sve2-intrinsics-fp-converts.ll
3.85 KB
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
; RUN: llc -mtriple=aarch64-linux-gnu -mattr=+sve2 < %s | FileCheck %s
;
; FCVTLT
;
define <vscale x 4 x float> @fcvtlt_f32_f16(<vscale x 4 x float> %a, <vscale x 16 x i1> %pg, <vscale x 8 x half> %b) {
; CHECK-LABEL: fcvtlt_f32_f16:
; CHECK: fcvtlt z0.s, p0/m, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fcvtlt.f32f16(<vscale x 4 x float> %a,
<vscale x 16 x i1> %pg,
<vscale x 8 x half> %b)
ret <vscale x 4 x float> %out
}
define <vscale x 2 x double> @fcvtlt_f64_f32(<vscale x 2 x double> %a, <vscale x 16 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: fcvtlt_f64_f32:
; CHECK: fcvtlt z0.d, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 2 x double> @llvm.aarch64.sve.fcvtlt.f64f32(<vscale x 2 x double> %a,
<vscale x 16 x i1> %pg,
<vscale x 4 x float> %b)
ret <vscale x 2 x double> %out
}
;
; FCVTNT
;
define <vscale x 8 x half> @fcvtnt_f16_f32(<vscale x 8 x half> %a, <vscale x 16 x i1> %pg, <vscale x 4 x float> %b) {
; CHECK-LABEL: fcvtnt_f16_f32:
; CHECK: fcvtnt z0.h, p0/m, z1.s
; CHECK-NEXT: ret
%out = call <vscale x 8 x half> @llvm.aarch64.sve.fcvtnt.f16f32(<vscale x 8 x half> %a,
<vscale x 16 x i1> %pg,
<vscale x 4 x float> %b)
ret <vscale x 8 x half> %out
}
define <vscale x 4 x float> @fcvtnt_f32_f64(<vscale x 4 x float> %a, <vscale x 16 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fcvtnt_f32_f64:
; CHECK: fcvtnt z0.s, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fcvtnt.f32f64(<vscale x 4 x float> %a,
<vscale x 16 x i1> %pg,
<vscale x 2 x double> %b)
ret <vscale x 4 x float> %out
}
;
; FCVTX
;
define <vscale x 4 x float> @fcvtx_f32_f64(<vscale x 4 x float> %a, <vscale x 16 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fcvtx_f32_f64:
; CHECK: fcvtx z0.s, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fcvtx.f32f64(<vscale x 4 x float> %a,
<vscale x 16 x i1> %pg,
<vscale x 2 x double> %b)
ret <vscale x 4 x float> %out
}
;
; FCVTXNT
;
define <vscale x 4 x float> @fcvtxnt_f32_f64(<vscale x 4 x float> %a, <vscale x 16 x i1> %pg, <vscale x 2 x double> %b) {
; CHECK-LABEL: fcvtxnt_f32_f64:
; CHECK: fcvtxnt z0.s, p0/m, z1.d
; CHECK-NEXT: ret
%out = call <vscale x 4 x float> @llvm.aarch64.sve.fcvtxnt.f32f64(<vscale x 4 x float> %a,
<vscale x 16 x i1> %pg,
<vscale x 2 x double> %b)
ret <vscale x 4 x float> %out
}
declare <vscale x 4 x float> @llvm.aarch64.sve.fcvtlt.f32f16(<vscale x 4 x float>, <vscale x 16 x i1>, <vscale x 8 x half>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fcvtlt.f64f32(<vscale x 2 x double>, <vscale x 16 x i1>, <vscale x 4 x float>)
declare <vscale x 8 x half> @llvm.aarch64.sve.fcvtnt.f16f32(<vscale x 8 x half>, <vscale x 16 x i1>, <vscale x 4 x float>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcvtnt.f32f64(<vscale x 4 x float>, <vscale x 16 x i1>, <vscale x 2 x double>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcvtx.f32f64(<vscale x 4 x float>, <vscale x 16 x i1>, <vscale x 2 x double>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fcvtxnt.f32f64(<vscale x 4 x float>, <vscale x 16 x i1>, <vscale x 2 x double>)