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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve < %s | FileCheck %s
; Zeroing.
define <vscale x 16 x i8> @mov_z_b(<vscale x 16 x i1> %pg) {
; CHECK-LABEL: mov_z_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.b, p0/z, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> zeroinitializer, <vscale x 16 x i1> %pg, i8 1)
ret <vscale x 16 x i8> %r
}
define <vscale x 8 x i16> @mov_z_h(<vscale x 8 x i1> %pg) {
; CHECK-LABEL: mov_z_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.h, p0/z, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> zeroinitializer, <vscale x 8 x i1> %pg, i16 1)
ret <vscale x 8 x i16> %r
}
define <vscale x 4 x i32> @mov_z_s(<vscale x 4 x i1> %pg) {
; CHECK-LABEL: mov_z_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.s, p0/z, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> zeroinitializer, <vscale x 4 x i1> %pg, i32 1)
ret <vscale x 4 x i32> %r
}
define <vscale x 2 x i64> @mov_z_d(<vscale x 2 x i1> %pg) {
; CHECK-LABEL: mov_z_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.d, p0/z, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> zeroinitializer, <vscale x 2 x i1> %pg, i64 1)
ret <vscale x 2 x i64> %r
}
; Merging.
define <vscale x 16 x i8> @mov_m_b(<vscale x 16 x i8> %zd, <vscale x 16 x i1> %pg) {
; CHECK-LABEL: mov_m_b:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.b, p0/m, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8> %zd, <vscale x 16 x i1> %pg, i8 1)
ret <vscale x 16 x i8> %r
}
define <vscale x 8 x i16> @mov_m_h(<vscale x 8 x i16> %zd, <vscale x 8 x i1> %pg) {
; CHECK-LABEL: mov_m_h:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.h, p0/m, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16> %zd, <vscale x 8 x i1> %pg, i16 1)
ret <vscale x 8 x i16> %r
}
define <vscale x 4 x i32> @mov_m_s(<vscale x 4 x i32> %zd, <vscale x 4 x i1> %pg) {
; CHECK-LABEL: mov_m_s:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.s, p0/m, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32> %zd, <vscale x 4 x i1> %pg, i32 1)
ret <vscale x 4 x i32> %r
}
define <vscale x 2 x i64> @mov_m_d(<vscale x 2 x i64> %zd, <vscale x 2 x i1> %pg) {
; CHECK-LABEL: mov_m_d:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z0.d, p0/m, #1 // =0x1
; CHECK-NEXT: ret
%r = tail call <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64> %zd, <vscale x 2 x i1> %pg, i64 1)
ret <vscale x 2 x i64> %r
}
declare <vscale x 16 x i8> @llvm.aarch64.sve.dup.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i1>, i8)
declare <vscale x 8 x i16> @llvm.aarch64.sve.dup.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i1>, i16)
declare <vscale x 4 x i32> @llvm.aarch64.sve.dup.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i1>, i32)
declare <vscale x 2 x i64> @llvm.aarch64.sve.dup.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i1>, i64)
|
