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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
; RUN: llc -mattr=+sve2 < %s | FileCheck %s
; RUN: llc -mattr=+sve,+sme2 < %s | FileCheck %s
; RUN: llc -mattr=+sme2 -force-streaming < %s | FileCheck %s
target triple = "aarch64-linux"
define <vscale x 8 x half> @famin_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: famin_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famin.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
ret <vscale x 8 x half> %r
}
define <vscale x 4 x float> @famin_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: famin_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famin.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
ret <vscale x 4 x float> %r
}
define <vscale x 2 x double> @famin_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: famin_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famin.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
ret <vscale x 2 x double> %r
}
define <vscale x 8 x half> @famin_u_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: famin_u_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famin.u.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %b, <vscale x 8 x half> %a)
ret <vscale x 8 x half> %r
}
define <vscale x 4 x float> @famin_u_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: famin_u_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famin.u.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %b, <vscale x 4 x float> %a)
ret <vscale x 4 x float> %r
}
define <vscale x 2 x double> @famin_u_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: famin_u_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: famin z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famin.u.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %b, <vscale x 2 x double> %a)
ret <vscale x 2 x double> %r
}
define <vscale x 8 x half> @famax_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: famax_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famax.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b)
ret <vscale x 8 x half> %r
}
define <vscale x 4 x float> @famax_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: famax_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famax.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b)
ret <vscale x 4 x float> %r
}
define <vscale x 2 x double> @famax_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: famax_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famax.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b)
ret <vscale x 2 x double> %r
}
define <vscale x 8 x half> @famax_u_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) #0 {
; CHECK-LABEL: famax_u_f16:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: ret
%r = call <vscale x 8 x half> @llvm.aarch64.sve.famax.u.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %b, <vscale x 8 x half> %a)
ret <vscale x 8 x half> %r
}
define <vscale x 4 x float> @famax_u_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %b) #0 {
; CHECK-LABEL: famax_u_f32:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: ret
%r = call <vscale x 4 x float> @llvm.aarch64.sve.famax.u.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %b, <vscale x 4 x float> %a)
ret <vscale x 4 x float> %r
}
define <vscale x 2 x double> @famax_u_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %b) #0 {
; CHECK-LABEL: famax_u_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: famax z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: ret
%r = call <vscale x 2 x double> @llvm.aarch64.sve.famax.u.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %b, <vscale x 2 x double> %a)
ret <vscale x 2 x double> %r
}
attributes #0 = { nounwind "target-features" = "+faminmax" }
|
