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
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+m,+zfbfmin,+zvfbfmin -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+m,+zfbfmin,+zvfbfmin -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv32 -mattr=+d,+v,+zvfh,+m,+zfbfmin,+zvfbfmin -target-abi=ilp32d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
; RUN: llc -mtriple=riscv64 -mattr=+d,+v,+zvfh,+m,+zfbfmin,+zvfbfmin -target-abi=lp64d \
; RUN: -verify-machineinstrs < %s | FileCheck %s
declare <vscale x 1 x bfloat> @llvm.vp.merge.nxv1bf16(<vscale x 1 x i1>, <vscale x 1 x bfloat>, <vscale x 1 x bfloat>, i32)
define <vscale x 1 x bfloat> @vpmerge_vv_nxv1bf16(<vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv1bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, tu, ma
; CHECK-NEXT: vmerge.vvm v9, v9, v8, v0
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <vscale x 1 x bfloat> @llvm.vp.merge.nxv1bf16(<vscale x 1 x i1> %m, <vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, i32 %evl)
ret <vscale x 1 x bfloat> %v
}
define <vscale x 1 x bfloat> @vpmerge_vf_nxv1bf16(bfloat %a, <vscale x 1 x bfloat> %vb, <vscale x 1 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv1bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, mf2, ta, ma
; CHECK-NEXT: vfmv.v.f v9, fa5
; CHECK-NEXT: vsetvli zero, a0, e16, mf4, tu, mu
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v9, v0.t
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 1 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 1 x bfloat> %elt.head, <vscale x 1 x bfloat> poison, <vscale x 1 x i32> zeroinitializer
%v = call <vscale x 1 x bfloat> @llvm.vp.merge.nxv1bf16(<vscale x 1 x i1> %m, <vscale x 1 x bfloat> %va, <vscale x 1 x bfloat> %vb, i32 %evl)
ret <vscale x 1 x bfloat> %v
}
declare <vscale x 2 x bfloat> @llvm.vp.merge.nxv2bf16(<vscale x 2 x i1>, <vscale x 2 x bfloat>, <vscale x 2 x bfloat>, i32)
define <vscale x 2 x bfloat> @vpmerge_vv_nxv2bf16(<vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vb, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv2bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, tu, ma
; CHECK-NEXT: vmerge.vvm v9, v9, v8, v0
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <vscale x 2 x bfloat> @llvm.vp.merge.nxv2bf16(<vscale x 2 x i1> %m, <vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vb, i32 %evl)
ret <vscale x 2 x bfloat> %v
}
define <vscale x 2 x bfloat> @vpmerge_vf_nxv2bf16(bfloat %a, <vscale x 2 x bfloat> %vb, <vscale x 2 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv2bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, m1, ta, ma
; CHECK-NEXT: vfmv.v.f v9, fa5
; CHECK-NEXT: vsetvli zero, a0, e16, mf2, tu, mu
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v9, v0.t
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 2 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 2 x bfloat> %elt.head, <vscale x 2 x bfloat> poison, <vscale x 2 x i32> zeroinitializer
%v = call <vscale x 2 x bfloat> @llvm.vp.merge.nxv2bf16(<vscale x 2 x i1> %m, <vscale x 2 x bfloat> %va, <vscale x 2 x bfloat> %vb, i32 %evl)
ret <vscale x 2 x bfloat> %v
}
declare <vscale x 4 x bfloat> @llvm.vp.merge.nxv4bf16(<vscale x 4 x i1>, <vscale x 4 x bfloat>, <vscale x 4 x bfloat>, i32)
define <vscale x 4 x bfloat> @vpmerge_vv_nxv4bf16(<vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vb, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m1, tu, ma
; CHECK-NEXT: vmerge.vvm v9, v9, v8, v0
; CHECK-NEXT: vmv1r.v v8, v9
; CHECK-NEXT: ret
%v = call <vscale x 4 x bfloat> @llvm.vp.merge.nxv4bf16(<vscale x 4 x i1> %m, <vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vb, i32 %evl)
ret <vscale x 4 x bfloat> %v
}
define <vscale x 4 x bfloat> @vpmerge_vf_nxv4bf16(bfloat %a, <vscale x 4 x bfloat> %vb, <vscale x 4 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv4bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, m2, ta, ma
; CHECK-NEXT: vfmv.v.f v10, fa5
; CHECK-NEXT: vsetvli zero, a0, e16, m1, tu, mu
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v10, v0.t
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 4 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 4 x bfloat> %elt.head, <vscale x 4 x bfloat> poison, <vscale x 4 x i32> zeroinitializer
%v = call <vscale x 4 x bfloat> @llvm.vp.merge.nxv4bf16(<vscale x 4 x i1> %m, <vscale x 4 x bfloat> %va, <vscale x 4 x bfloat> %vb, i32 %evl)
ret <vscale x 4 x bfloat> %v
}
declare <vscale x 8 x bfloat> @llvm.vp.merge.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>, i32)
define <vscale x 8 x bfloat> @vpmerge_vv_nxv8bf16(<vscale x 8 x bfloat> %va, <vscale x 8 x bfloat> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m2, tu, ma
; CHECK-NEXT: vmerge.vvm v10, v10, v8, v0
; CHECK-NEXT: vmv2r.v v8, v10
; CHECK-NEXT: ret
%v = call <vscale x 8 x bfloat> @llvm.vp.merge.nxv8bf16(<vscale x 8 x i1> %m, <vscale x 8 x bfloat> %va, <vscale x 8 x bfloat> %vb, i32 %evl)
ret <vscale x 8 x bfloat> %v
}
define <vscale x 8 x bfloat> @vpmerge_vf_nxv8bf16(bfloat %a, <vscale x 8 x bfloat> %vb, <vscale x 8 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv8bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, m4, ta, ma
; CHECK-NEXT: vfmv.v.f v12, fa5
; CHECK-NEXT: vsetvli zero, a0, e16, m2, tu, mu
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v12, v0.t
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 8 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 8 x bfloat> %elt.head, <vscale x 8 x bfloat> poison, <vscale x 8 x i32> zeroinitializer
%v = call <vscale x 8 x bfloat> @llvm.vp.merge.nxv8bf16(<vscale x 8 x i1> %m, <vscale x 8 x bfloat> %va, <vscale x 8 x bfloat> %vb, i32 %evl)
ret <vscale x 8 x bfloat> %v
}
declare <vscale x 16 x bfloat> @llvm.vp.merge.nxv16bf16(<vscale x 16 x i1>, <vscale x 16 x bfloat>, <vscale x 16 x bfloat>, i32)
define <vscale x 16 x bfloat> @vpmerge_vv_nxv16bf16(<vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m4, tu, ma
; CHECK-NEXT: vmerge.vvm v12, v12, v8, v0
; CHECK-NEXT: vmv4r.v v8, v12
; CHECK-NEXT: ret
%v = call <vscale x 16 x bfloat> @llvm.vp.merge.nxv16bf16(<vscale x 16 x i1> %m, <vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb, i32 %evl)
ret <vscale x 16 x bfloat> %v
}
define <vscale x 16 x bfloat> @vpmerge_vf_nxv16bf16(bfloat %a, <vscale x 16 x bfloat> %vb, <vscale x 16 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv16bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmv.v.f v16, fa5
; CHECK-NEXT: vsetvli zero, a0, e16, m4, tu, mu
; CHECK-NEXT: vfncvtbf16.f.f.w v8, v16, v0.t
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 16 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 16 x bfloat> %elt.head, <vscale x 16 x bfloat> poison, <vscale x 16 x i32> zeroinitializer
%v = call <vscale x 16 x bfloat> @llvm.vp.merge.nxv16bf16(<vscale x 16 x i1> %m, <vscale x 16 x bfloat> %va, <vscale x 16 x bfloat> %vb, i32 %evl)
ret <vscale x 16 x bfloat> %v
}
declare <vscale x 32 x bfloat> @llvm.vp.merge.nxv32bf16(<vscale x 32 x i1>, <vscale x 32 x bfloat>, <vscale x 32 x bfloat>, i32)
define <vscale x 32 x bfloat> @vpmerge_vv_nxv32bf16(<vscale x 32 x bfloat> %va, <vscale x 32 x bfloat> %vb, <vscale x 32 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vv_nxv32bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: vsetvli zero, a0, e16, m8, tu, ma
; CHECK-NEXT: vmerge.vvm v16, v16, v8, v0
; CHECK-NEXT: vmv8r.v v8, v16
; CHECK-NEXT: ret
%v = call <vscale x 32 x bfloat> @llvm.vp.merge.nxv32bf16(<vscale x 32 x i1> %m, <vscale x 32 x bfloat> %va, <vscale x 32 x bfloat> %vb, i32 %evl)
ret <vscale x 32 x bfloat> %v
}
define <vscale x 32 x bfloat> @vpmerge_vf_nxv32bf16(bfloat %a, <vscale x 32 x bfloat> %vb, <vscale x 32 x i1> %m, i32 zeroext %evl) {
; CHECK-LABEL: vpmerge_vf_nxv32bf16:
; CHECK: # %bb.0:
; CHECK-NEXT: fcvt.s.bf16 fa5, fa0
; CHECK-NEXT: vsetvli a1, zero, e32, m8, ta, ma
; CHECK-NEXT: vfmv.v.f v24, fa5
; CHECK-NEXT: vsetvli zero, zero, e16, m4, ta, ma
; CHECK-NEXT: vfncvtbf16.f.f.w v16, v24
; CHECK-NEXT: vmv.v.v v20, v16
; CHECK-NEXT: vsetvli zero, a0, e16, m8, tu, ma
; CHECK-NEXT: vmerge.vvm v8, v8, v16, v0
; CHECK-NEXT: ret
%elt.head = insertelement <vscale x 32 x bfloat> poison, bfloat %a, i32 0
%va = shufflevector <vscale x 32 x bfloat> %elt.head, <vscale x 32 x bfloat> poison, <vscale x 32 x i32> zeroinitializer
%v = call <vscale x 32 x bfloat> @llvm.vp.merge.nxv32bf16(<vscale x 32 x i1> %m, <vscale x 32 x bfloat> %va, <vscale x 32 x bfloat> %vb, i32 %evl)
ret <vscale x 32 x bfloat> %v
}
|
