The intent of this code is to split larger vectors into smaller shuffles, but
it currently triggering on some small vector types. Limit it to vectors of size
>128bit.
The shuffle needn't be twice the original number of vector elements, so
the intermediate type used between the shuffle and the intrinsic should
use the ShuffleDstTy number of elements.
I found this when looking at shuffle costs and do not have test where it
alters the output, but have added some cases where the shuffle output is
not twice the size of the input.
This adds a test that exercises the part of scalarizeBinOpOrCmp that
produces immediate UB as described in
https://github.com/llvm/llvm-project/pull/138095#discussion_r2070133432,
but is fortunately currently folded into a correct transform.
I also noticed a bunch of immediate UB in some of the existing tests so
this also cleans them up. They should still all be scalarized though.
Since e39f6c1844fab59c638d8059a6cf139adb42279a opt will infer the
correct datalayout when given a triple. Avoid explicitly specifying it
in tests that depend on the AMDGPU target being present to avoid the
string becoming out of sync with the TargetInfo value.
Only tests with REQUIRES: amdgpu-registered-target or a local lit.cfg
were updated to ensure that tests for non-target-specific passes that
happen to use the AMDGPU layout still pass when building with a limited
set of targets.
Reviewed By: shiltian, arsenm
Pull Request: https://github.com/llvm/llvm-project/pull/137921
Previously only fixed vector splats were handled. This adds supports for
scalable vectors too by allowing ConstantExpr splats.
We need to add the extra V->getType()->isVectorTy() check because a
ConstantExpr might be a scalar to vector bitcast.
By allowing ConstantExprs this also allow fixed vector ConstantExprs to
be folded, which causes the diffs in
llvm/test/Analysis/ValueTracking/known-bits-from-operator-constexpr.ll
and llvm/test/Transforms/InstSimplify/ConstProp/cast-vector.ll. I can
remove them from this PR if reviewers would prefer.
Fixes#132922
In the previous code (#128032), it specified the destination vector as the
getShuffleCost argument. Because the shuffle mask specifies the indices
of the two vectors specified as elements, the maximum value is twice the
size of the source vector. This causes a problem if the destination
vector is smaller than the source vector and specify an index in the
mask that exceeds the size of the destination vector.
Fix the problem by correcting the previous code, which was using wrong
argument in the Cost calculation.
Fixes#130250
(shuffle(select(c1,t1,f1)), (select(c2,t2,f2)), m)
-> (select (shuffle c1,c2,m), (shuffle t1,t2,m), (shuffle f1,f2,m))
The behaviour of SelectInst on vectors is the same as for
`V'select[i] = Condition[i] ? V'True[i] : V'False[i]`.
If a ShuffleVector is performed on two selects, it will be like:
`V'[mask] = (V'select[i] = Condition[i] ? V'True[i] : V'False[i])`
That's why a ShuffleVector with two SelectInst is equivalent to
first ShuffleVector Condition/True/False and then SelectInst that
result.
This patch implements the transforming described above.
Proof: https://alive2.llvm.org/ce/z/97wfHpFixes#120775
Replace binary of of two reductions with one reduction of the binary op
applied to vectors. For example:
```
%v0_red = tail call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %v0)
%v1_red = tail call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %v1)
%res = add i32 %v0_red, %v1_red
```
gets transformed to:
```
%1 = add <16 x i32> %v0, %v1
%res = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> %1)
```
`foldInsExtVectorToShuffle` function combines the extract/insert of a vector into a vector through a shuffle. However, we only supported coupling between vectors of the same size.
This commit allows combining extract/insert for vectors of the same type but with different sizes by converting the length of the vectors.
Proof: https://alive2.llvm.org/ce/z/ELNLr7
Fixed https://github.com/llvm/llvm-project/issues/120772
If we're interleaving 2 constant splats, for instance `<vscale x 8 x
i32> <splat of 666>` and `<vscale x 8 x i32> <splat of 777>`, we can
create a larger splat `<vscale x 8 x i64> <splat of ((777 << 32) |
666)>` first before casting it back into `<vscale x 16 x i32>`.
Add foldInsExtBinop fold to cleanup missed vectorization cases which can happen on targets with cheap insert/extract instructions which prevent foldExtractExtract (binop(extract(x),extract(y)) -> extract(binop(x,shuffle(y)))) from helping with the merge.
These were based off instruction count, not throughput - we can probably improve these further, but these throughput numbers match the worse expanded shuffles we see in the vector-shuffle-128-v* codegen tests.
If we're just moving a single element around inside a 128-bit lane (probably as an alternative to extracting it), we can assume this is cheap as a single PSRLDQ/PSHUFD/SHUFPS.
I've got the horrid feeling we're moving towards matching all SSE shuffle patterns inside the cost model, but I'm going to do my best to avoid this for now :|
CmpPredicate::getMatching implicitly assumes that both predicates are
integer-predicates, and this has led to a crash being reported in
VectorCombine after e409204 (VectorCombine: teach foldExtractedCmps
about samesign). FP predicates are simple enough to handle as there is
never any samesign information associated with them: hence handle them
in CmpPredicate::getMatching, fixing the VectorCombine crash and
guarding against future incorrect usages.
Follow up on 4a0d53a (PatternMatch: migrate to CmpPredicate) to get rid
of one of the FIXMEs it introduced by replacing a predicate comparison
with CmpPredicate::getMatching.
foldPermuteOfBinops currently requires both binop operands to be oneuse shuffles to fold the shuffles across the binop, but there will be cases where its still profitable to fold across the binop with only one foldable shuffle.
improveShuffleKindFromMask matches this as a SK_InsertSubvector of a v1f32 (which legalises to f32) into a v4f32 base vector, making it easy to recognise. MOVSS is limited to index0.
Avoid always assuming the worst for v4f32 2 input shuffles, and match the SHUFPS pattern where possible - each pair of output elements must come from the same source register.
Now that processShuffleMasks can correctly handle 2 src shuffles, we can completely remove the shuffle kind limits and correctly recognize the number of active subvectors per legalized shuffle - improveShuffleKindFromMask will determine the shuffle kind for each split subvector.
<u,1,u,u> 'inplace' single src shuffles can be treated as free identity shuffles - ignore any shuffle cost (similar to what we already do in other folds like foldShuffleOfShuffles) - eventually getShuffleCost should just return TCC_Free in these cases but in a lot of the targets' shuffle cost logic this currently ends up treated as a generic SK_PermuteSingleSrc.
We still want to generate the shuffle as it will help further shuffle folds with the additional PoisonMaskElem 'undemanded' elements.
Some patterns (in particular horizontal style patterns) can end up with shuffles straddling both sides of a binop/cmp.
Where individually the folds aren't worth it, by merging the (oneuse) shuffles we can notably reduce the net instruction count and cost.
One of the final steps towards finally addressing #34072
As we're reducing the use count of the operands its more likely that they will now fold, as they were previously being prevented by a m_OneUse check, or the cost of retaining the extra instruction had been too high.
This is necessary for some upcoming patches, although the only change so far is instruction ordering as it allows some SSE folds of 256/512-bit with 128-bit subvectors to occur earlier in foldShuffleToIdentity as the subvector concats are free.
Reapplied with a fix for foldSingleElementStore/scalarizeLoadExtract which were replacing/removing memory operations - we need to ensure that the worklist is populated in the correct order so all users of the old memory operations are erased first, so there are no remaining users of the loads when its time to remove them as well.
Pulled out of #120984
scalarizeLoadExtract replaces instructions up the use list, which can result in the vectorcombine worklist adding users back to the worklist when they should really be erased first.
As we're reducing the use count of the operands its more likely that they will now fold, as they were previously being prevented by a m_OneUse check, or the cost of retaining the extra instruction had been too high.
This is necessary for some upcoming patches, although the only change so far is instruction ordering as it allows some SSE folds of 256/512-bit with 128-bit subvectors to occur earlier in foldShuffleToIdentity as the subvector concats are free.
Pulled out of #120984
m_SpecificCmp allowed equivalent predicate+flags which don't necessarily work after being folded from "shuffle (cmpop), (cmpop)" into "cmpop (shuffle), (shuffle)"
Fixes#121110
We already canonicalized an undef base vector to the RHS to improve further folding, this extends this to improve the shuffle cost estimate of the single src shuffle
foldShuffleOfShuffles currently only folds unary shuffles to ensure we don't end up with a merged shuffle with more than 2 sources, but this prevented cases where both shuffles were sharing sources.
This patch generalizes the merge process to find up to 2 sources as it merges with the inner shuffles, it also moves the undef/poison handling stages into the merge loop as well.
Fixes#120764
This fixes some regressions from recent changes to vector combine in
#120216. It allows shuffleToIdentity to look through fp casts as other
casts, and makes sure mismatching vector types in splats and casts do
not block the transform, as only the lanes should matter.
insertelt DestVec, (fneg (extractelt SrcVec, Index)), Index
-> shuffle DestVec, (shuffle (fneg SrcVec), poison, SrcMask), Mask
Original combining left the combine between vectors of different lengths as a TODO. this commit do that. (see
#[baab4aa1ba])
processShuffleMasks can now correctly handle 2 src shuffles, so we can use the existing SK_PermuteSingleSrc splitting cost logic to handle SK_PermuteTwoSrc as well and correctly recognise the number of active subvectors per legalised shuffle.
processShuffleMasks can now correctly handle 2 src shuffles, so we can use the existing SK_PermuteSingleSrc splitting cost logic to handle SK_PermuteTwoSrc as well and correctly recognise the number of active subvectors per legalised shuffle.
insertelt DestVec, (fneg (extractelt SrcVec, Index)), Index
-> shuffle DestVec, (shuffle (fneg SrcVec), poison, SrcMask), Mask
Original combining left the combine between vectors of different lengths as a TODO.
We don't fold "shuffle (binop), (binop)" -> "binop (shuffle), (shuffle)" if the old/new costs are equal, but we can relax this if either new shuffle will constant fold as it will reduce instruction count.
