[InstCombine] Only fold extract element to trunc if vector `hasOneUse` (#115627)

This fixes a missed optimization caused by the `foldBitcastExtElt`
pattern interfering with other combine patterns.

[InstCombine] Only fold extract element to trunc if vector `hasOneUse` (#115627)

This fixes a missed optimization caused by the `foldBitcastExtElt`
pattern interfering with other combine patterns. In the case I was
hitting, we have IR that combines two vectors into a new larger vector
by extracting elements and inserting them into the new vector.

```llvm
define <4 x half> @bitcast_extract_insert_to_shuffle(i32 %a, i32 %b) {
%avec = bitcast i32 %a to <2 x half>
%a0 = extractelement <2 x half> %avec, i32 0
%a1 = extractelement <2 x half> %avec, i32 1
%bvec = bitcast i32 %b to <2 x half>
%b0 = extractelement <2 x half> %bvec, i32 0
%b1 = extractelement <2 x half> %bvec, i32 1
%ins0 = insertelement <4 x half> undef, half %a0, i32 0
%ins1 = insertelement <4 x half> %ins0, half %a1, i32 1
%ins2 = insertelement <4 x half> %ins1, half %b0, i32 2
%ins3 = insertelement <4 x half> %ins2, half %b1, i32 3
ret <4 x half> %ins3
}
```

With the current behavior, `InstCombine` converts each vector extract
sequence to

```llvm
%tmp = trunc i32 %a to i16
%a0 = bitcast i16 %tmp to half
%a1 = extractelement <2 x half> %avec, i32 1
```

where the extraction of `%a0` is now done by truncating the original
integer. While on it's own this is fairly reasonable, in this case it
also blocks the pattern which converts `extractelement` -
`insertelement` into shuffles which gives the overall simpler result:

```llvm
define <4 x half> @bitcast_extract_insert_to_shuffle(i32 %a, i32 %b) {
%avec = bitcast i32 %a to <2 x half>
%bvec = bitcast i32 %b to <2 x half>
%ins3 = shufflevector <2 x half> %avec, <2 x half> %bvec, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
ret <4 x half> %ins3
}
```

In this PR I fix the conflict by obeying the `hasOneUse` check even if
there is no shift instruction required. In these cases we can't remove
the vector completely, so the pattern has less benefit anyway.

Also fwiw, I think dropping the `hasOneUse` check for the 0th element
might have been a mistake in the first place. Looking at
https://github.com/llvm/llvm-project/commit/535c5d56a7bc9966036a11362d8984983a4bf090
the commit message only mentions loosening the `isDesirableIntType`
requirement and doesn't mention changing the `hasOneUse` check at all.

show more ...

[test] Use -passes=instcombine instead of -instcombine in lots of tests. NFC

Another step moving away from the deprecated syntax of specifying
pass pipeline in opt.

Differential Revision: https://r

[test] Use -passes=instcombine instead of -instcombine in lots of tests. NFC

Another step moving away from the deprecated syntax of specifying
pass pipeline in opt.

Differential Revision: https://reviews.llvm.org/D119081

show more ...

[instcombine] Canonicalize constant index type to i64 for extractelement/insertelement

The basic idea to this is that a) having a single canonical type makes CSE easier, and b) many of our transform

[instcombine] Canonicalize constant index type to i64 for extractelement/insertelement

The basic idea to this is that a) having a single canonical type makes CSE easier, and b) many of our transforms are inconsistent about which types we end up with based on visit order.

I'm restricting this to constants as for non-constants, we'd have to decide whether the simplicity was worth extra instructions. For constants, there are no extra instructions.

We chose the canonical type as i64 arbitrarily. We might consider changing this to something else in the future if we have cause.

Differential Revision: https://reviews.llvm.org/D115387

show more ...

[InstSimplify] Return poison if insertelement touches out of bounds

This is a simple patch that updates InstSimplify to return poison if the index is/can be out-of-bounds

Reviewed By: nikic

Differ

[InstSimplify] Return poison if insertelement touches out of bounds

This is a simple patch that updates InstSimplify to return poison if the index is/can be out-of-bounds

Reviewed By: nikic

Differential Revision: https://reviews.llvm.org/D93990

show more ...

[InstCombine] use poison as placeholder for undemanded elems

Currently undef is used as a don’t-care vector when constructing a vector using a series of insertelement.
However, this is problematic b

[InstCombine] use poison as placeholder for undemanded elems

Currently undef is used as a don’t-care vector when constructing a vector using a series of insertelement.
However, this is problematic because undef isn’t undefined enough.
Especially, a sequence of insertelement can be optimized to shufflevector, but using undef as its placeholder makes shufflevector a poison-blocking instruction because undef cannot be optimized to poison.
This makes a few straightforward optimizations incorrect, such as:

```
; https://bugs.llvm.org/show_bug.cgi?id=44185

define <4 x float> @insert_not_undef_shuffle_translate_commute(float %x, <4 x float> %y, <4 x float> %q) {
%xv = insertelement <4 x float> %q, float %x, i32 2
%r = shufflevector <4 x float> %y, <4 x float> %xv, <4 x i32> { 0, 6, 2, undef }
ret <4 x float> %r ; %r[3] is undef
}
=>
define <4 x float> @insert_not_undef_shuffle_translate_commute(float %x, <4 x float> %y, <4 x float> %q) {
%r = insertelement <4 x float> %y, float %x, i32 1
ret <4 x float> %r ; %r[3] = %y[3], incorrect if %y[3] = poison
}

Transformation doesn't verify!
ERROR: Target is more poisonous than source
```

I’d like to suggest
1. Using poison as insertelement’s placeholder value (IRBuilder::CreateVectorSplat should be patched too)
2. Updating shufflevector’s semantics to return poison element if mask is undef

Note that poison is currently lowered into UNDEF in SelDag, so codegen part is okay.
m_Undef() matches PoisonValue as well, so existing optimizations will still fire.

The only concern is hidden miscompilations that will go incorrect when poison constant is given.
A conservative way is copying all tests having `insertelement undef` & replacing it with `insertelement poison` & run Alive2 on it, but it will create many tests and people won’t like it. :(

Instead, I’ll simply locally maintain the tests and run Alive2.
If there is any bug found, I’ll report it.

Relevant links: https://bugs.llvm.org/show_bug.cgi?id=43958 , http://lists.llvm.org/pipermail/llvm-dev/2019-November/137242.html

Reviewed By: nikic

Differential Revision: https://reviews.llvm.org/D93586

show more ...

Revert "Temporarily Revert "Add basic loop fusion pass.""

The reversion apparently deleted the test/Transforms directory.

Will be re-reverting again.

llvm-svn: 358552

[instsimplify] consistently handle undef and out of bound indices for insertelement and extractelement

In one case, we were handling out of bounds, but not undef indices. In the other, we were hand

[instsimplify] consistently handle undef and out of bound indices for insertelement and extractelement

In one case, we were handling out of bounds, but not undef indices. In the other, we were handling undef (with the comment making the analogy to out of bounds), but not out of bounds. Be consistent and treat both undef and constant out of bounds indices as producing undefined results.

As a side effect, this also protects instcombine from having to handle large constant indices as we always simplify first.

llvm-svn: 321575

show more ...

Reintroduce r320049, r320014 and r319894.
OpenGL issues should be fixed by now.

llvm-svn: 320568

Revert r320049, r320014 and r319894
They were causing failures of the piglit OpenGL tests with AMD GPUs using the
Mesa radeonsi driver.

llvm-svn: 320466

[InstCombine] Don't crash on out of bounds index in the insertelement

Differential Revision: https://reviews.llvm.org/D40390

llvm-svn: 320049

[InstCombine] canonicalize insertelement of scalar constant ahead of insertelement of variable

insertelement (insertelement X, Y, IdxC1), ScalarC, IdxC2 -->
insertelement (insertelement X, ScalarC,

[InstCombine] canonicalize insertelement of scalar constant ahead of insertelement of variable

insertelement (insertelement X, Y, IdxC1), ScalarC, IdxC2 -->
insertelement (insertelement X, ScalarC, IdxC2), Y, IdxC1

As noted in the code comment and seen in the test changes, the motivation is that by pulling
constant insertion up, we may be able to constant fold some insertelement instructions.

Differential Revision: https://reviews.llvm.org/D31196

llvm-svn: 298520

show more ...

[InstCombine] regenerate checks; NFC

llvm-svn: 298432

[InstCombine] Fix for PR29124: reduce insertelements to shufflevector

If inserting more than one constant into a vector:

define <4 x float> @foo(<4 x float> %x) {
%ins1 = insertelement <4 x float

[InstCombine] Fix for PR29124: reduce insertelements to shufflevector

If inserting more than one constant into a vector:

define <4 x float> @foo(<4 x float> %x) {
%ins1 = insertelement <4 x float> %x, float 1.0, i32 1
%ins2 = insertelement <4 x float> %ins1, float 2.0, i32 2
ret <4 x float> %ins2
}

InstCombine could reduce that to a shufflevector:

define <4 x float> @goo(<4 x float> %x) {
%shuf = shufflevector <4 x float> %x, <4 x float> <float undef, float 1.0, float 2.0, float undef>, <4 x i32><i32 0, i32 5, i32 6, i32 3>
ret <4 x float> %shuf
}
Also, InstCombine tries to convert shuffle instruction to single insertelement, if one of the vectors is a constant vector and only a single element from this constant should be used in shuffle, i.e.
shufflevector <4 x float> %v, <4 x float> <float undef, float 1.0, float
undef, float undef>, <4 x i32> <i32 0, i32 5, i32 undef, i32 undef> ->
insertelement <4 x float> %v, float 1.0, 1

Differential Revision: https://reviews.llvm.org/D24182

llvm-svn: 282237

show more ...

[InstCombine] Add test for insertelementinsts with constants.

Added a tests that shows that several insertelementinsts with constant
indexes/data are not folded into a single shuffleinst.

llvm-svn:

[InstCombine] Add test for insertelementinsts with constants.

Added a tests that shows that several insertelementinsts with constant
indexes/data are not folded into a single shuffleinst.

llvm-svn: 280474

show more ...