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
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
|
# RUN: llc %s -start-after=shrink-wrap -march=mips64 -mcpu=mips64r6 -mattr=+fp64,+msa -o /dev/null
# Test that estimated size of the stack leads to the creation of an emergency
# spill when MSA is in use. Previously, this test case would fail during
# register scavenging due to the lack of a spill slot.
--- |
define inreg { i64, i64 } @test(i64 inreg %a.coerce0, i64 inreg %a.coerce1, i64 inreg %b.coerce0, i64 inreg %b.coerce1, i32 signext %c) #0 {
entry:
%retval = alloca <16 x i8>, align 16
%a = alloca <16 x i8>, align 16
%b = alloca <16 x i8>, align 16
%a.addr = alloca <16 x i8>, align 16
%b.addr = alloca <16 x i8>, align 16
%c.addr = alloca i32, align 4
%g = alloca <16 x i8>*, align 8
%d = alloca i8*, align 8
%0 = bitcast <16 x i8>* %a to { i64, i64 }*
%1 = getelementptr inbounds { i64, i64 }, { i64, i64 }* %0, i32 0, i32 0
store i64 %a.coerce0, i64* %1, align 16
%2 = getelementptr inbounds { i64, i64 }, { i64, i64 }* %0, i32 0, i32 1
store i64 %a.coerce1, i64* %2, align 8
%a1 = load <16 x i8>, <16 x i8>* %a, align 16
%3 = bitcast <16 x i8>* %b to { i64, i64 }*
%4 = getelementptr inbounds { i64, i64 }, { i64, i64 }* %3, i32 0, i32 0
store i64 %b.coerce0, i64* %4, align 16
%5 = getelementptr inbounds { i64, i64 }, { i64, i64 }* %3, i32 0, i32 1
store i64 %b.coerce1, i64* %5, align 8
%b2 = load <16 x i8>, <16 x i8>* %b, align 16
store <16 x i8> %a1, <16 x i8>* %a.addr, align 16
store <16 x i8> %b2, <16 x i8>* %b.addr, align 16
store i32 %c, i32* %c.addr, align 4
%6 = alloca i8, i64 6400, align 16
%7 = bitcast i8* %6 to <16 x i8>*
store <16 x i8>* %7, <16 x i8>** %g, align 8
%8 = load <16 x i8>*, <16 x i8>** %g, align 8
call void @h(<16 x i8>* %b.addr, <16 x i8>* %8)
%9 = load <16 x i8>*, <16 x i8>** %g, align 8
%10 = bitcast <16 x i8>* %9 to i8*
store i8* %10, i8** %d, align 8
%11 = load <16 x i8>, <16 x i8>* %a.addr, align 16
%12 = load i8*, i8** %d, align 8
%arrayidx = getelementptr inbounds i8, i8* %12, i64 0
%13 = load i8, i8* %arrayidx, align 1
%conv = sext i8 %13 to i32
%14 = call <16 x i8> @llvm.mips.fill.b(i32 %conv)
%add = add <16 x i8> %11, %14
%15 = load i8*, i8** %d, align 8
%arrayidx3 = getelementptr inbounds i8, i8* %15, i64 1
%16 = load i8, i8* %arrayidx3, align 1
%conv4 = sext i8 %16 to i32
%17 = call <16 x i8> @llvm.mips.fill.b(i32 %conv4)
%add5 = add <16 x i8> %add, %17
%18 = load <16 x i8>, <16 x i8>* %b.addr, align 16
%add6 = add <16 x i8> %18, %add5
store <16 x i8> %add6, <16 x i8>* %b.addr, align 16
%19 = load <16 x i8>, <16 x i8>* %b.addr, align 16
store <16 x i8> %19, <16 x i8>* %retval, align 16
%20 = bitcast <16 x i8>* %retval to { i64, i64 }*
%21 = load { i64, i64 }, { i64, i64 }* %20, align 16
ret { i64, i64 } %21
}
declare void @h(<16 x i8>*, <16 x i8>*)
declare <16 x i8> @llvm.mips.fill.b(i32)
declare void @llvm.stackprotector(i8*, i8**)
...
---
name: test
alignment: 8
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
liveins:
- { reg: '$a0_64', virtual-reg: '' }
- { reg: '$a1_64', virtual-reg: '' }
- { reg: '$a2_64', virtual-reg: '' }
- { reg: '$a3_64', virtual-reg: '' }
- { reg: '$t0_64', virtual-reg: '' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 16
adjustsStack: false
hasCalls: true
stackProtector: ''
maxCallFrameSize: 4294967295
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
savePoint: ''
restorePoint: ''
fixedStack:
stack:
- { id: 0, name: retval, type: default, offset: 0, size: 16, alignment: 16,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: a, type: default, offset: 0, size: 16, alignment: 16,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 2, name: b, type: default, offset: 0, size: 16, alignment: 16,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 3, name: a.addr, type: default, offset: 0, size: 16, alignment: 16,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 4, name: b.addr, type: default, offset: 0, size: 16, alignment: 16,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 5, name: c.addr, type: default, offset: 0, size: 4, alignment: 4,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 6, name: g, type: default, offset: 0, size: 8, alignment: 8,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 7, name: d, type: default, offset: 0, size: 8, alignment: 8,
callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
- { id: 8, name: '', type: default, offset: 0, size: 6400,
alignment: 16, callee-saved-register: '', debug-info-variable: '',
debug-info-expression: '', debug-info-location: '' }
constants:
body: |
bb.0.entry:
liveins: $a0_64, $a1_64, $a2_64, $a3_64, $t0_64
SD killed $a0_64, %stack.1.a, 0 :: (store 8 into %ir.1, align 16)
SD killed $a1_64, %stack.1.a, 8 :: (store 8 into %ir.2)
$w0 = LD_B %stack.1.a, 0 :: (dereferenceable load 16 from %ir.a)
SD killed $a2_64, %stack.2.b, 0 :: (store 8 into %ir.4, align 16)
SD killed $a3_64, %stack.2.b, 8 :: (store 8 into %ir.5)
$w1 = LD_B %stack.2.b, 0 :: (dereferenceable load 16 from %ir.b)
ST_B killed $w0, %stack.3.a.addr, 0 :: (store 16 into %ir.a.addr)
ST_B killed $w1, %stack.4.b.addr, 0 :: (store 16 into %ir.b.addr)
SW $t0, %stack.5.c.addr, 0, implicit killed $t0_64 :: (store 4 into %ir.c.addr)
$at_64 = LEA_ADDiu64 %stack.8, 0
SD killed $at_64, %stack.6.g, 0 :: (store 8 into %ir.g)
$a1_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
ADJCALLSTACKDOWN 0, 0, implicit-def dead $sp, implicit $sp
$a0_64 = LEA_ADDiu64 %stack.4.b.addr, 0
JAL @h, csr_n64, implicit-def dead $ra, implicit $a0_64, implicit $a1_64, implicit-def $sp
ADJCALLSTACKUP 0, 0, implicit-def dead $sp, implicit $sp
$at_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$v0_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$v1_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$a0_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$a1_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$a2_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$a3_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t0_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t1_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t2_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t3_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t4_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t5_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t6_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t7_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s0_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s1_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s2_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s3_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s4_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s5_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s6_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$s7_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t8_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$t9_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$ra_64 = LD %stack.6.g, 0 :: (dereferenceable load 8 from %ir.g)
$w0 = LD_B %stack.3.a.addr, 0 :: (dereferenceable load 16 from %ir.a.addr)
SD $at_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $v0_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $v1_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $a0_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $a1_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $a2_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $a3_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t0_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t1_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t2_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t3_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t4_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t5_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t6_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t7_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s0_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s1_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s2_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s3_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s4_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s5_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s6_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $s7_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t8_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $t9_64, %stack.7.d, 0 :: (store 8 into %ir.d)
SD $ra_64, %stack.7.d, 0 :: (store 8 into %ir.d)
$at_64 = LD %stack.7.d, 0 :: (dereferenceable load 8 from %ir.d)
$v0 = LB $at_64, 0 :: (load 1 from %ir.arrayidx)
$w1 = FILL_B killed $v0
$w0 = ADDV_B killed $w0, killed $w1
$at = LB killed $at_64, 1 :: (load 1 from %ir.arrayidx3)
$w1 = FILL_B killed $at
$w0 = ADDV_B killed $w0, killed $w1
$w1 = LD_B %stack.4.b.addr, 0 :: (dereferenceable load 16 from %ir.b.addr)
$w0 = ADDV_B killed $w1, killed $w0
ST_B killed $w0, %stack.4.b.addr, 0 :: (store 16 into %ir.b.addr)
$w0 = LD_B %stack.4.b.addr, 0 :: (dereferenceable load 16 from %ir.b.addr)
ST_B killed $w0, %stack.0.retval, 0 :: (store 16 into %ir.retval)
$v0_64 = LD %stack.0.retval, 0 :: (dereferenceable load 8 from %ir.20, align 16)
$v1_64 = LD %stack.0.retval, 8 :: (dereferenceable load 8 from %ir.20 + 8, align 16)
RetRA implicit $v0_64, implicit $v1_64
...
|
