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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
; RUN: opt -passes=loop-vectorize -mtriple=arm64-apple-macosx -S %s | FileCheck %s
define i8 @select_icmp_var_start(ptr %a, i8 %n, i8 %start) {
; CHECK-LABEL: define i8 @select_icmp_var_start(
; CHECK-SAME: ptr [[A:%.*]], i8 [[N:%.*]], i8 [[START:%.*]]) {
; CHECK-NEXT: [[ENTRY:.*]]:
; CHECK-NEXT: [[TMP0:%.*]] = add i8 [[N]], -1
; CHECK-NEXT: [[TMP1:%.*]] = zext i8 [[TMP0]] to i32
; CHECK-NEXT: [[TMP2:%.*]] = add nuw nsw i32 [[TMP1]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i32 [[TMP2]], 32
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[TMP2]], 32
; CHECK-NEXT: [[N_VEC:%.*]] = sub i32 [[TMP2]], [[N_MOD_VF]]
; CHECK-NEXT: [[TMP3:%.*]] = trunc i32 [[N_VEC]] to i8
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <16 x i8> [ <i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP10:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <16 x i8> [ splat (i8 -128), %[[VECTOR_PH]] ], [ [[TMP11:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[STEP_ADD:%.*]] = add <16 x i8> [[VEC_IND]], splat (i8 16)
; CHECK-NEXT: [[INDEX4:%.*]] = trunc i32 [[INDEX]] to i8
; CHECK-NEXT: [[TMP5:%.*]] = add i8 [[INDEX4]], 0
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[TMP5]]
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i8, ptr [[TMP8]], i32 16
; CHECK-NEXT: [[WIDE_LOAD:%.*]] = load <16 x i8>, ptr [[TMP9]], align 8
; CHECK-NEXT: [[WIDE_LOAD3:%.*]] = load <16 x i8>, ptr [[TMP7]], align 8
; CHECK-NEXT: [[TMP17:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD]], splat (i8 3)
; CHECK-NEXT: [[TMP23:%.*]] = icmp eq <16 x i8> [[WIDE_LOAD3]], splat (i8 3)
; CHECK-NEXT: [[TMP10]] = select <16 x i1> [[TMP17]], <16 x i8> [[VEC_IND]], <16 x i8> [[VEC_PHI]]
; CHECK-NEXT: [[TMP11]] = select <16 x i1> [[TMP23]], <16 x i8> [[STEP_ADD]], <16 x i8> [[VEC_PHI2]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 32
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <16 x i8> [[STEP_ADD]], splat (i8 16)
; CHECK-NEXT: [[TMP12:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP12]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <16 x i8> @llvm.smax.v16i8(<16 x i8> [[TMP10]], <16 x i8> [[TMP11]])
; CHECK-NEXT: [[TMP13:%.*]] = call i8 @llvm.vector.reduce.smax.v16i8(<16 x i8> [[RDX_MINMAX]])
; CHECK-NEXT: [[RDX_SELECT_CMP12:%.*]] = icmp ne i8 [[TMP13]], -128
; CHECK-NEXT: [[RDX_SELECT:%.*]] = select i1 [[RDX_SELECT_CMP12]], i8 [[TMP13]], i8 [[START]]
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[TMP2]], [[N_VEC]]
; CHECK-NEXT: br i1 [[CMP_N]], label %[[EXIT:.*]], label %[[SCALAR_PH]]
; CHECK: [[SCALAR_PH]]:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i8 [ [[TMP3]], %[[MIDDLE_BLOCK]] ], [ 0, %[[ENTRY]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i8 [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV1:%.*]] = phi i8 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[RDX:%.*]] = phi i8 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[SEL:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i8, ptr [[A]], i8 [[IV1]]
; CHECK-NEXT: [[L:%.*]] = load i8, ptr [[GEP1]], align 8
; CHECK-NEXT: [[C:%.*]] = icmp eq i8 [[L]], 3
; CHECK-NEXT: [[SEL]] = select i1 [[C]], i8 [[IV1]], i8 [[RDX]]
; CHECK-NEXT: [[IV_NEXT]] = add nuw nsw i8 [[IV1]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i8 [[IV_NEXT]], [[N]]
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i8 [ [[SEL]], %[[LOOP]] ], [ [[RDX_SELECT]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i8 [[SEL_LCSSA]]
;
entry:
br label %loop
loop:
%iv = phi i8 [ 0, %entry ], [ %iv.next, %loop ]
%rdx = phi i8 [ %start, %entry ], [ %sel, %loop ]
%gep = getelementptr inbounds i8, ptr %a, i8 %iv
%l = load i8, ptr %gep, align 8
%c = icmp eq i8 %l, 3
%sel = select i1 %c, i8 %iv, i8 %rdx
%iv.next = add nuw nsw i8 %iv, 1
%ec = icmp eq i8 %iv.next, %n
br i1 %ec, label %exit, label %loop
exit:
ret i8 %sel
}
define i32 @select_icmp_var_start_iv_trunc(i32 %N, i32 %start) #0 {
; CHECK-LABEL: define i32 @select_icmp_var_start_iv_trunc(
; CHECK-SAME: i32 [[N:%.*]], i32 [[START:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: [[ENTRY:.*]]:
; CHECK-NEXT: [[N_POS:%.*]] = icmp sgt i32 [[N]], 0
; CHECK-NEXT: call void @llvm.assume(i1 [[N_POS]])
; CHECK-NEXT: [[N_EXT:%.*]] = zext i32 [[N]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = add nuw nsw i64 [[N_EXT]], 1
; CHECK-NEXT: [[MIN_ITERS_CHECK1:%.*]] = icmp ult i64 [[TMP0]], 16
; CHECK-NEXT: br i1 [[MIN_ITERS_CHECK1]], label %[[SCALAR_PH:.*]], label %[[VECTOR_PH:.*]]
; CHECK: [[VECTOR_PH]]:
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[TMP0]], 16
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[TMP0]], [[N_MOD_VF]]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[START]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = icmp eq <4 x i32> [[BROADCAST_SPLAT]], zeroinitializer
; CHECK-NEXT: br label %[[VECTOR_BODY:.*]]
; CHECK: [[VECTOR_BODY]]:
; CHECK-NEXT: [[INDEX:%.*]] = phi i64 [ 0, %[[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP3:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI2:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP4:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI3:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP5:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI4:%.*]] = phi <4 x i32> [ splat (i32 -2147483648), %[[VECTOR_PH]] ], [ [[TMP6:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_IND:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 2, i32 3>, %[[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], %[[VECTOR_BODY]] ]
; CHECK-NEXT: [[STEP_ADD:%.*]] = add <4 x i32> [[VEC_IND]], splat (i32 4)
; CHECK-NEXT: [[STEP_ADD_2:%.*]] = add <4 x i32> [[STEP_ADD]], splat (i32 4)
; CHECK-NEXT: [[STEP_ADD_3:%.*]] = add <4 x i32> [[STEP_ADD_2]], splat (i32 4)
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <4 x i1> [[TMP1]], i32 0
; CHECK-NEXT: [[TMP3]] = select i1 [[TMP2]], <4 x i32> [[VEC_IND]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT: [[TMP4]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD]], <4 x i32> [[VEC_PHI2]]
; CHECK-NEXT: [[TMP5]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_2]], <4 x i32> [[VEC_PHI3]]
; CHECK-NEXT: [[TMP6]] = select i1 [[TMP2]], <4 x i32> [[STEP_ADD_3]], <4 x i32> [[VEC_PHI4]]
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 16
; CHECK-NEXT: [[VEC_IND_NEXT]] = add <4 x i32> [[STEP_ADD_3]], splat (i32 4)
; CHECK-NEXT: [[TMP7:%.*]] = icmp eq i64 [[INDEX_NEXT]], [[N_VEC]]
; CHECK-NEXT: br i1 [[TMP7]], label %[[MIDDLE_BLOCK:.*]], label %[[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: [[MIDDLE_BLOCK]]:
; CHECK-NEXT: [[RDX_MINMAX:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[TMP3]], <4 x i32> [[TMP4]])
; CHECK-NEXT: [[RDX_MINMAX5:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX]], <4 x i32> [[TMP5]])
; CHECK-NEXT: [[RDX_MINMAX6:%.*]] = call <4 x i32> @llvm.smax.v4i32(<4 x i32> [[RDX_MINMAX5]], <4 x i32> [[TMP6]])
; CHECK-NEXT: [[TMP16:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[RDX_MINMAX6]])
; CHECK-NEXT: [[RDX_SELECT_CMP18:%.*]] = icmp ne i32 [[TMP16]], -2147483648
; CHECK-NEXT: [[RDX_SELECT19:%.*]] = select i1 [[RDX_SELECT_CMP18]], i32 [[TMP16]], i32 [[START]]
; CHECK-NEXT: [[CMP_N:%.*]] = icmp eq i64 [[TMP0]], [[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: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ], [ [[START]], %[[ENTRY]] ]
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[BC_RESUME_VAL]], %[[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], %[[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[C:%.*]] = icmp eq i32 [[START]], 0
; CHECK-NEXT: [[IV_TRUNC:%.*]] = trunc i64 [[IV]] to i32
; CHECK-NEXT: [[RED_NEXT]] = select i1 [[C]], i32 [[IV_TRUNC]], i32 [[RED]]
; CHECK-NEXT: [[IV_NEXT]] = add i64 [[IV]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV]], [[N_EXT]]
; CHECK-NEXT: br i1 [[EC]], label %[[EXIT]], label %[[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: [[RED_NEXT_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], %[[LOOP]] ], [ [[RDX_SELECT19]], %[[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[RED_NEXT_LCSSA]]
;
entry:
%N.pos = icmp sgt i32 %N, 0
call void @llvm.assume(i1 %N.pos)
%N.ext = zext i32 %N to i64
br label %loop
loop:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %loop ]
%red = phi i32 [ %start, %entry ], [ %red.next, %loop ]
%c = icmp eq i32 %start, 0
%iv.trunc = trunc i64 %iv to i32
%red.next = select i1 %c, i32 %iv.trunc, i32 %red
%iv.next = add i64 %iv, 1
%ec = icmp eq i64 %iv, %N.ext
br i1 %ec, label %exit, label %loop
exit:
ret i32 %red.next
}
declare void @llvm.assume(i1 noundef)
attributes #0 = { "target-cpu"="apple-m1" }
|
