tail-folding-vectorization-factor-1.ll
5.56 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -pass-remarks='loop-vectorize' -disable-output -S 2>&1 | FileCheck %s --check-prefix=CHECK-REMARKS
; RUN: opt < %s -loop-vectorize -force-vector-interleave=4 -S | FileCheck %s
; These tests are to check that fold-tail procedure produces correct scalar code when
; loop-vectorization is only unrolling but not vectorizing.
; CHECK-REMARKS: remark: {{.*}} interleaved loop (interleaved count: 4)
; CHECK-REMARKS-NEXT: remark: {{.*}} interleaved loop (interleaved count: 4)
; CHECK-REMARKS-NOT: remark: {{.*}} vectorized loop
define void @VF1-VPlanExe() {
; CHECK-LABEL: @VF1-VPlanExe
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[INDUCTION:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[INDUCTION1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[INDUCTION2:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[INDUCTION3:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule i64 [[INDUCTION]], 14
; CHECK-NEXT: [[TMP1:%.*]] = icmp ule i64 [[INDUCTION1]], 14
; CHECK-NEXT: [[TMP2:%.*]] = icmp ule i64 [[INDUCTION2]], 14
; CHECK-NEXT: [[TMP3:%.*]] = icmp ule i64 [[INDUCTION3]], 14
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ 16, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INDVARS_IV_NEXT]], 15
; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop !2
;
entry:
br label %for.body
for.cond.cleanup:
ret void
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, 15
br i1 %exitcond, label %for.cond.cleanup, label %for.body
}
define void @VF1-VPWidenCanonicalIVRecipeExe(double* %ptr1) {
; CHECK-LABEL: @VF1-VPWidenCanonicalIVRecipeExe
; CHECK-NEXT: entry:
; CHECK-NEXT: [[PTR2:%.*]] = getelementptr inbounds double, double* [[PTR1:%.*]], i64 15
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[IND_END:%.*]] = getelementptr double, double* [[PTR1]], i64 16
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[NEXT_GEP:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[NEXT_GEP1:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[NEXT_GEP2:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[NEXT_GEP3:%.*]] = getelementptr double, double* [[PTR1]], i64 [[TMP3]]
; CHECK-NEXT: [[VEC_IV:%.*]] = add i64 [[INDEX]], 0
; CHECK-NEXT: [[VEC_IV4:%.*]] = add i64 [[INDEX]], 1
; CHECK-NEXT: [[VEC_IV5:%.*]] = add i64 [[INDEX]], 2
; CHECK-NEXT: [[VEC_IV6:%.*]] = add i64 [[INDEX]], 3
; CHECK-NEXT: [[TMP4:%.*]] = icmp ule i64 [[VEC_IV]], 14
; CHECK-NEXT: [[TMP5:%.*]] = icmp ule i64 [[VEC_IV4]], 14
; CHECK-NEXT: [[TMP6:%.*]] = icmp ule i64 [[VEC_IV5]], 14
; CHECK-NEXT: [[TMP7:%.*]] = icmp ule i64 [[VEC_IV6]], 14
; CHECK-NEXT: [[INDEX_NEXT]] = add i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP8:%.*]] = icmp eq i64 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !3
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi double* [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[PTR1]], [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.cond.cleanup:
; CHECK-NEXT: ret void
; CHECK: for.body:
; CHECK-NEXT: [[ADDR:%.*]] = phi double* [ [[PTR:%.*]], [[FOR_BODY]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[PTR]] = getelementptr inbounds double, double* [[ADDR]], i64 1
; CHECK-NEXT: [[COND:%.*]] = icmp eq double* [[PTR]], [[PTR2]]
; CHECK-NEXT: br i1 [[COND]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop !4
;
entry:
%ptr2 = getelementptr inbounds double, double* %ptr1, i64 15
br label %for.body
for.cond.cleanup:
ret void
for.body:
%addr = phi double* [ %ptr, %for.body ], [ %ptr1, %entry ]
%ptr = getelementptr inbounds double, double* %addr, i64 1
%cond = icmp eq double* %ptr, %ptr2
br i1 %cond, label %for.cond.cleanup, label %for.body
}