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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve -verify-machineinstrs < %s | FileCheck %s
;
; LDFF1B, LDFF1W, LDFF1H, LDFF1D: base + 64-bit unscaled offset
; e.g. ldff1h { z0.d }, p0/z, [x0, z0.d]
;
define <vscale x 2 x i64> @gldff1b_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1b_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1b { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.nxv2i8(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
%res = zext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @gldff1h_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1h_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1h { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.nxv2i16(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
%res = zext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @gldff1w_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %offsets) {
; CHECK-LABEL: gldff1w_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1w { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.nxv2i32(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %offsets)
%res = zext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @gldff1d_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1d_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i64> @llvm.aarch64.sve.ldff1.gather.nxv2i64(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
ret <vscale x 2 x i64> %load
}
define <vscale x 2 x double> @gldff1d_d_double(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1d_d_double:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1d { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x double> @llvm.aarch64.sve.ldff1.gather.nxv2f64(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
ret <vscale x 2 x double> %load
}
;
; LDFF1SB, LDFF1SW, LDFF1SH: base + 64-bit unscaled offset
; e.g. ldff1sh { z0.d }, p0/z, [x0, z0.d]
;
define <vscale x 2 x i64> @gldff1sb_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1sb_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sb { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.nxv2i8(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
%res = sext <vscale x 2 x i8> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @gldff1sh_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %b) {
; CHECK-LABEL: gldff1sh_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sh { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.nxv2i16(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %b)
%res = sext <vscale x 2 x i16> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
define <vscale x 2 x i64> @gldff1sw_d(<vscale x 2 x i1> %pg, ptr %base, <vscale x 2 x i64> %offsets) {
; CHECK-LABEL: gldff1sw_d:
; CHECK: // %bb.0:
; CHECK-NEXT: ldff1sw { z0.d }, p0/z, [x0, z0.d]
; CHECK-NEXT: ret
%load = call <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.nxv2i32(<vscale x 2 x i1> %pg,
ptr %base,
<vscale x 2 x i64> %offsets)
%res = sext <vscale x 2 x i32> %load to <vscale x 2 x i64>
ret <vscale x 2 x i64> %res
}
declare <vscale x 2 x i8> @llvm.aarch64.sve.ldff1.gather.nxv2i8(<vscale x 2 x i1>, ptr, <vscale x 2 x i64>)
declare <vscale x 2 x i16> @llvm.aarch64.sve.ldff1.gather.nxv2i16(<vscale x 2 x i1>, ptr, <vscale x 2 x i64>)
declare <vscale x 2 x i32> @llvm.aarch64.sve.ldff1.gather.nxv2i32(<vscale x 2 x i1>, ptr, <vscale x 2 x i64>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.ldff1.gather.nxv2i64(<vscale x 2 x i1>, ptr, <vscale x 2 x i64>)
declare <vscale x 2 x double> @llvm.aarch64.sve.ldff1.gather.nxv2f64(<vscale x 2 x i1>, ptr, <vscale x 2 x i64>)
|
