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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=data-with-evl \
; RUN: -prefer-predicate-over-epilogue=predicate-dont-vectorize \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=IF-EVL %s
; RUN: opt -passes=loop-vectorize \
; RUN: -force-tail-folding-style=none \
; RUN: -prefer-predicate-over-epilogue=predicate-else-scalar-epilogue \
; RUN: -mtriple=riscv64 -mattr=+v -S < %s | FileCheck --check-prefix=NO-VP %s
define void @iv32(ptr noalias %a, ptr noalias %b, i32 %N) {
; IF-EVL-LABEL: @iv32(
; IF-EVL-NEXT: entry:
; IF-EVL-NEXT: [[TMP19:%.*]] = sub i32 -1, [[N:%.*]]
; IF-EVL-NEXT: [[TMP1:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-NEXT: [[TMP2:%.*]] = mul i32 [[TMP1]], 4
; IF-EVL-NEXT: [[TMP3:%.*]] = icmp ult i32 [[TMP19]], [[TMP2]]
; IF-EVL-NEXT: br i1 [[TMP3]], label [[SCALAR_PH:%.*]], label [[ENTRY:%.*]]
; IF-EVL: vector.ph:
; IF-EVL-NEXT: [[TMP4:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-NEXT: [[TMP5:%.*]] = mul i32 [[TMP4]], 4
; IF-EVL-NEXT: [[TMP8:%.*]] = sub i32 [[TMP5]], 1
; IF-EVL-NEXT: [[N_RND_UP:%.*]] = add i32 [[N]], [[TMP8]]
; IF-EVL-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N_RND_UP]], [[TMP5]]
; IF-EVL-NEXT: [[N_VEC:%.*]] = sub i32 [[N_RND_UP]], [[N_MOD_VF]]
; IF-EVL-NEXT: [[TMP9:%.*]] = call i32 @llvm.vscale.i32()
; IF-EVL-NEXT: [[TMP10:%.*]] = mul i32 [[TMP9]], 4
; IF-EVL-NEXT: br label [[FOR_BODY:%.*]]
; IF-EVL: vector.body:
; IF-EVL-NEXT: [[IV:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT: [[EVL_BASED_IV:%.*]] = phi i32 [ 0, [[ENTRY]] ], [ [[INDEX_EVL_NEXT:%.*]], [[FOR_BODY]] ]
; IF-EVL-NEXT: [[TMP11:%.*]] = sub i32 [[N]], [[EVL_BASED_IV]]
; IF-EVL-NEXT: [[TMP12:%.*]] = call i32 @llvm.experimental.get.vector.length.i32(i32 [[TMP11]], i32 4, i1 true)
; IF-EVL-NEXT: [[TMP13:%.*]] = add i32 [[EVL_BASED_IV]], 0
; IF-EVL-NEXT: [[TMP14:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i32 [[TMP13]]
; IF-EVL-NEXT: [[TMP15:%.*]] = getelementptr inbounds i32, ptr [[TMP14]], i32 0
; IF-EVL-NEXT: [[VP_OP_LOAD:%.*]] = call <vscale x 4 x i32> @llvm.vp.load.nxv4i32.p0(ptr align 4 [[TMP15]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
; IF-EVL-NEXT: [[TMP16:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP13]]
; IF-EVL-NEXT: [[TMP17:%.*]] = getelementptr inbounds i32, ptr [[TMP16]], i32 0
; IF-EVL-NEXT: call void @llvm.vp.store.nxv4i32.p0(<vscale x 4 x i32> [[VP_OP_LOAD]], ptr align 4 [[TMP17]], <vscale x 4 x i1> shufflevector (<vscale x 4 x i1> insertelement (<vscale x 4 x i1> poison, i1 true, i64 0), <vscale x 4 x i1> poison, <vscale x 4 x i32> zeroinitializer), i32 [[TMP12]])
; IF-EVL-NEXT: [[INDEX_EVL_NEXT]] = add i32 [[TMP12]], [[EVL_BASED_IV]]
; IF-EVL-NEXT: [[IV_NEXT]] = add i32 [[IV]], [[TMP10]]
; IF-EVL-NEXT: [[TMP18:%.*]] = icmp eq i32 [[IV_NEXT]], [[N_VEC]]
; IF-EVL-NEXT: br i1 [[TMP18]], label [[MIDDLE_BLOCK:%.*]], label [[FOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; IF-EVL: middle.block:
; IF-EVL-NEXT: br i1 true, label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; IF-EVL: scalar.ph:
; IF-EVL-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY1:%.*]] ]
; IF-EVL-NEXT: br label [[FOR_BODY1:%.*]]
; IF-EVL: for.body:
; IF-EVL-NEXT: [[IV1:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT1:%.*]], [[FOR_BODY1]] ]
; IF-EVL-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 [[IV1]]
; IF-EVL-NEXT: [[TMP0:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; IF-EVL-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[IV1]]
; IF-EVL-NEXT: store i32 [[TMP0]], ptr [[ARRAYIDX4]], align 4
; IF-EVL-NEXT: [[IV_NEXT1]] = add nuw nsw i32 [[IV1]], 1
; IF-EVL-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[IV_NEXT1]], [[N]]
; IF-EVL-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY1]], !llvm.loop [[LOOP3:![0-9]+]]
; IF-EVL: for.cond.cleanup:
; IF-EVL-NEXT: ret void
;
; NO-VP-LABEL: @iv32(
; NO-VP-NEXT: entry:
; NO-VP-NEXT: [[TMP0:%.*]] = call i32 @llvm.vscale.i32()
; NO-VP-NEXT: [[TMP10:%.*]] = mul i32 [[TMP0]], 4
; NO-VP-NEXT: [[MIN_ITERS_CHECK:%.*]] = icmp ult i32 [[N:%.*]], [[TMP10]]
; NO-VP-NEXT: br i1 [[MIN_ITERS_CHECK]], label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; NO-VP: vector.ph:
; NO-VP-NEXT: [[TMP1:%.*]] = call i32 @llvm.vscale.i32()
; NO-VP-NEXT: [[TMP11:%.*]] = mul i32 [[TMP1]], 4
; NO-VP-NEXT: [[N_MOD_VF:%.*]] = urem i32 [[N]], [[TMP11]]
; NO-VP-NEXT: [[N_VEC:%.*]] = sub i32 [[N]], [[N_MOD_VF]]
; NO-VP-NEXT: [[TMP2:%.*]] = call i32 @llvm.vscale.i32()
; NO-VP-NEXT: [[TMP12:%.*]] = mul i32 [[TMP2]], 4
; NO-VP-NEXT: br label [[VECTOR_BODY:%.*]]
; NO-VP: vector.body:
; NO-VP-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; NO-VP-NEXT: [[TMP3:%.*]] = add i32 [[INDEX]], 0
; NO-VP-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[B:%.*]], i32 [[TMP3]]
; NO-VP-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[TMP4]], i32 0
; NO-VP-NEXT: [[WIDE_LOAD:%.*]] = load <vscale x 4 x i32>, ptr [[TMP5]], align 4
; NO-VP-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP3]]
; NO-VP-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP6]], i32 0
; NO-VP-NEXT: store <vscale x 4 x i32> [[WIDE_LOAD]], ptr [[TMP7]], align 4
; NO-VP-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], [[TMP12]]
; NO-VP-NEXT: [[TMP8:%.*]] = icmp eq i32 [[INDEX_NEXT]], [[N_VEC]]
; NO-VP-NEXT: br i1 [[TMP8]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; NO-VP: middle.block:
; NO-VP-NEXT: [[CMP_N:%.*]] = icmp eq i32 [[N]], [[N_VEC]]
; NO-VP-NEXT: br i1 [[CMP_N]], label [[FOR_COND_CLEANUP:%.*]], label [[SCALAR_PH]]
; NO-VP: scalar.ph:
; NO-VP-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ [[N_VEC]], [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; NO-VP-NEXT: br label [[FOR_BODY:%.*]]
; NO-VP: for.body:
; NO-VP-NEXT: [[IV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[IV_NEXT:%.*]], [[FOR_BODY]] ]
; NO-VP-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[B]], i32 [[IV]]
; NO-VP-NEXT: [[TMP9:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
; NO-VP-NEXT: [[ARRAYIDX4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[IV]]
; NO-VP-NEXT: store i32 [[TMP9]], ptr [[ARRAYIDX4]], align 4
; NO-VP-NEXT: [[IV_NEXT]] = add nuw nsw i32 [[IV]], 1
; NO-VP-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[IV_NEXT]], [[N]]
; NO-VP-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; NO-VP: for.cond.cleanup:
; NO-VP-NEXT: ret void
;
entry:
br label %for.body
for.body:
%iv = phi i32 [ 0, %entry ], [ %iv.next, %for.body ]
%arrayidx = getelementptr inbounds i32, ptr %b, i32 %iv
%0 = load i32, ptr %arrayidx, align 4
%arrayidx4 = getelementptr inbounds i32, ptr %a, i32 %iv
store i32 %0, ptr %arrayidx4, align 4
%iv.next = add nuw nsw i32 %iv, 1
%exitcond.not = icmp eq i32 %iv.next, %N
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
for.cond.cleanup:
ret void
}
|
