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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
; UNPREDICATED
define <vscale x 4 x i16> @load_promote_4i16(ptr %a) {
; CHECK-LABEL: load_promote_4i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ret
%load = load <vscale x 4 x i16>, ptr %a
ret <vscale x 4 x i16> %load
}
define <vscale x 16 x i16> @load_split_i16(ptr %a) {
; CHECK-LABEL: load_split_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ld1h { z1.h }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ret
%load = load <vscale x 16 x i16>, ptr %a
ret <vscale x 16 x i16> %load
}
define <vscale x 24 x i16> @load_split_24i16(ptr %a) {
; CHECK-LABEL: load_split_24i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ld1h { z1.h }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ld1h { z2.h }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT: ret
%load = load <vscale x 24 x i16>, ptr %a
ret <vscale x 24 x i16> %load
}
define <vscale x 32 x i16> @load_split_32i16(ptr %a) {
; CHECK-LABEL: load_split_32i16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: ld1h { z0.h }, p0/z, [x0]
; CHECK-NEXT: ld1h { z1.h }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ld1h { z2.h }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT: ld1h { z3.h }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT: ret
%load = load <vscale x 32 x i16>, ptr %a
ret <vscale x 32 x i16> %load
}
define <vscale x 16 x i64> @load_split_16i64(ptr %a) {
; CHECK-LABEL: load_split_16i64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1d { z0.d }, p0/z, [x0]
; CHECK-NEXT: ld1d { z1.d }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ld1d { z2.d }, p0/z, [x0, #2, mul vl]
; CHECK-NEXT: ld1d { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT: ld1d { z4.d }, p0/z, [x0, #4, mul vl]
; CHECK-NEXT: ld1d { z5.d }, p0/z, [x0, #5, mul vl]
; CHECK-NEXT: ld1d { z6.d }, p0/z, [x0, #6, mul vl]
; CHECK-NEXT: ld1d { z7.d }, p0/z, [x0, #7, mul vl]
; CHECK-NEXT: ret
%load = load <vscale x 16 x i64>, ptr %a
ret <vscale x 16 x i64> %load
}
; MASKED
define <vscale x 2 x i32> @masked_load_promote_2i32(ptr %a, <vscale x 2 x i1> %pg) {
; CHECK-LABEL: masked_load_promote_2i32:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.masked.load.nxv2i32(ptr %a, i32 1, <vscale x 2 x i1> %pg, <vscale x 2 x i32> undef)
ret <vscale x 2 x i32> %load
}
define <vscale x 32 x i8> @masked_load_split_32i8(ptr %a, <vscale x 32 x i1> %pg) {
; CHECK-LABEL: masked_load_split_32i8:
; CHECK: // %bb.0:
; CHECK-NEXT: ld1b { z0.b }, p0/z, [x0]
; CHECK-NEXT: ld1b { z1.b }, p1/z, [x0, #1, mul vl]
; CHECK-NEXT: ret
%load = call <vscale x 32 x i8> @llvm.masked.load.nxv32i8(ptr %a, i32 1, <vscale x 32 x i1> %pg, <vscale x 32 x i8> undef)
ret <vscale x 32 x i8> %load
}
define <vscale x 32 x i16> @masked_load_split_32i16(ptr %a, <vscale x 32 x i1> %pg) {
; CHECK-LABEL: masked_load_split_32i16:
; CHECK: // %bb.0:
; CHECK-NEXT: punpklo p2.h, p0.b
; CHECK-NEXT: punpkhi p0.h, p0.b
; CHECK-NEXT: punpklo p3.h, p1.b
; CHECK-NEXT: ld1h { z0.h }, p2/z, [x0]
; CHECK-NEXT: punpkhi p1.h, p1.b
; CHECK-NEXT: ld1h { z1.h }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ld1h { z2.h }, p3/z, [x0, #2, mul vl]
; CHECK-NEXT: ld1h { z3.h }, p1/z, [x0, #3, mul vl]
; CHECK-NEXT: ret
%load = call <vscale x 32 x i16> @llvm.masked.load.nxv32i16(ptr %a, i32 1, <vscale x 32 x i1> %pg, <vscale x 32 x i16> undef)
ret <vscale x 32 x i16> %load
}
define <vscale x 8 x i32> @masked_load_split_8i32(ptr %a, <vscale x 8 x i1> %pg) {
; CHECK-LABEL: masked_load_split_8i32:
; CHECK: // %bb.0:
; CHECK-NEXT: punpklo p1.h, p0.b
; CHECK-NEXT: punpkhi p0.h, p0.b
; CHECK-NEXT: ld1w { z0.s }, p1/z, [x0]
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x0, #1, mul vl]
; CHECK-NEXT: ret
%load = call <vscale x 8 x i32> @llvm.masked.load.nxv8i32(ptr %a, i32 1, <vscale x 8 x i1> %pg, <vscale x 8 x i32> undef)
ret <vscale x 8 x i32> %load
}
define <vscale x 8 x i64> @masked_load_split_8i64(ptr %a, <vscale x 8 x i1> %pg) {
; CHECK-LABEL: masked_load_split_8i64:
; CHECK: // %bb.0:
; CHECK-NEXT: punpklo p1.h, p0.b
; CHECK-NEXT: punpkhi p0.h, p0.b
; CHECK-NEXT: punpklo p2.h, p1.b
; CHECK-NEXT: punpkhi p1.h, p1.b
; CHECK-NEXT: punpklo p3.h, p0.b
; CHECK-NEXT: ld1d { z0.d }, p2/z, [x0]
; CHECK-NEXT: punpkhi p0.h, p0.b
; CHECK-NEXT: ld1d { z1.d }, p1/z, [x0, #1, mul vl]
; CHECK-NEXT: ld1d { z2.d }, p3/z, [x0, #2, mul vl]
; CHECK-NEXT: ld1d { z3.d }, p0/z, [x0, #3, mul vl]
; CHECK-NEXT: ret
%load = call <vscale x 8 x i64> @llvm.masked.load.nxv8i64(ptr %a, i32 1, <vscale x 8 x i1> %pg, <vscale x 8 x i64> undef)
ret <vscale x 8 x i64> %load
}
declare <vscale x 32 x i8> @llvm.masked.load.nxv32i8(ptr, i32, <vscale x 32 x i1>, <vscale x 32 x i8>)
declare <vscale x 32 x i16> @llvm.masked.load.nxv32i16(ptr, i32, <vscale x 32 x i1>, <vscale x 32 x i16>)
declare <vscale x 2 x i32> @llvm.masked.load.nxv2i32(ptr, i32, <vscale x 2 x i1>, <vscale x 2 x i32>)
declare <vscale x 8 x i32> @llvm.masked.load.nxv8i32(ptr, i32, <vscale x 8 x i1>, <vscale x 8 x i32>)
declare <vscale x 8 x i64> @llvm.masked.load.nxv8i64(ptr, i32, <vscale x 8 x i1>, <vscale x 8 x i64>)
|
