Merging r321870, r321872, and r321994:

------------------------------------------------------------------------
r321870 | abataev | 2018-01-05 07:20:40 -0800 (Fri, 05 Jan 2018) | 1 line

[SLP] Update test checks, NFC.
------------------------------------------------------------------------

------------------------------------------------------------------------
r321872 | abataev | 2018-01-05 08:15:17 -0800 (Fri, 05 Jan 2018) | 1 line

[SLP] Update more test checks, NFC.
------------------------------------------------------------------------

------------------------------------------------------------------------
r321994 | abataev | 2018-01-08 06:43:06 -0800 (Mon, 08 Jan 2018) | 13 lines

[SLP] Fix PR35777: Incorrect handling of aggregate values.

Summary:
Fixes the bug with incorrect handling of InsertValue|InsertElement
instrucions in SLP vectorizer. Currently, we may use incorrect
ExtractElement instructions as the operands of the original
InsertValue|InsertElement instructions.

Reviewers: mkuper, hfinkel, RKSimon, spatel

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D41767
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_60@322675 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 337 insertions, 141 deletions

diff --git a/test/Transforms/SLPVectorizer/X86/PR35777.ll b/test/Transforms/SLPVectorizer/X86/PR35777.ll
new file mode 100644
index 00000000000..f3983d716d0
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/PR35777.ll
@@ -0,0 +1,48 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -verify -slp-vectorizer -o - -S -mtriple=x86_64-apple-macosx10.13.0 | FileCheck %s
+
+@global = local_unnamed_addr global [6 x double] zeroinitializer, align 16
+
+define { i64, i64 } @patatino(double %arg) {
+; CHECK-LABEL: @patatino(
+; CHECK-NEXT:  bb:
+; CHECK-NEXT:    [[TMP0:%.*]] = load <2 x double>, <2 x double>* bitcast ([6 x double]* @global to <2 x double>*), align 16
+; CHECK-NEXT:    [[TMP1:%.*]] = load <2 x double>, <2 x double>* bitcast (double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 2) to <2 x double>*), align 16
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x double> undef, double [[ARG:%.*]], i32 0
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <2 x double> [[TMP2]], double [[ARG]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = fmul <2 x double> [[TMP3]], [[TMP1]]
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> [[TMP0]], [[TMP4]]
+; CHECK-NEXT:    [[TMP6:%.*]] = load <2 x double>, <2 x double>* bitcast (double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 4) to <2 x double>*), align 16
+; CHECK-NEXT:    [[TMP7:%.*]] = fadd <2 x double> [[TMP6]], [[TMP5]]
+; CHECK-NEXT:    [[TMP8:%.*]] = fptosi <2 x double> [[TMP7]] to <2 x i32>
+; CHECK-NEXT:    [[TMP9:%.*]] = sext <2 x i32> [[TMP8]] to <2 x i64>
+; CHECK-NEXT:    [[TMP10:%.*]] = trunc <2 x i64> [[TMP9]] to <2 x i32>
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x i32> [[TMP10]], i32 0
+; CHECK-NEXT:    [[TMP12:%.*]] = sext i32 [[TMP11]] to i64
+; CHECK-NEXT:    [[TMP16:%.*]] = insertvalue { i64, i64 } undef, i64 [[TMP12]], 0
+; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x i32> [[TMP10]], i32 1
+; CHECK-NEXT:    [[TMP14:%.*]] = sext i32 [[TMP13]] to i64
+; CHECK-NEXT:    [[TMP17:%.*]] = insertvalue { i64, i64 } [[TMP16]], i64 [[TMP14]], 1
+; CHECK-NEXT:    ret { i64, i64 } [[TMP17]]
+;
+bb:
+  %tmp = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 0), align 16
+  %tmp1 = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 2), align 16
+  %tmp2 = fmul double %tmp1, %arg
+  %tmp3 = fadd double %tmp, %tmp2
+  %tmp4 = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 4), align 16
+  %tmp5 = fadd double %tmp4, %tmp3
+  %tmp6 = fptosi double %tmp5 to i32
+  %tmp7 = sext i32 %tmp6 to i64
+  %tmp8 = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 1), align 8
+  %tmp9 = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 3), align 8
+  %tmp10 = fmul double %tmp9, %arg
+  %tmp11 = fadd double %tmp8, %tmp10
+  %tmp12 = load double, double* getelementptr inbounds ([6 x double], [6 x double]* @global, i64 0, i64 5), align 8
+  %tmp13 = fadd double %tmp12, %tmp11
+  %tmp14 = fptosi double %tmp13 to i32
+  %tmp15 = sext i32 %tmp14 to i64
+  %tmp16 = insertvalue { i64, i64 } undef, i64 %tmp7, 0
+  %tmp17 = insertvalue { i64, i64 } %tmp16, i64 %tmp15, 1
+  ret { i64, i64 } %tmp17
+}
diff --git a/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll b/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
index 46386e8b63e..750a44736c9 100644
--- a/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
+++ b/test/Transforms/SLPVectorizer/X86/insert-element-build-vector.ll
@@ -7,8 +7,8 @@ target triple = "x86_64-apple-macosx10.8.0"
 
 define <4 x float> @simple_select(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select(
-; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -20,8 +20,8 @@ define <4 x float> @simple_select(<4 x float> %a, <4 x float> %b, <4 x i32> %c)
 ; CHECK-NEXT:    ret <4 x float> [[RD]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; ZEROTHRESH-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -64,18 +64,18 @@ declare void @llvm.assume(i1) nounwind
 ; This entire tree is ephemeral, don't vectorize any of it.
 define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_eph(
-; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; CHECK-NEXT:    [[C2:%.*]] = extractelement <4 x i32> %c, i32 2
-; CHECK-NEXT:    [[C3:%.*]] = extractelement <4 x i32> %c, i32 3
-; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; CHECK-NEXT:    [[A2:%.*]] = extractelement <4 x float> %a, i32 2
-; CHECK-NEXT:    [[A3:%.*]] = extractelement <4 x float> %a, i32 3
-; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
-; CHECK-NEXT:    [[B2:%.*]] = extractelement <4 x float> %b, i32 2
-; CHECK-NEXT:    [[B3:%.*]] = extractelement <4 x float> %b, i32 3
+; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT:    [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; CHECK-NEXT:    [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; CHECK-NEXT:    [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; CHECK-NEXT:    [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
 ; CHECK-NEXT:    [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
 ; CHECK-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
 ; CHECK-NEXT:    [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
@@ -100,18 +100,18 @@ define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32>
 ; CHECK-NEXT:    ret <4 x float> undef
 ;
 ; ZEROTHRESH-LABEL: @simple_select_eph(
-; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; ZEROTHRESH-NEXT:    [[C2:%.*]] = extractelement <4 x i32> %c, i32 2
-; ZEROTHRESH-NEXT:    [[C3:%.*]] = extractelement <4 x i32> %c, i32 3
-; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; ZEROTHRESH-NEXT:    [[A2:%.*]] = extractelement <4 x float> %a, i32 2
-; ZEROTHRESH-NEXT:    [[A3:%.*]] = extractelement <4 x float> %a, i32 3
-; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
-; ZEROTHRESH-NEXT:    [[B2:%.*]] = extractelement <4 x float> %b, i32 2
-; ZEROTHRESH-NEXT:    [[B3:%.*]] = extractelement <4 x float> %b, i32 3
+; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; ZEROTHRESH-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; ZEROTHRESH-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; ZEROTHRESH-NEXT:    [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; ZEROTHRESH-NEXT:    [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; ZEROTHRESH-NEXT:    [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; ZEROTHRESH-NEXT:    [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
 ; ZEROTHRESH-NEXT:    [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
 ; ZEROTHRESH-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
 ; ZEROTHRESH-NEXT:    [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
@@ -175,8 +175,8 @@ define <4 x float> @simple_select_eph(<4 x float> %a, <4 x float> %b, <4 x i32>
 ; doesn't matter
 define <4 x float> @simple_select_insert_out_of_order(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_insert_out_of_order(
-; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 2
 ; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -188,8 +188,8 @@ define <4 x float> @simple_select_insert_out_of_order(<4 x float> %a, <4 x float
 ; CHECK-NEXT:    ret <4 x float> [[RD]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select_insert_out_of_order(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; ZEROTHRESH-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 2
 ; ZEROTHRESH-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -233,8 +233,8 @@ declare void @f32_user(float) #0
 ; Multiple users of the final constructed vector
 define <4 x float> @simple_select_users(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_users(
-; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -247,8 +247,8 @@ define <4 x float> @simple_select_users(<4 x float> %a, <4 x float> %b, <4 x i32
 ; CHECK-NEXT:    ret <4 x float> [[RD]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select_users(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> %c, zeroinitializer
-; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> %a, <4 x float> %b
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = icmp ne <4 x i32> [[C:%.*]], zeroinitializer
+; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = select <4 x i1> [[TMP1]], <4 x float> [[A:%.*]], <4 x float> [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP2]], i32 0
 ; ZEROTHRESH-NEXT:    [[RA:%.*]] = insertelement <4 x float> undef, float [[TMP3]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP4:%.*]] = extractelement <4 x float> [[TMP2]], i32 1
@@ -291,18 +291,18 @@ define <4 x float> @simple_select_users(<4 x float> %a, <4 x float> %b, <4 x i32
 ; Unused insertelement
 define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_no_users(
-; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; CHECK-NEXT:    [[C2:%.*]] = extractelement <4 x i32> %c, i32 2
-; CHECK-NEXT:    [[C3:%.*]] = extractelement <4 x i32> %c, i32 3
-; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; CHECK-NEXT:    [[A2:%.*]] = extractelement <4 x float> %a, i32 2
-; CHECK-NEXT:    [[A3:%.*]] = extractelement <4 x float> %a, i32 3
-; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
-; CHECK-NEXT:    [[B2:%.*]] = extractelement <4 x float> %b, i32 2
-; CHECK-NEXT:    [[B3:%.*]] = extractelement <4 x float> %b, i32 3
+; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT:    [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; CHECK-NEXT:    [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; CHECK-NEXT:    [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; CHECK-NEXT:    [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
@@ -330,18 +330,18 @@ define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x
 ; CHECK-NEXT:    ret <4 x float> [[RD]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select_no_users(
-; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; ZEROTHRESH-NEXT:    [[C2:%.*]] = extractelement <4 x i32> %c, i32 2
-; ZEROTHRESH-NEXT:    [[C3:%.*]] = extractelement <4 x i32> %c, i32 3
-; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; ZEROTHRESH-NEXT:    [[A2:%.*]] = extractelement <4 x float> %a, i32 2
-; ZEROTHRESH-NEXT:    [[A3:%.*]] = extractelement <4 x float> %a, i32 3
-; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
-; ZEROTHRESH-NEXT:    [[B2:%.*]] = extractelement <4 x float> %b, i32 2
-; ZEROTHRESH-NEXT:    [[B3:%.*]] = extractelement <4 x float> %b, i32 3
+; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; ZEROTHRESH-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; ZEROTHRESH-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; ZEROTHRESH-NEXT:    [[A2:%.*]] = extractelement <4 x float> [[A]], i32 2
+; ZEROTHRESH-NEXT:    [[A3:%.*]] = extractelement <4 x float> [[A]], i32 3
+; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
+; ZEROTHRESH-NEXT:    [[B2:%.*]] = extractelement <4 x float> [[B]], i32 2
+; ZEROTHRESH-NEXT:    [[B3:%.*]] = extractelement <4 x float> [[B]], i32 3
 ; ZEROTHRESH-NEXT:    [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
 ; ZEROTHRESH-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
 ; ZEROTHRESH-NEXT:    [[CMP2:%.*]] = icmp ne i32 [[C2]], 0
@@ -387,25 +387,25 @@ define <4 x float> @simple_select_no_users(<4 x float> %a, <4 x float> %b, <4 x
 ; to do this backwards this backwards
 define <4 x i32> @reconstruct(<4 x i32> %c) #0 {
 ; CHECK-LABEL: @reconstruct(
-; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i32> %c, i32 0
-; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[TMP1]], i32 0
-; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> %c, i32 1
-; CHECK-NEXT:    [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[TMP2]], i32 1
-; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> %c, i32 2
-; CHECK-NEXT:    [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[TMP3]], i32 2
-; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x i32> %c, i32 3
-; CHECK-NEXT:    [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[TMP4]], i32 3
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 3
+; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <4 x i32> [[C]], i32 0
+; CHECK-NEXT:    [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[TMP4]], i32 0
+; CHECK-NEXT:    [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[TMP3]], i32 1
+; CHECK-NEXT:    [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[TMP2]], i32 2
+; CHECK-NEXT:    [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[TMP1]], i32 3
 ; CHECK-NEXT:    ret <4 x i32> [[RD]]
 ;
 ; ZEROTHRESH-LABEL: @reconstruct(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = extractelement <4 x i32> %c, i32 0
-; ZEROTHRESH-NEXT:    [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[TMP1]], i32 0
-; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = extractelement <4 x i32> %c, i32 1
-; ZEROTHRESH-NEXT:    [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[TMP2]], i32 1
-; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x i32> %c, i32 2
-; ZEROTHRESH-NEXT:    [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[TMP3]], i32 2
-; ZEROTHRESH-NEXT:    [[TMP4:%.*]] = extractelement <4 x i32> %c, i32 3
-; ZEROTHRESH-NEXT:    [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[TMP4]], i32 3
+; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; ZEROTHRESH-NEXT:    [[C2:%.*]] = extractelement <4 x i32> [[C]], i32 2
+; ZEROTHRESH-NEXT:    [[C3:%.*]] = extractelement <4 x i32> [[C]], i32 3
+; ZEROTHRESH-NEXT:    [[RA:%.*]] = insertelement <4 x i32> undef, i32 [[C0]], i32 0
+; ZEROTHRESH-NEXT:    [[RB:%.*]] = insertelement <4 x i32> [[RA]], i32 [[C1]], i32 1
+; ZEROTHRESH-NEXT:    [[RC:%.*]] = insertelement <4 x i32> [[RB]], i32 [[C2]], i32 2
+; ZEROTHRESH-NEXT:    [[RD:%.*]] = insertelement <4 x i32> [[RC]], i32 [[C3]], i32 3
 ; ZEROTHRESH-NEXT:    ret <4 x i32> [[RD]]
 ;
   %c0 = extractelement <4 x i32> %c, i32 0
@@ -421,8 +421,8 @@ define <4 x i32> @reconstruct(<4 x i32> %c) #0 {
 
 define <2 x float> @simple_select_v2(<2 x float> %a, <2 x float> %b, <2 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_v2(
-; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <2 x i32> %c, zeroinitializer
-; CHECK-NEXT:    [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x float> %a, <2 x float> %b
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ne <2 x i32> [[C:%.*]], zeroinitializer
+; CHECK-NEXT:    [[TMP2:%.*]] = select <2 x i1> [[TMP1]], <2 x float> [[A:%.*]], <2 x float> [[B:%.*]]
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x float> [[TMP2]], i32 0
 ; CHECK-NEXT:    [[RA:%.*]] = insertelement <2 x float> undef, float [[TMP3]], i32 0
 ; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x float> [[TMP2]], i32 1
@@ -430,12 +430,12 @@ define <2 x float> @simple_select_v2(<2 x float> %a, <2 x float> %b, <2 x i32> %
 ; CHECK-NEXT:    ret <2 x float> [[RB]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select_v2(
-; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <2 x i32> %c, i32 0
-; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <2 x i32> %c, i32 1
-; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <2 x float> %a, i32 0
-; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <2 x float> %a, i32 1
-; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <2 x float> %b, i32 0
-; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <2 x float> %b, i32 1
+; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <2 x i32> [[C:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <2 x i32> [[C]], i32 1
+; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <2 x float> [[A:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <2 x float> [[A]], i32 1
+; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <2 x float> [[B:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <2 x float> [[B]], i32 1
 ; ZEROTHRESH-NEXT:    [[CMP0:%.*]] = icmp ne i32 [[C0]], 0
 ; ZEROTHRESH-NEXT:    [[CMP1:%.*]] = icmp ne i32 [[C1]], 0
 ; ZEROTHRESH-NEXT:    [[S0:%.*]] = select i1 [[CMP0]], float [[A0]], float [[B0]]
@@ -464,12 +464,12 @@ define <2 x float> @simple_select_v2(<2 x float> %a, <2 x float> %b, <2 x i32> %
 ; (low cost threshold needed to force this to happen)
 define <4 x float> @simple_select_partial_vector(<4 x float> %a, <4 x float> %b, <4 x i32> %c) #0 {
 ; CHECK-LABEL: @simple_select_partial_vector(
-; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
+; CHECK-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; CHECK-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; CHECK-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; CHECK-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; CHECK-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; CHECK-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
 ; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
 ; CHECK-NEXT:    [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
@@ -485,12 +485,12 @@ define <4 x float> @simple_select_partial_vector(<4 x float> %a, <4 x float> %b,
 ; CHECK-NEXT:    ret <4 x float> [[RB]]
 ;
 ; ZEROTHRESH-LABEL: @simple_select_partial_vector(
-; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> %c, i32 0
-; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> %c, i32 1
-; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> %a, i32 0
-; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> %a, i32 1
-; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> %b, i32 0
-; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> %b, i32 1
+; ZEROTHRESH-NEXT:    [[C0:%.*]] = extractelement <4 x i32> [[C:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[C1:%.*]] = extractelement <4 x i32> [[C]], i32 1
+; ZEROTHRESH-NEXT:    [[A0:%.*]] = extractelement <4 x float> [[A:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[A1:%.*]] = extractelement <4 x float> [[A]], i32 1
+; ZEROTHRESH-NEXT:    [[B0:%.*]] = extractelement <4 x float> [[B:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[B1:%.*]] = extractelement <4 x float> [[B]], i32 1
 ; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = insertelement <2 x i32> undef, i32 [[C0]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = insertelement <2 x i32> [[TMP1]], i32 [[C1]], i32 1
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = icmp ne <2 x i32> [[TMP2]], zeroinitializer
@@ -530,7 +530,7 @@ define <4 x float> @simple_select_partial_vector(<4 x float> %a, <4 x float> %b,
 ; must be rescheduled. The case here is from compiling Julia.
 define <4 x float> @reschedule_extract(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @reschedule_extract(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> %a, %b
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
 ; CHECK-NEXT:    [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
@@ -542,7 +542,7 @@ define <4 x float> @reschedule_extract(<4 x float> %a, <4 x float> %b) {
 ; CHECK-NEXT:    ret <4 x float> [[V3]]
 ;
 ; ZEROTHRESH-LABEL: @reschedule_extract(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = fadd <4 x float> %a, %b
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
 ; ZEROTHRESH-NEXT:    [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
@@ -576,7 +576,7 @@ define <4 x float> @reschedule_extract(<4 x float> %a, <4 x float> %b) {
 ; instructions that are erased.
 define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: @take_credit(
-; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> %a, %b
+; CHECK-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
 ; CHECK-NEXT:    [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
 ; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
@@ -588,7 +588,7 @@ define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
 ; CHECK-NEXT:    ret <4 x float> [[V3]]
 ;
 ; ZEROTHRESH-LABEL: @take_credit(
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = fadd <4 x float> %a, %b
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = fadd <4 x float> [[A:%.*]], [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = extractelement <4 x float> [[TMP1]], i32 0
 ; ZEROTHRESH-NEXT:    [[V0:%.*]] = insertelement <4 x float> undef, float [[TMP2]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = extractelement <4 x float> [[TMP1]], i32 1
@@ -622,10 +622,10 @@ define <4 x float> @take_credit(<4 x float> %a, <4 x float> %b) {
 define <4 x double> @multi_tree(double %w, double %x, double %y, double %z) {
 ; CHECK-LABEL: @multi_tree(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x double> undef, double %w, i32 0
-; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double %x, i32 1
-; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double %y, i32 2
-; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double %z, i32 3
+; CHECK-NEXT:    [[TMP0:%.*]] = insertelement <4 x double> undef, double [[W:%.*]], i32 0
+; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double [[X:%.*]], i32 1
+; CHECK-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[Y:%.*]], i32 2
+; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[Z:%.*]], i32 3
 ; CHECK-NEXT:    [[TMP4:%.*]] = fadd <4 x double> [[TMP3]], <double 0.000000e+00, double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>
 ; CHECK-NEXT:    [[TMP5:%.*]] = fmul <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[TMP4]]
 ; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x double> [[TMP5]], i32 0
@@ -640,10 +640,10 @@ define <4 x double> @multi_tree(double %w, double %x, double %y, double %z) {
 ;
 ; ZEROTHRESH-LABEL: @multi_tree(
 ; ZEROTHRESH-NEXT:  entry:
-; ZEROTHRESH-NEXT:    [[TMP0:%.*]] = insertelement <4 x double> undef, double %w, i32 0
-; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double %x, i32 1
-; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double %y, i32 2
-; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double %z, i32 3
+; ZEROTHRESH-NEXT:    [[TMP0:%.*]] = insertelement <4 x double> undef, double [[W:%.*]], i32 0
+; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> [[TMP0]], double [[X:%.*]], i32 1
+; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = insertelement <4 x double> [[TMP1]], double [[Y:%.*]], i32 2
+; ZEROTHRESH-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP2]], double [[Z:%.*]], i32 3
 ; ZEROTHRESH-NEXT:    [[TMP4:%.*]] = fadd <4 x double> [[TMP3]], <double 0.000000e+00, double 1.000000e+00, double 2.000000e+00, double 3.000000e+00>
 ; ZEROTHRESH-NEXT:    [[TMP5:%.*]] = fmul <4 x double> <double 1.000000e+00, double 1.000000e+00, double 1.000000e+00, double 1.000000e+00>, [[TMP4]]
 ; ZEROTHRESH-NEXT:    [[TMP6:%.*]] = extractelement <4 x double> [[TMP5]], i32 0
@@ -675,7 +675,7 @@ entry:
 define <8 x float> @_vadd256(<8 x float> %a, <8 x float> %b) local_unnamed_addr #0 {
 ; CHECK-LABEL: @_vadd256(
 ; CHECK-NEXT:  entry:
-; CHECK-NEXT:    [[TMP0:%.*]] = fadd <8 x float> %a, %b
+; CHECK-NEXT:    [[TMP0:%.*]] = fadd <8 x float> [[A:%.*]], [[B:%.*]]
 ; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <8 x float> [[TMP0]], i32 0
 ; CHECK-NEXT:    [[VECINIT_I:%.*]] = insertelement <8 x float> undef, float [[TMP1]], i32 0
 ; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <8 x float> [[TMP0]], i32 1
@@ -696,7 +696,7 @@ define <8 x float> @_vadd256(<8 x float> %a, <8 x float> %b) local_unnamed_addr
 ;
 ; ZEROTHRESH-LABEL: @_vadd256(
 ; ZEROTHRESH-NEXT:  entry:
-; ZEROTHRESH-NEXT:    [[TMP0:%.*]] = fadd <8 x float> %a, %b
+; ZEROTHRESH-NEXT:    [[TMP0:%.*]] = fadd <8 x float> [[A:%.*]], [[B:%.*]]
 ; ZEROTHRESH-NEXT:    [[TMP1:%.*]] = extractelement <8 x float> [[TMP0]], i32 0
 ; ZEROTHRESH-NEXT:    [[VECINIT_I:%.*]] = insertelement <8 x float> undef, float [[TMP1]], i32 0
 ; ZEROTHRESH-NEXT:    [[TMP2:%.*]] = extractelement <8 x float> [[TMP0]], i32 1
diff --git a/test/Transforms/SLPVectorizer/X86/insertvalue.ll b/test/Transforms/SLPVectorizer/X86/insertvalue.ll
index 5884ee7a267..1af11609fe6 100644
--- a/test/Transforms/SLPVectorizer/X86/insertvalue.ll
+++ b/test/Transforms/SLPVectorizer/X86/insertvalue.ll
@@ -1,11 +1,30 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt < %s -basicaa -slp-vectorizer -S -mtriple=x86_64-unknown-linux-gnu -mcpu=corei7-avx | FileCheck %s
 
-; CHECK-LABEL: julia_2xdouble
-; CHECK: load <2 x double>
-; CHECK: load <2 x double>
-; CHECK: fmul <2 x double>
-; CHECK: fadd <2 x double>
 define void @julia_2xdouble([2 x double]* sret, [2 x double]*, [2 x double]*, [2 x double]*) {
+; CHECK-LABEL: @julia_2xdouble(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[PX0:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP2:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PY0:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP3:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PX1:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP2]], i64 0, i64 1
+; CHECK-NEXT:    [[TMP4:%.*]] = bitcast double* [[PX0]] to <2 x double>*
+; CHECK-NEXT:    [[TMP5:%.*]] = load <2 x double>, <2 x double>* [[TMP4]], align 4
+; CHECK-NEXT:    [[PY1:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP3]], i64 0, i64 1
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast double* [[PY0]] to <2 x double>*
+; CHECK-NEXT:    [[TMP7:%.*]] = load <2 x double>, <2 x double>* [[TMP6]], align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> [[TMP5]], [[TMP7]]
+; CHECK-NEXT:    [[PZ0:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP1:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PZ1:%.*]] = getelementptr inbounds [2 x double], [2 x double]* [[TMP1]], i64 0, i64 1
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast double* [[PZ0]] to <2 x double>*
+; CHECK-NEXT:    [[TMP10:%.*]] = load <2 x double>, <2 x double>* [[TMP9]], align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = fadd <2 x double> [[TMP8]], [[TMP10]]
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[TMP11]], i32 0
+; CHECK-NEXT:    [[I0:%.*]] = insertvalue [2 x double] undef, double [[TMP12]], 0
+; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x double> [[TMP11]], i32 1
+; CHECK-NEXT:    [[I1:%.*]] = insertvalue [2 x double] [[I0]], double [[TMP13]], 1
+; CHECK-NEXT:    store [2 x double] [[I1]], [2 x double]* [[TMP0:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %px0 = getelementptr inbounds [2 x double], [2 x double]* %2, i64 0, i64 0
   %x0 = load double, double* %px0, align 4
@@ -29,12 +48,40 @@ top:
   ret void
 }
 
-; CHECK-LABEL: julia_4xfloat
-; CHECK: load <4 x float>
-; CHECK: load <4 x float>
-; CHECK: fmul <4 x float>
-; CHECK: fadd <4 x float>
 define void @julia_4xfloat([4 x float]* sret, [4 x float]*, [4 x float]*, [4 x float]*) {
+; CHECK-LABEL: @julia_4xfloat(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[PX0:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP2:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PY0:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP3:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PX1:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP2]], i64 0, i64 1
+; CHECK-NEXT:    [[PY1:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP3]], i64 0, i64 1
+; CHECK-NEXT:    [[PX2:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP2]], i64 0, i64 2
+; CHECK-NEXT:    [[PY2:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP3]], i64 0, i64 2
+; CHECK-NEXT:    [[PX3:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP2]], i64 0, i64 3
+; CHECK-NEXT:    [[TMP4:%.*]] = bitcast float* [[PX0]] to <4 x float>*
+; CHECK-NEXT:    [[TMP5:%.*]] = load <4 x float>, <4 x float>* [[TMP4]], align 4
+; CHECK-NEXT:    [[PY3:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP3]], i64 0, i64 3
+; CHECK-NEXT:    [[TMP6:%.*]] = bitcast float* [[PY0]] to <4 x float>*
+; CHECK-NEXT:    [[TMP7:%.*]] = load <4 x float>, <4 x float>* [[TMP6]], align 4
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <4 x float> [[TMP5]], [[TMP7]]
+; CHECK-NEXT:    [[PZ0:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP1:%.*]], i64 0, i64 0
+; CHECK-NEXT:    [[PZ1:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP1]], i64 0, i64 1
+; CHECK-NEXT:    [[PZ2:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP1]], i64 0, i64 2
+; CHECK-NEXT:    [[PZ3:%.*]] = getelementptr inbounds [4 x float], [4 x float]* [[TMP1]], i64 0, i64 3
+; CHECK-NEXT:    [[TMP9:%.*]] = bitcast float* [[PZ0]] to <4 x float>*
+; CHECK-NEXT:    [[TMP10:%.*]] = load <4 x float>, <4 x float>* [[TMP9]], align 4
+; CHECK-NEXT:    [[TMP11:%.*]] = fadd <4 x float> [[TMP8]], [[TMP10]]
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <4 x float> [[TMP11]], i32 0
+; CHECK-NEXT:    [[I0:%.*]] = insertvalue [4 x float] undef, float [[TMP12]], 0
+; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <4 x float> [[TMP11]], i32 1
+; CHECK-NEXT:    [[I1:%.*]] = insertvalue [4 x float] [[I0]], float [[TMP13]], 1
+; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <4 x float> [[TMP11]], i32 2
+; CHECK-NEXT:    [[I2:%.*]] = insertvalue [4 x float] [[I1]], float [[TMP14]], 2
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <4 x float> [[TMP11]], i32 3
+; CHECK-NEXT:    [[I3:%.*]] = insertvalue [4 x float] [[I2]], float [[TMP15]], 3
+; CHECK-NEXT:    store [4 x float] [[I3]], [4 x float]* [[TMP0:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %px0 = getelementptr inbounds [4 x float], [4 x float]* %2, i64 0, i64 0
   %x0 = load float, float* %px0, align 4
@@ -76,9 +123,27 @@ top:
   ret void
 }
 
-; CHECK-LABEL: julia_load_array_of_float
-; CHECK: fsub <4 x float>
 define void @julia_load_array_of_float([4 x float]* %a, [4 x float]* %b, [4 x float]* %c) {
+; CHECK-LABEL: @julia_load_array_of_float(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast [4 x float]* [[A:%.*]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[A_ARR:%.*]] = load [4 x float], [4 x float]* [[A]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast [4 x float]* [[B:%.*]] to <4 x float>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
+; CHECK-NEXT:    [[B_ARR:%.*]] = load [4 x float], [4 x float]* [[B]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <4 x float> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP4]], i32 0
+; CHECK-NEXT:    [[C_ARR0:%.*]] = insertvalue [4 x float] undef, float [[TMP5]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[TMP4]], i32 1
+; CHECK-NEXT:    [[C_ARR1:%.*]] = insertvalue [4 x float] [[C_ARR0]], float [[TMP6]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x float> [[TMP4]], i32 2
+; CHECK-NEXT:    [[C_ARR2:%.*]] = insertvalue [4 x float] [[C_ARR1]], float [[TMP7]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x float> [[TMP4]], i32 3
+; CHECK-NEXT:    [[C_ARR3:%.*]] = insertvalue [4 x float] [[C_ARR2]], float [[TMP8]], 3
+; CHECK-NEXT:    store [4 x float] [[C_ARR3]], [4 x float]* [[C:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %a_arr = load [4 x float], [4 x float]* %a, align 4
   %a0 = extractvalue [4 x float] %a_arr, 0
@@ -102,11 +167,27 @@ top:
   ret void
 }
 
-; CHECK-LABEL: julia_load_array_of_i32
-; CHECK: load <4 x i32>
-; CHECK: load <4 x i32>
-; CHECK: sub <4 x i32>
 define void @julia_load_array_of_i32([4 x i32]* %a, [4 x i32]* %b, [4 x i32]* %c) {
+; CHECK-LABEL: @julia_load_array_of_i32(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast [4 x i32]* [[A:%.*]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x i32>, <4 x i32>* [[TMP0]], align 4
+; CHECK-NEXT:    [[A_ARR:%.*]] = load [4 x i32], [4 x i32]* [[A]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast [4 x i32]* [[B:%.*]] to <4 x i32>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x i32>, <4 x i32>* [[TMP2]], align 4
+; CHECK-NEXT:    [[B_ARR:%.*]] = load [4 x i32], [4 x i32]* [[B]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = sub <4 x i32> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x i32> [[TMP4]], i32 0
+; CHECK-NEXT:    [[C_ARR0:%.*]] = insertvalue [4 x i32] undef, i32 [[TMP5]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x i32> [[TMP4]], i32 1
+; CHECK-NEXT:    [[C_ARR1:%.*]] = insertvalue [4 x i32] [[C_ARR0]], i32 [[TMP6]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x i32> [[TMP4]], i32 2
+; CHECK-NEXT:    [[C_ARR2:%.*]] = insertvalue [4 x i32] [[C_ARR1]], i32 [[TMP7]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x i32> [[TMP4]], i32 3
+; CHECK-NEXT:    [[C_ARR3:%.*]] = insertvalue [4 x i32] [[C_ARR2]], i32 [[TMP8]], 3
+; CHECK-NEXT:    store [4 x i32] [[C_ARR3]], [4 x i32]* [[C:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %a_arr = load [4 x i32], [4 x i32]* %a, align 4
   %a0 = extractvalue [4 x i32] %a_arr, 0
@@ -132,9 +213,30 @@ top:
 
 ; Almost identical to previous test, but for type that should NOT be vectorized.
 ;
-; CHECK-LABEL: julia_load_array_of_i16
-; CHECK-NOT: i2>
 define void @julia_load_array_of_i16([4 x i16]* %a, [4 x i16]* %b, [4 x i16]* %c) {
+; CHECK-LABEL: @julia_load_array_of_i16(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[A_ARR:%.*]] = load [4 x i16], [4 x i16]* [[A:%.*]], align 4
+; CHECK-NEXT:    [[A0:%.*]] = extractvalue [4 x i16] [[A_ARR]], 0
+; CHECK-NEXT:    [[A2:%.*]] = extractvalue [4 x i16] [[A_ARR]], 2
+; CHECK-NEXT:    [[A1:%.*]] = extractvalue [4 x i16] [[A_ARR]], 1
+; CHECK-NEXT:    [[B_ARR:%.*]] = load [4 x i16], [4 x i16]* [[B:%.*]], align 4
+; CHECK-NEXT:    [[B0:%.*]] = extractvalue [4 x i16] [[B_ARR]], 0
+; CHECK-NEXT:    [[B2:%.*]] = extractvalue [4 x i16] [[B_ARR]], 2
+; CHECK-NEXT:    [[B1:%.*]] = extractvalue [4 x i16] [[B_ARR]], 1
+; CHECK-NEXT:    [[A3:%.*]] = extractvalue [4 x i16] [[A_ARR]], 3
+; CHECK-NEXT:    [[C1:%.*]] = sub i16 [[A1]], [[B1]]
+; CHECK-NEXT:    [[B3:%.*]] = extractvalue [4 x i16] [[B_ARR]], 3
+; CHECK-NEXT:    [[C0:%.*]] = sub i16 [[A0]], [[B0]]
+; CHECK-NEXT:    [[C2:%.*]] = sub i16 [[A2]], [[B2]]
+; CHECK-NEXT:    [[C_ARR0:%.*]] = insertvalue [4 x i16] undef, i16 [[C0]], 0
+; CHECK-NEXT:    [[C_ARR1:%.*]] = insertvalue [4 x i16] [[C_ARR0]], i16 [[C1]], 1
+; CHECK-NEXT:    [[C3:%.*]] = sub i16 [[A3]], [[B3]]
+; CHECK-NEXT:    [[C_ARR2:%.*]] = insertvalue [4 x i16] [[C_ARR1]], i16 [[C2]], 2
+; CHECK-NEXT:    [[C_ARR3:%.*]] = insertvalue [4 x i16] [[C_ARR2]], i16 [[C3]], 3
+; CHECK-NEXT:    store [4 x i16] [[C_ARR3]], [4 x i16]* [[C:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %a_arr = load [4 x i16], [4 x i16]* %a, align 4
   %a0 = extractvalue [4 x i16] %a_arr, 0
@@ -160,11 +262,27 @@ top:
 
 %pseudovec = type { float, float, float, float }
 
-; CHECK-LABEL: julia_load_struct_of_float
-; CHECK: load <4 x float>
-; CHECK: load <4 x float>
-; CHECK: fsub <4 x float>
 define void @julia_load_struct_of_float(%pseudovec* %a, %pseudovec* %b, %pseudovec* %c) {
+; CHECK-LABEL: @julia_load_struct_of_float(
+; CHECK-NEXT:  top:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast %pseudovec* [[A:%.*]] to <4 x float>*
+; CHECK-NEXT:    [[TMP1:%.*]] = load <4 x float>, <4 x float>* [[TMP0]], align 4
+; CHECK-NEXT:    [[A_STRUCT:%.*]] = load [[PSEUDOVEC:%.*]], %pseudovec* [[A]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast %pseudovec* [[B:%.*]] to <4 x float>*
+; CHECK-NEXT:    [[TMP3:%.*]] = load <4 x float>, <4 x float>* [[TMP2]], align 4
+; CHECK-NEXT:    [[B_STRUCT:%.*]] = load [[PSEUDOVEC]], %pseudovec* [[B]], align 4
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <4 x float> [[TMP1]], [[TMP3]]
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <4 x float> [[TMP4]], i32 0
+; CHECK-NEXT:    [[C_STRUCT0:%.*]] = insertvalue [[PSEUDOVEC]] undef, float [[TMP5]], 0
+; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <4 x float> [[TMP4]], i32 1
+; CHECK-NEXT:    [[C_STRUCT1:%.*]] = insertvalue [[PSEUDOVEC]] %c_struct0, float [[TMP6]], 1
+; CHECK-NEXT:    [[TMP7:%.*]] = extractelement <4 x float> [[TMP4]], i32 2
+; CHECK-NEXT:    [[C_STRUCT2:%.*]] = insertvalue [[PSEUDOVEC]] %c_struct1, float [[TMP7]], 2
+; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <4 x float> [[TMP4]], i32 3
+; CHECK-NEXT:    [[C_STRUCT3:%.*]] = insertvalue [[PSEUDOVEC]] %c_struct2, float [[TMP8]], 3
+; CHECK-NEXT:    store [[PSEUDOVEC]] %c_struct3, %pseudovec* [[C:%.*]], align 4
+; CHECK-NEXT:    ret void
+;
 top:
   %a_struct = load %pseudovec, %pseudovec* %a, align 4
   %a0 = extractvalue %pseudovec %a_struct, 0
diff --git a/test/Transforms/SLPVectorizer/X86/value-bug.ll b/test/Transforms/SLPVectorizer/X86/value-bug.ll
index 64d2ae1c7d7..7558c724a15 100644
--- a/test/Transforms/SLPVectorizer/X86/value-bug.ll
+++ b/test/Transforms/SLPVectorizer/X86/value-bug.ll
@@ -1,15 +1,46 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -slp-vectorizer < %s -S -mtriple="x86_64-grtev3-linux-gnu" -mcpu=corei7-avx | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-target triple = "x86_64-grtev3-linux-gnu"
 
 ; We used to crash on this example because we were building a constant
 ; expression during vectorization and the vectorizer expects instructions
 ; as elements of the vectorized tree.
-; CHECK-LABEL: @test
 ; PR19621
 
 define void @test() {
+; CHECK-LABEL: @test(
+; CHECK-NEXT:  bb279:
+; CHECK-NEXT:    br label [[BB283:%.*]]
+; CHECK:       bb283:
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x float> [ undef, [[BB279:%.*]] ], [ [[TMP11:%.*]], [[EXIT:%.*]] ]
+; CHECK-NEXT:    [[TMP1:%.*]] = phi <2 x float> [ undef, [[BB279]] ], [ [[TMP13:%.*]], [[EXIT]] ]
+; CHECK-NEXT:    br label [[BB284:%.*]]
+; CHECK:       bb284:
+; CHECK-NEXT:    [[TMP2:%.*]] = fpext <2 x float> [[TMP0]] to <2 x double>
+; CHECK-NEXT:    [[TMP3:%.*]] = fsub <2 x double> [[TMP2]], undef
+; CHECK-NEXT:    [[TMP4:%.*]] = fsub <2 x double> [[TMP3]], undef
+; CHECK-NEXT:    br label [[BB21_I:%.*]]
+; CHECK:       bb21.i:
+; CHECK-NEXT:    br i1 undef, label [[BB22_I:%.*]], label [[EXIT]]
+; CHECK:       bb22.i:
+; CHECK-NEXT:    [[TMP5:%.*]] = fadd <2 x double> undef, [[TMP4]]
+; CHECK-NEXT:    br label [[BB32_I:%.*]]
+; CHECK:       bb32.i:
+; CHECK-NEXT:    [[TMP6:%.*]] = phi <2 x double> [ [[TMP5]], [[BB22_I]] ], [ zeroinitializer, [[BB32_I]] ]
+; CHECK-NEXT:    br i1 undef, label [[BB32_I]], label [[BB21_I]]
+; CHECK:       exit:
+; CHECK-NEXT:    [[TMP7:%.*]] = fpext <2 x float> [[TMP1]] to <2 x double>
+; CHECK-NEXT:    [[TMP8:%.*]] = fmul <2 x double> <double undef, double 0.000000e+00>, [[TMP7]]
+; CHECK-NEXT:    [[TMP9:%.*]] = fadd <2 x double> undef, [[TMP8]]
+; CHECK-NEXT:    [[TMP10:%.*]] = fadd <2 x double> undef, [[TMP9]]
+; CHECK-NEXT:    [[TMP11]] = fptrunc <2 x double> [[TMP10]] to <2 x float>
+; CHECK-NEXT:    [[TMP317:%.*]] = fptrunc double undef to float
+; CHECK-NEXT:    [[TMP319:%.*]] = fptrunc double undef to float
+; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <2 x float> undef, float [[TMP317]], i32 0
+; CHECK-NEXT:    [[TMP13]] = insertelement <2 x float> [[TMP12]], float [[TMP319]], i32 1
+; CHECK-NEXT:    br label [[BB283]]
+;
 bb279:
   br label %bb283
 
@@ -62,6 +93,12 @@ exit:
 ; vectorizer starts at the type (%t2, %t3) and wil constant fold the tree.
 ; The code that handles insertelement instructions must handle this.
 define <4 x double> @constant_folding() {
+; CHECK-LABEL: @constant_folding(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[I1:%.*]] = insertelement <4 x double> undef, double 1.000000e+00, i32 1
+; CHECK-NEXT:    [[I2:%.*]] = insertelement <4 x double> [[I1]], double 2.000000e+00, i32 0
+; CHECK-NEXT:    ret <4 x double> [[I2]]
+;
 entry:
   %t0 = fadd double 1.000000e+00 , 0.000000e+00
   %t1 = fadd double 1.000000e+00 , 1.000000e+00
@@ -71,10 +108,3 @@ entry:
   %i2 = insertelement <4 x double> %i1, double %t3, i32 0
   ret <4 x double> %i2
 }
-
-; CHECK-LABEL: @constant_folding
-; CHECK: %[[V0:.+]] = extractelement <2 x double> <double 1.000000e+00, double 2.000000e+00>, i32 0
-; CHECK: %[[V1:.+]] = insertelement <4 x double> undef, double %[[V0]], i32 1
-; CHECK: %[[V2:.+]] = extractelement <2 x double> <double 1.000000e+00, double 2.000000e+00>, i32 1
-; CHECK: %[[V3:.+]] = insertelement <4 x double> %[[V1]], double %[[V2]], i32 0
-; CHECK: ret <4 x double> %[[V3]]