This patch fixes a bug in `DependencyGraph::extend()` when the old
interval contains no memory instructions. When this is the case we
should do a full dependency scan of the new interval.
When the operand comes from multiple inputs then we need additional
packing code. When the operands are scalar then we can use a single
InsertElementInst. But when the operands are vectors then we need a
chain of ExtractElementInst and InsertElementInst instructions to insert
the vector value into the destination vector. This is what this patch
implements.
This patch fixes a bug in the creation of shuffle masks when vectorizing
vectors in case of a diamond reuse with shuffle. The mask needs to
enumerate all elements of a vector, not treat the original vector value
as a single element. That is: if vectorizing two <2 x float> vectors
into a <4 x float> the mask needs to have 4 indices, not just 2.
This patch fixes the way the top-of-schedule variable gets set and
updated. Before this patch it used to get updated whenever we scheduled
a bundle, which is wrong, as the top-of-schedule needs to be maintained
across scheduling attempts.
It should get reset only when we clear the schedule or when we destroy
the current schedule and re-schedule.
We call collectInLoopReductions in multiple places asking
the same question with exactly the same answer. For
example, this was being called from a loop in
calculateRegisterUsage and this patch hoists the call out
to above the loop. In addition I've changed
collectInLoopReductions so that it bails out if we've
already built up a list.
When building the reorder for non-single use reuse mask, need to check
if the size of the mask is multiple of the number of unique scalars.
Otherwise, the compiler may crash when trying to reorder nodes.
Fixes#126304
Update getOrCreateVPValueForSCEVExpr to only skip expansion of
SCEVUnknown if the underlying value isn't an instruction. Instructions
may be defined in a loop and using them without expansion may break
LCSSA form. SCEVExpander will take care of preserving LCSSA if needed.
We could also try to pass LoopInfo, but there are some users of the
function where it won't be available and main benefit from skipping
expansion is slightly more concise VPlans.
Note that SCEVExpander is now used to expand SCEVUnknown with floats.
Adjust the check in expandCodeFor to only check the types and casts if
the type of the value is different to the requested type. Otherwise we
crash when trying to expand a float and requesting a float type.
Fixes https://github.com/llvm/llvm-project/issues/121518.
PR: https://github.com/llvm/llvm-project/pull/125235
`forgetLcssaPhiWithNewPredecessor` performs additional invalidation if
there is an existing SCEV for the phi, but earlier
`forgetBlockAndLoopDispositions` or `forgetLoop` may already invalidate
the SCEV for the phi.
Change the order to first call `forgetLcssaPhiWithNewPredecessor` to
ensure it runs before its SCEV gets invalidated too eagerly.
Fixes https://github.com/llvm/llvm-project/issues/119665.
PR: https://github.com/llvm/llvm-project/pull/119897
This patch adds a new loop to LoopIdiomVectorizePass, enabling it to
recognise and vectorise loops such as:
```cpp
template<class InputIt, class ForwardIt>
InputIt find_first_of(InputIt first, InputIt last,
ForwardIt s_first, ForwardIt s_last)
{
for (; first != last; ++first)
for (ForwardIt it = s_first; it != s_last; ++it)
if (*first == *it)
return first;
return last;
}
```
These loops match the C++ standard library function `std::find_first_of`.
This patch relands the changes from "[LV]: Teach LV to recursively
(de)interleave.#122989"
Reason for revert:
- The patch exposed an assert in the vectorizer related to VF difference
between
legacy cost model and VPlan-based cost model because of uncalculated
cost for
VPInstruction which is created by VPlanTransforms as a replacement to
'or disjoint'
instruction.
VPlanTransforms do that instructions change when there are memory
interleaving and
predicated blocks, but that change didn't cause problems because at most
cases the cost
difference between legacy/new models is not noticeable.
- Issue is fixed by #125434
Original patch: https://github.com/llvm/llvm-project/pull/89018
Reviewed-by: paulwalker-arm, Mel-Chen
Follow-up as discussed when using VPInstruction::ResumePhi for all resume
values (#112147). This patch explicitly adds incoming values for each
predecessor in VPlan. This simplifies codegen and allows transformations
adjusting the predecessors of blocks with
NFC modulo incoming block order in phis.
The TransactionAcceptOrRevert pass is the final pass in the Sandbox
Vectorizer's default pass pipeline. It's job is to check the cost
before/after vectorization and accept or revert the IR to its original
state.
Since we are now starting the transaction in BottomUpVec, tests that run
a custom pipeline need to accept the transaction. This is done with the
help of the TransactionAlwaysAccept pass (tr-accept).
Run recipe simplification and dead recipe removal after VPlan-based
unrolling and optimizeForVFAndUF, to clean up any redundant or dead
recipes introduced by them. Currently this is NFC, as it removes the
corresponding removeDeadRecipes run in optimizeForVFAndUF and no
additional simplifications kick in after unrolling yet. That is changing
with https://github.com/llvm/llvm-project/pull/123655.
Note that with this change, pattern-matching is now applied after
EVL-based recipes have been introduced.
Trying to match VPWidenEVLRecipe when not explicitly requested might
apply a pattern with 2 operands to one with 3 due to the extra EVL
operand and VPWidenEVLRecipe being a subclass of VPWidenRecipe.
To prevent this, update Recipe_match::match to only match
VPWidenEVLRecipe if it is in the requested recipe types (RecipeTy).
PR: https://github.com/llvm/llvm-project/pull/125926
Consistently use hasScalarVFOnly instead of using
hasVF(ElementCount::getFixed(1)). Also add an assert to ensure all cases
are covered by hasScalarVFOnly.
The legacy and vplan cost models did not agree because
VPWidenCallRecipe::computeCost only calculates the cost of the
call instruction, whereas
LoopVectorizationCostModel::setVectorizedCallDecision in some
cases adds on the cost of a synthesised mask argument. However,
this mask is always 'splat(i1 true)' which should be hoisted out
of the loop during codegen. In order to synchronise the two cost
models I have two options:
1) Also add the cost of the splat to the vplan model, or
2) Remove the cost of the splat from the legacy model.
I chose 2) because I feel this more closely represents what the
final code will look like. There is an argument that we should
take account of such broadcast costs in the preheader when
deciding if it's profitable to vectorise a loop, however there
isn't currently a mechanism to do this. We currently only take
account of the runtime checks when assessing profitability and
what the minimum trip count should be. However, I don't believe
this work needs doing as part of this PR.
The current legality check for folding with EVL has incomplete
verification for VF.
This patch fixes the VF check, ensuring that tail folding with EVL is
enabled only when a scalable VF is available. This allows loops that
prefer tail folding with EVL but cannot use scalable VF vectorization to
still be vectorized using a fixed VF, rather than abandoning
vectorization entirely.
This is extracted from #118638
After c7ebe4f we will crash in fixNonInductionPHIs if we use a
VPWidenPHIRecipe with the vector preheader as an incoming block, because
the phi will reference the old non-IRBB vector preheader.
This fixes this by updating VPBlockUtils::reassociateBlocks to update
any VPWidenPHIRecipes's incoming blocks.
This assumes that if the VPWidenPHIRecipe is in a VPRegionBlock, it's in
the entry block, and that we are replacing a VPBasicBlock with another
VPBasicBlock.
This patch implements the vectorizer's callback for getting notified
about new instructions being created. This updates the scheduler state,
which may involve removing dependent instructions from the ready list
and update the "scheduled" flag.
Since we need to remove elements from the ready list, this patch also
implements the `remove()` operation.
This patch fixes a bug in the dependency node iterators that would
incorrectly not skip nodes that are not in the current DAG. This
resulted in iterators returning nullptr when dereferenced.
The fix is to update the existing "skip" function to not only skip
non-instruction values but also to skip instructions not in the DAG.
`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
This patch adds an initial implementation of
VPInstruction::computeCost with support for only one
instruction so far - VPInstruction::AnyOf. This is only
used when vectorising loops with uncountable early exits.
The plans with scalar VF should not be transformed the plans folded by
EVL.
TODO: Move the scalar VF checking into `LoopVectorizationCostModel
::foldTailWithEVL()`.
If the calls won't be vectorized, but will be scalarized after
vectorization, they should be build as buildvector nodes, not vector
nodes. Vectorization of such calls leads to incorrect cost estimation,
does not allow to calculate correctly spills costs.
Reviewers: lukel97, preames
Reviewed By: preames
Pull Request: https://github.com/llvm/llvm-project/pull/125070
Better to use TTI::getScalarizationOverhead instead of
TTI::getVectorInstrCost to correctly calculate the costs of
buildvectors/extracts.
Reviewers: RKSimon
Reviewed By: RKSimon
Pull Request: https://github.com/llvm/llvm-project/pull/125725
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>`.
SelectInsts need special treatment because they are not always
straightforward to vectorize. This patch disables vectorization unless
they are trivially vectorizable.
We were only constructing the IntrinsicCostAttributes with the arg type info, and not the args themselves, preventing more detailed cost analysis (constant / uniform args etc.)
Just pass the whole IntrinsicInst to the constructor and let it resolve everything it can.
Noticed while having yet another attempt at #63980
Reapplied cleanup now that #125223 and #124984 have landed.
We currently call getVScaleForTuning in many places, doing a
lot of work asking the same question with the same answer.
I've refactored the code to cache the value if the max
scalable VF != 0 and pull out the cached value from
LoopVectorizationCostModel.
Nothing in VPlan.h directly depends on VPTransformState, VPCostContext,
VPFRange, VPlanPrinter or VPSlotTracker. Move them out to a separate
header to reduce the size of widely used VPlan.h.
This is a first step towards more cleanly separating declarations in
VPlan.
Besides reducing VPlan.h's size, this also allows including additional
VPlan-related headers in VPlanHelpers.h for use there. An example is
using VPDominatorTree in VPTransformState
(https://github.com/llvm/llvm-project/pull/117138).
PR: https://github.com/llvm/llvm-project/pull/124104
