; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+sse2     | FileCheck %s --check-prefixes=CHECK,SSE
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx      | FileCheck %s --check-prefixes=CHECK,AVX
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx2     | FileCheck %s --check-prefixes=CHECK,AVX2
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512f  | FileCheck %s --check-prefixes=CHECK,AVX512
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512vl | FileCheck %s --check-prefixes=CHECK,AVX512

define void @gather_load(i32* noalias nocapture %0, i32* noalias nocapture readonly %1) {
; CHECK-LABEL: @gather_load(
; CHECK-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TMP1:%.*]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP1]], align 4, [[TBAA0:!tbaa !.*]]
; CHECK-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 11
; CHECK-NEXT:    [[TMP6:%.*]] = load i32, i32* [[TMP5]], align 4, [[TBAA0]]
; CHECK-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 4
; CHECK-NEXT:    [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4, [[TBAA0]]
; CHECK-NEXT:    [[TMP9:%.*]] = load i32, i32* [[TMP3]], align 4, [[TBAA0]]
; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i32> undef, i32 [[TMP4]], i32 0
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x i32> [[TMP10]], i32 [[TMP6]], i32 1
; CHECK-NEXT:    [[TMP12:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP8]], i32 2
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x i32> [[TMP12]], i32 [[TMP9]], i32 3
; CHECK-NEXT:    [[TMP14:%.*]] = add nsw <4 x i32> [[TMP13]], <i32 1, i32 2, i32 3, i32 4>
; CHECK-NEXT:    [[TMP15:%.*]] = bitcast i32* [[TMP0:%.*]] to <4 x i32>*
; CHECK-NEXT:    store <4 x i32> [[TMP14]], <4 x i32>* [[TMP15]], align 4, [[TBAA0]]
; CHECK-NEXT:    ret void
;
  %3 = getelementptr inbounds i32, i32* %1, i64 1
  %4 = load i32, i32* %1, align 4, !tbaa !2
  %5 = getelementptr inbounds i32, i32* %0, i64 1
  %6 = getelementptr inbounds i32, i32* %1, i64 11
  %7 = load i32, i32* %6, align 4, !tbaa !2
  %8 = getelementptr inbounds i32, i32* %0, i64 2
  %9 = getelementptr inbounds i32, i32* %1, i64 4
  %10 = load i32, i32* %9, align 4, !tbaa !2
  %11 = getelementptr inbounds i32, i32* %0, i64 3
  %12 = load i32, i32* %3, align 4, !tbaa !2
  %13 = insertelement <4 x i32> undef, i32 %4, i32 0
  %14 = insertelement <4 x i32> %13, i32 %7, i32 1
  %15 = insertelement <4 x i32> %14, i32 %10, i32 2
  %16 = insertelement <4 x i32> %15, i32 %12, i32 3
  %17 = add nsw <4 x i32> %16, <i32 1, i32 2, i32 3, i32 4>
  %18 = bitcast i32* %0 to <4 x i32>*
  store <4 x i32> %17, <4 x i32>* %18, align 4, !tbaa !2
  ret void
}

define void @gather_load_2(i32* noalias nocapture %0, i32* noalias nocapture readonly %1) {
; SSE-LABEL: @gather_load_2(
; SSE-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TMP1:%.*]], i64 1
; SSE-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4, [[TBAA0:!tbaa !.*]]
; SSE-NEXT:    [[TMP5:%.*]] = add nsw i32 [[TMP4]], 1
; SSE-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; SSE-NEXT:    store i32 [[TMP5]], i32* [[TMP0]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 10
; SSE-NEXT:    [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP9:%.*]] = add nsw i32 [[TMP8]], 2
; SSE-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 2
; SSE-NEXT:    store i32 [[TMP9]], i32* [[TMP6]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 3
; SSE-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP13:%.*]] = add nsw i32 [[TMP12]], 3
; SSE-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; SSE-NEXT:    store i32 [[TMP13]], i32* [[TMP10]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 5
; SSE-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP17:%.*]] = add nsw i32 [[TMP16]], 4
; SSE-NEXT:    store i32 [[TMP17]], i32* [[TMP14]], align 4, [[TBAA0]]
; SSE-NEXT:    ret void
;
; AVX-LABEL: @gather_load_2(
; AVX-NEXT:    [[TMP3:%.*]] = getelementptr inbounds i32, i32* [[TMP1:%.*]], i64 1
; AVX-NEXT:    [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4, [[TBAA0:!tbaa !.*]]
; AVX-NEXT:    [[TMP5:%.*]] = add nsw i32 [[TMP4]], 1
; AVX-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; AVX-NEXT:    store i32 [[TMP5]], i32* [[TMP0]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP7:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 10
; AVX-NEXT:    [[TMP8:%.*]] = load i32, i32* [[TMP7]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP9:%.*]] = add nsw i32 [[TMP8]], 2
; AVX-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 2
; AVX-NEXT:    store i32 [[TMP9]], i32* [[TMP6]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 3
; AVX-NEXT:    [[TMP12:%.*]] = load i32, i32* [[TMP11]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP13:%.*]] = add nsw i32 [[TMP12]], 3
; AVX-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; AVX-NEXT:    store i32 [[TMP13]], i32* [[TMP10]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP15:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 5
; AVX-NEXT:    [[TMP16:%.*]] = load i32, i32* [[TMP15]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP17:%.*]] = add nsw i32 [[TMP16]], 4
; AVX-NEXT:    store i32 [[TMP17]], i32* [[TMP14]], align 4, [[TBAA0]]
; AVX-NEXT:    ret void
;
; AVX2-LABEL: @gather_load_2(
; AVX2-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32*> undef, i32* [[TMP1:%.*]], i32 0
; AVX2-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32*> [[TMP3]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr i32, <4 x i32*> [[TMP4]], <4 x i64> <i64 1, i64 10, i64 3, i64 5>
; AVX2-NEXT:    [[TMP6:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP5]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0:!tbaa !.*]]
; AVX2-NEXT:    [[TMP7:%.*]] = add nsw <4 x i32> [[TMP6]], <i32 1, i32 2, i32 3, i32 4>
; AVX2-NEXT:    [[TMP8:%.*]] = bitcast i32* [[TMP0:%.*]] to <4 x i32>*
; AVX2-NEXT:    store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4, [[TBAA0]]
; AVX2-NEXT:    ret void
;
; AVX512-LABEL: @gather_load_2(
; AVX512-NEXT:    [[TMP3:%.*]] = insertelement <4 x i32*> undef, i32* [[TMP1:%.*]], i32 0
; AVX512-NEXT:    [[TMP4:%.*]] = shufflevector <4 x i32*> [[TMP3]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr i32, <4 x i32*> [[TMP4]], <4 x i64> <i64 1, i64 10, i64 3, i64 5>
; AVX512-NEXT:    [[TMP6:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP5]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0:!tbaa !.*]]
; AVX512-NEXT:    [[TMP7:%.*]] = add nsw <4 x i32> [[TMP6]], <i32 1, i32 2, i32 3, i32 4>
; AVX512-NEXT:    [[TMP8:%.*]] = bitcast i32* [[TMP0:%.*]] to <4 x i32>*
; AVX512-NEXT:    store <4 x i32> [[TMP7]], <4 x i32>* [[TMP8]], align 4, [[TBAA0]]
; AVX512-NEXT:    ret void
;
  %3 = getelementptr inbounds i32, i32* %1, i64 1
  %4 = load i32, i32* %3, align 4, !tbaa !2
  %5 = add nsw i32 %4, 1
  %6 = getelementptr inbounds i32, i32* %0, i64 1
  store i32 %5, i32* %0, align 4, !tbaa !2
  %7 = getelementptr inbounds i32, i32* %1, i64 10
  %8 = load i32, i32* %7, align 4, !tbaa !2
  %9 = add nsw i32 %8, 2
  %10 = getelementptr inbounds i32, i32* %0, i64 2
  store i32 %9, i32* %6, align 4, !tbaa !2
  %11 = getelementptr inbounds i32, i32* %1, i64 3
  %12 = load i32, i32* %11, align 4, !tbaa !2
  %13 = add nsw i32 %12, 3
  %14 = getelementptr inbounds i32, i32* %0, i64 3
  store i32 %13, i32* %10, align 4, !tbaa !2
  %15 = getelementptr inbounds i32, i32* %1, i64 5
  %16 = load i32, i32* %15, align 4, !tbaa !2
  %17 = add nsw i32 %16, 4
  store i32 %17, i32* %14, align 4, !tbaa !2
  ret void
}


define void @gather_load_3(i32* noalias nocapture %0, i32* noalias nocapture readonly %1) {
; SSE-LABEL: @gather_load_3(
; SSE-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1:%.*]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP4:%.*]] = add i32 [[TMP3]], 1
; SSE-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; SSE-NEXT:    store i32 [[TMP4]], i32* [[TMP0]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 11
; SSE-NEXT:    [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP8:%.*]] = add i32 [[TMP7]], 2
; SSE-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 2
; SSE-NEXT:    store i32 [[TMP8]], i32* [[TMP5]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 4
; SSE-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP10]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP12:%.*]] = add i32 [[TMP11]], 3
; SSE-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; SSE-NEXT:    store i32 [[TMP12]], i32* [[TMP9]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 15
; SSE-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP16:%.*]] = add i32 [[TMP15]], 4
; SSE-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 4
; SSE-NEXT:    store i32 [[TMP16]], i32* [[TMP13]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 18
; SSE-NEXT:    [[TMP19:%.*]] = load i32, i32* [[TMP18]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP20:%.*]] = add i32 [[TMP19]], 1
; SSE-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 5
; SSE-NEXT:    store i32 [[TMP20]], i32* [[TMP17]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 9
; SSE-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP24:%.*]] = add i32 [[TMP23]], 2
; SSE-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 6
; SSE-NEXT:    store i32 [[TMP24]], i32* [[TMP21]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 6
; SSE-NEXT:    [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP28:%.*]] = add i32 [[TMP27]], 3
; SSE-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; SSE-NEXT:    store i32 [[TMP28]], i32* [[TMP25]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP30:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 21
; SSE-NEXT:    [[TMP31:%.*]] = load i32, i32* [[TMP30]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP32:%.*]] = add i32 [[TMP31]], 4
; SSE-NEXT:    store i32 [[TMP32]], i32* [[TMP29]], align 4, [[TBAA0]]
; SSE-NEXT:    ret void
;
; AVX-LABEL: @gather_load_3(
; AVX-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1:%.*]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP4:%.*]] = add i32 [[TMP3]], 1
; AVX-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; AVX-NEXT:    store i32 [[TMP4]], i32* [[TMP0]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP6:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 11
; AVX-NEXT:    [[TMP7:%.*]] = load i32, i32* [[TMP6]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP8:%.*]] = add i32 [[TMP7]], 2
; AVX-NEXT:    [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 2
; AVX-NEXT:    store i32 [[TMP8]], i32* [[TMP5]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP10:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 4
; AVX-NEXT:    [[TMP11:%.*]] = load i32, i32* [[TMP10]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP12:%.*]] = add i32 [[TMP11]], 3
; AVX-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 3
; AVX-NEXT:    store i32 [[TMP12]], i32* [[TMP9]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP14:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 15
; AVX-NEXT:    [[TMP15:%.*]] = load i32, i32* [[TMP14]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP16:%.*]] = add i32 [[TMP15]], 4
; AVX-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 4
; AVX-NEXT:    store i32 [[TMP16]], i32* [[TMP13]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP18:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 18
; AVX-NEXT:    [[TMP19:%.*]] = load i32, i32* [[TMP18]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP20:%.*]] = add i32 [[TMP19]], 1
; AVX-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 5
; AVX-NEXT:    store i32 [[TMP20]], i32* [[TMP17]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP22:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 9
; AVX-NEXT:    [[TMP23:%.*]] = load i32, i32* [[TMP22]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP24:%.*]] = add i32 [[TMP23]], 2
; AVX-NEXT:    [[TMP25:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 6
; AVX-NEXT:    store i32 [[TMP24]], i32* [[TMP21]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP26:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 6
; AVX-NEXT:    [[TMP27:%.*]] = load i32, i32* [[TMP26]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP28:%.*]] = add i32 [[TMP27]], 3
; AVX-NEXT:    [[TMP29:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; AVX-NEXT:    store i32 [[TMP28]], i32* [[TMP25]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP30:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 21
; AVX-NEXT:    [[TMP31:%.*]] = load i32, i32* [[TMP30]], align 4, [[TBAA0]]
; AVX-NEXT:    [[TMP32:%.*]] = add i32 [[TMP31]], 4
; AVX-NEXT:    store i32 [[TMP32]], i32* [[TMP29]], align 4, [[TBAA0]]
; AVX-NEXT:    ret void
;
; AVX2-LABEL: @gather_load_3(
; AVX2-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1:%.*]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP4:%.*]] = add i32 [[TMP3]], 1
; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; AVX2-NEXT:    store i32 [[TMP4]], i32* [[TMP0]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32*> undef, i32* [[TMP1]], i32 0
; AVX2-NEXT:    [[TMP7:%.*]] = shufflevector <4 x i32*> [[TMP6]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX2-NEXT:    [[TMP8:%.*]] = getelementptr i32, <4 x i32*> [[TMP7]], <4 x i64> <i64 11, i64 4, i64 15, i64 18>
; AVX2-NEXT:    [[TMP9:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP8]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0]]
; AVX2-NEXT:    [[TMP10:%.*]] = add <4 x i32> [[TMP9]], <i32 2, i32 3, i32 4, i32 1>
; AVX2-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 5
; AVX2-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; AVX2-NEXT:    store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 9
; AVX2-NEXT:    [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP15:%.*]] = add i32 [[TMP14]], 2
; AVX2-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 6
; AVX2-NEXT:    store i32 [[TMP15]], i32* [[TMP11]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 6
; AVX2-NEXT:    [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP19:%.*]] = add i32 [[TMP18]], 3
; AVX2-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; AVX2-NEXT:    store i32 [[TMP19]], i32* [[TMP16]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 21
; AVX2-NEXT:    [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP23:%.*]] = add i32 [[TMP22]], 4
; AVX2-NEXT:    store i32 [[TMP23]], i32* [[TMP20]], align 4, [[TBAA0]]
; AVX2-NEXT:    ret void
;
; AVX512-LABEL: @gather_load_3(
; AVX512-NEXT:    [[TMP3:%.*]] = load i32, i32* [[TMP1:%.*]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP4:%.*]] = add i32 [[TMP3]], 1
; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 1
; AVX512-NEXT:    store i32 [[TMP4]], i32* [[TMP0]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP6:%.*]] = insertelement <4 x i32*> undef, i32* [[TMP1]], i32 0
; AVX512-NEXT:    [[TMP7:%.*]] = shufflevector <4 x i32*> [[TMP6]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX512-NEXT:    [[TMP8:%.*]] = getelementptr i32, <4 x i32*> [[TMP7]], <4 x i64> <i64 11, i64 4, i64 15, i64 18>
; AVX512-NEXT:    [[TMP9:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP8]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0]]
; AVX512-NEXT:    [[TMP10:%.*]] = add <4 x i32> [[TMP9]], <i32 2, i32 3, i32 4, i32 1>
; AVX512-NEXT:    [[TMP11:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 5
; AVX512-NEXT:    [[TMP12:%.*]] = bitcast i32* [[TMP5]] to <4 x i32>*
; AVX512-NEXT:    store <4 x i32> [[TMP10]], <4 x i32>* [[TMP12]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP13:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 9
; AVX512-NEXT:    [[TMP14:%.*]] = load i32, i32* [[TMP13]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP15:%.*]] = add i32 [[TMP14]], 2
; AVX512-NEXT:    [[TMP16:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 6
; AVX512-NEXT:    store i32 [[TMP15]], i32* [[TMP11]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP17:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 6
; AVX512-NEXT:    [[TMP18:%.*]] = load i32, i32* [[TMP17]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP19:%.*]] = add i32 [[TMP18]], 3
; AVX512-NEXT:    [[TMP20:%.*]] = getelementptr inbounds i32, i32* [[TMP0]], i64 7
; AVX512-NEXT:    store i32 [[TMP19]], i32* [[TMP16]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP21:%.*]] = getelementptr inbounds i32, i32* [[TMP1]], i64 21
; AVX512-NEXT:    [[TMP22:%.*]] = load i32, i32* [[TMP21]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP23:%.*]] = add i32 [[TMP22]], 4
; AVX512-NEXT:    store i32 [[TMP23]], i32* [[TMP20]], align 4, [[TBAA0]]
; AVX512-NEXT:    ret void
;
  %3 = load i32, i32* %1, align 4, !tbaa !2
  %4 = add i32 %3, 1
  %5 = getelementptr inbounds i32, i32* %0, i64 1
  store i32 %4, i32* %0, align 4, !tbaa !2
  %6 = getelementptr inbounds i32, i32* %1, i64 11
  %7 = load i32, i32* %6, align 4, !tbaa !2
  %8 = add i32 %7, 2
  %9 = getelementptr inbounds i32, i32* %0, i64 2
  store i32 %8, i32* %5, align 4, !tbaa !2
  %10 = getelementptr inbounds i32, i32* %1, i64 4
  %11 = load i32, i32* %10, align 4, !tbaa !2
  %12 = add i32 %11, 3
  %13 = getelementptr inbounds i32, i32* %0, i64 3
  store i32 %12, i32* %9, align 4, !tbaa !2
  %14 = getelementptr inbounds i32, i32* %1, i64 15
  %15 = load i32, i32* %14, align 4, !tbaa !2
  %16 = add i32 %15, 4
  %17 = getelementptr inbounds i32, i32* %0, i64 4
  store i32 %16, i32* %13, align 4, !tbaa !2
  %18 = getelementptr inbounds i32, i32* %1, i64 18
  %19 = load i32, i32* %18, align 4, !tbaa !2
  %20 = add i32 %19, 1
  %21 = getelementptr inbounds i32, i32* %0, i64 5
  store i32 %20, i32* %17, align 4, !tbaa !2
  %22 = getelementptr inbounds i32, i32* %1, i64 9
  %23 = load i32, i32* %22, align 4, !tbaa !2
  %24 = add i32 %23, 2
  %25 = getelementptr inbounds i32, i32* %0, i64 6
  store i32 %24, i32* %21, align 4, !tbaa !2
  %26 = getelementptr inbounds i32, i32* %1, i64 6
  %27 = load i32, i32* %26, align 4, !tbaa !2
  %28 = add i32 %27, 3
  %29 = getelementptr inbounds i32, i32* %0, i64 7
  store i32 %28, i32* %25, align 4, !tbaa !2
  %30 = getelementptr inbounds i32, i32* %1, i64 21
  %31 = load i32, i32* %30, align 4, !tbaa !2
  %32 = add i32 %31, 4
  store i32 %32, i32* %29, align 4, !tbaa !2
  ret void
}

define void @gather_load_4(i32* noalias nocapture %t0, i32* noalias nocapture readonly %t1) {
; SSE-LABEL: @gather_load_4(
; SSE-NEXT:    [[T5:%.*]] = getelementptr inbounds i32, i32* [[T0:%.*]], i64 1
; SSE-NEXT:    [[T6:%.*]] = getelementptr inbounds i32, i32* [[T1:%.*]], i64 11
; SSE-NEXT:    [[T9:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 2
; SSE-NEXT:    [[T10:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 4
; SSE-NEXT:    [[T13:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 3
; SSE-NEXT:    [[T14:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 15
; SSE-NEXT:    [[T17:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 4
; SSE-NEXT:    [[T18:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 18
; SSE-NEXT:    [[T21:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 5
; SSE-NEXT:    [[T22:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 9
; SSE-NEXT:    [[T25:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 6
; SSE-NEXT:    [[T26:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 6
; SSE-NEXT:    [[T29:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 7
; SSE-NEXT:    [[T30:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 21
; SSE-NEXT:    [[T3:%.*]] = load i32, i32* [[T1]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T7:%.*]] = load i32, i32* [[T6]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T11:%.*]] = load i32, i32* [[T10]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T15:%.*]] = load i32, i32* [[T14]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T19:%.*]] = load i32, i32* [[T18]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T23:%.*]] = load i32, i32* [[T22]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T27:%.*]] = load i32, i32* [[T26]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T31:%.*]] = load i32, i32* [[T30]], align 4, [[TBAA0]]
; SSE-NEXT:    [[T4:%.*]] = add i32 [[T3]], 1
; SSE-NEXT:    [[T8:%.*]] = add i32 [[T7]], 2
; SSE-NEXT:    [[T12:%.*]] = add i32 [[T11]], 3
; SSE-NEXT:    [[T16:%.*]] = add i32 [[T15]], 4
; SSE-NEXT:    [[T20:%.*]] = add i32 [[T19]], 1
; SSE-NEXT:    [[T24:%.*]] = add i32 [[T23]], 2
; SSE-NEXT:    [[T28:%.*]] = add i32 [[T27]], 3
; SSE-NEXT:    [[T32:%.*]] = add i32 [[T31]], 4
; SSE-NEXT:    store i32 [[T4]], i32* [[T0]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T8]], i32* [[T5]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T12]], i32* [[T9]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T16]], i32* [[T13]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T20]], i32* [[T17]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T24]], i32* [[T21]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T28]], i32* [[T25]], align 4, [[TBAA0]]
; SSE-NEXT:    store i32 [[T32]], i32* [[T29]], align 4, [[TBAA0]]
; SSE-NEXT:    ret void
;
; AVX-LABEL: @gather_load_4(
; AVX-NEXT:    [[T5:%.*]] = getelementptr inbounds i32, i32* [[T0:%.*]], i64 1
; AVX-NEXT:    [[T6:%.*]] = getelementptr inbounds i32, i32* [[T1:%.*]], i64 11
; AVX-NEXT:    [[T9:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 2
; AVX-NEXT:    [[T10:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 4
; AVX-NEXT:    [[T13:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 3
; AVX-NEXT:    [[T14:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 15
; AVX-NEXT:    [[T17:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 4
; AVX-NEXT:    [[T18:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 18
; AVX-NEXT:    [[T21:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 5
; AVX-NEXT:    [[T22:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 9
; AVX-NEXT:    [[T25:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 6
; AVX-NEXT:    [[T26:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 6
; AVX-NEXT:    [[T29:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 7
; AVX-NEXT:    [[T30:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 21
; AVX-NEXT:    [[T3:%.*]] = load i32, i32* [[T1]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T7:%.*]] = load i32, i32* [[T6]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T11:%.*]] = load i32, i32* [[T10]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T15:%.*]] = load i32, i32* [[T14]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T19:%.*]] = load i32, i32* [[T18]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T23:%.*]] = load i32, i32* [[T22]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T27:%.*]] = load i32, i32* [[T26]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T31:%.*]] = load i32, i32* [[T30]], align 4, [[TBAA0]]
; AVX-NEXT:    [[T4:%.*]] = add i32 [[T3]], 1
; AVX-NEXT:    [[T8:%.*]] = add i32 [[T7]], 2
; AVX-NEXT:    [[T12:%.*]] = add i32 [[T11]], 3
; AVX-NEXT:    [[T16:%.*]] = add i32 [[T15]], 4
; AVX-NEXT:    [[T20:%.*]] = add i32 [[T19]], 1
; AVX-NEXT:    [[T24:%.*]] = add i32 [[T23]], 2
; AVX-NEXT:    [[T28:%.*]] = add i32 [[T27]], 3
; AVX-NEXT:    [[T32:%.*]] = add i32 [[T31]], 4
; AVX-NEXT:    store i32 [[T4]], i32* [[T0]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T8]], i32* [[T5]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T12]], i32* [[T9]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T16]], i32* [[T13]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T20]], i32* [[T17]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T24]], i32* [[T21]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T28]], i32* [[T25]], align 4, [[TBAA0]]
; AVX-NEXT:    store i32 [[T32]], i32* [[T29]], align 4, [[TBAA0]]
; AVX-NEXT:    ret void
;
; AVX2-LABEL: @gather_load_4(
; AVX2-NEXT:    [[T5:%.*]] = getelementptr inbounds i32, i32* [[T0:%.*]], i64 1
; AVX2-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32*> undef, i32* [[T1:%.*]], i32 0
; AVX2-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i32*> [[TMP1]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX2-NEXT:    [[TMP3:%.*]] = getelementptr i32, <4 x i32*> [[TMP2]], <4 x i64> <i64 11, i64 4, i64 15, i64 18>
; AVX2-NEXT:    [[T21:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 5
; AVX2-NEXT:    [[T22:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 9
; AVX2-NEXT:    [[T25:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 6
; AVX2-NEXT:    [[T26:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 6
; AVX2-NEXT:    [[T29:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 7
; AVX2-NEXT:    [[T30:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 21
; AVX2-NEXT:    [[T3:%.*]] = load i32, i32* [[T1]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP4:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP3]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0]]
; AVX2-NEXT:    [[T23:%.*]] = load i32, i32* [[T22]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[T27:%.*]] = load i32, i32* [[T26]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[T31:%.*]] = load i32, i32* [[T30]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[T4:%.*]] = add i32 [[T3]], 1
; AVX2-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], <i32 2, i32 3, i32 4, i32 1>
; AVX2-NEXT:    [[T24:%.*]] = add i32 [[T23]], 2
; AVX2-NEXT:    [[T28:%.*]] = add i32 [[T27]], 3
; AVX2-NEXT:    [[T32:%.*]] = add i32 [[T31]], 4
; AVX2-NEXT:    store i32 [[T4]], i32* [[T0]], align 4, [[TBAA0]]
; AVX2-NEXT:    [[TMP6:%.*]] = bitcast i32* [[T5]] to <4 x i32>*
; AVX2-NEXT:    store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4, [[TBAA0]]
; AVX2-NEXT:    store i32 [[T24]], i32* [[T21]], align 4, [[TBAA0]]
; AVX2-NEXT:    store i32 [[T28]], i32* [[T25]], align 4, [[TBAA0]]
; AVX2-NEXT:    store i32 [[T32]], i32* [[T29]], align 4, [[TBAA0]]
; AVX2-NEXT:    ret void
;
; AVX512-LABEL: @gather_load_4(
; AVX512-NEXT:    [[T5:%.*]] = getelementptr inbounds i32, i32* [[T0:%.*]], i64 1
; AVX512-NEXT:    [[TMP1:%.*]] = insertelement <4 x i32*> undef, i32* [[T1:%.*]], i32 0
; AVX512-NEXT:    [[TMP2:%.*]] = shufflevector <4 x i32*> [[TMP1]], <4 x i32*> undef, <4 x i32> zeroinitializer
; AVX512-NEXT:    [[TMP3:%.*]] = getelementptr i32, <4 x i32*> [[TMP2]], <4 x i64> <i64 11, i64 4, i64 15, i64 18>
; AVX512-NEXT:    [[T21:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 5
; AVX512-NEXT:    [[T22:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 9
; AVX512-NEXT:    [[T25:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 6
; AVX512-NEXT:    [[T26:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 6
; AVX512-NEXT:    [[T29:%.*]] = getelementptr inbounds i32, i32* [[T0]], i64 7
; AVX512-NEXT:    [[T30:%.*]] = getelementptr inbounds i32, i32* [[T1]], i64 21
; AVX512-NEXT:    [[T3:%.*]] = load i32, i32* [[T1]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP4:%.*]] = call <4 x i32> @llvm.masked.gather.v4i32.v4p0i32(<4 x i32*> [[TMP3]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x i32> undef), [[TBAA0]]
; AVX512-NEXT:    [[T23:%.*]] = load i32, i32* [[T22]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[T27:%.*]] = load i32, i32* [[T26]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[T31:%.*]] = load i32, i32* [[T30]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[T4:%.*]] = add i32 [[T3]], 1
; AVX512-NEXT:    [[TMP5:%.*]] = add <4 x i32> [[TMP4]], <i32 2, i32 3, i32 4, i32 1>
; AVX512-NEXT:    [[T24:%.*]] = add i32 [[T23]], 2
; AVX512-NEXT:    [[T28:%.*]] = add i32 [[T27]], 3
; AVX512-NEXT:    [[T32:%.*]] = add i32 [[T31]], 4
; AVX512-NEXT:    store i32 [[T4]], i32* [[T0]], align 4, [[TBAA0]]
; AVX512-NEXT:    [[TMP6:%.*]] = bitcast i32* [[T5]] to <4 x i32>*
; AVX512-NEXT:    store <4 x i32> [[TMP5]], <4 x i32>* [[TMP6]], align 4, [[TBAA0]]
; AVX512-NEXT:    store i32 [[T24]], i32* [[T21]], align 4, [[TBAA0]]
; AVX512-NEXT:    store i32 [[T28]], i32* [[T25]], align 4, [[TBAA0]]
; AVX512-NEXT:    store i32 [[T32]], i32* [[T29]], align 4, [[TBAA0]]
; AVX512-NEXT:    ret void
;
  %t5 = getelementptr inbounds i32, i32* %t0, i64 1
  %t6 = getelementptr inbounds i32, i32* %t1, i64 11
  %t9 = getelementptr inbounds i32, i32* %t0, i64 2
  %t10 = getelementptr inbounds i32, i32* %t1, i64 4
  %t13 = getelementptr inbounds i32, i32* %t0, i64 3
  %t14 = getelementptr inbounds i32, i32* %t1, i64 15
  %t17 = getelementptr inbounds i32, i32* %t0, i64 4
  %t18 = getelementptr inbounds i32, i32* %t1, i64 18
  %t21 = getelementptr inbounds i32, i32* %t0, i64 5
  %t22 = getelementptr inbounds i32, i32* %t1, i64 9
  %t25 = getelementptr inbounds i32, i32* %t0, i64 6
  %t26 = getelementptr inbounds i32, i32* %t1, i64 6
  %t29 = getelementptr inbounds i32, i32* %t0, i64 7
  %t30 = getelementptr inbounds i32, i32* %t1, i64 21

  %t3 = load i32, i32* %t1, align 4, !tbaa !2
  %t7 = load i32, i32* %t6, align 4, !tbaa !2
  %t11 = load i32, i32* %t10, align 4, !tbaa !2
  %t15 = load i32, i32* %t14, align 4, !tbaa !2
  %t19 = load i32, i32* %t18, align 4, !tbaa !2
  %t23 = load i32, i32* %t22, align 4, !tbaa !2
  %t27 = load i32, i32* %t26, align 4, !tbaa !2
  %t31 = load i32, i32* %t30, align 4, !tbaa !2

  %t4 = add i32 %t3, 1
  %t8 = add i32 %t7, 2
  %t12 = add i32 %t11, 3
  %t16 = add i32 %t15, 4
  %t20 = add i32 %t19, 1
  %t24 = add i32 %t23, 2
  %t28 = add i32 %t27, 3
  %t32 = add i32 %t31, 4

  store i32 %t4, i32* %t0, align 4, !tbaa !2
  store i32 %t8, i32* %t5, align 4, !tbaa !2
  store i32 %t12, i32* %t9, align 4, !tbaa !2
  store i32 %t16, i32* %t13, align 4, !tbaa !2
  store i32 %t20, i32* %t17, align 4, !tbaa !2
  store i32 %t24, i32* %t21, align 4, !tbaa !2
  store i32 %t28, i32* %t25, align 4, !tbaa !2
  store i32 %t32, i32* %t29, align 4, !tbaa !2

  ret void
}


define void @gather_load_div(float* noalias nocapture %0, float* noalias nocapture readonly %1) {
; SSE-LABEL: @gather_load_div(
; SSE-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP1:%.*]], i64 10
; SSE-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 3
; SSE-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 14
; SSE-NEXT:    [[TMP6:%.*]] = insertelement <4 x float*> undef, float* [[TMP1]], i32 0
; SSE-NEXT:    [[TMP7:%.*]] = insertelement <4 x float*> [[TMP6]], float* [[TMP3]], i32 1
; SSE-NEXT:    [[TMP8:%.*]] = insertelement <4 x float*> [[TMP7]], float* [[TMP4]], i32 2
; SSE-NEXT:    [[TMP9:%.*]] = insertelement <4 x float*> [[TMP8]], float* [[TMP5]], i32 3
; SSE-NEXT:    [[TMP10:%.*]] = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> [[TMP9]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef), [[TBAA0]]
; SSE-NEXT:    [[TMP11:%.*]] = shufflevector <4 x float*> [[TMP6]], <4 x float*> undef, <4 x i32> zeroinitializer
; SSE-NEXT:    [[TMP12:%.*]] = getelementptr float, <4 x float*> [[TMP11]], <4 x i64> <i64 4, i64 13, i64 11, i64 44>
; SSE-NEXT:    [[TMP13:%.*]] = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> [[TMP12]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef), [[TBAA0]]
; SSE-NEXT:    [[TMP14:%.*]] = fdiv <4 x float> [[TMP10]], [[TMP13]]
; SSE-NEXT:    [[TMP15:%.*]] = getelementptr inbounds float, float* [[TMP0:%.*]], i64 4
; SSE-NEXT:    [[TMP16:%.*]] = bitcast float* [[TMP0]] to <4 x float>*
; SSE-NEXT:    store <4 x float> [[TMP14]], <4 x float>* [[TMP16]], align 4, [[TBAA0]]
; SSE-NEXT:    [[TMP17:%.*]] = getelementptr float, <4 x float*> [[TMP11]], <4 x i64> <i64 17, i64 8, i64 5, i64 20>
; SSE-NEXT:    [[TMP18:%.*]] = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> [[TMP17]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef), [[TBAA0]]
; SSE-NEXT:    [[TMP19:%.*]] = getelementptr float, <4 x float*> [[TMP11]], <4 x i64> <i64 33, i64 30, i64 27, i64 23>
; SSE-NEXT:    [[TMP20:%.*]] = call <4 x float> @llvm.masked.gather.v4f32.v4p0f32(<4 x float*> [[TMP19]], i32 4, <4 x i1> <i1 true, i1 true, i1 true, i1 true>, <4 x float> undef), [[TBAA0]]
; SSE-NEXT:    [[TMP21:%.*]] = fdiv <4 x float> [[TMP18]], [[TMP20]]
; SSE-NEXT:    [[TMP22:%.*]] = bitcast float* [[TMP15]] to <4 x float>*
; SSE-NEXT:    store <4 x float> [[TMP21]], <4 x float>* [[TMP22]], align 4, [[TBAA0]]
; SSE-NEXT:    ret void
;
; AVX-LABEL: @gather_load_div(
; AVX-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP1:%.*]], i64 10
; AVX-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 3
; AVX-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 14
; AVX-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 17
; AVX-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 8
; AVX-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 5
; AVX-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 20
; AVX-NEXT:    [[TMP10:%.*]] = insertelement <8 x float*> undef, float* [[TMP1]], i32 0
; AVX-NEXT:    [[TMP11:%.*]] = insertelement <8 x float*> [[TMP10]], float* [[TMP3]], i32 1
; AVX-NEXT:    [[TMP12:%.*]] = insertelement <8 x float*> [[TMP11]], float* [[TMP4]], i32 2
; AVX-NEXT:    [[TMP13:%.*]] = insertelement <8 x float*> [[TMP12]], float* [[TMP5]], i32 3
; AVX-NEXT:    [[TMP14:%.*]] = insertelement <8 x float*> [[TMP13]], float* [[TMP6]], i32 4
; AVX-NEXT:    [[TMP15:%.*]] = insertelement <8 x float*> [[TMP14]], float* [[TMP7]], i32 5
; AVX-NEXT:    [[TMP16:%.*]] = insertelement <8 x float*> [[TMP15]], float* [[TMP8]], i32 6
; AVX-NEXT:    [[TMP17:%.*]] = insertelement <8 x float*> [[TMP16]], float* [[TMP9]], i32 7
; AVX-NEXT:    [[TMP18:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP17]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX-NEXT:    [[TMP19:%.*]] = shufflevector <8 x float*> [[TMP10]], <8 x float*> undef, <8 x i32> zeroinitializer
; AVX-NEXT:    [[TMP20:%.*]] = getelementptr float, <8 x float*> [[TMP19]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
; AVX-NEXT:    [[TMP21:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP20]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX-NEXT:    [[TMP22:%.*]] = fdiv <8 x float> [[TMP18]], [[TMP21]]
; AVX-NEXT:    [[TMP23:%.*]] = bitcast float* [[TMP0:%.*]] to <8 x float>*
; AVX-NEXT:    store <8 x float> [[TMP22]], <8 x float>* [[TMP23]], align 4, [[TBAA0]]
; AVX-NEXT:    ret void
;
; AVX2-LABEL: @gather_load_div(
; AVX2-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP1:%.*]], i64 10
; AVX2-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 3
; AVX2-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 14
; AVX2-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 17
; AVX2-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 8
; AVX2-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 5
; AVX2-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 20
; AVX2-NEXT:    [[TMP10:%.*]] = insertelement <8 x float*> undef, float* [[TMP1]], i32 0
; AVX2-NEXT:    [[TMP11:%.*]] = insertelement <8 x float*> [[TMP10]], float* [[TMP3]], i32 1
; AVX2-NEXT:    [[TMP12:%.*]] = insertelement <8 x float*> [[TMP11]], float* [[TMP4]], i32 2
; AVX2-NEXT:    [[TMP13:%.*]] = insertelement <8 x float*> [[TMP12]], float* [[TMP5]], i32 3
; AVX2-NEXT:    [[TMP14:%.*]] = insertelement <8 x float*> [[TMP13]], float* [[TMP6]], i32 4
; AVX2-NEXT:    [[TMP15:%.*]] = insertelement <8 x float*> [[TMP14]], float* [[TMP7]], i32 5
; AVX2-NEXT:    [[TMP16:%.*]] = insertelement <8 x float*> [[TMP15]], float* [[TMP8]], i32 6
; AVX2-NEXT:    [[TMP17:%.*]] = insertelement <8 x float*> [[TMP16]], float* [[TMP9]], i32 7
; AVX2-NEXT:    [[TMP18:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP17]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX2-NEXT:    [[TMP19:%.*]] = shufflevector <8 x float*> [[TMP10]], <8 x float*> undef, <8 x i32> zeroinitializer
; AVX2-NEXT:    [[TMP20:%.*]] = getelementptr float, <8 x float*> [[TMP19]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
; AVX2-NEXT:    [[TMP21:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP20]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX2-NEXT:    [[TMP22:%.*]] = fdiv <8 x float> [[TMP18]], [[TMP21]]
; AVX2-NEXT:    [[TMP23:%.*]] = bitcast float* [[TMP0:%.*]] to <8 x float>*
; AVX2-NEXT:    store <8 x float> [[TMP22]], <8 x float>* [[TMP23]], align 4, [[TBAA0]]
; AVX2-NEXT:    ret void
;
; AVX512-LABEL: @gather_load_div(
; AVX512-NEXT:    [[TMP3:%.*]] = getelementptr inbounds float, float* [[TMP1:%.*]], i64 10
; AVX512-NEXT:    [[TMP4:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 3
; AVX512-NEXT:    [[TMP5:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 14
; AVX512-NEXT:    [[TMP6:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 17
; AVX512-NEXT:    [[TMP7:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 8
; AVX512-NEXT:    [[TMP8:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 5
; AVX512-NEXT:    [[TMP9:%.*]] = getelementptr inbounds float, float* [[TMP1]], i64 20
; AVX512-NEXT:    [[TMP10:%.*]] = insertelement <8 x float*> undef, float* [[TMP1]], i32 0
; AVX512-NEXT:    [[TMP11:%.*]] = insertelement <8 x float*> [[TMP10]], float* [[TMP3]], i32 1
; AVX512-NEXT:    [[TMP12:%.*]] = insertelement <8 x float*> [[TMP11]], float* [[TMP4]], i32 2
; AVX512-NEXT:    [[TMP13:%.*]] = insertelement <8 x float*> [[TMP12]], float* [[TMP5]], i32 3
; AVX512-NEXT:    [[TMP14:%.*]] = insertelement <8 x float*> [[TMP13]], float* [[TMP6]], i32 4
; AVX512-NEXT:    [[TMP15:%.*]] = insertelement <8 x float*> [[TMP14]], float* [[TMP7]], i32 5
; AVX512-NEXT:    [[TMP16:%.*]] = insertelement <8 x float*> [[TMP15]], float* [[TMP8]], i32 6
; AVX512-NEXT:    [[TMP17:%.*]] = insertelement <8 x float*> [[TMP16]], float* [[TMP9]], i32 7
; AVX512-NEXT:    [[TMP18:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP17]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX512-NEXT:    [[TMP19:%.*]] = shufflevector <8 x float*> [[TMP10]], <8 x float*> undef, <8 x i32> zeroinitializer
; AVX512-NEXT:    [[TMP20:%.*]] = getelementptr float, <8 x float*> [[TMP19]], <8 x i64> <i64 4, i64 13, i64 11, i64 44, i64 33, i64 30, i64 27, i64 23>
; AVX512-NEXT:    [[TMP21:%.*]] = call <8 x float> @llvm.masked.gather.v8f32.v8p0f32(<8 x float*> [[TMP20]], i32 4, <8 x i1> <i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true, i1 true>, <8 x float> undef), [[TBAA0]]
; AVX512-NEXT:    [[TMP22:%.*]] = fdiv <8 x float> [[TMP18]], [[TMP21]]
; AVX512-NEXT:    [[TMP23:%.*]] = bitcast float* [[TMP0:%.*]] to <8 x float>*
; AVX512-NEXT:    store <8 x float> [[TMP22]], <8 x float>* [[TMP23]], align 4, [[TBAA0]]
; AVX512-NEXT:    ret void
;
  %3 = load float, float* %1, align 4, !tbaa !2
  %4 = getelementptr inbounds float, float* %1, i64 4
  %5 = load float, float* %4, align 4, !tbaa !2
  %6 = fdiv float %3, %5
  %7 = getelementptr inbounds float, float* %0, i64 1
  store float %6, float* %0, align 4, !tbaa !2
  %8 = getelementptr inbounds float, float* %1, i64 10
  %9 = load float, float* %8, align 4, !tbaa !2
  %10 = getelementptr inbounds float, float* %1, i64 13
  %11 = load float, float* %10, align 4, !tbaa !2
  %12 = fdiv float %9, %11
  %13 = getelementptr inbounds float, float* %0, i64 2
  store float %12, float* %7, align 4, !tbaa !2
  %14 = getelementptr inbounds float, float* %1, i64 3
  %15 = load float, float* %14, align 4, !tbaa !2
  %16 = getelementptr inbounds float, float* %1, i64 11
  %17 = load float, float* %16, align 4, !tbaa !2
  %18 = fdiv float %15, %17
  %19 = getelementptr inbounds float, float* %0, i64 3
  store float %18, float* %13, align 4, !tbaa !2
  %20 = getelementptr inbounds float, float* %1, i64 14
  %21 = load float, float* %20, align 4, !tbaa !2
  %22 = getelementptr inbounds float, float* %1, i64 44
  %23 = load float, float* %22, align 4, !tbaa !2
  %24 = fdiv float %21, %23
  %25 = getelementptr inbounds float, float* %0, i64 4
  store float %24, float* %19, align 4, !tbaa !2
  %26 = getelementptr inbounds float, float* %1, i64 17
  %27 = load float, float* %26, align 4, !tbaa !2
  %28 = getelementptr inbounds float, float* %1, i64 33
  %29 = load float, float* %28, align 4, !tbaa !2
  %30 = fdiv float %27, %29
  %31 = getelementptr inbounds float, float* %0, i64 5
  store float %30, float* %25, align 4, !tbaa !2
  %32 = getelementptr inbounds float, float* %1, i64 8
  %33 = load float, float* %32, align 4, !tbaa !2
  %34 = getelementptr inbounds float, float* %1, i64 30
  %35 = load float, float* %34, align 4, !tbaa !2
  %36 = fdiv float %33, %35
  %37 = getelementptr inbounds float, float* %0, i64 6
  store float %36, float* %31, align 4, !tbaa !2
  %38 = getelementptr inbounds float, float* %1, i64 5
  %39 = load float, float* %38, align 4, !tbaa !2
  %40 = getelementptr inbounds float, float* %1, i64 27
  %41 = load float, float* %40, align 4, !tbaa !2
  %42 = fdiv float %39, %41
  %43 = getelementptr inbounds float, float* %0, i64 7
  store float %42, float* %37, align 4, !tbaa !2
  %44 = getelementptr inbounds float, float* %1, i64 20
  %45 = load float, float* %44, align 4, !tbaa !2
  %46 = getelementptr inbounds float, float* %1, i64 23
  %47 = load float, float* %46, align 4, !tbaa !2
  %48 = fdiv float %45, %47
  store float %48, float* %43, align 4, !tbaa !2
  ret void
}

!2 = !{!3, !3, i64 0}
!3 = !{!"short", !4, i64 0}
!4 = !{!"omnipotent char", !5, i64 0}
!5 = !{!"Simple C++ TBAA"}