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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64--linux-gnu -mattr=+sve < %s | FileCheck %s
; fpext <vscale x 2 x half> -> <vscale x 2 x double>
define <vscale x 2 x double> @ext2_f16_f64(ptr %ptr, i64 %index) {
; CHECK-LABEL: ext2_f16_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1h { z0.d }, p0/z, [x0]
; CHECK-NEXT: fcvt z0.d, p0/m, z0.h
; CHECK-NEXT: ret
%load = load <vscale x 2 x half>, ptr %ptr, align 4
%load.ext = fpext <vscale x 2 x half> %load to <vscale x 2 x double>
ret <vscale x 2 x double> %load.ext
}
; fpext <vscale x 4 x half> -> <vscale x 4 x double>
define <vscale x 4 x double> @ext4_f16_f64(ptr %ptr, i64 %index) {
; CHECK-LABEL: ext4_f16_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: ld1h { z0.s }, p0/z, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: uunpkhi z2.d, z0.s
; CHECK-NEXT: movprfx z0, z1
; CHECK-NEXT: fcvt z0.d, p0/m, z1.h
; CHECK-NEXT: movprfx z1, z2
; CHECK-NEXT: fcvt z1.d, p0/m, z2.h
; CHECK-NEXT: ret
%load = load <vscale x 4 x half>, ptr %ptr, align 4
%load.ext = fpext <vscale x 4 x half> %load to <vscale x 4 x double>
ret <vscale x 4 x double> %load.ext
}
; fpext <vscale x 8 x half> -> <vscale x 8 x double>
define <vscale x 8 x double> @ext8_f16_f64(ptr %ptr, i64 %index) {
; CHECK-LABEL: ext8_f16_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldr z0, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: uunpklo z1.s, z0.h
; CHECK-NEXT: uunpkhi z0.s, z0.h
; CHECK-NEXT: uunpklo z2.d, z1.s
; CHECK-NEXT: uunpkhi z1.d, z1.s
; CHECK-NEXT: uunpklo z3.d, z0.s
; CHECK-NEXT: uunpkhi z4.d, z0.s
; CHECK-NEXT: fcvt z1.d, p0/m, z1.h
; CHECK-NEXT: movprfx z0, z2
; CHECK-NEXT: fcvt z0.d, p0/m, z2.h
; CHECK-NEXT: movprfx z2, z3
; CHECK-NEXT: fcvt z2.d, p0/m, z3.h
; CHECK-NEXT: movprfx z3, z4
; CHECK-NEXT: fcvt z3.d, p0/m, z4.h
; CHECK-NEXT: ret
%load = load <vscale x 8 x half>, ptr %ptr, align 4
%load.ext = fpext <vscale x 8 x half> %load to <vscale x 8 x double>
ret <vscale x 8 x double> %load.ext
}
; fpext <vscale x 2 x float> -> <vscale x 2 x double>
define <vscale x 2 x double> @ext2_f32_f64(ptr %ptr, i64 %index) {
; CHECK-LABEL: ext2_f32_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: ld1w { z0.d }, p0/z, [x0]
; CHECK-NEXT: fcvt z0.d, p0/m, z0.s
; CHECK-NEXT: ret
%load = load <vscale x 2 x float>, ptr %ptr, align 4
%load.ext = fpext <vscale x 2 x float> %load to <vscale x 2 x double>
ret <vscale x 2 x double> %load.ext
}
; fpext <vscale x 4 x float> -> <vscale x 4 x double>
define <vscale x 4 x double> @ext4_f32_f64(ptr %ptr, i64 %index) {
; CHECK-LABEL: ext4_f32_f64:
; CHECK: // %bb.0:
; CHECK-NEXT: ldr z0, [x0]
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: uunpklo z1.d, z0.s
; CHECK-NEXT: uunpkhi z2.d, z0.s
; CHECK-NEXT: movprfx z0, z1
; CHECK-NEXT: fcvt z0.d, p0/m, z1.s
; CHECK-NEXT: movprfx z1, z2
; CHECK-NEXT: fcvt z1.d, p0/m, z2.s
; CHECK-NEXT: ret
%load = load <vscale x 4 x float>, ptr %ptr, align 4
%load.ext = fpext <vscale x 4 x float> %load to <vscale x 4 x double>
ret <vscale x 4 x double> %load.ext
}
|
