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
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt -passes=loop-vectorize -force-vector-width=4 -S %s | FileCheck %s
define void @minbw_cast(ptr %dst, i64 %n, i1 %bool1, i1 %bool2) {
; CHECK-LABEL: define void @minbw_cast(
; CHECK-SAME: ptr [[DST:%.*]], i64 [[N:%.*]], i1 [[BOOL1:%.*]], i1 [[BOOL2:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
; CHECK-NEXT: [[BOOL1_EXT:%.*]] = zext i1 [[BOOL1]] to i32
; CHECK-NEXT: [[UMAX:%.*]] = call i64 @llvm.umax.i64(i64 [[N]], i64 1)
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i64 [[UMAX]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[UMAX]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[UMAX]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i1> poison, i1 [[BOOL2]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i1> [[BROADCAST_SPLATINSERT]], <4 x i1> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i32> poison, i32 [[BOOL1_EXT]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT1]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = trunc <4 x i32> [[BROADCAST_SPLAT2]] to <4 x i8>
; CHECK-NEXT: [[TMP1:%.*]] = zext <4 x i1> [[BROADCAST_SPLAT]] to <4 x i8>
; CHECK-NEXT: [[TMP2:%.*]] = xor <4 x i8> [[TMP0]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i8> [[TMP2]], i32 3
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: store i8 [[TMP3]], ptr [[DST]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP4]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[UMAX]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[BOOL2_EXT:%.*]] = zext i1 [[BOOL2]] to i32
; CHECK-NEXT: [[XOR:%.*]] = xor i32 [[BOOL1_EXT]], [[BOOL2_EXT]]
; CHECK-NEXT: [[XOR_TRUNC:%.*]] = trunc i32 [[XOR]] to i8
; CHECK-NEXT: store i8 [[XOR_TRUNC]], ptr [[DST]], align 1
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[CMP]], label %[[LOOP]], label %[[EXIT]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
%bool1.ext = zext i1 %bool1 to i32
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%bool2.ext = zext i1 %bool2 to i32
%xor = xor i32 %bool1.ext, %bool2.ext
%xor.trunc = trunc i32 %xor to i8
store i8 %xor.trunc, ptr %dst, align 1
%iv.next = add i64 %iv, 1
%cmp = icmp ult i64 %iv.next, %n
br i1 %cmp, label %loop, label %exit
exit:
ret void
}
; Test case for https://github.com/llvm/llvm-project/issues/151392.
define void @single_scalar_cast_stored(ptr %src, ptr %dst, i32 %n) {
; CHECK-LABEL: define void @single_scalar_cast_stored(
; CHECK-SAME: ptr [[SRC:%.*]], ptr [[DST:%.*]], i32 [[N:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
; CHECK-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N]], 4
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK]], label %[[SCALAR_PH:.*]], label %[[VECTOR_MEMCHECK:.*]]
; CHECK: [[VECTOR_MEMCHECK]]:
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr [[DST]], i64 2
; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr [[SRC]], i64 2
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr [[DST]], [[SCEVGEP1]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr [[SRC]], [[SCEVGEP]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[SCALAR_PH]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr [[SRC]], align 2, !alias.scope [[META4:![0-9]+]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i16> poison, i16 [[TMP0]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i16> [[BROADCAST_SPLATINSERT]], <4 x i16> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq <4 x i16> [[BROADCAST_SPLAT]], zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = and <4 x i16> [[BROADCAST_SPLAT]], splat (i16 15)
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <4 x i16> [[TMP2]], i32 0
; CHECK-NEXT: [[TMP5:%.*]] = select i1 [[TMP3]], i16 0, i16 [[TMP4]]
; CHECK-NEXT: store i16 [[TMP5]], ptr [[DST]], align 2, !alias.scope [[META7:![0-9]+]], !noalias [[META4]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP6:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP6]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP9:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ], [ 0, %[[VECTOR_MEMCHECK]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[L:%.*]] = load i16, ptr [[SRC]], align 2
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i16 [[L]], 0
; CHECK-NEXT: [[L_EXT:%.*]] = zext i16 [[L]] to i32
; CHECK-NEXT: [[AND:%.*]] = and i32 [[L_EXT]], 15
; CHECK-NEXT: [[SEL:%.*]] = select i1 [[CMP]], i32 0, i32 [[AND]]
; CHECK-NEXT: [[SEL_TRUNC:%.*]] = trunc i32 [[SEL]] to i16
; CHECK-NEXT: store i16 [[SEL_TRUNC]], ptr [[DST]], align 2
; CHECK-NEXT: [[IV_NEXT]] = add nuw i32 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp ne i32 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EC]], label %[[LOOP]], label %[[EXIT]], !llvm.loop [[LOOP10:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %loop ]
%l = load i16, ptr %src, align 2
%cmp = icmp eq i16 %l, 0
%l.ext = zext i16 %l to i32
%and = and i32 %l.ext, 15
%sel = select i1 %cmp, i32 0, i32 %and
%sel.trunc = trunc i32 %sel to i16
store i16 %sel.trunc, ptr %dst, align 2
%iv.next = add nuw i32 %iv, 1
%ec = icmp ne i32 %iv.next, %n
br i1 %ec, label %loop, label %exit
exit:
ret void
}
|
