[SLP]Move resulting vector before inert point, if the late generated buildvector fully matched

If the perfect diamond match was detected for the postponed buildvectors
and the vector for the previous node comes after the current node, need
to move the vector register before the current inserting point to
prevent compiler crash.

Fixes llvm#119002

Author: alexey-bataev

llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp

@@ -16215,6 +16215,11 @@ BoUpSLP::vectorizeTree(const ExtraValueToDebugLocsMap &ExternallyUsedValues,
     }
     Builder.SetCurrentDebugLocation(UserI->getDebugLoc());
     Value *Vec = vectorizeTree(TE, /*PostponedPHIs=*/false);
+    if (auto *VecI = dyn_cast<Instruction>(Vec);
+        VecI && VecI->getParent() == Builder.GetInsertBlock() &&
+        Builder.GetInsertPoint()->comesBefore(VecI))
+      VecI->moveBeforePreserving(*Builder.GetInsertBlock(),
+                                 Builder.GetInsertPoint());
     if (Vec->getType() != PrevVec->getType()) {
       assert(Vec->getType()->isIntOrIntVectorTy() &&
              PrevVec->getType()->isIntOrIntVectorTy() &&

llvm/test/Transforms/SLPVectorizer/X86/perfect-matched-reused-bv.ll

@@ -0,0 +1,42 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
+; RUN: opt -S --passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu -mattr=+avx512f < %s | FileCheck %s
+
+define void @test() {
+; CHECK-LABEL: define void @test(
+; CHECK-SAME: ) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[BB:.*]]:
+; CHECK-NEXT:    br label %[[BB1:.*]]
+; CHECK:       [[BB1]]:
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i32> [ zeroinitializer, %[[BB]] ], [ [[TMP4:%.*]], %[[BB4:.*]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = or <2 x i32> [[TMP0]], zeroinitializer
+; CHECK-NEXT:    br i1 false, label %[[BB7:.*]], label %[[BB4]]
+; CHECK:       [[BB4]]:
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <2 x i32> [[TMP0]], <2 x i32> <i32 0, i32 poison>, <2 x i32> <i32 2, i32 1>
+; CHECK-NEXT:    [[TMP3:%.*]] = add <2 x i32> zeroinitializer, [[TMP2]]
+; CHECK-NEXT:    [[TMP4]] = add <2 x i32> zeroinitializer, [[TMP2]]
+; CHECK-NEXT:    br i1 false, label %[[BB7]], label %[[BB1]]
+; CHECK:       [[BB7]]:
+; CHECK-NEXT:    [[TMP5:%.*]] = phi <2 x i32> [ [[TMP1]], %[[BB1]] ], [ [[TMP3]], %[[BB4]] ]
+; CHECK-NEXT:    ret void
+;
+bb:
+  br label %bb1
+
+bb1:
+  %phi = phi i32 [ 0, %bb ], [ %add6, %bb4 ]
+  %phi2 = phi i32 [ 0, %bb ], [ %add, %bb4 ]
+  %or = or i32 %phi2, 0
+  %or3 = or i32 %phi, 0
+  br i1 false, label %bb7, label %bb4
+
+bb4:
+  %add = add i32 0, 0
+  %add5 = add i32 0, 0
+  %add6 = add i32 %phi, 0
+  br i1 false, label %bb7, label %bb1
+
+bb7:
+  %phi8 = phi i32 [ %or, %bb1 ], [ %add5, %bb4 ]
+  %phi9 = phi i32 [ %or3, %bb1 ], [ %add6, %bb4 ]
+  ret void
+}