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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=arm-none-eabi -mattr=-neon | FileCheck %s --check-prefix=CHECK
declare half @llvm.vector.reduce.fmul.f16.v4f16(half, <4 x half>)
declare float @llvm.vector.reduce.fmul.f32.v4f32(float, <4 x float>)
declare double @llvm.vector.reduce.fmul.f64.v2f64(double, <2 x double>)
declare fp128 @llvm.vector.reduce.fmul.f128.v2f128(fp128, <2 x fp128>)
define half @test_v4f16(<4 x half> %a) nounwind {
; CHECK-LABEL: test_v4f16:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r4, r5, r6, r7, r8, lr}
; CHECK-NEXT: push {r4, r5, r6, r7, r8, lr}
; CHECK-NEXT: mov r8, #255
; CHECK-NEXT: mov r4, r3
; CHECK-NEXT: orr r8, r8, #65280
; CHECK-NEXT: mov r5, r2
; CHECK-NEXT: and r0, r0, r8
; CHECK-NEXT: mov r6, r1
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r7, r0
; CHECK-NEXT: and r0, r6, r8
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r1, r0
; CHECK-NEXT: mov r0, r7
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: bl __aeabi_f2h
; CHECK-NEXT: mov r6, r0
; CHECK-NEXT: and r0, r5, r8
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r5, r0
; CHECK-NEXT: and r0, r6, r8
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r1, r5
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: bl __aeabi_f2h
; CHECK-NEXT: mov r5, r0
; CHECK-NEXT: and r0, r4, r8
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r4, r0
; CHECK-NEXT: and r0, r5, r8
; CHECK-NEXT: bl __aeabi_h2f
; CHECK-NEXT: mov r1, r4
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: bl __aeabi_f2h
; CHECK-NEXT: pop {r4, r5, r6, r7, r8, lr}
; CHECK-NEXT: mov pc, lr
%b = call fast half @llvm.vector.reduce.fmul.f16.v4f16(half 1.0, <4 x half> %a)
ret half %b
}
define float @test_v4f32(<4 x float> %a) nounwind {
; CHECK-LABEL: test_v4f32:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r4, r5, r11, lr}
; CHECK-NEXT: push {r4, r5, r11, lr}
; CHECK-NEXT: mov r4, r3
; CHECK-NEXT: mov r5, r2
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: mov r1, r5
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: mov r1, r4
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: pop {r4, r5, r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call fast float @llvm.vector.reduce.fmul.f32.v4f32(float 1.0, <4 x float> %a)
ret float %b
}
define float @test_v4f32_strict(<4 x float> %a) nounwind {
; CHECK-LABEL: test_v4f32_strict:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r4, r5, r11, lr}
; CHECK-NEXT: push {r4, r5, r11, lr}
; CHECK-NEXT: mov r4, r3
; CHECK-NEXT: mov r5, r2
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: mov r1, r5
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: mov r1, r4
; CHECK-NEXT: bl __aeabi_fmul
; CHECK-NEXT: pop {r4, r5, r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call float @llvm.vector.reduce.fmul.f32.v4f32(float 1.0, <4 x float> %a)
ret float %b
}
define double @test_v2f64(<2 x double> %a) nounwind {
; CHECK-LABEL: test_v2f64:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r11, lr}
; CHECK-NEXT: push {r11, lr}
; CHECK-NEXT: bl __aeabi_dmul
; CHECK-NEXT: pop {r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call fast double @llvm.vector.reduce.fmul.f64.v2f64(double 1.0, <2 x double> %a)
ret double %b
}
define double @test_v2f64_strict(<2 x double> %a) nounwind {
; CHECK-LABEL: test_v2f64_strict:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r11, lr}
; CHECK-NEXT: push {r11, lr}
; CHECK-NEXT: bl __aeabi_dmul
; CHECK-NEXT: pop {r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call double @llvm.vector.reduce.fmul.f64.v2f64(double 1.0, <2 x double> %a)
ret double %b
}
define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r11, lr}
; CHECK-NEXT: push {r11, lr}
; CHECK-NEXT: .pad #16
; CHECK-NEXT: sub sp, sp, #16
; CHECK-NEXT: ldr r12, [sp, #36]
; CHECK-NEXT: str r12, [sp, #12]
; CHECK-NEXT: ldr r12, [sp, #32]
; CHECK-NEXT: str r12, [sp, #8]
; CHECK-NEXT: ldr r12, [sp, #28]
; CHECK-NEXT: str r12, [sp, #4]
; CHECK-NEXT: ldr r12, [sp, #24]
; CHECK-NEXT: str r12, [sp]
; CHECK-NEXT: bl __multf3
; CHECK-NEXT: add sp, sp, #16
; CHECK-NEXT: pop {r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call fast fp128 @llvm.vector.reduce.fmul.f128.v2f128(fp128 0xL00000000000000003fff00000000000000, <2 x fp128> %a)
ret fp128 %b
}
define fp128 @test_v2f128_strict(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128_strict:
; CHECK: @ %bb.0:
; CHECK-NEXT: .save {r11, lr}
; CHECK-NEXT: push {r11, lr}
; CHECK-NEXT: .pad #16
; CHECK-NEXT: sub sp, sp, #16
; CHECK-NEXT: ldr r12, [sp, #36]
; CHECK-NEXT: str r12, [sp, #12]
; CHECK-NEXT: ldr r12, [sp, #32]
; CHECK-NEXT: str r12, [sp, #8]
; CHECK-NEXT: ldr r12, [sp, #28]
; CHECK-NEXT: str r12, [sp, #4]
; CHECK-NEXT: ldr r12, [sp, #24]
; CHECK-NEXT: str r12, [sp]
; CHECK-NEXT: bl __multf3
; CHECK-NEXT: add sp, sp, #16
; CHECK-NEXT: pop {r11, lr}
; CHECK-NEXT: mov pc, lr
%b = call fp128 @llvm.vector.reduce.fmul.f128.v2f128(fp128 0xL00000000000000003fff00000000000000, <2 x fp128> %a)
ret fp128 %b
}
|
