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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64 -mattr=+sve < %s | FileCheck %s
define i1 @ptest_v16i1_256bit_min_sve(float* %a, float * %b) vscale_range(2, 0) {
; CHECK-LABEL: ptest_v16i1_256bit_min_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #8
; CHECK-NEXT: ptrue p0.s, vl8
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0, x8, lsl #2]
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x0]
; CHECK-NEXT: fcmne p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: fcmne p0.s, p0/z, z1.s, #0.0
; CHECK-NEXT: mov z0.s, p1/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: mov z1.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z1.h, z1.h, z1.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: uzp1 z1.b, z1.b, z1.b
; CHECK-NEXT: mov v1.d[1], v0.d[0]
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: orv b0, p0, z1.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = call i1 @llvm.vector.reduce.or.i1.v16i1 (<16 x i1> %v2)
ret i1 %v3
}
define i1 @ptest_v16i1_512bit_min_sve(float* %a, float * %b) vscale_range(4, 0) {
; CHECK-LABEL: ptest_v16i1_512bit_min_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl16
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: fcmne p0.s, p0/z, z0.s, #0.0
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: orv b0, p0, z0.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = call i1 @llvm.vector.reduce.or.i1.v16i1 (<16 x i1> %v2)
ret i1 %v3
}
define i1 @ptest_v16i1_512bit_sve(float* %a, float * %b) vscale_range(4, 4) {
; CHECK-LABEL: ptest_v16i1_512bit_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: fcmne p0.s, p0/z, z0.s, #0.0
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: orv b0, p0, z0.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = call i1 @llvm.vector.reduce.or.i1.v16i1 (<16 x i1> %v2)
ret i1 %v3
}
define i1 @ptest_or_v16i1_512bit_min_sve(float* %a, float * %b) vscale_range(4, 0) {
; CHECK-LABEL: ptest_or_v16i1_512bit_min_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl16
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x1]
; CHECK-NEXT: fcmne p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: fcmne p0.s, p0/z, z1.s, #0.0
; CHECK-NEXT: mov p0.b, p1/m, p1.b
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: orv b0, p0, z0.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = bitcast float* %b to <16 x float>*
%v4 = load <16 x float>, <16 x float>* %v3, align 4
%v5 = fcmp une <16 x float> %v4, zeroinitializer
%v6 = or <16 x i1> %v2, %v5
%v7 = call i1 @llvm.vector.reduce.or.i1.v16i1 (<16 x i1> %v6)
ret i1 %v7
}
declare i1 @llvm.vector.reduce.or.i1.v16i1(<16 x i1>)
;
; AND reduction.
;
define i1 @ptest_and_v16i1_512bit_sve(float* %a, float * %b) vscale_range(4, 4) {
; CHECK-LABEL: ptest_and_v16i1_512bit_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x1]
; CHECK-NEXT: fcmne p0.s, p0/z, z0.s, #0.0
; CHECK-NEXT: fcmne p0.s, p0/z, z1.s, #0.0
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: andv b0, p0, z0.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = bitcast float* %b to <16 x float>*
%v4 = load <16 x float>, <16 x float>* %v3, align 4
%v5 = fcmp une <16 x float> %v4, zeroinitializer
%v6 = and <16 x i1> %v2, %v5
%v7 = call i1 @llvm.vector.reduce.and.i1.v16i1 (<16 x i1> %v6)
ret i1 %v7
}
define i1 @ptest_and_v16i1_512bit_min_sve(float* %a, float * %b) vscale_range(4, 0) {
; CHECK-LABEL: ptest_and_v16i1_512bit_min_sve:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s, vl16
; CHECK-NEXT: ld1w { z0.s }, p0/z, [x0]
; CHECK-NEXT: ld1w { z1.s }, p0/z, [x1]
; CHECK-NEXT: fcmne p1.s, p0/z, z0.s, #0.0
; CHECK-NEXT: fcmne p0.s, p0/z, z1.s, #0.0
; CHECK-NEXT: and p0.b, p1/z, p1.b, p0.b
; CHECK-NEXT: mov z0.s, p0/z, #-1 // =0xffffffffffffffff
; CHECK-NEXT: ptrue p0.b, vl16
; CHECK-NEXT: uzp1 z0.h, z0.h, z0.h
; CHECK-NEXT: uzp1 z0.b, z0.b, z0.b
; CHECK-NEXT: andv b0, p0, z0.b
; CHECK-NEXT: fmov w8, s0
; CHECK-NEXT: and w0, w8, #0x1
; CHECK-NEXT: ret
%v0 = bitcast float* %a to <16 x float>*
%v1 = load <16 x float>, <16 x float>* %v0, align 4
%v2 = fcmp une <16 x float> %v1, zeroinitializer
%v3 = bitcast float* %b to <16 x float>*
%v4 = load <16 x float>, <16 x float>* %v3, align 4
%v5 = fcmp une <16 x float> %v4, zeroinitializer
%v6 = and <16 x i1> %v2, %v5
%v7 = call i1 @llvm.vector.reduce.and.i1.v16i1 (<16 x i1> %v6)
ret i1 %v7
}
declare i1 @llvm.vector.reduce.and.i1.v16i1(<16 x i1>)
|
