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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+zfh,+experimental-zvfh,+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+zfh,+experimental-zvfh,+v -riscv-v-vector-bits-min=128 -verify-machineinstrs < %s | FileCheck %s
declare <2 x half> @llvm.vp.fptrunc.v2f16.v2f32(<2 x float>, <2 x i1>, i32)
define <2 x half> @vfptrunc_v2f16_v2f32(<2 x float> %a, <2 x i1> %m, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f16_v2f32:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v9, v8, v0.t
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f32(<2 x float> %a, <2 x i1> %m, i32 %vl)
ret <2 x half> %v
}
define <2 x half> @vfptrunc_v2f16_v2f32_unmasked(<2 x float> %a, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f16_v2f32_unmasked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v9, v8
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f32(<2 x float> %a, <2 x i1> shufflevector (<2 x i1> insertelement (<2 x i1> undef, i1 true, i32 0), <2 x i1> undef, <2 x i32> zeroinitializer), i32 %vl)
ret <2 x half> %v
}
declare <2 x half> @llvm.vp.fptrunc.v2f16.v2f64(<2 x double>, <2 x i1>, i32)
define <2 x half> @vfptrunc_v2f16_v2f64(<2 x double> %a, <2 x i1> %m, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f16_v2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfncvt.rod.f.f.w v9, v8, v0.t
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v8, v9, v0.t
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f64(<2 x double> %a, <2 x i1> %m, i32 %vl)
ret <2 x half> %v
}
define <2 x half> @vfptrunc_v2f16_v2f64_unmasked(<2 x double> %a, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f16_v2f64_unmasked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfncvt.rod.f.f.w v9, v8
; CHECK-NEXT: vsetvli zero, zero, e16, mf4, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v8, v9
; CHECK-NEXT: ret
%v = call <2 x half> @llvm.vp.fptrunc.v2f16.v2f64(<2 x double> %a, <2 x i1> shufflevector (<2 x i1> insertelement (<2 x i1> undef, i1 true, i32 0), <2 x i1> undef, <2 x i32> zeroinitializer), i32 %vl)
ret <2 x half> %v
}
declare <2 x float> @llvm.vp.fptrunc.v2f64.v2f32(<2 x double>, <2 x i1>, i32)
define <2 x float> @vfptrunc_v2f32_v2f64(<2 x double> %a, <2 x i1> %m, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f32_v2f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v9, v8, v0.t
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <2 x float> @llvm.vp.fptrunc.v2f64.v2f32(<2 x double> %a, <2 x i1> %m, i32 %vl)
ret <2 x float> %v
}
define <2 x float> @vfptrunc_v2f32_v2f64_unmasked(<2 x double> %a, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v2f32_v2f64_unmasked:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, mf2, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v9, v8
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <2 x float> @llvm.vp.fptrunc.v2f64.v2f32(<2 x double> %a, <2 x i1> shufflevector (<2 x i1> insertelement (<2 x i1> undef, i1 true, i32 0), <2 x i1> undef, <2 x i32> zeroinitializer), i32 %vl)
ret <2 x float> %v
}
declare <15 x float> @llvm.vp.fptrunc.v15f64.v15f32(<15 x double>, <15 x i1>, i32)
define <15 x float> @vfptrunc_v15f32_v15f64(<15 x double> %a, <15 x i1> %m, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v15f32_v15f64:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT: vfncvt.f.f.w v16, v8, v0.t
; CHECK-NEXT: vmv.v.v v8, v16
; CHECK-NEXT: ret
%v = call <15 x float> @llvm.vp.fptrunc.v15f64.v15f32(<15 x double> %a, <15 x i1> %m, i32 %vl)
ret <15 x float> %v
}
declare <32 x float> @llvm.vp.fptrunc.v32f64.v32f32(<32 x double>, <32 x i1>, i32)
define <32 x float> @vfptrunc_v32f32_v32f64(<32 x double> %a, <32 x i1> %m, i32 zeroext %vl) {
; CHECK-LABEL: vfptrunc_v32f32_v32f64:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: sub sp, sp, a1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; CHECK-NEXT: vmv1r.v v24, v0
; CHECK-NEXT: addi a1, sp, 16
; CHECK-NEXT: vs8r.v v8, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: vsetivli zero, 2, e8, mf4, ta, ma
; CHECK-NEXT: vslidedown.vi v0, v0, 2
; CHECK-NEXT: addi a1, a0, -16
; CHECK-NEXT: sltu a2, a0, a1
; CHECK-NEXT: addi a2, a2, -1
; CHECK-NEXT: and a1, a2, a1
; CHECK-NEXT: vsetvli zero, a1, e32, m4, ta, ma
; CHECK-NEXT: li a1, 16
; CHECK-NEXT: vfncvt.f.f.w v8, v16, v0.t
; CHECK-NEXT: bltu a0, a1, .LBB7_2
; CHECK-NEXT: # %bb.1:
; CHECK-NEXT: li a0, 16
; CHECK-NEXT: .LBB7_2:
; CHECK-NEXT: vsetvli zero, a0, e32, m4, ta, ma
; CHECK-NEXT: vmv1r.v v0, v24
; CHECK-NEXT: addi a0, sp, 16
; CHECK-NEXT: vl8r.v v24, (a0) # Unknown-size Folded Reload
; CHECK-NEXT: vfncvt.f.f.w v16, v24, v0.t
; CHECK-NEXT: li a0, 32
; CHECK-NEXT: vsetvli zero, a0, e32, m8, tu, ma
; CHECK-NEXT: vslideup.vi v16, v8, 16
; CHECK-NEXT: vmv8r.v v8, v16
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%v = call <32 x float> @llvm.vp.fptrunc.v32f64.v32f32(<32 x double> %a, <32 x i1> %m, i32 %vl)
ret <32 x float> %v
}
|
