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
|
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv7m-none-eabi -mcpu=cortex-m7 -run-pass=pipeliner --pipeliner-force-issue-width=10 -o - %s | FileCheck %s --check-prefix=CHECK
--- |
define hidden float @dot(ptr nocapture noundef readonly %a, ptr nocapture noundef readonly %b, i32 noundef %sz) local_unnamed_addr #0 {
entry:
%cmp8 = icmp sgt i32 %sz, 0
br i1 %cmp8, label %for.body.preheader, label %for.end
for.body.preheader: ; preds = %entry
%scevgep = getelementptr float, ptr %b, i32 -1
%scevgep4 = getelementptr float, ptr %a, i32 -1
br label %for.body
for.body: ; preds = %for.body.preheader, %for.body
%lsr.iv5 = phi ptr [ %scevgep4, %for.body.preheader ], [ %scevgep6, %for.body ]
%lsr.iv1 = phi ptr [ %scevgep, %for.body.preheader ], [ %scevgep2, %for.body ]
%lsr.iv = phi i32 [ %sz, %for.body.preheader ], [ %lsr.iv.next, %for.body ]
%sum.010 = phi float [ %add, %for.body ], [ 0.000000e+00, %for.body.preheader ]
%scevgep7 = getelementptr float, ptr %lsr.iv5, i32 1
%0 = load float, ptr %scevgep7, align 4
%scevgep3 = getelementptr float, ptr %lsr.iv1, i32 1
%1 = load float, ptr %scevgep3, align 4
%mul = fmul fast float %1, %0
%add = fadd fast float %mul, %sum.010
%lsr.iv.next = add i32 %lsr.iv, -1
%scevgep2 = getelementptr float, ptr %lsr.iv1, i32 1
%scevgep6 = getelementptr float, ptr %lsr.iv5, i32 1
%exitcond.not = icmp ne i32 %lsr.iv.next, 0
br i1 %exitcond.not, label %for.body, label %for.end, !llvm.loop !0
for.end: ; preds = %for.body, %entry
%sum.0.lcssa = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
ret float %sum.0.lcssa
}
!0 = distinct !{!0, !1, !2, !3}
!1 = !{!"llvm.loop.mustprogress"}
!2 = !{!"llvm.loop.unroll.disable"}
!3 = !{!"llvm.loop.pipeline.initiationinterval", i32 3}
...
---
name: dot
alignment: 2
tracksRegLiveness: true
registers:
- { id: 25, class: spr, preferred-register: '' }
constants:
- id: 0
value: 'float 0.000000e+00'
alignment: 4
isTargetSpecific: false
body: |
; CHECK-LABEL: name: dot
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.2(0x50000000), %bb.1(0x30000000)
; CHECK-NEXT: liveins: $r0, $r1, $r2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:gprnopc = COPY $r2
; CHECK-NEXT: [[COPY1:%[0-9]+]]:gprnopc = COPY $r1
; CHECK-NEXT: [[COPY2:%[0-9]+]]:gprnopc = COPY $r0
; CHECK-NEXT: t2CMPri [[COPY]], 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
; CHECK-NEXT: t2Bcc %bb.2, 10 /* CC::ge */, $cpsr
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1:
; CHECK-NEXT: successors: %bb.4(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[VLDRS:%[0-9]+]]:spr = VLDRS %const.0, 0, 14 /* CC::al */, $noreg :: (load (s32) from constant-pool)
; CHECK-NEXT: t2B %bb.4, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2.for.body.preheader:
; CHECK-NEXT: successors: %bb.5(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[t2SUBri:%[0-9]+]]:rgpr = t2SUBri [[COPY1]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[COPY3:%[0-9]+]]:gprnopc = COPY [[t2SUBri]]
; CHECK-NEXT: [[t2SUBri1:%[0-9]+]]:rgpr = t2SUBri [[COPY2]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VLDRS1:%[0-9]+]]:spr = VLDRS %const.0, 0, 14 /* CC::al */, $noreg :: (load (s32) from constant-pool)
; CHECK-NEXT: [[COPY4:%[0-9]+]]:gprnopc = COPY [[t2SUBri1]]
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.5.for.body:
; CHECK-NEXT: successors: %bb.6(0x40000000), %bb.9(0x40000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[t2ADDri:%[0-9]+]]:rgpr = t2ADDri [[COPY4]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VLDRS2:%[0-9]+]]:spr = VLDRS [[COPY4]], 1, 14 /* CC::al */, $noreg :: (load (s32) from %ir.scevgep7)
; CHECK-NEXT: [[t2ADDri1:%[0-9]+]]:rgpr = t2ADDri [[COPY3]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VLDRS3:%[0-9]+]]:spr = VLDRS [[COPY3]], 1, 14 /* CC::al */, $noreg :: (load (s32) from %ir.scevgep3)
; CHECK-NEXT: INLINEASM &nop, 0 /* attdialect */, 196618 /* regdef:SPR */, def %30, 2147483657 /* reguse tiedto:$0 */, [[VLDRS2]](tied-def 3)
; CHECK-NEXT: [[t2SUBri2:%[0-9]+]]:rgpr = t2SUBri [[COPY]], 1, 14 /* CC::al */, $noreg, def $cpsr
; CHECK-NEXT: [[COPY5:%[0-9]+]]:gprnopc = COPY [[t2SUBri2]]
; CHECK-NEXT: [[COPY6:%[0-9]+]]:gprnopc = COPY [[t2ADDri1]]
; CHECK-NEXT: [[COPY7:%[0-9]+]]:gprnopc = COPY [[t2ADDri]]
; CHECK-NEXT: t2Bcc %bb.9, 0 /* CC::eq */, $cpsr
; CHECK-NEXT: t2B %bb.6, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.6.for.body:
; CHECK-NEXT: successors: %bb.7(0x80000000), %bb.8(0x00000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[VMULS:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VMULS [[VLDRS3]], %30, 14 /* CC::al */, $noreg
; CHECK-NEXT: [[t2ADDri2:%[0-9]+]]:rgpr = t2ADDri [[COPY7]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VLDRS4:%[0-9]+]]:spr = VLDRS [[COPY7]], 1, 14 /* CC::al */, $noreg :: (load unknown-size from %ir.scevgep7, align 4)
; CHECK-NEXT: [[t2ADDri3:%[0-9]+]]:rgpr = t2ADDri [[COPY6]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VLDRS5:%[0-9]+]]:spr = VLDRS [[COPY6]], 1, 14 /* CC::al */, $noreg :: (load unknown-size from %ir.scevgep3, align 4)
; CHECK-NEXT: INLINEASM &nop, 0 /* attdialect */, 196618 /* regdef:SPR */, def %40, 2147483657 /* reguse tiedto:$0 */, [[VLDRS4]](tied-def 3)
; CHECK-NEXT: [[t2SUBri3:%[0-9]+]]:rgpr = t2SUBri [[COPY5]], 1, 14 /* CC::al */, $noreg, def $cpsr
; CHECK-NEXT: [[COPY8:%[0-9]+]]:gpr = COPY [[t2SUBri3]]
; CHECK-NEXT: [[COPY9:%[0-9]+]]:gpr = COPY [[t2ADDri3]]
; CHECK-NEXT: [[COPY10:%[0-9]+]]:gpr = COPY [[t2ADDri2]]
; CHECK-NEXT: t2Bcc %bb.8, 0 /* CC::eq */, $cpsr
; CHECK-NEXT: t2B %bb.7, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.7.for.body:
; CHECK-NEXT: successors: %bb.8(0x04000000), %bb.7(0x7c000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[PHI:%[0-9]+]]:gprnopc = PHI [[COPY10]], %bb.6, %52, %bb.7
; CHECK-NEXT: [[PHI1:%[0-9]+]]:gprnopc = PHI [[COPY9]], %bb.6, %53, %bb.7
; CHECK-NEXT: [[PHI2:%[0-9]+]]:gprnopc = PHI [[COPY8]], %bb.6, %54, %bb.7
; CHECK-NEXT: [[PHI3:%[0-9]+]]:spr = PHI [[VLDRS1]], %bb.6, %51, %bb.7
; CHECK-NEXT: [[PHI4:%[0-9]+]]:spr = PHI [[VLDRS5]], %bb.6, %47, %bb.7
; CHECK-NEXT: [[PHI5:%[0-9]+]]:spr = PHI %40, %bb.6, %55, %bb.7
; CHECK-NEXT: [[PHI6:%[0-9]+]]:spr = PHI [[VMULS]], %bb.6, %45, %bb.7
; CHECK-NEXT: [[VMULS1:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VMULS [[PHI4]], [[PHI5]], 14 /* CC::al */, $noreg
; CHECK-NEXT: [[t2SUBri4:%[0-9]+]]:rgpr = t2SUBri [[PHI2]], 1, 14 /* CC::al */, $noreg, def $cpsr
; CHECK-NEXT: [[VLDRS6:%[0-9]+]]:spr = VLDRS [[PHI1]], 1, 14 /* CC::al */, $noreg :: (load unknown-size from %ir.scevgep3, align 4)
; CHECK-NEXT: [[VLDRS7:%[0-9]+]]:spr = VLDRS [[PHI]], 1, 14 /* CC::al */, $noreg :: (load unknown-size from %ir.scevgep7, align 4)
; CHECK-NEXT: [[t2ADDri4:%[0-9]+]]:rgpr = t2ADDri [[PHI]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[t2ADDri5:%[0-9]+]]:rgpr = t2ADDri [[PHI1]], 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: [[VADDS:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VADDS [[PHI6]], [[PHI3]], 14 /* CC::al */, $noreg
; CHECK-NEXT: [[COPY11:%[0-9]+]]:gpr = COPY [[t2ADDri4]]
; CHECK-NEXT: [[COPY12:%[0-9]+]]:gpr = COPY [[t2ADDri5]]
; CHECK-NEXT: [[COPY13:%[0-9]+]]:gpr = COPY [[t2SUBri4]]
; CHECK-NEXT: INLINEASM &nop, 0 /* attdialect */, 196618 /* regdef:SPR */, def %55, 2147483657 /* reguse tiedto:$0 */, [[VLDRS7]](tied-def 3)
; CHECK-NEXT: t2Bcc %bb.8, 0 /* CC::eq */, $cpsr
; CHECK-NEXT: t2B %bb.7, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.8:
; CHECK-NEXT: successors: %bb.9(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[PHI7:%[0-9]+]]:spr = PHI [[VLDRS1]], %bb.6, [[VADDS]], %bb.7
; CHECK-NEXT: [[PHI8:%[0-9]+]]:spr = PHI [[VLDRS5]], %bb.6, [[VLDRS6]], %bb.7
; CHECK-NEXT: [[PHI9:%[0-9]+]]:spr = PHI %40, %bb.6, %55, %bb.7
; CHECK-NEXT: [[PHI10:%[0-9]+]]:spr = PHI [[VMULS]], %bb.6, [[VMULS1]], %bb.7
; CHECK-NEXT: [[VADDS1:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VADDS [[PHI10]], [[PHI7]], 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.9:
; CHECK-NEXT: successors: %bb.4(0x80000000)
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[PHI11:%[0-9]+]]:spr = PHI [[VLDRS1]], %bb.5, [[VADDS1]], %bb.8
; CHECK-NEXT: [[PHI12:%[0-9]+]]:spr = PHI [[VLDRS3]], %bb.5, [[PHI8]], %bb.8
; CHECK-NEXT: [[PHI13:%[0-9]+]]:spr = PHI %30, %bb.5, [[PHI9]], %bb.8
; CHECK-NEXT: [[VMULS2:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VMULS [[PHI12]], [[PHI13]], 14 /* CC::al */, $noreg
; CHECK-NEXT: [[VADDS2:%[0-9]+]]:spr = nnan ninf nsz arcp contract afn reassoc VADDS [[VMULS2]], [[PHI11]], 14 /* CC::al */, $noreg
; CHECK-NEXT: t2B %bb.4, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.4.for.end:
; CHECK-NEXT: [[PHI14:%[0-9]+]]:spr = PHI [[VLDRS]], %bb.1, [[VADDS2]], %bb.9
; CHECK-NEXT: [[VMOVRS:%[0-9]+]]:gpr = VMOVRS [[PHI14]], 14 /* CC::al */, $noreg
; CHECK-NEXT: $r0 = COPY [[VMOVRS]]
; CHECK-NEXT: tBX_RET 14 /* CC::al */, $noreg, implicit $r0
bb.0.entry:
successors: %bb.1(0x50000000), %bb.4(0x30000000)
liveins: $r0, $r1, $r2
%13:gprnopc = COPY $r2
%12:gprnopc = COPY $r1
%11:gprnopc = COPY $r0
t2CMPri %13, 1, 14 /* CC::al */, $noreg, implicit-def $cpsr
t2Bcc %bb.1, 10 /* CC::ge */, $cpsr
bb.4:
successors: %bb.3(0x80000000)
%14:spr = VLDRS %const.0, 0, 14 /* CC::al */, $noreg :: (load (s32) from constant-pool)
t2B %bb.3, 14 /* CC::al */, $noreg
bb.1.for.body.preheader:
successors: %bb.2(0x80000000)
%16:rgpr = t2SUBri %12, 4, 14 /* CC::al */, $noreg, $noreg
%0:gpr = COPY %16
%17:rgpr = t2SUBri %11, 4, 14 /* CC::al */, $noreg, $noreg
%15:spr = VLDRS %const.0, 0, 14 /* CC::al */, $noreg :: (load (s32) from constant-pool)
%1:gpr = COPY %17
bb.2.for.body:
successors: %bb.3(0x04000000), %bb.2(0x7c000000)
%2:gprnopc = PHI %1, %bb.1, %9, %bb.2
%3:gprnopc = PHI %0, %bb.1, %8, %bb.2
%4:gprnopc = PHI %13, %bb.1, %7, %bb.2
%5:spr = PHI %15, %bb.1, %6, %bb.2
%18:rgpr = t2ADDri %2, 4, 14 /* CC::al */, $noreg, $noreg
%19:spr = VLDRS %2, 1, 14 /* CC::al */, $noreg :: (load (s32) from %ir.scevgep7)
%20:rgpr = t2ADDri %3, 4, 14 /* CC::al */, $noreg, $noreg
%21:spr = VLDRS %3, 1, 14 /* CC::al */, $noreg :: (load (s32) from %ir.scevgep3)
INLINEASM &nop, 0 /* attdialect */, 196618 /* regdef:SPR */, def %25, 2147483657 /* reguse tiedto:$0 */, %19(tied-def 3)
%22:spr = nnan ninf nsz arcp contract afn reassoc VMULS killed %21, killed %25, 14 /* CC::al */, $noreg
%6:spr = nnan ninf nsz arcp contract afn reassoc VADDS killed %22, %5, 14 /* CC::al */, $noreg
%23:rgpr = t2SUBri %4, 1, 14 /* CC::al */, $noreg, def $cpsr
%7:gpr = COPY %23
%8:gpr = COPY %20
%9:gpr = COPY %18
t2Bcc %bb.3, 0 /* CC::eq */, $cpsr
t2B %bb.2, 14 /* CC::al */, $noreg
bb.3.for.end:
%10:spr = PHI %14, %bb.4, %6, %bb.2
%24:gpr = VMOVRS %10, 14 /* CC::al */, $noreg
$r0 = COPY %24
tBX_RET 14 /* CC::al */, $noreg, implicit $r0
...
|
