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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -force-vector-width=4 -force-vector-interleave=1 -passes=loop-vectorize -S %s | FileCheck %s
target datalayout = "e-m:o-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
define i32 @test(i64 %N, i32 %x) {
; CHECK-LABEL: @test(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[EXTRA_ITER:%.*]] = and i64 [[N:%.*]], 7
; CHECK-NEXT: br label [[CHECK:%.*]]
; CHECK: check:
; CHECK-NEXT: [[EXTRA_ITER_CHECK:%.*]] = icmp eq i64 [[EXTRA_ITER]], 0
; CHECK-NEXT: br i1 [[EXTRA_ITER_CHECK]], label [[EXIT:%.*]], label [[LOOP_PREHEADER:%.*]]
; CHECK: loop.preheader:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: [[N_RND_UP:%.*]] = add i64 [[EXTRA_ITER]], 3
; CHECK-NEXT: [[N_MOD_VF:%.*]] = urem i64 [[N_RND_UP]], 4
; CHECK-NEXT: [[N_VEC:%.*]] = sub i64 [[N_RND_UP]], [[N_MOD_VF]]
; CHECK-NEXT: [[IND_END:%.*]] = sub i64 [[EXTRA_ITER]], [[N_VEC]]
; CHECK-NEXT: [[TRIP_COUNT_MINUS_1:%.*]] = sub i64 [[EXTRA_ITER]], 1
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i64> poison, i64 [[TRIP_COUNT_MINUS_1]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT]], <4 x i64> poison, <4 x i32> 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> [ zeroinitializer, [[VECTOR_PH]] ], [ [[TMP2:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT1:%.*]] = insertelement <4 x i64> poison, i64 [[INDEX]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT2:%.*]] = shufflevector <4 x i64> [[BROADCAST_SPLATINSERT1]], <4 x i64> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[VEC_IV:%.*]] = add <4 x i64> [[BROADCAST_SPLAT2]], <i64 0, i64 1, i64 2, i64 3>
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule <4 x i64> [[VEC_IV]], [[BROADCAST_SPLAT]]
; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt <4 x i32> [[VEC_PHI]], <i32 10, i32 10, i32 10, i32 10>
; CHECK-NEXT: [[TMP2]] = select <4 x i1> [[TMP1]], <4 x i32> [[VEC_PHI]], <4 x i32> <i32 10, i32 10, i32 10, i32 10>
; CHECK-NEXT: [[TMP3:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[TMP2]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT: [[INDEX_NEXT]] = add 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: [[TMP5:%.*]] = call i32 @llvm.vector.reduce.smax.v4i32(<4 x i32> [[TMP3]])
; CHECK-NEXT: br i1 true, label [[EXIT_LOOPEXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i64 [ [[IND_END]], [[MIDDLE_BLOCK]] ], [ [[EXTRA_ITER]], [[LOOP_PREHEADER]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP5]], [[MIDDLE_BLOCK]] ], [ 0, [[LOOP_PREHEADER]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[NEXT:%.*]] = phi i32 [ [[SEL:%.*]], [[LOOP]] ], [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[IV:%.*]] = phi i64 [ [[IV_NEXT:%.*]], [[LOOP]] ], [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ]
; CHECK-NEXT: [[SEL_COND:%.*]] = icmp sgt i32 [[NEXT]], 10
; CHECK-NEXT: [[SEL]] = select i1 [[SEL_COND]], i32 [[NEXT]], i32 10
; CHECK-NEXT: [[IV_NEXT]] = add nsw i64 [[IV]], -1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i64 [[IV_NEXT]], 0
; CHECK-NEXT: br i1 [[EC]], label [[EXIT_LOOPEXIT]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: exit.loopexit:
; CHECK-NEXT: [[SEL_LCSSA:%.*]] = phi i32 [ [[SEL]], [[LOOP]] ], [ [[TMP5]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: br label [[EXIT]]
; CHECK: exit:
; CHECK-NEXT: [[RESULT:%.*]] = phi i32 [ 0, [[CHECK]] ], [ [[SEL_LCSSA]], [[EXIT_LOOPEXIT]] ]
; CHECK-NEXT: ret i32 [[RESULT]]
;
entry:
%extra.iter = and i64 %N, 7
br label %check
check:
%extra.iter.check = icmp eq i64 %extra.iter, 0
br i1 %extra.iter.check, label %exit, label %loop
loop:
%next = phi i32 [ %sel, %loop ], [ 0, %check ]
%iv = phi i64 [ %iv.next, %loop ], [ %extra.iter, %check ]
%sel.cond = icmp sgt i32 %next, 10
%sel = select i1 %sel.cond, i32 %next, i32 10
%iv.next = add nsw i64 %iv, -1
%ec = icmp eq i64 %iv.next, 0
br i1 %ec, label %exit, label %loop
exit:
%result = phi i32 [ %sel, %loop], [ 0, %check ]
ret i32 %result
}
define i32 @pr66895_tail_fold_reduction_exit_inst_gets_simplified(i32 %n) {
; CHECK-LABEL: @pr66895_tail_fold_reduction_exit_inst_gets_simplified(
; 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 i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[VEC_PHI:%.*]] = phi <4 x i32> [ <i32 0, i32 1, i32 1, i32 1>, [[VECTOR_PH]] ], [ [[VEC_PHI]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[BROADCAST_SPLATINSERT:%.*]] = insertelement <4 x i32> poison, i32 [[INDEX]], i64 0
; CHECK-NEXT: [[BROADCAST_SPLAT:%.*]] = shufflevector <4 x i32> [[BROADCAST_SPLATINSERT]], <4 x i32> poison, <4 x i32> zeroinitializer
; CHECK-NEXT: [[VEC_IV:%.*]] = add <4 x i32> [[BROADCAST_SPLAT]], <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT: [[TMP0:%.*]] = icmp ule <4 x i32> [[VEC_IV]], <i32 12, i32 12, i32 12, i32 12>
; CHECK-NEXT: [[TMP1:%.*]] = select <4 x i1> [[TMP0]], <4 x i32> [[VEC_PHI]], <4 x i32> [[VEC_PHI]]
; CHECK-NEXT: [[INDEX_NEXT]] = add i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = icmp eq i32 [[INDEX_NEXT]], 16
; CHECK-NEXT: br i1 [[TMP2]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.vector.reduce.mul.v4i32(<4 x i32> [[TMP1]])
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ -4, [[MIDDLE_BLOCK]] ], [ 12, [[ENTRY:%.*]] ]
; CHECK-NEXT: [[BC_MERGE_RDX:%.*]] = phi i32 [ [[TMP3]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[RED:%.*]] = phi i32 [ [[BC_MERGE_RDX]], [[SCALAR_PH]] ], [ [[RED_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[IV_NEXT]] = add i32 [[IV]], -1
; CHECK-NEXT: [[RED_NEXT]] = mul i32 [[RED]], 1
; CHECK-NEXT: [[EC:%.*]] = icmp eq i32 [[IV]], 0
; CHECK-NEXT: br i1 [[EC]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: [[RED_LCSSA:%.*]] = phi i32 [ [[RED_NEXT]], [[LOOP]] ], [ [[TMP3]], [[MIDDLE_BLOCK]] ]
; CHECK-NEXT: ret i32 [[RED_LCSSA]]
;
entry:
br label %loop
loop:
%iv = phi i32 [ 12, %entry ], [ %iv.next, %loop ]
%red = phi i32 [ 0, %entry ], [ %red.next, %loop ]
%iv.next = add i32 %iv, -1
%red.next = mul i32 %red, 1
%ec = icmp eq i32 %iv, 0
br i1 %ec, label %exit, label %loop
exit:
%red.lcssa = phi i32 [ %red.next, %loop ]
ret i32 %red.lcssa
}
|
