[SLP]Better decision making on whether to try stores packs for vectorization

Since the stores are sorted by distance, comparing the indices in the
original array and early exit, if the index is less than the index of
the last store, not always the best strategy. Better to remove such
stores explicitly to try better to check for the vectorization
opportunity.

Fixes #115008

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -18515,25 +18515,30 @@ bool SLPVectorizerPass::vectorizeStores(
       }
       // Try to vectorize the first found set to avoid duplicate analysis.
       TryToVectorize(Set.second);
+      unsigned ItIdx = It->first;
+      int ItDist = It->second;
       StoreIndexToDistSet PrevSet;
-      PrevSet.swap(Set.second);
+      copy_if(Set.second, std::inserter(PrevSet, PrevSet.end()),
+              [&](const std::pair<unsigned, int> &Pair) {
+                return Pair.first > ItIdx;
+              });
+      Set.second.clear();
       Set.first = Idx;
       Set.second.emplace(Idx, 0);
       // Insert stores that followed previous match to try to vectorize them
       // with this store.
-      unsigned StartIdx = It->first + 1;
+      unsigned StartIdx = ItIdx + 1;
       SmallBitVector UsedStores(Idx - StartIdx);
       // Distances to previously found dup store (or this store, since they
       // store to the same addresses).
       SmallVector<int> Dists(Idx - StartIdx, 0);
       for (const std::pair<unsigned, int> &Pair : reverse(PrevSet)) {
         // Do not try to vectorize sequences, we already tried.
-        if (Pair.first <= It->first ||
-            VectorizedStores.contains(Stores[Pair.first]))
+        if (VectorizedStores.contains(Stores[Pair.first]))
           break;
         unsigned BI = Pair.first - StartIdx;
         UsedStores.set(BI);
-        Dists[BI] = Pair.second - It->second;
+        Dists[BI] = Pair.second - ItDist;
       }
       for (unsigned I = StartIdx; I < Idx; ++I) {
         unsigned BI = I - StartIdx;

llvm/test/Transforms/SLPVectorizer/RISCV/repeated-address-store.ll

@@ -6,12 +6,7 @@ define void @test(ptr %dest) {
 ; CHECK-SAME: ptr [[DEST:%.*]]) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
 ; CHECK-NEXT:    [[INC3:%.*]] = getelementptr inbounds i32, ptr [[DEST]], i64 3
-; CHECK-NEXT:    store i32 1, ptr [[INC3]], align 2
-; CHECK-NEXT:    store i32 1, ptr [[DEST]], align 4
-; CHECK-NEXT:    [[INC1:%.*]] = getelementptr inbounds i32, ptr [[DEST]], i64 1
-; CHECK-NEXT:    store i32 1, ptr [[INC1]], align 2
-; CHECK-NEXT:    [[INC2:%.*]] = getelementptr inbounds i32, ptr [[DEST]], i64 2
-; CHECK-NEXT:    store i32 1, ptr [[INC2]], align 2
+; CHECK-NEXT:    store <4 x i32> splat (i32 1), ptr [[DEST]], align 4
 ; CHECK-NEXT:    store i32 2, ptr [[DEST]], align 2
 ; CHECK-NEXT:    store i32 1, ptr [[INC3]], align 2
 ; CHECK-NEXT:    ret void