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
181
182
183
184
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -mattr=+m,+v < %s | FileCheck %s --check-prefixes=CHECK,RV32
; RUN: llc -mtriple=riscv64 -mattr=+m,+v < %s | FileCheck %s --check-prefixes=CHECK,RV64
; Check that we correctly scale the split part indirect offsets by VSCALE.
define <vscale x 32 x i32> @callee_scalable_vector_split_indirect(<vscale x 32 x i32> %x, <vscale x 32 x i32> %y) {
; CHECK-LABEL: callee_scalable_vector_split_indirect:
; CHECK: # %bb.0:
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: add a1, a0, a1
; CHECK-NEXT: vl8re32.v v24, (a0)
; CHECK-NEXT: vl8re32.v v0, (a1)
; CHECK-NEXT: vsetvli a0, zero, e32, m8, ta, ma
; CHECK-NEXT: vadd.vv v8, v8, v24
; CHECK-NEXT: vadd.vv v16, v16, v0
; CHECK-NEXT: ret
%a = add <vscale x 32 x i32> %x, %y
ret <vscale x 32 x i32> %a
}
; Call the function above. Check that we set the arguments correctly.
define <vscale x 32 x i32> @caller_scalable_vector_split_indirect(<vscale x 32 x i32> %x) {
; RV32-LABEL: caller_scalable_vector_split_indirect:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -144
; RV32-NEXT: .cfi_def_cfa_offset 144
; RV32-NEXT: sw ra, 140(sp) # 4-byte Folded Spill
; RV32-NEXT: sw s0, 136(sp) # 4-byte Folded Spill
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: .cfi_offset s0, -8
; RV32-NEXT: addi s0, sp, 144
; RV32-NEXT: .cfi_def_cfa s0, 0
; RV32-NEXT: csrr a0, vlenb
; RV32-NEXT: slli a0, a0, 4
; RV32-NEXT: sub sp, sp, a0
; RV32-NEXT: andi sp, sp, -128
; RV32-NEXT: addi a0, sp, 128
; RV32-NEXT: csrr a1, vlenb
; RV32-NEXT: vs8r.v v8, (a0)
; RV32-NEXT: vsetvli a2, zero, e32, m8, ta, ma
; RV32-NEXT: vmv.v.i v8, 0
; RV32-NEXT: slli a1, a1, 3
; RV32-NEXT: add a1, a0, a1
; RV32-NEXT: addi a0, sp, 128
; RV32-NEXT: vs8r.v v16, (a1)
; RV32-NEXT: vmv.v.i v16, 0
; RV32-NEXT: call callee_scalable_vector_split_indirect
; RV32-NEXT: addi sp, s0, -144
; RV32-NEXT: .cfi_def_cfa sp, 144
; RV32-NEXT: lw ra, 140(sp) # 4-byte Folded Reload
; RV32-NEXT: lw s0, 136(sp) # 4-byte Folded Reload
; RV32-NEXT: .cfi_restore ra
; RV32-NEXT: .cfi_restore s0
; RV32-NEXT: addi sp, sp, 144
; RV32-NEXT: .cfi_def_cfa_offset 0
; RV32-NEXT: ret
;
; RV64-LABEL: caller_scalable_vector_split_indirect:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -144
; RV64-NEXT: .cfi_def_cfa_offset 144
; RV64-NEXT: sd ra, 136(sp) # 8-byte Folded Spill
; RV64-NEXT: sd s0, 128(sp) # 8-byte Folded Spill
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: .cfi_offset s0, -16
; RV64-NEXT: addi s0, sp, 144
; RV64-NEXT: .cfi_def_cfa s0, 0
; RV64-NEXT: csrr a0, vlenb
; RV64-NEXT: slli a0, a0, 4
; RV64-NEXT: sub sp, sp, a0
; RV64-NEXT: andi sp, sp, -128
; RV64-NEXT: addi a0, sp, 128
; RV64-NEXT: csrr a1, vlenb
; RV64-NEXT: vs8r.v v8, (a0)
; RV64-NEXT: vsetvli a2, zero, e32, m8, ta, ma
; RV64-NEXT: vmv.v.i v8, 0
; RV64-NEXT: slli a1, a1, 3
; RV64-NEXT: add a1, a0, a1
; RV64-NEXT: addi a0, sp, 128
; RV64-NEXT: vs8r.v v16, (a1)
; RV64-NEXT: vmv.v.i v16, 0
; RV64-NEXT: call callee_scalable_vector_split_indirect
; RV64-NEXT: addi sp, s0, -144
; RV64-NEXT: .cfi_def_cfa sp, 144
; RV64-NEXT: ld ra, 136(sp) # 8-byte Folded Reload
; RV64-NEXT: ld s0, 128(sp) # 8-byte Folded Reload
; RV64-NEXT: .cfi_restore ra
; RV64-NEXT: .cfi_restore s0
; RV64-NEXT: addi sp, sp, 144
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
%c = alloca i64
%a = call <vscale x 32 x i32> @callee_scalable_vector_split_indirect(<vscale x 32 x i32> zeroinitializer, <vscale x 32 x i32> %x)
ret <vscale x 32 x i32> %a
}
define target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @caller_tuple_return() {
; RV32-LABEL: caller_tuple_return:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: call callee_tuple_return
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; RV32-NEXT: vmv2r.v v6, v8
; RV32-NEXT: vmv2r.v v8, v10
; RV32-NEXT: vmv2r.v v10, v6
; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT: .cfi_restore ra
; RV32-NEXT: addi sp, sp, 16
; RV32-NEXT: .cfi_def_cfa_offset 0
; RV32-NEXT: ret
;
; RV64-LABEL: caller_tuple_return:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -16
; RV64-NEXT: .cfi_def_cfa_offset 16
; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: call callee_tuple_return
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; RV64-NEXT: vmv2r.v v6, v8
; RV64-NEXT: vmv2r.v v8, v10
; RV64-NEXT: vmv2r.v v10, v6
; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64-NEXT: .cfi_restore ra
; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
%a = call target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @callee_tuple_return()
%b = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_2t(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %a, i32 0)
%c = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_2t(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %a, i32 1)
%d = call target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv16i8_2t.nxv4i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) poison, <vscale x 4 x i32> %c, i32 0)
%e = call target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv16i8_2t.nxv4i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %d, <vscale x 4 x i32> %b, i32 1)
ret target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %e
}
declare target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @callee_tuple_return()
define void @caller_tuple_argument(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %x) {
; RV32-LABEL: caller_tuple_argument:
; RV32: # %bb.0:
; RV32-NEXT: addi sp, sp, -16
; RV32-NEXT: .cfi_def_cfa_offset 16
; RV32-NEXT: sw ra, 12(sp) # 4-byte Folded Spill
; RV32-NEXT: .cfi_offset ra, -4
; RV32-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; RV32-NEXT: vmv2r.v v6, v8
; RV32-NEXT: vmv2r.v v8, v10
; RV32-NEXT: vmv2r.v v10, v6
; RV32-NEXT: call callee_tuple_argument
; RV32-NEXT: lw ra, 12(sp) # 4-byte Folded Reload
; RV32-NEXT: .cfi_restore ra
; RV32-NEXT: addi sp, sp, 16
; RV32-NEXT: .cfi_def_cfa_offset 0
; RV32-NEXT: ret
;
; RV64-LABEL: caller_tuple_argument:
; RV64: # %bb.0:
; RV64-NEXT: addi sp, sp, -16
; RV64-NEXT: .cfi_def_cfa_offset 16
; RV64-NEXT: sd ra, 8(sp) # 8-byte Folded Spill
; RV64-NEXT: .cfi_offset ra, -8
; RV64-NEXT: vsetivli zero, 1, e8, m1, ta, ma
; RV64-NEXT: vmv2r.v v6, v8
; RV64-NEXT: vmv2r.v v8, v10
; RV64-NEXT: vmv2r.v v10, v6
; RV64-NEXT: call callee_tuple_argument
; RV64-NEXT: ld ra, 8(sp) # 8-byte Folded Reload
; RV64-NEXT: .cfi_restore ra
; RV64-NEXT: addi sp, sp, 16
; RV64-NEXT: .cfi_def_cfa_offset 0
; RV64-NEXT: ret
%a = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_2t(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %x, i32 0)
%b = call <vscale x 4 x i32> @llvm.riscv.tuple.extract.nxv4i32.triscv.vector.tuple_nxv16i8_2t(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %x, i32 1)
%c = call target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv16i8_2t.nxv4i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) poison, <vscale x 4 x i32> %b, i32 0)
%d = call target("riscv.vector.tuple", <vscale x 16 x i8>, 2) @llvm.riscv.tuple.insert.triscv.vector.tuple_nxv16i8_2t.nxv4i32(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %c, <vscale x 4 x i32> %a, i32 1)
call void @callee_tuple_argument(target("riscv.vector.tuple", <vscale x 16 x i8>, 2) %d)
ret void
}
declare void @callee_tuple_argument(target("riscv.vector.tuple", <vscale x 16 x i8>, 2))
|
