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
|
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=thumbv8.1m.main -mattr=+mve %s -run-pass=arm-low-overhead-loops -o - | FileCheck %s
--- |
define dso_local void @variant_max_use(ptr nocapture readonly %a, ptr %c, i32 %N) #0 {
entry:
%cmp9 = icmp eq i32 %N, 0
%tmp = add i32 %N, 3
%tmp1 = lshr i32 %tmp, 2
%tmp2 = shl nuw i32 %tmp1, 2
%tmp3 = add i32 %tmp2, -4
%tmp4 = lshr i32 %tmp3, 2
%tmp5 = add nuw nsw i32 %tmp4, 1
br i1 %cmp9, label %exit, label %vector.ph
vector.ph: ; preds = %entry
%start = call i32 @llvm.start.loop.iterations.i32(i32 %tmp5)
br label %vector.body
vector.body: ; preds = %vector.body, %vector.ph
%lsr.iv1 = phi i32 [ %lsr.iv.next, %vector.body ], [ %start, %vector.ph ]
%lsr.iv = phi ptr [ %scevgep, %vector.body ], [ %a, %vector.ph ]
%lsr.iv.2 = phi ptr [ %scevgep.2, %vector.body ], [ %c, %vector.ph ]
%tmp7 = phi i32 [ %N, %vector.ph ], [ %tmp9, %vector.body ]
%lsr.iv17 = bitcast ptr %lsr.iv to ptr
%tmp8 = call <8 x i1> @llvm.arm.mve.vctp16(i32 %tmp7)
%tmp9 = sub i32 %tmp7, 8
%wide.masked.load = call <8 x i16> @llvm.masked.load.v8i16.p0(ptr %lsr.iv17, i32 2, <8 x i1> %tmp8, <8 x i16> undef)
%min = tail call i16 @llvm.vector.reduce.smax.v8i16(<8 x i16> %wide.masked.load)
store i16 %min, ptr %lsr.iv.2
%scevgep = getelementptr i16, ptr %lsr.iv, i32 8
%scevgep.2 = getelementptr i16, ptr %lsr.iv.2, i32 1
%tmp10 = call i32 @llvm.loop.decrement.reg.i32.i32.i32(i32 %lsr.iv1, i32 1)
%tmp11 = icmp ne i32 %tmp10, 0
%lsr.iv.next = add nsw i32 %lsr.iv1, -1
br i1 %tmp11, label %vector.body, label %exit
exit: ; preds = %vector.body, %entry
ret void
}
declare <8 x i16> @llvm.masked.load.v8i16.p0(ptr, i32 immarg, <8 x i1>, <8 x i16>)
declare i32 @llvm.start.loop.iterations.i32(i32)
declare i32 @llvm.loop.decrement.reg.i32.i32.i32(i32, i32)
declare <8 x i1> @llvm.arm.mve.vctp16(i32)
declare i16 @llvm.vector.reduce.smax.v8i16(<8 x i16>)
...
---
name: variant_max_use
alignment: 2
tracksRegLiveness: true
registers: []
liveins:
- { reg: '$r0', virtual-reg: '' }
- { reg: '$r1', virtual-reg: '' }
- { reg: '$r2', virtual-reg: '' }
frameInfo:
stackSize: 8
offsetAdjustment: 0
maxAlignment: 4
fixedStack: []
stack:
- { id: 0, name: '', type: spill-slot, offset: -4, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$lr', callee-saved-restored: false,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
- { id: 1, name: '', type: spill-slot, offset: -8, size: 4, alignment: 4,
stack-id: default, callee-saved-register: '$r5', callee-saved-restored: true,
debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
callSites: []
constants: []
machineFunctionInfo: {}
body: |
; CHECK-LABEL: name: variant_max_use
; CHECK: bb.0.entry:
; CHECK-NEXT: successors: %bb.1(0x80000000)
; CHECK-NEXT: liveins: $lr, $r0, $r1, $r2, $r5
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r5, killed $lr, implicit-def $sp, implicit $sp
; CHECK-NEXT: frame-setup CFI_INSTRUCTION def_cfa_offset 8
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $lr, -4
; CHECK-NEXT: frame-setup CFI_INSTRUCTION offset $r5, -8
; CHECK-NEXT: tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
; CHECK-NEXT: t2IT 0, 8, implicit-def $itstate
; CHECK-NEXT: tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r5, def $pc, implicit killed $itstate
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.1.vector.ph:
; CHECK-NEXT: successors: %bb.2(0x80000000)
; CHECK-NEXT: liveins: $r0, $r1, $r2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
; CHECK-NEXT: renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
; CHECK-NEXT: renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
; CHECK-NEXT: $r12 = t2MOVi16 32768, 14 /* CC::al */, $noreg
; CHECK-NEXT: $r12 = t2MOVTi16 killed $r12, 65535, 14 /* CC::al */, $noreg
; CHECK-NEXT: dead $lr = t2DLS renamable $r3
; CHECK-NEXT: $r5 = tMOVr killed $r3, 14 /* CC::al */, $noreg
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.2.vector.body:
; CHECK-NEXT: successors: %bb.2(0x7c000000), %bb.3(0x04000000)
; CHECK-NEXT: liveins: $r0, $r1, $r2, $r5, $r12
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: $r3 = tMOVr $r12, 14 /* CC::al */, $noreg
; CHECK-NEXT: renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg, $noreg
; CHECK-NEXT: MVE_VPST 8, implicit $vpr
; CHECK-NEXT: renamable $r0, renamable $q0 = MVE_VLDRHU16_post killed renamable $r0, 16, 1, killed renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv17, align 2)
; CHECK-NEXT: renamable $r3 = MVE_VMAXVs16 killed renamable $r3, killed renamable $q0, 0, $noreg, $noreg
; CHECK-NEXT: $lr = tMOVr $r5, 14 /* CC::al */, $noreg
; CHECK-NEXT: early-clobber renamable $r1 = t2STRH_POST killed renamable $r3, killed renamable $r1, 2, 14 /* CC::al */, $noreg :: (store (s16) into %ir.lsr.iv.2)
; CHECK-NEXT: renamable $r5, dead $cpsr = nsw tSUBi8 killed $r5, 1, 14 /* CC::al */, $noreg
; CHECK-NEXT: renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14 /* CC::al */, $noreg
; CHECK-NEXT: dead $lr = t2LEUpdate killed renamable $lr, %bb.2
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: bb.3.exit:
; CHECK-NEXT: tPOP_RET 14 /* CC::al */, $noreg, def $r5, def $pc
bb.0.entry:
successors: %bb.1(0x80000000)
liveins: $r0, $r1, $r2, $r5, $lr
frame-setup tPUSH 14 /* CC::al */, $noreg, killed $r5, killed $lr, implicit-def $sp, implicit $sp
frame-setup CFI_INSTRUCTION def_cfa_offset 8
frame-setup CFI_INSTRUCTION offset $lr, -4
frame-setup CFI_INSTRUCTION offset $r5, -8
tCMPi8 renamable $r2, 0, 14 /* CC::al */, $noreg, implicit-def $cpsr
t2IT 0, 8, implicit-def $itstate
tPOP_RET 0 /* CC::eq */, killed $cpsr, def $r5, def $pc, implicit killed $itstate
bb.1.vector.ph:
successors: %bb.2(0x80000000)
liveins: $r0, $r1, $r2, $r5, $lr
renamable $r3, dead $cpsr = tADDi3 renamable $r2, 3, 14 /* CC::al */, $noreg
renamable $r3 = t2BICri killed renamable $r3, 3, 14 /* CC::al */, $noreg, $noreg
renamable $r12 = t2SUBri killed renamable $r3, 4, 14 /* CC::al */, $noreg, $noreg
renamable $r3, dead $cpsr = tMOVi8 1, 14 /* CC::al */, $noreg
renamable $r3 = nuw nsw t2ADDrs killed renamable $r3, killed renamable $r12, 19, 14 /* CC::al */, $noreg, $noreg
$r12 = t2MOVi16 32768, 14 /* CC::al */, $noreg
$r12 = t2MOVTi16 killed $r12, 65535, 14 /* CC::al */, $noreg
$lr = t2DoLoopStart renamable $r3
$r5 = tMOVr killed $r3, 14 /* CC::al */, $noreg
bb.2.vector.body:
successors: %bb.2(0x7c000000), %bb.3(0x04000000)
liveins: $r0, $r1, $r2, $r5, $r12
$r3 = tMOVr $r12, 14 /* CC::al */, $noreg
renamable $vpr = MVE_VCTP16 renamable $r2, 0, $noreg, $noreg
MVE_VPST 8, implicit $vpr
renamable $r0, renamable $q0 = MVE_VLDRHU16_post killed renamable $r0, 16, 1, killed renamable $vpr, $noreg :: (load (s128) from %ir.lsr.iv17, align 2)
renamable $r3 = MVE_VMAXVs16 killed renamable $r3, killed renamable $q0, 0, $noreg, $noreg
$lr = tMOVr $r5, 14 /* CC::al */, $noreg
early-clobber renamable $r1 = t2STRH_POST killed renamable $r3, killed renamable $r1, 2, 14 /* CC::al */, $noreg :: (store (s16) into %ir.lsr.iv.2)
renamable $r5, dead $cpsr = nsw tSUBi8 killed $r5, 1, 14 /* CC::al */, $noreg
renamable $r2, dead $cpsr = tSUBi8 killed renamable $r2, 8, 14 /* CC::al */, $noreg
renamable $lr = t2LoopDec killed renamable $lr, 1
t2LoopEnd killed renamable $lr, %bb.2, implicit-def dead $cpsr
tB %bb.3, 14 /* CC::al */, $noreg
bb.3.exit:
tPOP_RET 14 /* CC::al */, $noreg, def $r5, def $pc
...
|
