[SLP]Fix PR108421: Correctly deduce VF from the masks

Need to select the max of CommonMask and V1 Mask size to correctly
perform reshuffling of the vectors, otherwise incorrect result is
generated.

Fixes llvm#108421

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -12486,11 +12486,12 @@ class BoUpSLP::ShuffleInstructionBuilder final : public BaseShuffleAnalysis {
           V = createShuffle(InVectors.front(), nullptr, CommonMask);
           transformMaskAfterShuffle(CommonMask, CommonMask);
         }
+        unsigned VF = std::max(CommonMask.size(), Mask.size());
         for (unsigned Idx = 0, Sz = CommonMask.size(); Idx < Sz; ++Idx)
           if (CommonMask[Idx] == PoisonMaskElem && Mask[Idx] != PoisonMaskElem)
             CommonMask[Idx] =
                 V->getType() != V1->getType()
-                    ? Idx + Sz
+                    ? Idx + VF
                     : Mask[Idx] + cast<FixedVectorType>(V1->getType())
                                       ->getNumElements();
         if (V->getType() != V1->getType())

llvm/test/Transforms/SLPVectorizer/X86/multi-extracts-bv-combined.ll

@@ -6,7 +6,7 @@ define i32 @foo() {
 ; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
 ; CHECK-NEXT:    [[D:%.*]] = load i32, ptr null, align 4
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> <i32 0, i32 undef, i32 1, i32 undef>, i32 [[D]], i32 1
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x i32> <i32 0, i32 undef, i32 1, i32 0>, i32 [[D]], i32 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <4 x i32> [[TMP0]], <4 x i32> poison, <8 x i32> <i32 0, i32 1, i32 1, i32 2, i32 3, i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    [[TMP2:%.*]] = or <8 x i32> zeroinitializer, [[TMP1]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = add <8 x i32> zeroinitializer, [[TMP1]]