Index: lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -2192,10 +2192,24 @@
           // If all users are going to be vectorized, instruction can be
           // considered as dead.
           // The same, if have only one user, it will be vectorized for sure.
-          if (areAllUsersVectorized(E))
+          if (areAllUsersVectorized(E)) {
             // Take credit for instruction that will become dead.
+            if (E->hasOneUse()) {
+              Instruction *Ext = E->user_back();
+              if (isa<SExtInst>(Ext) || isa<ZExtInst>(Ext)) {
+                // Use getExtractWithExtendCost() to calculate the cost of 
+                // extractelement/ext pair.
+                DeadCost -= TTI->getExtractWithExtendCost(
+                    Ext->getOpcode(), Ext->getType(), VecTy, i);
+                // Add back the cost of s|zext which is subtracted seperately.
+                DeadCost += TTI->getCastInstrCost(
+                    Ext->getOpcode(), Ext->getType(), E->getType(), Ext);
+                continue;
+              }
+            }
             DeadCost -=
                 TTI->getVectorInstrCost(Instruction::ExtractElement, VecTy, i);
+          }
         }
         return DeadCost;
       }
Index: test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
===================================================================
--- test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
+++ test/Transforms/SLPVectorizer/AArch64/ext-trunc.ll
@@ -1,5 +1,5 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -S -slp-vectorizer -mtriple=aarch64--linux-gnu -instcombine < %s | FileCheck %s
+; RUN: opt -S -slp-vectorizer -mtriple=aarch64--linux-gnu < %s | FileCheck %s
 
 target datalayout = "e-m:e-i32:64-i128:128-n32:64-S128"
 
@@ -11,23 +11,23 @@
 ; 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:    [[SUB0:%.*]] = sub <4 x i32> [[Z0]], [[Z1]]
+; CHECK-NEXT:    [[E0:%.*]] = extractelement <4 x i32> [[SUB0]], i32 0
+; CHECK-NEXT:    [[S0:%.*]] = sext i32 [[E0]] to i64
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr inbounds i64, i64* [[P:%.*]], i64 [[S0]]
+; CHECK-NEXT:    [[LOAD0:%.*]] = load i64, i64* [[GEP0]]
+; CHECK-NEXT:    [[E1:%.*]] = extractelement <4 x i32> [[SUB0]], i32 1
+; CHECK-NEXT:    [[S1:%.*]] = sext i32 [[E1]] to i64
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[S1]]
+; CHECK-NEXT:    [[LOAD1:%.*]] = load i64, i64* [[GEP1]]
+; CHECK-NEXT:    [[E2:%.*]] = extractelement <4 x i32> [[SUB0]], i32 2
+; CHECK-NEXT:    [[S2:%.*]] = sext i32 [[E2]] to i64
+; CHECK-NEXT:    [[GEP2:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[S2]]
+; CHECK-NEXT:    [[LOAD2:%.*]] = load i64, i64* [[GEP2]]
+; CHECK-NEXT:    [[E3:%.*]] = extractelement <4 x i32> [[SUB0]], i32 3
+; CHECK-NEXT:    [[S3:%.*]] = sext i32 [[E3]] to i64
+; CHECK-NEXT:    [[GEP3:%.*]] = getelementptr inbounds i64, i64* [[P]], i64 [[S3]]
+; CHECK-NEXT:    [[LOAD3:%.*]] = load i64, i64* [[GEP3]]
 ; CHECK-NEXT:    call void @foo(i64 [[LOAD0]], i64 [[LOAD1]], i64 [[LOAD2]], i64 [[LOAD3]])
 ; CHECK-NEXT:    ret void
 ;