diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1417,7 +1417,11 @@
           HashMap[NumFreeOpsHash.Hash] = std::make_pair(1, Lane);
         } else if (NumFreeOpsHash.NumOfAPOs == Min &&
                    NumFreeOpsHash.NumOpsWithSameOpcodeParent == SameOpNumber) {
-          ++HashMap[NumFreeOpsHash.Hash].first;
+          auto It = HashMap.find(NumFreeOpsHash.Hash);
+          if (It == HashMap.end())
+            HashMap[NumFreeOpsHash.Hash] = std::make_pair(1, Lane);
+          else
+            ++It->second.first;
         }
       }
       // Select the lane with the minimum counter.
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/transpose-inseltpoison.ll
@@ -68,10 +68,11 @@
 ; CHECK-LABEL: @build_vec_v4i32(
 ; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i32> [[V0:%.*]], [[V1:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = sub <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 3, i32 6>
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 3, i32 6>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
 ; CHECK-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
-; CHECK-NEXT:    ret <4 x i32> [[TMP5]]
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 1, i32 0, i32 2, i32 3>
+; CHECK-NEXT:    ret <4 x i32> [[TMP6]]
 ;
   %v0.0 = extractelement <4 x i32> %v0, i32 0
   %v0.1 = extractelement <4 x i32> %v0, i32 1
@@ -207,8 +208,8 @@
 ; CHECK-LABEL: @reduction_v4i32(
 ; CHECK-NEXT:    [[TMP1:%.*]] = sub <4 x i32> [[V0:%.*]], [[V1:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = add <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 7, i32 2>
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 7, i32 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
 ; CHECK-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = lshr <4 x i32> [[TMP5]], <i32 15, i32 15, i32 15, i32 15>
 ; CHECK-NEXT:    [[TMP7:%.*]] = and <4 x i32> [[TMP6]], <i32 65537, i32 65537, i32 65537, i32 65537>
diff --git a/llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll b/llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
--- a/llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
+++ b/llvm/test/Transforms/SLPVectorizer/AArch64/transpose.ll
@@ -68,10 +68,11 @@
 ; CHECK-LABEL: @build_vec_v4i32(
 ; CHECK-NEXT:    [[TMP1:%.*]] = add <4 x i32> [[V0:%.*]], [[V1:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = sub <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 3, i32 6>
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 3, i32 6>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
 ; CHECK-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
-; CHECK-NEXT:    ret <4 x i32> [[TMP5]]
+; CHECK-NEXT:    [[TMP6:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> poison, <4 x i32> <i32 1, i32 0, i32 2, i32 3>
+; CHECK-NEXT:    ret <4 x i32> [[TMP6]]
 ;
   %v0.0 = extractelement <4 x i32> %v0, i32 0
   %v0.1 = extractelement <4 x i32> %v0, i32 1
@@ -207,8 +208,8 @@
 ; CHECK-LABEL: @reduction_v4i32(
 ; CHECK-NEXT:    [[TMP1:%.*]] = sub <4 x i32> [[V0:%.*]], [[V1:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = add <4 x i32> [[V0]], [[V1]]
-; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 1, i32 4, i32 7, i32 2>
-; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 0, i32 5, i32 6, i32 3>
+; CHECK-NEXT:    [[TMP3:%.*]] = shufflevector <4 x i32> [[TMP1]], <4 x i32> [[TMP2]], <4 x i32> <i32 5, i32 0, i32 7, i32 2>
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32> [[TMP2]], <4 x i32> [[TMP1]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
 ; CHECK-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], [[TMP3]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = lshr <4 x i32> [[TMP5]], <i32 15, i32 15, i32 15, i32 15>
 ; CHECK-NEXT:    [[TMP7:%.*]] = and <4 x i32> [[TMP6]], <i32 65537, i32 65537, i32 65537, i32 65537>
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/insert-shuffle.ll b/llvm/test/Transforms/SLPVectorizer/X86/insert-shuffle.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/insert-shuffle.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/insert-shuffle.ll
@@ -17,7 +17,7 @@
 ; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x float> [[TMP4]], float [[TMP3]], i32 1
 ; CHECK-NEXT:    [[SHUFFLE1:%.*]] = shufflevector <4 x float> [[TMP5]], <4 x float> poison, <4 x i32> <i32 0, i32 undef, i32 1, i32 undef>
 ; CHECK-NEXT:    [[TMP6:%.*]] = fmul <4 x float> [[SHUFFLE]], [[SHUFFLE1]]
-; CHECK-NEXT:    [[TMP7:%.*]] = fadd <4 x float> poison, [[TMP6]]
+; CHECK-NEXT:    [[TMP7:%.*]] = fadd <4 x float> [[TMP6]], poison
 ; CHECK-NEXT:    [[TMP8:%.*]] = fadd <4 x float> [[TMP7]], poison
 ; CHECK-NEXT:    [[TMP9:%.*]] = fadd <4 x float> [[TMP8]], poison
 ; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <4 x float> [[TMP9]], i32 0
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll b/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/matched-shuffled-entries.ll
@@ -16,24 +16,23 @@
 ; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <16 x i32> [[TMP2]], i32 [[ADD78_1]], i32 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = insertelement <16 x i32> [[TMP3]], i32 [[SUB86_1]], i32 4
 ; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <16 x i32> [[TMP4]], i32 [[ADD78_2]], i32 5
-; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> poison, <16 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 3, i32 4, i32 undef, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <16 x i32> [[TMP5]], <16 x i32> poison, <16 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 2, i32 3, i32 4, i32 5, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
 ; CHECK-NEXT:    [[TMP6:%.*]] = insertelement <16 x i32> poison, i32 [[SUB86_1]], i32 0
 ; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <16 x i32> [[TMP6]], i32 [[ADD78_1]], i32 1
 ; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <16 x i32> [[TMP7]], i32 [[ADD94_1]], i32 2
 ; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <16 x i32> [[TMP8]], i32 [[SUB102_1]], i32 3
-; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i32> [[TMP9]], i32 [[ADD78_2]], i32 4
-; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <16 x i32> [[TMP10]], i32 [[SUB102_3]], i32 5
-; CHECK-NEXT:    [[SHUFFLE1:%.*]] = shufflevector <16 x i32> [[TMP11]], <16 x i32> poison, <16 x i32> <i32 undef, i32 undef, i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 2, i32 3, i32 4, i32 undef, i32 undef, i32 undef, i32 undef, i32 5>
-; CHECK-NEXT:    [[TMP12:%.*]] = add nsw <16 x i32> [[SHUFFLE]], [[SHUFFLE1]]
-; CHECK-NEXT:    [[TMP13:%.*]] = sub nsw <16 x i32> [[SHUFFLE]], [[SHUFFLE1]]
-; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x i32> [[TMP12]], <16 x i32> [[TMP13]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 21, i32 22, i32 7, i32 24, i32 25, i32 10, i32 27, i32 28, i32 13, i32 30, i32 31>
-; CHECK-NEXT:    [[TMP15:%.*]] = lshr <16 x i32> [[TMP14]], <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
-; CHECK-NEXT:    [[TMP16:%.*]] = and <16 x i32> [[TMP15]], <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
-; CHECK-NEXT:    [[TMP17:%.*]] = mul nuw <16 x i32> [[TMP16]], <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
-; CHECK-NEXT:    [[TMP18:%.*]] = add <16 x i32> [[TMP17]], [[TMP14]]
-; CHECK-NEXT:    [[TMP19:%.*]] = xor <16 x i32> [[TMP18]], [[TMP17]]
-; CHECK-NEXT:    [[TMP20:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP19]])
-; CHECK-NEXT:    [[SHR:%.*]] = lshr i32 [[TMP20]], 16
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <16 x i32> [[TMP9]], i32 [[SUB102_3]], i32 4
+; CHECK-NEXT:    [[SHUFFLE1:%.*]] = shufflevector <16 x i32> [[TMP10]], <16 x i32> poison, <16 x i32> <i32 undef, i32 undef, i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 4>
+; CHECK-NEXT:    [[TMP11:%.*]] = add nsw <16 x i32> [[SHUFFLE]], [[SHUFFLE1]]
+; CHECK-NEXT:    [[TMP12:%.*]] = sub nsw <16 x i32> [[SHUFFLE]], [[SHUFFLE1]]
+; CHECK-NEXT:    [[TMP13:%.*]] = shufflevector <16 x i32> [[TMP11]], <16 x i32> [[TMP12]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 21, i32 22, i32 7, i32 24, i32 25, i32 10, i32 27, i32 28, i32 13, i32 30, i32 31>
+; CHECK-NEXT:    [[TMP14:%.*]] = lshr <16 x i32> [[TMP13]], <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
+; CHECK-NEXT:    [[TMP15:%.*]] = and <16 x i32> [[TMP14]], <i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537, i32 65537>
+; CHECK-NEXT:    [[TMP16:%.*]] = mul nuw <16 x i32> [[TMP15]], <i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535, i32 65535>
+; CHECK-NEXT:    [[TMP17:%.*]] = add <16 x i32> [[TMP16]], [[TMP13]]
+; CHECK-NEXT:    [[TMP18:%.*]] = xor <16 x i32> [[TMP17]], [[TMP16]]
+; CHECK-NEXT:    [[TMP19:%.*]] = call i32 @llvm.vector.reduce.add.v16i32(<16 x i32> [[TMP18]])
+; CHECK-NEXT:    [[SHR:%.*]] = lshr i32 [[TMP19]], 16
 ; CHECK-NEXT:    [[ADD119:%.*]] = add nuw nsw i32 undef, [[SHR]]
 ; CHECK-NEXT:    [[SHR120:%.*]] = lshr i32 [[ADD119]], 1
 ; CHECK-NEXT:    ret i32 [[SHR120]]
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll b/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
--- a/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/operandorder.ll
@@ -421,7 +421,7 @@
 ; CHECK-NEXT:    [[TMP5:%.*]] = fadd <4 x float> [[TMP2]], [[TMP4]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[D:%.*]] to <4 x float>*
 ; CHECK-NEXT:    [[TMP7:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4
-; CHECK-NEXT:    [[TMP8:%.*]] = fadd <4 x float> [[TMP5]], [[TMP7]]
+; CHECK-NEXT:    [[TMP8:%.*]] = fadd <4 x float> [[TMP7]], [[TMP5]]
 ; CHECK-NEXT:    [[TMP9:%.*]] = bitcast float* [[A:%.*]] to <4 x float>*
 ; CHECK-NEXT:    store <4 x float> [[TMP8]], <4 x float>* [[TMP9]], align 4
 ; CHECK-NEXT:    ret void