembly like this:

    define @foo(i32 %v) {
      call void @llvm.foo(metadata !{i32 %v}, metadata !0)
      call void @llvm.foo(metadata !{i32 7}, metadata !0)
      call void @llvm.foo(metadata !1, metadata !0)
      call void @llvm.foo(metadata !3, metadata !0)
      call void @llvm.foo(metadata !{metadata !3}, metadata !0)
      ret void, !bar !2
    }
    !0 = metadata !{metadata !2}
    !1 = metadata !{i32* @global}
    !2 = metadata !{metadata !3}
    !3 = metadata !{}

turns into this:

    define @foo(i32 %v) {
      call void @llvm.foo(metadata i32 %v, metadata !0)
      call void @llvm.foo(metadata i32 7, metadata !0)
      call void @llvm.foo(metadata i32* @global, metadata !0)
      call void @llvm.foo(metadata !3, metadata !0)
      call void @llvm.foo(metadata !{!3}, metadata !0)
      ret void, !bar !2
    }
    !0 = !{!2}
    !1 = !{i32* @global}
    !2 = !{!3}
    !3 = !{}

I wrote an upgrade script that handled almost all of the tests in llvm
and many of the tests in cfe (even handling many `CHECK` lines).  I've
attached it (or will attach it in a moment if you're speedy) to PR21532
to help everyone update their out-of-tree testcases.

This is part of PR21532.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224257 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-15 19:07:53 +00:00
Suyog Sarda
4dcffed444 Typo Correction in Test Case. NFC.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224244 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-15 12:19:46 +00:00
Suyog Sarda
1dea0dc279 This patch recognizes (+ (+ v0, v1) (+ v2, v3)), reorders them for bundling into vector of loads,
and vectorizes it. 
 
 Test case :
 
       float hadd(float* a) {
           return (a[0] + a[1]) + (a[2] + a[3]);
        }
 
 
 AArch64 assembly before patch :
 
        ldp	s0, s1, [x0]
 	ldp	s2, s3, [x0, #8]
 	fadd	s0, s0, s1
 	fadd	s1, s2, s3
 	fadd	s0, s0, s1
 	ret
 
 AArch64 assembly after patch :
 
        ldp	d0, d1, [x0]
 	fadd	v0.2s, v0.2s, v1.2s
 	faddp	s0, v0.2s
 	ret

Reviewed Link : http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20141208/248531.html



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@224119 91177308-0d34-0410-b5e6-96231b3b80d8
2014-12-12 12:53:44 +00:00
Suyog Sarda
ca72befdb5 Vectorize a reduction chain feeding into a 'return' statement.
e.x 
return (a[0]+b[0]) + (a[1]+b[1])

Differential Revision: http://reviews.llvm.org/D6227



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@222364 91177308-0d34-0410-b5e6-96231b3b80d8
2014-11-19 16:07:38 +00:00
Hal Finkel
6c15862fd3 [SLPVectorize] Basic ephemeral-value awareness
The SLP vectorizer should not vectorize ephemeral values. These are used to
express information to the optimizer, and vectorizing them does not lead to
faster code (because the ephemeral values are dropped prior to code generation,
vectorized or not), and obscures the information the instructions are
attempting to communicate (the logic that interprets the arguments to
@llvm.assume generically does not understand vectorized conditions).

Also, uses by ephemeral values are free (because they, and the necessary
extractelement instructions, will be dropped prior to code generation).

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219816 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-15 17:35:01 +00:00
Duncan P. N. Exon Smith
83902832de Revert "Revert "DI: Fold constant arguments into a single MDString""
This reverts commit r218918, effectively reapplying r218914 after fixing
an Ocaml bindings test and an Asan crash.  The root cause of the latter
was a tightened-up check in `DILexicalBlock::Verify()`, so I'll file a
PR to investigate who requires the loose check (and why).

Original commit message follows.

--

This patch addresses the first stage of PR17891 by folding constant
arguments together into a single MDString.  Integers are stringified and
a `\0` character is used as a separator.

Part of PR17891.

Note: I've attached my testcases upgrade scripts to the PR.  If I've
just broken your out-of-tree testcases, they might help.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@219010 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-03 20:01:09 +00:00
Duncan P. N. Exon Smith
32e192aeb3 Revert "DI: Fold constant arguments into a single MDString"
This reverts commit r218914 while I investigate some bots.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218918 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-02 22:15:31 +00:00
Duncan P. N. Exon Smith
0917b70630 DI: Fold constant arguments into a single MDString
This patch addresses the first stage of PR17891 by folding constant
arguments together into a single MDString.  Integers are stringified and
a `\0` character is used as a separator.

Part of PR17891.

Note: I've attached my testcases upgrade scripts to the PR.  If I've
just broken your out-of-tree testcases, they might help.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218914 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-02 21:56:57 +00:00
Adrian Prantl
02474a32eb Move the complex address expression out of DIVariable and into an extra
argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.

Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.

By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.

The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)

This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.

What this patch doesn't do:

This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.

http://reviews.llvm.org/D4919
rdar://problem/17994491

Thanks to dblaikie and dexonsmith for reviewing this patch!

Note: I accidentally committed a bogus older version of this patch previously.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218787 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 18:55:02 +00:00
Adrian Prantl
10c4265675 Revert r218778 while investigating buldbot breakage.
"Move the complex address expression out of DIVariable and into an extra"

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218782 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 18:10:54 +00:00
Adrian Prantl
076fd5dfc1 Move the complex address expression out of DIVariable and into an extra
argument of the llvm.dbg.declare/llvm.dbg.value intrinsics.

Previously, DIVariable was a variable-length field that has an optional
reference to a Metadata array consisting of a variable number of
complex address expressions. In the case of OpPiece expressions this is
wasting a lot of storage in IR, because when an aggregate type is, e.g.,
SROA'd into all of its n individual members, the IR will contain n copies
of the DIVariable, all alike, only differing in the complex address
reference at the end.

By making the complex address into an extra argument of the
dbg.value/dbg.declare intrinsics, all of the pieces can reference the
same variable and the complex address expressions can be uniqued across
the CU, too.
Down the road, this will allow us to move other flags, such as
"indirection" out of the DIVariable, too.

The new intrinsics look like this:
declare void @llvm.dbg.declare(metadata %storage, metadata %var, metadata %expr)
declare void @llvm.dbg.value(metadata %storage, i64 %offset, metadata %var, metadata %expr)

This patch adds a new LLVM-local tag to DIExpressions, so we can detect
and pretty-print DIExpression metadata nodes.

What this patch doesn't do:

This patch does not touch the "Indirect" field in DIVariable; but moving
that into the expression would be a natural next step.

http://reviews.llvm.org/D4919
rdar://problem/17994491

Thanks to dblaikie and dexonsmith for reviewing this patch!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218778 91177308-0d34-0410-b5e6-96231b3b80d8
2014-10-01 17:55:39 +00:00
Chad Rosier
ea64dce261 [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
2014-09-29 13:59:31 +00:00
Sanjay Patel
b89304eb7c Preserve IR flags (nsw, nuw, exact, fast-math) in SLP vectorizer (PR20802).
The SLP vectorizer should propagate IR-level optimization hints/flags (nsw, nuw, exact, fast-math)
when converting scalar instructions into vectors. But this isn't a simple copy - we need to take
the intersection (the logical 'and') of the sets of flags on the scalars.

The solution is further complicated because we can have non-uniform (non-SIMD) vector ops after:
http://reviews.llvm.org/D4015
http://llvm.org/viewvc/llvm-project?view=revision&revision=211339

The vast majority of changed files are existing tests that were not propagating IR flags, but I've
also added a new test file for focused testing of IR flag possibilities.

Differential Revision: http://reviews.llvm.org/D5172



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@217051 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-03 17:40:30 +00:00
Yi Jiang
cb2522448c Generate extract for in-tree uses if the use is scalar operand in vectorized instruction. radar://18144665
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216946 91177308-0d34-0410-b5e6-96231b3b80d8
2014-09-02 21:00:39 +00:00
Erik Eckstein
c84ba857ea Fix: SLPVectorizer tried to move an instruction which was replaced by a vector instruction.
For a detailed description of the problem see the comment in the test file.
The problematic moveBefore() calls are not required anymore because the new
scheduling algorithm ensures a correct ordering anyway.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216656 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-28 07:04:02 +00:00
Michael Zolotukhin
b8c95a89e6 [SLP] Re-enable vectorization of GEP expressions (re-apply r210342 with a fix).
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216549 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-27 15:01:18 +00:00
Joerg Sonnenberger
1d5cdfd751 Revert r210342 and r210343, add test case for the crasher.
PR 20642.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216475 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-26 19:06:41 +00:00
Karthik Bhat
e637d65af3 Allow vectorization of division by uniform power of 2.
This patch adds support to recognize division by uniform power of 2 and modifies the cost table to vectorize division by uniform power of 2 whenever possible.
Updates Cost model for Loop and SLP Vectorizer.The cost table is currently only updated for X86 backend.
Thanks to Hal, Andrea, Sanjay for the review. (http://reviews.llvm.org/D4971)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216371 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-25 04:56:54 +00:00
Erik Eckstein
6ca2d8b7c7 fix: SLPVectorizer crashes for unreachable blocks containing not schedulable instructions.
In unreachable blocks it's legal to have instructions like "%x = op %x".
Such instuctions are not schedulable. Therefore the SLPVectorizer has to check for
unreachable blocks and ignore them.

Fixes bug 20646.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@216256 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-22 01:18:39 +00:00
Arnold Schwaighofer
2158dec965 SLPVectorizer: Use the type of the value loaded/stored to get the ABI alignment
We were using the pointer type which is incorrect.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@215162 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-07 22:47:27 +00:00
James Molloy
72035e9a8e Teach the SLP Vectorizer that keeping some values live over a callsite can have a cost.
Some types, such as 128-bit vector types on AArch64, don't have any callee-saved registers. So if a value needs to stay live over a callsite, it must be spilled and refilled. This cost is now taken into account.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214859 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-05 12:30:34 +00:00
Erik Eckstein
8624519c0c fix bug 20513 - Crash in SLP Vectorizer
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214638 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-02 19:39:42 +00:00
Erik Eckstein
956268f9dc SLPVectorizer: improved scheduling algorithm.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214494 91177308-0d34-0410-b5e6-96231b3b80d8
2014-08-01 09:20:42 +00:00
Chad Rosier
7f6a685444 SLP Vectorizer: Canonicalize tree operands of commutitive binary operands.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@214338 91177308-0d34-0410-b5e6-96231b3b80d8
2014-07-30 21:07:56 +00:00
Karthik Bhat
d2ce9392dc Add Support to Recognize and Vectorize NON SIMD instructions in SLPVectorizer.
This patch adds support to recognize patterns such as fadd,fsub,fadd,fsub.../add,sub,add,sub... and
vectorizes them as vector shuffles if they are profitable.
These patterns of vector shuffle can later be converted to instructions such as addsubpd etc on X86.
Thanks to Arnold and Hal for the reviews. http://reviews.llvm.org/D4015 


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@211339 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-20 04:32:48 +00:00
Alp Toker
8aeca44558 Reduce verbiage of lit.local.cfg files
We can just split targets_to_build in one place and make it immutable.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210496 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-09 22:42:55 +00:00
Michael Zolotukhin
f4f9c6bfc1 Fix typo in a test from r210342.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210343 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-06 15:49:47 +00:00
Michael Zolotukhin
afbe82d590 [SLP] Enable vectorization of GEP expressions.
The use cases look like the following:
    x->a = y->a + 10
    x->b = y->b + 12

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210342 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-06 15:34:24 +00:00
Karthik Bhat
b73a9b384e Fix PR19657 (scalar loads not combined into vector load)
If we have common uses on separate paths in the tree; process the one with greater common depth first.
This makes sure that we do not assume we need to extract a load when it is actually going to be part of a vectorized tree.

Review: http://reviews.llvm.org/D3800


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@210310 91177308-0d34-0410-b5e6-96231b3b80d8
2014-06-06 06:20:08 +00:00
Karthik Bhat
8ffc96a163 Allow vectorization of intrinsics such as powi,cttz and ctlz in Loop and SLP Vectorizer.
This patch adds support to vectorize intrinsics such as powi, cttz and ctlz in Vectorizer. These intrinsics are different from other
intrinsics as second argument to these function must be same in order to vectorize them and it should be represented as a scalar.
Review: http://reviews.llvm.org/D3851#inline-32769 and http://reviews.llvm.org/D3937#inline-32857


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209873 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-30 04:31:24 +00:00
Tim Northover
29f94c7201 AArch64/ARM64: move ARM64 into AArch64's place
This commit starts with a "git mv ARM64 AArch64" and continues out
from there, renaming the C++ classes, intrinsics, and other
target-local objects for consistency.

"ARM64" test directories are also moved, and tests that began their
life in ARM64 use an arm64 triple, those from AArch64 use an aarch64
triple. Both should be equivalent though.

This finishes the AArch64 merge, and everyone should feel free to
continue committing as normal now.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209577 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-24 12:50:23 +00:00
Michael Zolotukhin
45788be6e2 Implement sext(C1 + C2*X) --> sext(C1) + sext(C2*X) and
sext{C1,+,C2} --> sext(C1) + sext{0,+,C2} transformation in Scalar
Evolution.

That helps SLP-vectorizer to recognize consecutive loads/stores.

<rdar://problem/14860614>

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209568 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-24 08:09:57 +00:00
Nico Rieck
a739ea33a0 Fix broken FileCheck prefixes
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209538 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-23 19:06:24 +00:00
Benjamin Kramer
29e068bac0 Flip on vectorization of bswap intrinsics.
The cost model conservatively assumes that it will always get scalarized and
that's about as good as we can get with the generic TTI; reasoning whether a
shuffle with an efficient lowering is available is hard. We can override that
conservative estimate for some targets in the future.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@209125 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-19 13:48:08 +00:00
Benjamin Kramer
3ae331d81a SLPVectorizer: When sorting by domination for CSE don't assert on unreachable code.
There is no total ordering if the CFG is disconnected. We don't care if we
catch all CSE opportunities in dead code either so just exclude ignore them in
the assert.

PR19646

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@208461 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-09 23:28:49 +00:00
Yi Jiang
606660f1f3 Always set alignment of vectorized LD/ST in SLP-Vectorizer. <rdar://problem/16812145>
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207983 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-05 17:59:14 +00:00
Arnold Schwaighofer
28a739b4dc SLPVectorizer: Bring back the insertelement patch (r205965) with fixes
When can't assume a vectorized tree is rooted in an instruction. The IRBuilder
could have constant folded it. When we rebuild the build_vector (the series of
InsertElement instructions) use the last original InsertElement instruction. The
vectorized tree root is guaranteed to be before it.

Also, we can't assume that the n-th InsertElement inserts the n-th element into
a vector.

This reverts r207746 which reverted the revert of the revert of r205018 or so.

Fixes the test case in PR19621.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207939 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-04 17:10:15 +00:00
Karthik Bhat
486ad6262e Vectorize intrinsic math function calls in SLPVectorizer.
This patch adds support to recognize and vectorize intrinsic math functions in SLPVectorizer.
Review: http://reviews.llvm.org/D3560 and http://reviews.llvm.org/D3559


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207901 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-03 09:59:54 +00:00
Chandler Carruth
06ace3c869 Revert r205965, which essentially reverts r205018 for the second time.
=[

Turns out that this was the root cause of PR19621. We found a crasher
only recently (likely due to improvements elsewhere in the SLP
vectorizer) but the reduced test case failed all the way back to here.
I've confirmed that reverting this patch both fixes the reduced test
case in PR19621 and the actual source file that led to it, so it seems
to really be rooted here. I've replied to the commit thread with
discussion of my (feeble) attempts to debug this. Didn't make it very
far, so reverting now that we have a good test case so that things can
get back to healthy while the debugging carries on.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207746 91177308-0d34-0410-b5e6-96231b3b80d8
2014-05-01 11:24:11 +00:00
Yi Jiang
bbea6143f2 Continue slp vectorization even the BB already has vectorized store radar://16641956
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@207572 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-29 19:37:20 +00:00
Arnold Schwaighofer
e2d124d396 Reapply "SLPVectorizer: Ignore users that are insertelements we can reschedule them"
This commit reapplies 205018. After 205855 we should correctly vectorize
intrinsics.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205965 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-10 13:41:35 +00:00
Arnold Schwaighofer
b0ee2374ce SLPVectorizer: Only vectorize intrinsics whose operands are widened equally
The vectorizer only knows how to vectorize intrinics by widening all operands by
the same factor.

Patch by Tyler Nowicki!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205855 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-09 14:20:47 +00:00
Tim Northover
24e78e0125 SLPVectorizer: compare entire intrinsic for SLP compatibility.
Some Intrinsics are overloaded to the extent that return type equality (all
that's been checked up to now) does not guarantee that the arguments are the
same. In these cases SLP vectorizer should not recurse into the operands, which
can be achieved by comparing them as "Function *" rather than simply the ID.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205424 91177308-0d34-0410-b5e6-96231b3b80d8
2014-04-02 14:39:02 +00:00
Arnold Schwaighofer
694365f955 Revert "SLPVectorizer: Ignore users that are insertelements we can reschedule them"
This reverts commit r205018.

Conflicts:
	lib/Transforms/Vectorize/SLPVectorizer.cpp
	test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll

This is breaking libclc build.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205260 91177308-0d34-0410-b5e6-96231b3b80d8
2014-03-31 23:05:56 +00:00