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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-- -mattr=+sse2 | FileCheck %s
define float @ext_fadd_v4f32(<4 x float> %x) {
; CHECK-LABEL: ext_fadd_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: addss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: retq
%bo = fadd <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 42.0>
%ext = extractelement <4 x float> %bo, i32 2
ret float %ext
}
define float @ext_fsub_v4f32(<4 x float> %x) {
; CHECK-LABEL: ext_fsub_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: subss %xmm0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retq
%bo = fsub <4 x float> <float 1.0, float 2.0, float 3.0, float 42.0>, %x
%ext = extractelement <4 x float> %bo, i32 1
ret float %ext
}
define float @ext_fmul_v4f32(<4 x float> %x) {
; CHECK-LABEL: ext_fmul_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
; CHECK-NEXT: mulss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: retq
%bo = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 42.0>
%ext = extractelement <4 x float> %bo, i32 3
ret float %ext
}
; X / 1.0 --> X
define float @ext_fdiv_v4f32(<4 x float> %x) {
; CHECK-LABEL: ext_fdiv_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: retq
%bo = fdiv <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 42.0>
%ext = extractelement <4 x float> %bo, i32 0
ret float %ext
}
define float @ext_fdiv_v4f32_constant_op0(<4 x float> %x) {
; CHECK-LABEL: ext_fdiv_v4f32_constant_op0:
; CHECK: # %bb.0:
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: divss %xmm0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retq
%bo = fdiv <4 x float> <float 1.0, float 2.0, float 3.0, float 42.0>, %x
%ext = extractelement <4 x float> %bo, i32 1
ret float %ext
}
define float @ext_frem_v4f32(<4 x float> %x) {
; CHECK-LABEL: ext_frem_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: jmp fmodf@PLT # TAILCALL
%bo = frem <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 42.0>
%ext = extractelement <4 x float> %bo, i32 2
ret float %ext
}
define float @ext_frem_v4f32_constant_op0(<4 x float> %x) {
; CHECK-LABEL: ext_frem_v4f32_constant_op0:
; CHECK: # %bb.0:
; CHECK-NEXT: movaps %xmm0, %xmm1
; CHECK-NEXT: shufps {{.*#+}} xmm1 = xmm1[1,1],xmm0[1,1]
; CHECK-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: jmp fmodf@PLT # TAILCALL
%bo = frem <4 x float> <float 1.0, float 2.0, float 3.0, float 42.0>, %x
%ext = extractelement <4 x float> %bo, i32 1
ret float %ext
}
define float @ext_maxnum_v4f32(<4 x float> %x) nounwind {
; CHECK-LABEL: ext_maxnum_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: maxss {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: retq
%v = call <4 x float> @llvm.maxnum.v4f32(<4 x float> %x, <4 x float> <float 0.0, float 1.0, float 2.0, float 3.0>)
%r = extractelement <4 x float> %v, i32 2
ret float %r
}
define double @ext_minnum_v2f64(<2 x double> %x) nounwind {
; CHECK-LABEL: ext_minnum_v2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: minsd {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0
; CHECK-NEXT: retq
%v = call <2 x double> @llvm.minnum.v2f64(<2 x double> <double 0.0, double 1.0>, <2 x double> %x)
%r = extractelement <2 x double> %v, i32 1
ret double %r
}
define double @ext_maximum_v4f64(<2 x double> %x) nounwind {
; CHECK-LABEL: ext_maximum_v4f64:
; CHECK: # %bb.0:
; CHECK-NEXT: unpckhpd {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT: maxsd %xmm0, %xmm1
; CHECK-NEXT: movapd %xmm1, %xmm0
; CHECK-NEXT: retq
%v = call <2 x double> @llvm.maximum.v2f64(<2 x double> %x, <2 x double> <double 42.0, double 43.0>)
%r = extractelement <2 x double> %v, i32 1
ret double %r
}
define float @ext_minimum_v4f32(<4 x float> %x) nounwind {
; CHECK-LABEL: ext_minimum_v4f32:
; CHECK: # %bb.0:
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: minss %xmm0, %xmm1
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: retq
%v = call <4 x float> @llvm.minimum.v4f32(<4 x float> %x, <4 x float> <float 0.0, float 1.0, float 2.0, float 42.0>)
%r = extractelement <4 x float> %v, i32 1
ret float %r
}
declare <4 x float> @llvm.maxnum.v4f32(<4 x float>, <4 x float>)
declare <2 x double> @llvm.minnum.v2f64(<2 x double>, <2 x double>)
declare <2 x double> @llvm.maximum.v2f64(<2 x double>, <2 x double>)
declare <4 x float> @llvm.minimum.v4f32(<4 x float>, <4 x float>)
|
