1; NOTE: Assertions have been autogenerated by utils/update_test_checks.py 2; RUN: opt < %s -S -mtriple=x86_64-unknown -mattr=+avx -slp-vectorizer | FileCheck %s 3 4@array = external global [20 x [13 x i32]] 5 6define void @hoge(i64 %idx, <4 x i32>* %sink) { 7; CHECK-LABEL: @hoge( 8; CHECK-NEXT: bb: 9; CHECK-NEXT: [[TMP0:%.*]] = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 [[IDX:%.*]], i64 5 10; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 [[IDX]], i64 6 11; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 [[IDX]], i64 7 12; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 [[IDX]], i64 8 13; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[TMP0]] to <4 x i32>* 14; CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 15; CHECK-NEXT: [[REORDER_SHUFFLE:%.*]] = shufflevector <4 x i32> [[TMP5]], <4 x i32> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 0> 16; CHECK-NEXT: [[TMP6:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 0 17; CHECK-NEXT: [[TMP7:%.*]] = insertelement <4 x i32> undef, i32 [[TMP6]], i32 0 18; CHECK-NEXT: [[TMP8:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 1 19; CHECK-NEXT: [[TMP9:%.*]] = insertelement <4 x i32> [[TMP7]], i32 [[TMP8]], i32 1 20; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 2 21; CHECK-NEXT: [[TMP11:%.*]] = insertelement <4 x i32> [[TMP9]], i32 [[TMP10]], i32 2 22; CHECK-NEXT: [[TMP12:%.*]] = extractelement <4 x i32> [[REORDER_SHUFFLE]], i32 3 23; CHECK-NEXT: [[TMP13:%.*]] = insertelement <4 x i32> [[TMP11]], i32 [[TMP12]], i32 3 24; CHECK-NEXT: store <4 x i32> [[TMP13]], <4 x i32>* [[SINK:%.*]] 25; CHECK-NEXT: ret void 26; 27bb: 28 %0 = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 %idx, i64 5 29 %1 = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 %idx, i64 6 30 %2 = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 %idx, i64 7 31 %3 = getelementptr inbounds [20 x [13 x i32]], [20 x [13 x i32]]* @array, i64 0, i64 %idx, i64 8 32 %4 = load i32, i32* %1, align 4 33 %5 = insertelement <4 x i32> undef, i32 %4, i32 0 34 %6 = load i32, i32* %2, align 4 35 %7 = insertelement <4 x i32> %5, i32 %6, i32 1 36 %8 = load i32, i32* %3, align 4 37 %9 = insertelement <4 x i32> %7, i32 %8, i32 2 38 %10 = load i32, i32* %0, align 4 39 %11 = insertelement <4 x i32> %9, i32 %10, i32 3 40 store <4 x i32> %11, <4 x i32>* %sink 41 ret void 42} 43 44