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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mattr=+sve < %s | FileCheck %s
; Streaming-compatible SVE doesn't include FADDA, so this shouldn't compile!
; RUN: not --crash llc -mattr=+sve -force-streaming-compatible < %s
target triple = "aarch64-linux-gnu"
; FADD
define half @fadda_nxv2f16(half %init, <vscale x 2 x half> %a) {
; CHECK-LABEL: fadda_nxv2f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv2f16(half %init, <vscale x 2 x half> %a)
ret half %res
}
define half @fadda_nxv4f16(half %init, <vscale x 4 x half> %a) {
; CHECK-LABEL: fadda_nxv4f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv4f16(half %init, <vscale x 4 x half> %a)
ret half %res
}
define half @fadda_nxv8f16(half %init, <vscale x 8 x half> %a) {
; CHECK-LABEL: fadda_nxv8f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: // kill: def $h0 killed $h0 def $z0
; CHECK-NEXT: fadda h0, p0, h0, z1.h
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv8f16(half %init, <vscale x 8 x half> %a)
ret half %res
}
define half @fadda_nxv6f16(<vscale x 6 x half> %v, half %s) {
; CHECK-LABEL: fadda_nxv6f16:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 8 * VG
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: mov w8, #32768 // =0x8000
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: mov z2.h, w8
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: st1h { z0.h }, p0, [sp]
; CHECK-NEXT: fmov s0, s1
; CHECK-NEXT: st1h { z2.d }, p1, [sp, #3, mul vl]
; CHECK-NEXT: ld1h { z2.h }, p0/z, [sp]
; CHECK-NEXT: fadda h0, p0, h0, z2.h
; CHECK-NEXT: // kill: def $h0 killed $h0 killed $z0
; CHECK-NEXT: addvl sp, sp, #1
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv6f16(half %s, <vscale x 6 x half> %v)
ret half %res
}
define half @fadda_nxv10f16(<vscale x 10 x half> %v, half %s) {
; CHECK-LABEL: fadda_nxv10f16:
; CHECK: // %bb.0:
; CHECK-NEXT: str x29, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: addvl sp, sp, #-3
; CHECK-NEXT: .cfi_escape 0x0f, 0x0c, 0x8f, 0x00, 0x11, 0x10, 0x22, 0x11, 0x18, 0x92, 0x2e, 0x00, 0x1e, 0x22 // sp + 16 + 24 * VG
; CHECK-NEXT: .cfi_offset w29, -16
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: // kill: def $h2 killed $h2 def $z2
; CHECK-NEXT: mov w8, #32768 // =0x8000
; CHECK-NEXT: ptrue p1.d
; CHECK-NEXT: fadda h2, p0, h2, z0.h
; CHECK-NEXT: st1h { z1.h }, p0, [sp]
; CHECK-NEXT: mov z0.h, w8
; CHECK-NEXT: addvl x8, sp, #1
; CHECK-NEXT: st1h { z0.d }, p1, [sp, #1, mul vl]
; CHECK-NEXT: ld1h { z1.h }, p0/z, [sp]
; CHECK-NEXT: st1h { z1.h }, p0, [sp, #1, mul vl]
; CHECK-NEXT: st1h { z0.d }, p1, [sp, #6, mul vl]
; CHECK-NEXT: ld1h { z1.h }, p0/z, [sp, #1, mul vl]
; CHECK-NEXT: st1h { z1.h }, p0, [sp, #2, mul vl]
; CHECK-NEXT: st1h { z0.d }, p1, [x8, #7, mul vl]
; CHECK-NEXT: ld1h { z0.h }, p0/z, [sp, #2, mul vl]
; CHECK-NEXT: fadda h2, p0, h2, z0.h
; CHECK-NEXT: fmov s0, s2
; CHECK-NEXT: addvl sp, sp, #3
; CHECK-NEXT: ldr x29, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv10f16(half %s, <vscale x 10 x half> %v)
ret half %res
}
define half @fadda_nxv12f16(<vscale x 12 x half> %v, half %s) {
; CHECK-LABEL: fadda_nxv12f16:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: // kill: def $h2 killed $h2 def $z2
; CHECK-NEXT: mov w8, #32768 // =0x8000
; CHECK-NEXT: fadda h2, p0, h2, z0.h
; CHECK-NEXT: uunpklo z0.s, z1.h
; CHECK-NEXT: mov z1.h, w8
; CHECK-NEXT: uzp1 z0.h, z0.h, z1.h
; CHECK-NEXT: fadda h2, p0, h2, z0.h
; CHECK-NEXT: fmov s0, s2
; CHECK-NEXT: ret
%res = call half @llvm.vector.reduce.fadd.nxv12f16(half %s, <vscale x 12 x half> %v)
ret half %res
}
define float @fadda_nxv2f32(float %init, <vscale x 2 x float> %a) {
; CHECK-LABEL: fadda_nxv2f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: // kill: def $s0 killed $s0 def $z0
; CHECK-NEXT: fadda s0, p0, s0, z1.s
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $z0
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fadd.nxv2f32(float %init, <vscale x 2 x float> %a)
ret float %res
}
define float @fadda_nxv4f32(float %init, <vscale x 4 x float> %a) {
; CHECK-LABEL: fadda_nxv4f32:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: // kill: def $s0 killed $s0 def $z0
; CHECK-NEXT: fadda s0, p0, s0, z1.s
; CHECK-NEXT: // kill: def $s0 killed $s0 killed $z0
; CHECK-NEXT: ret
%res = call float @llvm.vector.reduce.fadd.nxv4f32(float %init, <vscale x 4 x float> %a)
ret float %res
}
define double @fadda_nxv2f64(double %init, <vscale x 2 x double> %a) {
; CHECK-LABEL: fadda_nxv2f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: // kill: def $d0 killed $d0 def $z0
; CHECK-NEXT: fadda d0, p0, d0, z1.d
; CHECK-NEXT: // kill: def $d0 killed $d0 killed $z0
; CHECK-NEXT: ret
%res = call double @llvm.vector.reduce.fadd.nxv2f64(double %init, <vscale x 2 x double> %a)
ret double %res
}
declare half @llvm.vector.reduce.fadd.nxv2f16(half, <vscale x 2 x half>)
declare half @llvm.vector.reduce.fadd.nxv4f16(half, <vscale x 4 x half>)
declare half @llvm.vector.reduce.fadd.nxv8f16(half, <vscale x 8 x half>)
declare half @llvm.vector.reduce.fadd.nxv6f16(half, <vscale x 6 x half>)
declare half @llvm.vector.reduce.fadd.nxv10f16(half, <vscale x 10 x half>)
declare half @llvm.vector.reduce.fadd.nxv12f16(half, <vscale x 12 x half>)
declare float @llvm.vector.reduce.fadd.nxv2f32(float, <vscale x 2 x float>)
declare float @llvm.vector.reduce.fadd.nxv4f32(float, <vscale x 4 x float>)
declare float @llvm.vector.reduce.fadd.nxv8f32(float, <vscale x 8 x float>)
declare double @llvm.vector.reduce.fadd.nxv2f64(double, <vscale x 2 x double>)
|
