Index: lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -4301,24 +4301,9 @@
   // additional roots that require investigating in Roots.
   SmallVector<Value *, 32> ToDemote;
   SmallVector<Value *, 4> Roots;
-  for (auto *Root : TreeRoot) {
-    // Do not include top zext/sext/trunc operations to those to be demoted, it
-    // produces noise cast<vect>, trunc <vect>, exctract <vect>, cast <extract>
-    // sequence.
-    if (isa<Constant>(Root))
-      continue;
-    auto *I = dyn_cast<Instruction>(Root);
-    if (!I || !I->hasOneUse() || !Expr.count(I))
-      return;
-    if (isa<ZExtInst>(I) || isa<SExtInst>(I))
-      continue;
-    if (auto *TI = dyn_cast<TruncInst>(I)) {
-      Roots.push_back(TI->getOperand(0));
-      continue;
-    }
+  for (auto *Root : TreeRoot)
     if (!collectValuesToDemote(Root, Expr, ToDemote, Roots))
       return;
-  }
 
   // The maximum bit width required to represent all the values that can be
   // demoted without loss of precision. It would be safe to truncate the roots
@@ -4347,7 +4332,10 @@
   // We start by looking at each entry that can be demoted. We compute the
   // maximum bit width required to store the scalar by using ValueTracking to
   // compute the number of high-order bits we can truncate.
-  if (MaxBitWidth == DL->getTypeSizeInBits(TreeRoot[0]->getType())) {
+  if (MaxBitWidth == DL->getTypeSizeInBits(TreeRoot[0]->getType()) &&
+      llvm::all_of(TreeRoot, [](Value *R) {
+        return isa<GetElementPtrInst>(*R->user_begin());
+      })) {
     MaxBitWidth = 8u;
 
     // Determine if the sign bit of all the roots is known to be zero. If not,
Index: test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
===================================================================
--- /dev/null
+++ test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
@@ -0,0 +1,56 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -S -slp-vectorizer -mtriple=aarch64--linux-gnu -instcombine < %s | FileCheck %s
+
+target datalayout = "e-m:e-i32:64-i128:128-n32:64-S128"
+
+declare void @foo(i64, i64, i64, i64)
+
+define void @test(<4 x i16> %a, <4 x i16> %b, i64* %p) {
+; Make sure types of sub and its sources are not extended.
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[Z0:%.*]] = zext <4 x i16> [[A:%.*]] to <4 x i32>
+; CHECK-NEXT:    [[Z1:%.*]] = zext <4 x i16> [[B:%.*]] to <4 x i32>
+; CHECK-NEXT:    [[SUB0:%.*]] = sub nsw <4 x i32> [[Z0]], [[Z1]]
+; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <4 x i32> [[SUB0]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = sext i32 [[TMP0]] to i64
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds i64, i64* [[P:%.*]], i64 [[TMP1]]
+; CHECK-NEXT:    [[LOAD0:%.*]] = load i64, i64* [[GEP0]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[SUB0]], i32 1
+; CHECK-NEXT:    [[TMP3:%.*]] = sext i32 [[TMP2]] to i64
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP3]]
+; CHECK-NEXT:    [[LOAD1:%.*]] = load i64, i64* [[GEP1]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x i32> [[SUB0]], i32 2
+; CHECK-NEXT:    [[TMP5:%.*]] = sext i32 [[TMP4]] to i64
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP5]]
+; CHECK-NEXT:    [[LOAD2:%.*]] = load i64, i64* [[GEP2]], align 4
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i32> [[SUB0]], i32 3
+; CHECK-NEXT:    [[TMP7:%.*]] = sext i32 [[TMP6]] to i64
+; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[TMP7]]
+; CHECK-NEXT:    [[LOAD3:%.*]] = load i64, i64* [[GEP3]], align 4
+; CHECK-NEXT:    call void @foo(i64 [[LOAD0]], i64 [[LOAD1]], i64 [[LOAD2]], i64 [[LOAD3]])
+; CHECK-NEXT:    ret void
+;
+entry:
+  %z0 = zext <4 x i16> %a to <4 x i32>
+  %z1 = zext <4 x i16> %b to <4 x i32>
+  %sub0 = sub <4 x i32> %z0, %z1
+  %e0 = extractelement <4 x i32> %sub0, i32 0
+  %s0 = sext i32 %e0 to i64
+  %gep0 = getelementptr inbounds i64, i64* %p, i64 %s0
+  %load0 = load i64, i64* %gep0
+  %e1 = extractelement <4 x i32> %sub0, i32 1
+  %s1 = sext i32 %e1 to i64
+  %gep1 = getelementptr inbounds i64, i64* %p, i64 %s1
+  %load1 = load i64, i64* %gep1
+  %e2 = extractelement <4 x i32> %sub0, i32 2
+  %s2 = sext i32 %e2 to i64
+  %gep2 = getelementptr inbounds i64, i64* %p, i64 %s2
+  %load2 = load i64, i64* %gep2
+  %e3 = extractelement <4 x i32> %sub0, i32 3
+  %s3 = sext i32 %e3 to i64
+  %gep3 = getelementptr inbounds i64, i64* %p, i64 %s3
+  %load3 = load i64, i64* %gep3
+  call void @foo(i64 %load0, i64 %load1, i64 %load2, i64 %load3)
+  ret void
+}