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
112
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph" --version 6
; RUN: opt -p loop-vectorize -force-vector-width=4 -S %s | FileCheck %s
define void @induction_with_multiple_instructions_in_chain(ptr %p, ptr noalias %q) {
; CHECK-LABEL: define void @induction_with_multiple_instructions_in_chain(
; CHECK-SAME: ptr [[P:%.*]], ptr noalias [[Q:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br 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: [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 3, i32 6, i32 9, i32 12>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND1:%.*]] = phi <4 x i32> [ <i32 0, i32 3, i32 6, i32 9>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT2:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = sext <4 x i32> [[VEC_IND]] to <4 x i64>
; CHECK-NEXT: [[TMP1:%.*]] = extractelement <4 x i64> [[TMP0]], i32 0
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i64> [[TMP0]], i32 1
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i64> [[TMP0]], i32 2
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x i64> [[TMP0]], i32 3
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP2]]
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP3]]
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr i8, ptr [[P]], i64 [[TMP4]]
; CHECK-NEXT: store i8 0, ptr [[TMP5]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP6]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP7]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP8]], align 1
; CHECK-NEXT: [[TMP9:%.*]] = sext <4 x i32> [[VEC_IND1]] to <4 x i64>
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <4 x i64> [[TMP9]], i32 0
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x i64> [[TMP9]], i32 1
; CHECK-NEXT: [[TMP12:%.*]] = extractelement <4 x i64> [[TMP9]], i32 2
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x i64> [[TMP9]], i32 3
; CHECK-NEXT: [[TMP14:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP10]]
; CHECK-NEXT: [[TMP15:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP11]]
; CHECK-NEXT: [[TMP16:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP12]]
; CHECK-NEXT: [[TMP17:%.*]] = getelementptr i8, ptr [[Q]], i64 [[TMP13]]
; CHECK-NEXT: store i8 0, ptr [[TMP14]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP15]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP16]], align 1
; CHECK-NEXT: store i8 0, ptr [[TMP17]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[VEC_IND]], splat (i32 12)
; CHECK-NEXT: [[VEC_IND_NEXT2]] = add <4 x i32> [[VEC_IND1]], splat (i32 12)
; CHECK-NEXT: [[TMP18:%.*]] = icmp eq i64 [[INDEX_NEXT]], 1024
; CHECK-NEXT: br i1 [[TMP18]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[SCALAR_PH:.*]]
; CHECK: [[SCALAR_PH]]:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%ind.1 = phi i32 [ 3, %entry ], [ %ind.1.next, %loop ]
%ind.2 = phi i32 [ 0, %entry ], [ %ind.1, %loop ]
%sext.1 = sext i32 %ind.1 to i64
%gep.1 = getelementptr i8, ptr %p, i64 %sext.1
store i8 0, ptr %gep.1
%sext.2 = sext i32 %ind.2 to i64
%gep.2 = getelementptr i8, ptr %q, i64 %sext.2
store i8 0, ptr %gep.2
%iv.next = add i64 %iv, 1
%ind.1.next = add i32 %ind.1, 3
%ec = icmp eq i64 %iv, 1024
br i1 %ec, label %exit, label %loop
exit:
ret void
}
define i32 @induction_trunc_wrapflags(ptr %p) {
; CHECK-LABEL: define i32 @induction_trunc_wrapflags(
; CHECK-SAME: ptr [[P:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*:]]
; CHECK-NEXT: br 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: [[VEC_IND:%.*]] = phi <4 x i8> [ <i8 -72, i8 -68, i8 -64, i8 -60>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[OFFSET_IDX:%.*]] = sub i64 326, [[INDEX]]
; CHECK-NEXT: [[TMP0:%.*]] = getelementptr i8, ptr [[P]], i64 [[OFFSET_IDX]]
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr i8, ptr [[TMP0]], i64 0
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr i8, ptr [[TMP1]], i64 -3
; CHECK-NEXT: [[REVERSE:%.*]] = shufflevector <4 x i8> [[VEC_IND]], <4 x i8> poison, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
; CHECK-NEXT: store <4 x i8> [[REVERSE]], ptr [[TMP2]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i8> [[VEC_IND]], splat (i8 16)
; CHECK-NEXT: [[TMP3:%.*]] = icmp eq i64 [[INDEX_NEXT]], 324
; CHECK-NEXT: br i1 [[TMP3]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: br label %[[SCALAR_PH:.*]]
; CHECK: [[SCALAR_PH]]:
;
entry:
br label %loop
loop:
%iv = phi i64 [ 326, %entry ], [ %iv.next, %loop ]
%ind = phi i64 [ -72, %entry ], [ %ind.next, %loop ]
%trunc = trunc i64 %ind to i8
%gep.p.iv = getelementptr i8, ptr %p, i64 %iv
store i8 %trunc, ptr %gep.p.iv, align 1
%ind.next = add nsw i64 %ind, 4
%iv.next = add i64 %iv, -1
%ec = icmp eq i64 %iv, 0
br i1 %ec, label %exit, label %loop
exit:
ret i32 0
}
|
