; 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=SSE
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx      | FileCheck %s --check-prefixes=AVX
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx2     | FileCheck %s --check-prefixes=AVX
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512f  | FileCheck %s --check-prefixes=AVX
; RUN:  opt < %s -slp-vectorizer -instcombine -S -mtriple=x86_64-unknown-linux -mattr=+avx512vl | FileCheck %s --check-prefixes=AVX


@b = global [8 x i32] zeroinitializer, align 16
@a = global [8 x i32] zeroinitializer, align 16

define void @foo() {
; SSE-LABEL: @foo(
; SSE-NEXT:    [[TMP1:%.*]] = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 0), align 16
; SSE-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 0), align 16
; SSE-NEXT:    [[TMP2:%.*]] = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 2), align 8
; SSE-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 1), align 4
; SSE-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 2), align 8
; SSE-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 3), align 4
; SSE-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 4), align 16
; SSE-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 5), align 4
; SSE-NEXT:    store i32 [[TMP1]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 6), align 8
; SSE-NEXT:    store i32 [[TMP2]], i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 7), align 4
; SSE-NEXT:    ret void
;
; AVX-LABEL: @foo(
; AVX-NEXT:    [[TMP1:%.*]] = call <2 x i32> @llvm.masked.gather.v2i32.v2p0i32(<2 x i32*> <i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 0), i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 2)>, i32 8, <2 x i1> <i1 true, i1 true>, <2 x i32> undef)
; AVX-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i32> [[TMP1]], <2 x i32> poison, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
; AVX-NEXT:    store <8 x i32> [[SHUFFLE]], <8 x i32>* bitcast ([8 x i32]* @a to <8 x i32>*), align 16
; AVX-NEXT:    ret void
;
  %1 = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 0), align 16
  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 0), align 16
  %2 = load i32, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @b, i64 0, i64 2), align 8
  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 1), align 4
  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 2), align 8
  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 3), align 4
  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 4), align 16
  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 5), align 4
  store i32 %1, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 6), align 8
  store i32 %2, i32* getelementptr inbounds ([8 x i32], [8 x i32]* @a, i64 0, i64 7), align 4
  ret void
}