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
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
| ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve,+fullfp16 -verify-machineinstrs %s -o - | FileCheck %s
; RUN: llc -mtriple=thumbv8.1m.main-arm-none-eabi -mattr=+mve.fp -verify-machineinstrs %s -o - | FileCheck %s
define arm_aapcs_vfpcc <4 x i32> @vdup_i32(i32 %src) {
; CHECK-LABEL: vdup_i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vdup.32 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <4 x i32> undef, i32 %src, i32 0
%out = shufflevector <4 x i32> %0, <4 x i32> undef, <4 x i32> zeroinitializer
ret <4 x i32> %out
}
define arm_aapcs_vfpcc <8 x i16> @vdup_i16(i16 %src) {
; CHECK-LABEL: vdup_i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vdup.16 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <8 x i16> undef, i16 %src, i32 0
%out = shufflevector <8 x i16> %0, <8 x i16> undef, <8 x i32> zeroinitializer
ret <8 x i16> %out
}
define arm_aapcs_vfpcc <16 x i8> @vdup_i8(i8 %src) {
; CHECK-LABEL: vdup_i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vdup.8 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <16 x i8> undef, i8 %src, i32 0
%out = shufflevector <16 x i8> %0, <16 x i8> undef, <16 x i32> zeroinitializer
ret <16 x i8> %out
}
define arm_aapcs_vfpcc <2 x i64> @vdup_i64(i64 %src) {
; CHECK-LABEL: vdup_i64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.32 q0[0], r0
; CHECK-NEXT: vmov.32 q0[1], r1
; CHECK-NEXT: vmov.32 q0[2], r0
; CHECK-NEXT: vmov.32 q0[3], r1
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <2 x i64> undef, i64 %src, i32 0
%out = shufflevector <2 x i64> %0, <2 x i64> undef, <2 x i32> zeroinitializer
ret <2 x i64> %out
}
define arm_aapcs_vfpcc <4 x float> @vdup_f32_1(float %src) {
; CHECK-LABEL: vdup_f32_1:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov r0, s0
; CHECK-NEXT: vdup.32 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <4 x float> undef, float %src, i32 0
%out = shufflevector <4 x float> %0, <4 x float> undef, <4 x i32> zeroinitializer
ret <4 x float> %out
}
define arm_aapcs_vfpcc <4 x float> @vdup_f32_2(float %src1, float %src2) {
; CHECK-LABEL: vdup_f32_2:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vadd.f32 s0, s0, s1
; CHECK-NEXT: vmov r0, s0
; CHECK-NEXT: vdup.32 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = fadd float %src1, %src2
%1 = insertelement <4 x float> undef, float %0, i32 0
%out = shufflevector <4 x float> %1, <4 x float> undef, <4 x i32> zeroinitializer
ret <4 x float> %out
}
; TODO: Calling convention needs fixing to pass half types directly to functions
define arm_aapcs_vfpcc <8 x half> @vdup_f16(half* %src1, half* %src2) {
; CHECK-LABEL: vdup_f16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vldr.16 s0, [r1]
; CHECK-NEXT: vldr.16 s2, [r0]
; CHECK-NEXT: vadd.f16 s0, s2, s0
; CHECK-NEXT: vmov r0, s0
; CHECK-NEXT: vdup.16 q0, r0
; CHECK-NEXT: bx lr
entry:
%0 = load half, half *%src1, align 2
%1 = load half, half *%src2, align 2
%2 = fadd half %0, %1
%3 = insertelement <8 x half> undef, half %2, i32 0
%out = shufflevector <8 x half> %3, <8 x half> undef, <8 x i32> zeroinitializer
ret <8 x half> %out
}
define arm_aapcs_vfpcc <2 x double> @vdup_f64(double %src) {
; CHECK-LABEL: vdup_f64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: @ kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: vmov.f32 s2, s0
; CHECK-NEXT: vmov.f32 s3, s1
; CHECK-NEXT: bx lr
entry:
%0 = insertelement <2 x double> undef, double %src, i32 0
%out = shufflevector <2 x double> %0, <2 x double> undef, <2 x i32> zeroinitializer
ret <2 x double> %out
}
define arm_aapcs_vfpcc <4 x i32> @vduplane_i32(<4 x i32> %src) {
; CHECK-LABEL: vduplane_i32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.32 r0, q0[3]
; CHECK-NEXT: vdup.32 q0, r0
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <4 x i32> %src, <4 x i32> undef, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
ret <4 x i32> %out
}
define arm_aapcs_vfpcc <8 x i16> @vduplane_i16(<8 x i16> %src) {
; CHECK-LABEL: vduplane_i16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.u16 r0, q0[3]
; CHECK-NEXT: vdup.16 q0, r0
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <8 x i16> %src, <8 x i16> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
ret <8 x i16> %out
}
define arm_aapcs_vfpcc <16 x i8> @vduplane_i8(<16 x i8> %src) {
; CHECK-LABEL: vduplane_i8:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.u8 r0, q0[3]
; CHECK-NEXT: vdup.8 q0, r0
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <16 x i8> %src, <16 x i8> undef, <16 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
ret <16 x i8> %out
}
define arm_aapcs_vfpcc <2 x i64> @vduplane_i64(<2 x i64> %src) {
; CHECK-LABEL: vduplane_i64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f32 s0, s2
; CHECK-NEXT: vmov.f32 s1, s3
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <2 x i64> %src, <2 x i64> undef, <2 x i32> <i32 1, i32 1>
ret <2 x i64> %out
}
define arm_aapcs_vfpcc <4 x float> @vduplane_f32(<4 x float> %src) {
; CHECK-LABEL: vduplane_f32:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.32 r0, q0[3]
; CHECK-NEXT: vdup.32 q0, r0
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <4 x float> %src, <4 x float> undef, <4 x i32> <i32 3, i32 3, i32 3, i32 3>
ret <4 x float> %out
}
define arm_aapcs_vfpcc <8 x half> @vduplane_f16(<8 x half> %src) {
; CHECK-LABEL: vduplane_f16:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.u16 r0, q0[3]
; CHECK-NEXT: vdup.16 q0, r0
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <8 x half> %src, <8 x half> undef, <8 x i32> <i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3, i32 3>
ret <8 x half> %out
}
define arm_aapcs_vfpcc <2 x double> @vduplane_f64(<2 x double> %src) {
; CHECK-LABEL: vduplane_f64:
; CHECK: @ %bb.0: @ %entry
; CHECK-NEXT: vmov.f32 s0, s2
; CHECK-NEXT: vmov.f32 s1, s3
; CHECK-NEXT: bx lr
entry:
%out = shufflevector <2 x double> %src, <2 x double> undef, <2 x i32> <i32 1, i32 1>
ret <2 x double> %out
}
|