; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=x86_64-pc-linux-gnu -mcpu=generic -slp-vectorizer -pass-remarks-output=%t < %s | FileCheck %s
; RUN: FileCheck --input-file=%t --check-prefix=YAML %s
define i32 @foo(i32* nocapture readonly %diff) #0 {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[M2:%.*]] = alloca [8 x [8 x i32]], align 16
; CHECK-NEXT: [[TMP0:%.*]] = bitcast [8 x [8 x i32]]* [[M2]] to i8*
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[A_088:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[ADD24:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP1:%.*]] = shl i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[DIFF:%.*]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = or i64 [[TMP1]], 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i32, i32* [[DIFF]], i64 [[TMP2]]
; CHECK-NEXT: [[ARRAYIDX6:%.*]] = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* [[M2]], i64 0, i64 [[INDVARS_IV]], i64 0
; CHECK-NEXT: [[TMP3:%.*]] = bitcast i32* [[ARRAYIDX]] to <2 x i32>*
; CHECK-NEXT: [[TMP4:%.*]] = load <2 x i32>, <2 x i32>* [[TMP3]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = bitcast i32* [[ARRAYIDX2]] to <2 x i32>*
; CHECK-NEXT: [[TMP6:%.*]] = load <2 x i32>, <2 x i32>* [[TMP5]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = add nsw <2 x i32> [[TMP6]], [[TMP4]]
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <2 x i32> [[TMP7]], i32 0
; CHECK-NEXT: [[ADD10:%.*]] = add nsw i32 [[TMP8]], [[A_088]]
; CHECK-NEXT: [[TMP9:%.*]] = bitcast i32* [[ARRAYIDX6]] to <2 x i32>*
; CHECK-NEXT: store <2 x i32> [[TMP7]], <2 x i32>* [[TMP9]], align 16
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <2 x i32> [[TMP7]], i32 1
; CHECK-NEXT: [[ADD24]] = add nsw i32 [[ADD10]], [[TMP10]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 8
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: [[ARRAYDECAY:%.*]] = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* [[M2]], i64 0, i64 0
; CHECK-NEXT: ret i32 [[ADD24]]
;
entry:
%m2 = alloca [8 x [8 x i32]], align 16
%0 = bitcast [8 x [8 x i32]]* %m2 to i8*
br label %for.body
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%a.088 = phi i32 [ 0, %entry ], [ %add24, %for.body ]
%1 = shl i64 %indvars.iv, 3
%arrayidx = getelementptr inbounds i32, i32* %diff, i64 %1
%2 = load i32, i32* %arrayidx, align 4
%3 = or i64 %1, 4
%arrayidx2 = getelementptr inbounds i32, i32* %diff, i64 %3
%4 = load i32, i32* %arrayidx2, align 4
%add3 = add nsw i32 %4, %2
%arrayidx6 = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* %m2, i64 0, i64 %indvars.iv, i64 0
store i32 %add3, i32* %arrayidx6, align 16
%add10 = add nsw i32 %add3, %a.088
%5 = or i64 %1, 1
%arrayidx13 = getelementptr inbounds i32, i32* %diff, i64 %5
%6 = load i32, i32* %arrayidx13, align 4
%7 = or i64 %1, 5
%arrayidx16 = getelementptr inbounds i32, i32* %diff, i64 %7
%8 = load i32, i32* %arrayidx16, align 4
%add17 = add nsw i32 %8, %6
%arrayidx20 = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* %m2, i64 0, i64 %indvars.iv, i64 1
store i32 %add17, i32* %arrayidx20, align 4
%add24 = add nsw i32 %add10, %add17
; YAML: Pass: slp-vectorizer
; YAML-NEXT: Name: StoresVectorized
; YAML-NEXT: Function: foo
; YAML-NEXT: Args:
; YAML-NEXT: - String: 'Stores SLP vectorized with cost '
; YAML-NEXT: - Cost: '-1'
; YAML-NEXT: - String: ' and with tree size '
; YAML-NEXT: - TreeSize: '4'
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 8
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
%arraydecay = getelementptr inbounds [8 x [8 x i32]], [8 x [8 x i32]]* %m2, i64 0, i64 0
ret i32 %add24
}