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
|
; RUN: opt -mtriple=thumbv8.1m.main -mve-tail-predication -tail-predication=enabled -mattr=+mve,+lob %s -S -o - | FileCheck %s
; CHECK-LABEL: expand_v8i16_v8i32
; CHECK-NOT: call i32 @llvm.arm.mve.vctp
define void @expand_v8i16_v8i32(ptr noalias nocapture readonly %a, ptr noalias nocapture readonly %b, ptr noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 7
%tmp9 = lshr i32 %tmp8, 3
%tmp10 = shl nuw i32 %tmp9, 3
%tmp11 = add i32 %tmp10, -8
%tmp12 = lshr i32 %tmp11, 3
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%start = call i32 @llvm.start.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %start, %vector.ph ], [ %tmp15, %vector.body ]
%tmp = getelementptr inbounds i16, ptr %a, i32 %index
%tmp1 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %N)
%wide.masked.load = tail call <8 x i16> @llvm.masked.load.v8i16.p0(ptr %tmp, i32 4, <8 x i1> %tmp1, <8 x i16> undef)
%tmp3 = getelementptr inbounds i16, ptr %b, i32 %index
%wide.masked.load2 = tail call <8 x i16> @llvm.masked.load.v8i16.p0(ptr %tmp3, i32 4, <8 x i1> %tmp1, <8 x i16> undef)
%expand.1 = zext <8 x i16> %wide.masked.load to <8 x i32>
%expand.2 = zext <8 x i16> %wide.masked.load2 to <8 x i32>
%mul = mul nsw <8 x i32> %expand.2, %expand.1
%tmp6 = getelementptr inbounds i32, ptr %c, i32 %index
tail call void @llvm.masked.store.v8i32.p0(<8 x i32> %mul, ptr %tmp6, i32 4, <8 x i1> %tmp1)
%index.next = add i32 %index, 8
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; CHECK-LABEL: expand_v8i16_v4i32
; CHECK: [[ELEMS:%[^ ]+]] = phi i32 [ %N, %vector.ph ], [ [[ELEMS_REM:%[^ ]+]], %vector.body ]
; CHECK: [[VCTP:%[^ ]+]] = call <8 x i1> @llvm.arm.mve.vctp16(i32 [[ELEMS]])
; CHECK: [[ELEMS_REM]] = sub i32 [[ELEMS]], 8
; CHECK: tail call <8 x i16> @llvm.masked.load.v8i16.p0(ptr {{.*}}, i32 4, <8 x i1> [[VCTP]], <8 x i16> undef)
; CHECK: %store.pred = icmp ule <4 x i32> %induction.store
; CHECK: tail call void @llvm.masked.store.v4i32.p0(<4 x i32> {{.*}}, ptr {{.*}}, i32 4, <4 x i1> %store.pred)
; CHECK: tail call void @llvm.masked.store.v4i32.p0(<4 x i32> {{.*}}, ptr {{.*}}, i32 4, <4 x i1> %store.pred)
define void @expand_v8i16_v4i32(ptr readonly %a, ptr readonly %b, ptr %c, ptr %d, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 7
%tmp9 = lshr i32 %tmp8, 3
%tmp10 = shl nuw i32 %tmp9, 3
%tmp11 = add i32 %tmp10, -8
%tmp12 = lshr i32 %tmp11, 3
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%trip.count.minus.1 = add i32 %N, -1
%broadcast.splatinsert10.store = insertelement <4 x i32> undef, i32 %trip.count.minus.1, i32 0
%broadcast.splat11.store = shufflevector <4 x i32> %broadcast.splatinsert10.store, <4 x i32> undef, <4 x i32> zeroinitializer
%start = call i32 @llvm.start.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%store.idx = phi i32 [ 0, %vector.ph ], [ %store.idx.next, %vector.body ]
%tmp14 = phi i32 [ %start, %vector.ph ], [ %tmp15, %vector.body ]
%tmp = getelementptr inbounds i16, ptr %a, i32 %index
%tmp1 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 %index, i32 %N)
%wide.masked.load = tail call <8 x i16> @llvm.masked.load.v8i16.p0(ptr %tmp, i32 4, <8 x i1> %tmp1, <8 x i16> undef)
%tmp3 = getelementptr inbounds i16, ptr %b, i32 %index
%wide.masked.load2 = tail call <8 x i16> @llvm.masked.load.v8i16.p0(ptr %tmp3, i32 4, <8 x i1> %tmp1, <8 x i16> undef)
%extract.2.low = shufflevector <8 x i16> %wide.masked.load2, <8 x i16> undef, < 4 x i32> <i32 0, i32 1, i32 2, i32 3>
%extract.2.high = shufflevector <8 x i16> %wide.masked.load2, <8 x i16> undef, < 4 x i32> <i32 4, i32 5, i32 6, i32 7>
%expand.1 = zext <4 x i16> %extract.2.low to <4 x i32>
%expand.2 = zext <4 x i16> %extract.2.high to <4 x i32>
%mul = mul nsw <4 x i32> %expand.2, %expand.1
%sub = mul nsw <4 x i32> %expand.1, %expand.2
%broadcast.splatinsert.store = insertelement <4 x i32> undef, i32 %store.idx, i32 0
%broadcast.splat.store = shufflevector <4 x i32> %broadcast.splatinsert.store, <4 x i32> undef, <4 x i32> zeroinitializer
%induction.store = add <4 x i32> %broadcast.splat.store, <i32 0, i32 1, i32 2, i32 3>
%store.pred = icmp ule <4 x i32> %induction.store, %broadcast.splat11.store
%tmp6 = getelementptr inbounds i32, ptr %c, i32 %store.idx
tail call void @llvm.masked.store.v4i32.p0(<4 x i32> %mul, ptr %tmp6, i32 4, <4 x i1> %store.pred)
%gep = getelementptr inbounds i32, ptr %d, i32 %store.idx
tail call void @llvm.masked.store.v4i32.p0(<4 x i32> %sub, ptr %gep, i32 4, <4 x i1> %store.pred)
%store.idx.next = add i32 %store.idx, 4
%index.next = add i32 %index, 8
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
; CHECK-LABEL: expand_v4i32_v4i64
; CHECK-NOT: call i32 @llvm.arm.mve.vctp
define void @expand_v4i32_v4i64(ptr noalias nocapture readonly %a, ptr noalias nocapture readonly %b, ptr noalias nocapture %c, i32 %N) {
entry:
%cmp8 = icmp eq i32 %N, 0
%tmp8 = add i32 %N, 3
%tmp9 = lshr i32 %tmp8, 2
%tmp10 = shl nuw i32 %tmp9, 2
%tmp11 = add i32 %tmp10, -4
%tmp12 = lshr i32 %tmp11, 2
%tmp13 = add nuw nsw i32 %tmp12, 1
br i1 %cmp8, label %for.cond.cleanup, label %vector.ph
vector.ph: ; preds = %entry
%start = call i32 @llvm.start.loop.iterations.i32(i32 %tmp13)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
%tmp14 = phi i32 [ %start, %vector.ph ], [ %tmp15, %vector.body ]
%tmp = getelementptr inbounds i32, ptr %a, i32 %index
%tmp1 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 %index, i32 %N)
%wide.masked.load = tail call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %tmp, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%tmp3 = getelementptr inbounds i32, ptr %b, i32 %index
%wide.masked.load2 = tail call <4 x i32> @llvm.masked.load.v4i32.p0(ptr %tmp3, i32 4, <4 x i1> %tmp1, <4 x i32> undef)
%expand.1 = zext <4 x i32> %wide.masked.load to <4 x i64>
%expand.2 = zext <4 x i32> %wide.masked.load2 to <4 x i64>
%mul = mul nsw <4 x i64> %expand.2, %expand.1
%tmp6 = getelementptr inbounds i64, ptr %c, i32 %index
tail call void @llvm.masked.store.v4i64.p0(<4 x i64> %mul, ptr %tmp6, i32 4, <4 x i1> %tmp1)
%index.next = add i32 %index, 4
%tmp15 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %tmp14, i32 1)
%tmp16 = icmp ne i32 %tmp15, 0
br i1 %tmp16, label %vector.body, label %for.cond.cleanup
for.cond.cleanup: ; preds = %vector.body, %entry
ret void
}
declare <8 x i16> @llvm.masked.load.v8i16.p0(ptr, i32 immarg, <8 x i1>, <8 x i16>)
declare void @llvm.masked.store.v8i32.p0(<8 x i32>, ptr, i32 immarg, <8 x i1>)
declare <4 x i32> @llvm.masked.load.v4i32.p0(ptr, i32 immarg, <4 x i1>, <4 x i32>)
declare void @llvm.masked.store.v4i32.p0(<4 x i32>, ptr, i32 immarg, <4 x i1>)
declare void @llvm.masked.store.v4i64.p0(<4 x i64>, ptr, i32 immarg, <4 x i1>)
declare i32 @llvm.start.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
|
