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
|
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-none-linux-gnu -mattr=+neon -fp-contract=fast | FileCheck %s
declare float @llvm.fma.f32(float, float, float)
declare double @llvm.fma.f64(double, double, double)
define float @test_fmla_ss4S(float %a, float %b, <4 x float> %v) {
; CHECK: test_fmla_ss4S
; CHECK: fmla {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = call float @llvm.fma.f32(float %b, float %tmp1, float %a)
ret float %tmp2
}
define float @test_fmla_ss4S_swap(float %a, float %b, <4 x float> %v) {
; CHECK: test_fmla_ss4S_swap
; CHECK: fmla {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = call float @llvm.fma.f32(float %tmp1, float %a, float %a)
ret float %tmp2
}
define float @test_fmla_ss2S(float %a, float %b, <2 x float> %v) {
; CHECK: test_fmla_ss2S
; CHECK: fmla {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[1]
%tmp1 = extractelement <2 x float> %v, i32 1
%tmp2 = call float @llvm.fma.f32(float %b, float %tmp1, float %a)
ret float %tmp2
}
define double @test_fmla_ddD(double %a, double %b, <1 x double> %v) {
; CHECK: test_fmla_ddD
; CHECK: fmla {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[0]
%tmp1 = extractelement <1 x double> %v, i32 0
%tmp2 = call double @llvm.fma.f64(double %b, double %tmp1, double %a)
ret double %tmp2
}
define double @test_fmla_dd2D(double %a, double %b, <2 x double> %v) {
; CHECK: test_fmla_dd2D
; CHECK: fmla {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = call double @llvm.fma.f64(double %b, double %tmp1, double %a)
ret double %tmp2
}
define double @test_fmla_dd2D_swap(double %a, double %b, <2 x double> %v) {
; CHECK: test_fmla_dd2D_swap
; CHECK: fmla {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = call double @llvm.fma.f64(double %tmp1, double %b, double %a)
ret double %tmp2
}
define float @test_fmls_ss4S(float %a, float %b, <4 x float> %v) {
; CHECK: test_fmls_ss4S
; CHECK: fmls {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = fsub float -0.0, %tmp1
%tmp3 = call float @llvm.fma.f32(float %tmp2, float %tmp1, float %a)
ret float %tmp3
}
define float @test_fmls_ss4S_swap(float %a, float %b, <4 x float> %v) {
; CHECK: test_fmls_ss4S_swap
; CHECK: fmls {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[3]
%tmp1 = extractelement <4 x float> %v, i32 3
%tmp2 = fsub float -0.0, %tmp1
%tmp3 = call float @llvm.fma.f32(float %tmp1, float %tmp2, float %a)
ret float %tmp3
}
define float @test_fmls_ss2S(float %a, float %b, <2 x float> %v) {
; CHECK: test_fmls_ss2S
; CHECK: fmls {{s[0-9]+}}, {{s[0-9]+}}, {{v[0-31]+}}.s[1]
%tmp1 = extractelement <2 x float> %v, i32 1
%tmp2 = fsub float -0.0, %tmp1
%tmp3 = call float @llvm.fma.f32(float %tmp2, float %tmp1, float %a)
ret float %tmp3
}
define double @test_fmls_ddD(double %a, double %b, <1 x double> %v) {
; CHECK: test_fmls_ddD
; CHECK: fmls {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[0]
%tmp1 = extractelement <1 x double> %v, i32 0
%tmp2 = fsub double -0.0, %tmp1
%tmp3 = call double @llvm.fma.f64(double %tmp2, double %tmp1, double %a)
ret double %tmp3
}
define double @test_fmls_dd2D(double %a, double %b, <2 x double> %v) {
; CHECK: test_fmls_dd2D
; CHECK: fmls {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = fsub double -0.0, %tmp1
%tmp3 = call double @llvm.fma.f64(double %tmp2, double %tmp1, double %a)
ret double %tmp3
}
define double @test_fmls_dd2D_swap(double %a, double %b, <2 x double> %v) {
; CHECK: test_fmls_dd2D_swap
; CHECK: fmls {{d[0-9]+}}, {{d[0-9]+}}, {{v[0-31]+}}.d[1]
%tmp1 = extractelement <2 x double> %v, i32 1
%tmp2 = fsub double -0.0, %tmp1
%tmp3 = call double @llvm.fma.f64(double %tmp1, double %tmp2, double %a)
ret double %tmp3
}
|
