Skip to content

[SLP] Cluster SortedBases before sorting. #101144

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Jul 30, 2024
Merged

[SLP] Cluster SortedBases before sorting. #101144

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
62f69dc
[SLP] Cluster SortedBases before sorting.
davemgreen Jul 30, 2024
2900800
Compute LessThan by walking up gep chains
davemgreen Jul 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
50 changes: 34 additions & 16 deletions llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4843,25 +4843,43 @@ static bool clusterSortPtrAccesses(ArrayRef<Value *> VL, Type *ElemTy,
return false;

// If we have a better order, also sort the base pointers by increasing
// (variable) values if possible, to try and keep the order more regular.
SmallVector<std::pair<Value *, Value *>> SortedBases;
for (auto &Base : Bases)
SortedBases.emplace_back(Base.first,
Base.first->stripInBoundsConstantOffsets());
llvm::stable_sort(SortedBases, [](std::pair<Value *, Value *> V1,
std::pair<Value *, Value *> V2) {
const Value *V = V2.second;
while (auto *Gep = dyn_cast<GetElementPtrInst>(V)) {
if (Gep->getOperand(0) == V1.second)
return true;
V = Gep->getOperand(0);
}
return false;
});
// (variable) values if possible, to try and keep the order more regular. In
// order to create a valid strict-weak order we cluster by the Root of gep
// chains and sort within each.
SmallVector<std::tuple<Value *, Value *, Value *>> SortedBases;
for (auto &Base : Bases) {
Value *Strip = Base.first->stripInBoundsConstantOffsets();
Value *Root = Strip;
while (auto *Gep = dyn_cast<GetElementPtrInst>(Root))
Root = Gep->getOperand(0);
SortedBases.emplace_back(Base.first, Strip, Root);
}
auto *Begin = SortedBases.begin();
auto *End = SortedBases.end();
while (Begin != End) {
Value *Root = std::get<2>(*Begin);
auto *Mid = std::stable_partition(
Begin, End, [&Root](auto V) { return std::get<2>(V) == Root; });
DenseMap<Value *, DenseMap<Value *, bool>> LessThan;
for (auto I = Begin; I < Mid; ++I)
LessThan.try_emplace(std::get<1>(*I));
for (auto I = Begin; I < Mid; ++I) {
Value *V = std::get<1>(*I);
while (auto *Gep = dyn_cast<GetElementPtrInst>(V)) {
V = Gep->getOperand(0);
if (LessThan.contains(V))
LessThan[V][std::get<1>(*I)] = true;
}
}
std::stable_sort(Begin, Mid, [&LessThan](auto &V1, auto &V2) {
return LessThan[std::get<1>(V1)][std::get<1>(V2)];
});
Begin = Mid;
}

// Collect the final order of sorted indices
for (auto Base : SortedBases)
for (auto &T : Bases[Base.first])
for (auto &T : Bases[std::get<0>(Base)])
SortedIndices.push_back(std::get<2>(T));

assert(SortedIndices.size() == VL.size() &&
Expand Down
8 changes: 4 additions & 4 deletions llvm/test/Transforms/SLPVectorizer/AArch64/loadorder.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -428,14 +428,14 @@ define i32 @reduce_blockstrided4x4(ptr nocapture noundef readonly %p1, i32 nound
; CHECK-NEXT: [[TMP5:%.*]] = load <4 x i8>, ptr [[ADD_PTR64]], align 1
; CHECK-NEXT: [[TMP6:%.*]] = load <4 x i8>, ptr [[ARRAYIDX3_1]], align 1
; CHECK-NEXT: [[TMP7:%.*]] = load <4 x i8>, ptr [[ARRAYIDX5_1]], align 1
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i8> [[TMP0]], <4 x i8> [[TMP1]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x i8> [[TMP4]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP8:%.*]] = shufflevector <4 x i8> [[TMP0]], <4 x i8> [[TMP4]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <16 x i8> [[TMP8]], <16 x i8> [[TMP9]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP11:%.*]] = shufflevector <4 x i8> [[TMP5]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <16 x i8> [[TMP10]], <16 x i8> [[TMP11]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
; CHECK-NEXT: [[TMP13:%.*]] = zext <16 x i8> [[TMP12]] to <16 x i32>
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <4 x i8> [[TMP2]], <4 x i8> [[TMP3]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <4 x i8> [[TMP6]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP14:%.*]] = shufflevector <4 x i8> [[TMP2]], <4 x i8> [[TMP6]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP15:%.*]] = shufflevector <4 x i8> [[TMP3]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP16:%.*]] = shufflevector <16 x i8> [[TMP14]], <16 x i8> [[TMP15]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP17:%.*]] = shufflevector <4 x i8> [[TMP7]], <4 x i8> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <16 x i8> [[TMP16]], <16 x i8> [[TMP17]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 16, i32 17, i32 18, i32 19>
Expand Down
Loading