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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=riscv32 -mattr=+m | FileCheck %s --check-prefixes=RISCV32
; RUN: llc < %s -mtriple=riscv64 -mattr=+m | FileCheck %s --check-prefixes=RISCV64
define { i128, i8 } @muloti_test(i128 %l, i128 %r) unnamed_addr #0 {
; RISCV32-LABEL: muloti_test:
; RISCV32: # %bb.0: # %start
; RISCV32-NEXT: addi sp, sp, -80
; RISCV32-NEXT: sw ra, 76(sp)
; RISCV32-NEXT: sw s1, 72(sp)
; RISCV32-NEXT: sw s2, 68(sp)
; RISCV32-NEXT: sw s3, 64(sp)
; RISCV32-NEXT: sw s4, 60(sp)
; RISCV32-NEXT: sw s5, 56(sp)
; RISCV32-NEXT: sw s6, 52(sp)
; RISCV32-NEXT: sw s7, 48(sp)
; RISCV32-NEXT: mv s3, a2
; RISCV32-NEXT: mv s1, a1
; RISCV32-NEXT: mv s2, a0
; RISCV32-NEXT: sw zero, 12(sp)
; RISCV32-NEXT: sw zero, 8(sp)
; RISCV32-NEXT: sw zero, 28(sp)
; RISCV32-NEXT: sw zero, 24(sp)
; RISCV32-NEXT: lw s5, 4(a2)
; RISCV32-NEXT: sw s5, 4(sp)
; RISCV32-NEXT: lw s6, 0(a2)
; RISCV32-NEXT: sw s6, 0(sp)
; RISCV32-NEXT: lw s4, 4(a1)
; RISCV32-NEXT: sw s4, 20(sp)
; RISCV32-NEXT: lw s7, 0(a1)
; RISCV32-NEXT: sw s7, 16(sp)
; RISCV32-NEXT: addi a0, sp, 32
; RISCV32-NEXT: addi a1, sp, 16
; RISCV32-NEXT: mv a2, sp
; RISCV32-NEXT: call __multi3
; RISCV32-NEXT: lw t1, 12(s1)
; RISCV32-NEXT: lw a1, 8(s1)
; RISCV32-NEXT: mul a0, s5, a1
; RISCV32-NEXT: mul a2, t1, s6
; RISCV32-NEXT: add a0, a2, a0
; RISCV32-NEXT: lw t5, 12(s3)
; RISCV32-NEXT: lw a3, 8(s3)
; RISCV32-NEXT: mul a2, s4, a3
; RISCV32-NEXT: mul a4, t5, s7
; RISCV32-NEXT: add a2, a4, a2
; RISCV32-NEXT: mul a4, a3, s7
; RISCV32-NEXT: mul a5, a1, s6
; RISCV32-NEXT: add s1, a5, a4
; RISCV32-NEXT: sltu a4, s1, a5
; RISCV32-NEXT: mulhu a6, a3, s7
; RISCV32-NEXT: add a7, a6, a2
; RISCV32-NEXT: mulhu t2, a1, s6
; RISCV32-NEXT: add t4, t2, a0
; RISCV32-NEXT: add a0, t4, a7
; RISCV32-NEXT: add a0, a0, a4
; RISCV32-NEXT: xor a2, s5, zero
; RISCV32-NEXT: snez a2, a2
; RISCV32-NEXT: xor a4, t1, zero
; RISCV32-NEXT: snez a4, a4
; RISCV32-NEXT: and a2, a4, a2
; RISCV32-NEXT: xor a4, s4, zero
; RISCV32-NEXT: snez a4, a4
; RISCV32-NEXT: xor a5, t5, zero
; RISCV32-NEXT: snez a5, a5
; RISCV32-NEXT: and a4, a5, a4
; RISCV32-NEXT: mulhu a5, t5, s7
; RISCV32-NEXT: xor a5, a5, zero
; RISCV32-NEXT: snez a5, a5
; RISCV32-NEXT: or t0, a4, a5
; RISCV32-NEXT: mulhu a4, t1, s6
; RISCV32-NEXT: xor a4, a4, zero
; RISCV32-NEXT: snez a4, a4
; RISCV32-NEXT: or t3, a2, a4
; RISCV32-NEXT: lw a4, 44(sp)
; RISCV32-NEXT: add a5, a4, a0
; RISCV32-NEXT: lw a2, 40(sp)
; RISCV32-NEXT: add a0, a2, s1
; RISCV32-NEXT: sltu t6, a0, a2
; RISCV32-NEXT: add s1, a5, t6
; RISCV32-NEXT: beq s1, a4, .LBB0_2
; RISCV32-NEXT: # %bb.1: # %start
; RISCV32-NEXT: sltu t6, s1, a4
; RISCV32-NEXT: .LBB0_2: # %start
; RISCV32-NEXT: xor a4, s1, a4
; RISCV32-NEXT: xor a2, a0, a2
; RISCV32-NEXT: or a2, a2, a4
; RISCV32-NEXT: sltu t2, t4, t2
; RISCV32-NEXT: mulhu a4, s5, a1
; RISCV32-NEXT: xor a4, a4, zero
; RISCV32-NEXT: snez a4, a4
; RISCV32-NEXT: or t3, t3, a4
; RISCV32-NEXT: sltu a6, a7, a6
; RISCV32-NEXT: mulhu a4, s4, a3
; RISCV32-NEXT: xor a4, a4, zero
; RISCV32-NEXT: snez a4, a4
; RISCV32-NEXT: or a4, t0, a4
; RISCV32-NEXT: lw a5, 36(sp)
; RISCV32-NEXT: sw a5, 4(s2)
; RISCV32-NEXT: lw a5, 32(sp)
; RISCV32-NEXT: sw a5, 0(s2)
; RISCV32-NEXT: sw a0, 8(s2)
; RISCV32-NEXT: sw s1, 12(s2)
; RISCV32-NEXT: mv a0, zero
; RISCV32-NEXT: beqz a2, .LBB0_4
; RISCV32-NEXT: # %bb.3: # %start
; RISCV32-NEXT: mv a0, t6
; RISCV32-NEXT: .LBB0_4: # %start
; RISCV32-NEXT: or a2, a4, a6
; RISCV32-NEXT: or a4, t3, t2
; RISCV32-NEXT: or a3, a3, t5
; RISCV32-NEXT: or a1, a1, t1
; RISCV32-NEXT: xor a1, a1, zero
; RISCV32-NEXT: xor a3, a3, zero
; RISCV32-NEXT: snez a3, a3
; RISCV32-NEXT: snez a1, a1
; RISCV32-NEXT: and a1, a1, a3
; RISCV32-NEXT: or a1, a1, a4
; RISCV32-NEXT: or a1, a1, a2
; RISCV32-NEXT: or a0, a1, a0
; RISCV32-NEXT: andi a0, a0, 1
; RISCV32-NEXT: sb a0, 16(s2)
; RISCV32-NEXT: lw s7, 48(sp)
; RISCV32-NEXT: lw s6, 52(sp)
; RISCV32-NEXT: lw s5, 56(sp)
; RISCV32-NEXT: lw s4, 60(sp)
; RISCV32-NEXT: lw s3, 64(sp)
; RISCV32-NEXT: lw s2, 68(sp)
; RISCV32-NEXT: lw s1, 72(sp)
; RISCV32-NEXT: lw ra, 76(sp)
; RISCV32-NEXT: addi sp, sp, 80
; RISCV32-NEXT: ret
;
; RISCV64-LABEL: muloti_test:
; RISCV64: # %bb.0: # %start
; RISCV64-NEXT: mul a6, a4, a1
; RISCV64-NEXT: mul a5, a2, a3
; RISCV64-NEXT: add a6, a5, a6
; RISCV64-NEXT: mul a5, a1, a3
; RISCV64-NEXT: sw a5, 0(a0)
; RISCV64-NEXT: mulhu a7, a1, a3
; RISCV64-NEXT: add a5, a7, a6
; RISCV64-NEXT: sw a5, 8(a0)
; RISCV64-NEXT: sltu a6, a5, a7
; RISCV64-NEXT: xor a5, a4, zero
; RISCV64-NEXT: snez a7, a5
; RISCV64-NEXT: xor a5, a2, zero
; RISCV64-NEXT: snez a5, a5
; RISCV64-NEXT: and a5, a5, a7
; RISCV64-NEXT: mulhu a2, a2, a3
; RISCV64-NEXT: xor a2, a2, zero
; RISCV64-NEXT: snez a2, a2
; RISCV64-NEXT: or a2, a5, a2
; RISCV64-NEXT: mulhu a1, a4, a1
; RISCV64-NEXT: xor a1, a1, zero
; RISCV64-NEXT: snez a1, a1
; RISCV64-NEXT: or a1, a2, a1
; RISCV64-NEXT: or a1, a1, a6
; RISCV64-NEXT: sb a1, 16(a0)
; RISCV64-NEXT: ret
start:
%0 = tail call { i128, i1 } @llvm.umul.with.overflow.i128(i128 %l, i128 %r) #2
%1 = extractvalue { i128, i1 } %0, 0
%2 = extractvalue { i128, i1 } %0, 1
%3 = zext i1 %2 to i8
%4 = insertvalue { i128, i8 } undef, i128 %1, 0
%5 = insertvalue { i128, i8 } %4, i8 %3, 1
ret { i128, i8 } %5
}
; Function Attrs: nounwind readnone speculatable
declare { i128, i1 } @llvm.umul.with.overflow.i128(i128, i128) #1
attributes #0 = { nounwind readnone uwtable }
attributes #1 = { nounwind readnone speculatable }
attributes #2 = { nounwind }
|
