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
185
186
187
188
189
190
191
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck -check-prefix=RV32I %s
@x = local_unnamed_addr global fp128 0xL00000000000000007FFF000000000000, align 16
@y = local_unnamed_addr global fp128 0xL00000000000000007FFF000000000000, align 16
; Besides anything else, these tests help verify that libcall ABI lowering
; works correctly
define i32 @test_load_and_cmp() nounwind {
; RV32I-LABEL: test_load_and_cmp:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -48
; RV32I-NEXT: sw ra, 44(sp) # 4-byte Folded Spill
; RV32I-NEXT: lui a0, %hi(x)
; RV32I-NEXT: lui a1, %hi(y)
; RV32I-NEXT: lw a2, %lo(x)(a0)
; RV32I-NEXT: lw a3, %lo(x+4)(a0)
; RV32I-NEXT: lw a4, %lo(x+8)(a0)
; RV32I-NEXT: lw a5, %lo(x+12)(a0)
; RV32I-NEXT: lw a0, %lo(y)(a1)
; RV32I-NEXT: lw a6, %lo(y+4)(a1)
; RV32I-NEXT: lw a7, %lo(y+8)(a1)
; RV32I-NEXT: lw a1, %lo(y+12)(a1)
; RV32I-NEXT: sw a0, 8(sp)
; RV32I-NEXT: sw a6, 12(sp)
; RV32I-NEXT: sw a7, 16(sp)
; RV32I-NEXT: sw a1, 20(sp)
; RV32I-NEXT: addi a0, sp, 24
; RV32I-NEXT: addi a1, sp, 8
; RV32I-NEXT: sw a2, 24(sp)
; RV32I-NEXT: sw a3, 28(sp)
; RV32I-NEXT: sw a4, 32(sp)
; RV32I-NEXT: sw a5, 36(sp)
; RV32I-NEXT: call __netf2
; RV32I-NEXT: snez a0, a0
; RV32I-NEXT: lw ra, 44(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 48
; RV32I-NEXT: ret
%1 = load fp128, ptr @x, align 16
%2 = load fp128, ptr @y, align 16
%cmp = fcmp une fp128 %1, %2
%3 = zext i1 %cmp to i32
ret i32 %3
}
define i32 @test_add_and_fptosi() nounwind {
; RV32I-LABEL: test_add_and_fptosi:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -80
; RV32I-NEXT: sw ra, 76(sp) # 4-byte Folded Spill
; RV32I-NEXT: lui a0, %hi(x)
; RV32I-NEXT: lui a1, %hi(y)
; RV32I-NEXT: lw a3, %lo(x)(a0)
; RV32I-NEXT: lw a4, %lo(x+4)(a0)
; RV32I-NEXT: lw a5, %lo(x+8)(a0)
; RV32I-NEXT: lw a6, %lo(x+12)(a0)
; RV32I-NEXT: lw a0, %lo(y)(a1)
; RV32I-NEXT: lw a2, %lo(y+4)(a1)
; RV32I-NEXT: lw a7, %lo(y+8)(a1)
; RV32I-NEXT: lw a1, %lo(y+12)(a1)
; RV32I-NEXT: sw a0, 24(sp)
; RV32I-NEXT: sw a2, 28(sp)
; RV32I-NEXT: sw a7, 32(sp)
; RV32I-NEXT: sw a1, 36(sp)
; RV32I-NEXT: addi a0, sp, 56
; RV32I-NEXT: addi a1, sp, 40
; RV32I-NEXT: addi a2, sp, 24
; RV32I-NEXT: sw a3, 40(sp)
; RV32I-NEXT: sw a4, 44(sp)
; RV32I-NEXT: sw a5, 48(sp)
; RV32I-NEXT: sw a6, 52(sp)
; RV32I-NEXT: call __addtf3
; RV32I-NEXT: lw a1, 56(sp)
; RV32I-NEXT: lw a2, 60(sp)
; RV32I-NEXT: lw a3, 64(sp)
; RV32I-NEXT: lw a4, 68(sp)
; RV32I-NEXT: addi a0, sp, 8
; RV32I-NEXT: sw a1, 8(sp)
; RV32I-NEXT: sw a2, 12(sp)
; RV32I-NEXT: sw a3, 16(sp)
; RV32I-NEXT: sw a4, 20(sp)
; RV32I-NEXT: call __fixtfsi
; RV32I-NEXT: lw ra, 76(sp) # 4-byte Folded Reload
; RV32I-NEXT: addi sp, sp, 80
; RV32I-NEXT: ret
%1 = load fp128, ptr @x, align 16
%2 = load fp128, ptr @y, align 16
%3 = fadd fp128 %1, %2
%4 = fptosi fp128 %3 to i32
ret i32 %4
}
define fp128 @fmaximum(fp128 %x, fp128 %y) {
; RV32I-LABEL: fmaximum:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -64
; RV32I-NEXT: .cfi_def_cfa_offset 64
; RV32I-NEXT: sw ra, 60(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 56(sp) # 4-byte Folded Spill
; RV32I-NEXT: .cfi_offset ra, -4
; RV32I-NEXT: .cfi_offset s0, -8
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: lw a4, 4(a1)
; RV32I-NEXT: lw a5, 8(a1)
; RV32I-NEXT: lw a6, 12(a1)
; RV32I-NEXT: lw a1, 0(a2)
; RV32I-NEXT: lw a7, 4(a2)
; RV32I-NEXT: lw t0, 8(a2)
; RV32I-NEXT: lw a2, 12(a2)
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: sw a1, 8(sp)
; RV32I-NEXT: sw a7, 12(sp)
; RV32I-NEXT: sw t0, 16(sp)
; RV32I-NEXT: sw a2, 20(sp)
; RV32I-NEXT: addi a0, sp, 40
; RV32I-NEXT: addi a1, sp, 24
; RV32I-NEXT: addi a2, sp, 8
; RV32I-NEXT: sw a3, 24(sp)
; RV32I-NEXT: sw a4, 28(sp)
; RV32I-NEXT: sw a5, 32(sp)
; RV32I-NEXT: sw a6, 36(sp)
; RV32I-NEXT: call fmaximuml
; RV32I-NEXT: lw a0, 40(sp)
; RV32I-NEXT: lw a1, 44(sp)
; RV32I-NEXT: lw a2, 48(sp)
; RV32I-NEXT: lw a3, 52(sp)
; RV32I-NEXT: sw a0, 0(s0)
; RV32I-NEXT: sw a1, 4(s0)
; RV32I-NEXT: sw a2, 8(s0)
; RV32I-NEXT: sw a3, 12(s0)
; RV32I-NEXT: lw ra, 60(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 56(sp) # 4-byte Folded Reload
; RV32I-NEXT: .cfi_restore ra
; RV32I-NEXT: .cfi_restore s0
; RV32I-NEXT: addi sp, sp, 64
; RV32I-NEXT: .cfi_def_cfa_offset 0
; RV32I-NEXT: ret
%a = call fp128 @llvm.maximum.fp128(fp128 %x, fp128 %y)
ret fp128 %a
}
define fp128 @fminimum(fp128 %x, fp128 %y) {
; RV32I-LABEL: fminimum:
; RV32I: # %bb.0:
; RV32I-NEXT: addi sp, sp, -64
; RV32I-NEXT: .cfi_def_cfa_offset 64
; RV32I-NEXT: sw ra, 60(sp) # 4-byte Folded Spill
; RV32I-NEXT: sw s0, 56(sp) # 4-byte Folded Spill
; RV32I-NEXT: .cfi_offset ra, -4
; RV32I-NEXT: .cfi_offset s0, -8
; RV32I-NEXT: lw a3, 0(a1)
; RV32I-NEXT: lw a4, 4(a1)
; RV32I-NEXT: lw a5, 8(a1)
; RV32I-NEXT: lw a6, 12(a1)
; RV32I-NEXT: lw a1, 0(a2)
; RV32I-NEXT: lw a7, 4(a2)
; RV32I-NEXT: lw t0, 8(a2)
; RV32I-NEXT: lw a2, 12(a2)
; RV32I-NEXT: mv s0, a0
; RV32I-NEXT: sw a1, 8(sp)
; RV32I-NEXT: sw a7, 12(sp)
; RV32I-NEXT: sw t0, 16(sp)
; RV32I-NEXT: sw a2, 20(sp)
; RV32I-NEXT: addi a0, sp, 40
; RV32I-NEXT: addi a1, sp, 24
; RV32I-NEXT: addi a2, sp, 8
; RV32I-NEXT: sw a3, 24(sp)
; RV32I-NEXT: sw a4, 28(sp)
; RV32I-NEXT: sw a5, 32(sp)
; RV32I-NEXT: sw a6, 36(sp)
; RV32I-NEXT: call fminimuml
; RV32I-NEXT: lw a0, 40(sp)
; RV32I-NEXT: lw a1, 44(sp)
; RV32I-NEXT: lw a2, 48(sp)
; RV32I-NEXT: lw a3, 52(sp)
; RV32I-NEXT: sw a0, 0(s0)
; RV32I-NEXT: sw a1, 4(s0)
; RV32I-NEXT: sw a2, 8(s0)
; RV32I-NEXT: sw a3, 12(s0)
; RV32I-NEXT: lw ra, 60(sp) # 4-byte Folded Reload
; RV32I-NEXT: lw s0, 56(sp) # 4-byte Folded Reload
; RV32I-NEXT: .cfi_restore ra
; RV32I-NEXT: .cfi_restore s0
; RV32I-NEXT: addi sp, sp, 64
; RV32I-NEXT: .cfi_def_cfa_offset 0
; RV32I-NEXT: ret
%a = call fp128 @llvm.minimum.fp128(fp128 %x, fp128 %y)
ret fp128 %a
}
|
